Rapid and accurate detection of road cracks is of great significance for road health monitoring, but currently this work is mainly completed through manual site surveys. Low-altitude UAV remote sensing can obtain images with centimeter or even subcentimeter ground resolution, which provides a new efficient and economical approach for rapid crack detection. Nevertheless, crack detection networks face challenges such as edge blurring and misidentification due to the heterogeneity of road cracks and the complexity of the background. To address these issues, we propose a real-time edge reconstruction crack detection network (ERNet) which adopts multi-level information aggregation to reconstruct crack edges and improve the accuracy of segmentation between the target and background. To capture global dependencies across spatial and channel levels, we propose an efficient bilateral decomposed convolutional attention module (BDAM) that combines depth separable convolution and dilated convolution to capture global dependencies across spatial and channel levels. To enhance the accuracy of crack detection, we use a coordinate-based fusion module that integrates spatial, semantic, and edge reconstruction information. In addition, we propose an automatic measurement of crack information for extracting the crack trunk and its corresponding length and width. Experimental results demonstrate that our network achieves the best balance between accuracy and inference speed.

The value of artificial intelligence and machine learning applications for use in heritage research is increasingly appreciated [1]. In specific areas, notably remote sensing, data sets have increased in extent and resolution to the point that manual interpretation is problematic and availability of skilled interpreters to undertake such work is limited. Interpretation of geophysical data sets associated with prehistoric submerged landscapes is particularly challenging. Following the last glacial, sea levels rose 120 metres globally, and vast, habitable landscapes were lost to the sea. These landscapes were inaccessible until extensive remote sensing data sets were provided by the offshore energy sector. In this paper, we provide results of a research programme centred on AI applications using data from the southern North Sea. Here, an area of c.188,000 km2 of habitable terrestrial land was inundated between c. 20,000 BP and 7,0000 BP, along with the cultural heritage it contained [2]. As part of this project, machine learning tools were applied to detect and interpret features of archaeological significance from shallow seismic data. The output provides a proof-of-concept model demonstrating verifiable results and the potential for further, more complex leveraging of AI interpretation for the study of submarine palaeolandscapes. Image: Adobe Firefly Generative AI using keywords - marsh landscape deep underwater, auroch skull half-buried in peat

This research addresses the respiratory distress syndrome (RDS) in preterm newborns, caused by insufficient surfactant synthesis, which can lead to serious complications, including pneumothorax, pulmonary hypertension, and pulmonary hemorrhage, increasing the risk of a fatal outcome. By analyzing chest radiographs and blood gases, we specifically focus on the significant contributions of these parameters to the diagnosis and analysis of the recovery of patients with RDS. The study involved 32 preterm newborns, and the analysis of gas parameters before and after the administration of surfactants and inhalation corticosteroid therapy revealed statistically significant changes in values of parameters such as FiO2, pH, pCO2, HCO3 and BE (Sig.<0.05), ehile the pO2 parameter showed a potential change (Sig.=0.061). Parallel to this, the research emphasizes the development of a lung segmentation algorithm implemented in the MATLAB programming environment. The key steps of the algorithm include preprocessing, segmentation, and visualization for a more detailed understanding of the recovery dynamics after RDS. These algorithms have achieved promising results, with a global accuracy of 0.93±0.06, precision 0.81±0.16 and an F-score of 0.82±0.14. These results highlight the potential application of algorithms in the analysis and monitoring of recovery in newborns with RDS, also underscoring the need for further development of software solutions in medicine, particularly in neonatology, to enhance the diagnosis and treatment of preterm newborns with respiratory distress syndrome.

In high-traffic harbor waters, marine radar frequently encounters signal interference stemming from various obstructive elements, thereby presenting formidable obstacles in the precise identification of ships. To achieve precise pixel-level ship identification in the complex environments, a customized neural network-based ship segmentation algorithm named MrisNet is proposed. MrisNet employs a lightweight and efficient FasterYOLO network to extract features from radar images at different levels, capturing fine-grained edge information and deep semantic features of ship pixels. To address the limitation of deep features in the backbone network lacking detailed shape and structured information, an adaptive attention mechanism is introduced after the FasterYOLO network to enhance crucial ship features. To fully utilize the multi-dimensional feature outputs, MrisNet incorporates a Transformer structure to reconstruct the PANet feature fusion network, allowing for the fusion of contextual information and capturing more essential ship information and semantic correlations. In the prediction stage, MrisNet optimizes the target position loss using the EIoU function, enabling the algorithm to adapt to ship position deviations and size variations, thereby improving segmentation accuracy and convergence speed. Experimental results demonstrate that MrisNet achieves high recall and precision rates of 94.8% and 95.2%, respectively, in ship instance segmentation, outperforming various YOLO and other single-stage algorithms. Moreover, MrisNet has a model parameter size of 13.8M and real-time computational cost of 23.5G, demonstrating notable advantages in terms of convolutional efficiency. In conclusion, MrisNet accurately segments ships with different spot features and under diverse environmental conditions in marine radar images. It exhibits outstanding performance, particularly in extreme scenarios and challenging interference conditions, showcasing robustness and applicability.

The extraction of roof feature lines is an important foundation for realizing large-scale and batch 3D modeling. However, the current traditional point cloud segmentation algorithms do not have satisfactory results in extracting roof feature lines of Chinese traditional residential buildings. In this paper, taking Jingping Village in Western Hunan as an example, we propose a method that combines multiple algorithms based on slope segmentation of roof patches to extract feature lines. Firstly, VDVI and CSF algorithms are used to extract the building and roof point cloud based on the MVS point cloud. Secondly, according to roof features, village buildings are classified, and 3D roof point cloud is projected into 2D regular grid data. Finally, the roof slope is segmented via slope direction, and internal and external feature lines are obtained after refinement through Canny edge detection and Hough straight line detection. Results reveal that this method effectively extracts feature lines of low-building roofs in traditional villages, with slope-based roof surface segmentation accuracy surpassing 99.6%. This method significantly outperforms the RANSAC algorithm and region segmentation algorithm.

Leukemia is a cancer of the bone marrow, a spongy tissue that secretes into the bones and serves as the site for the production of blood cells. One of the most prevalent kinds of leukemia in adults is acute myeloid leukemia (AML). Leukemia has non-specific signs and symptoms that are also similar to those of other interpersonal illnesses. The only way to accurately diagnose leukemia is by manually examining a stained blood smear or bone marrow aspirate under the microscope. However, this approach takes more time and is less precise. This paper describes a method for the automatic recognition and classification of AML in blood smears. Classification techniques include decision trees, logistic regression, support vector machines, and naive bayes.

Bone Scan Index (BSI) is an image biomarker for quantification on bone metastasis of cancers. To compute BSI, not only the hotspots (metastasis) but also the bones have to be segmented. Most related researches focus on binary classification on bone scintigraphy: having metastasis or none. Rare studies focus on pixelwise segmentation. In this study we compare three advanced convolutional neural network (CNN) based models to explore the bone segmentation on dataset in house. The best model is Mask R-CNN, which reaches the precision, sensitivity and F1-score: 0.93, 0.87, 0.90 for prostate cancer patients and 0.92, 0.86, 0.88 for breast cancer patients, respectively. The results are the average of 10-fold cross-validation, which reveals the reliability for clinical use on bone segmentation.

Target detection and segmentation in synthetic aperture radar (SAR) images are vital steps for many remote sensing applications. In the era of data-driven deep learning, this task is extremely challenging due to the limited labeled data. Few-shot Learning has the ability to learn quickly from few samples with supervised information. Inspired by this, a few-shot learning framework named MSG-FN is proposed to solve the segmentation of ship targets in heterologous SAR images with few annotated samples. The proposed MSG-FN adopts a dual-branch network consisting of a support branch and a query branch. The support branch is used to extract features with an encoder, and the query branch uses a U-shaped encoder-decoder structure to segment the target in the query image. The encoder of each branch is composed of well-designed residual blocks combined with filter response normalization to capture robust and domain-independent features. A multi-scale similarity guidance module is proposed to improve the scale adaptability of detection by applying hand-on-hand guidance of support features to query features of various scales. In addition, a SAR dataset named SARShip-4i is built to evaluate the proposed MSG-FN and the experimental results show that the proposed method achieves superior segmentation results compared with the state-of-the-arts.

Early detection of breast cancer, one of the most common cancers in women worldwide, raises survival rates and lowers the cost of treatment. Although breast cancer detection and classification (CAD) tools have improved, some issues and restrictions still require further research. The creation of breast cancer CAD systems, particularly with deep learning models, was significantly impacted by recent advancements in machine learning and image processing techniques. The current deep learning-based CAD system to identify and categorize masses in mammography is presented in a structured manner in this survey. The survey provides the most popular breast cancer CAD system evaluation metrics, publicly available mammographic datasets, and current image modalities. The survey examines the available literature, emphasizing its strengths and limitations. The survey also emphasizes the difficulties and drawbacks of the current methods for classifying and detecting breast cancer. We point out research gaps and make suggestions for further study. This systematic review may be beneficial for clinicians using CAD systems to diagnose breast cancer early on and for researchers looking for knowledge gaps and making more contributions to the field.

The third trimester of pregnancy is the most critical period for human brain development, during which significant changes occur in the morphology of the brain. The development of sulci and gyri allows considerable increase of the brain surface. In premature childrens, these alterations take place outside the womb that may cause a disruption of the normal brain maturation process. We hypothesize that a normalized atlas of brain maturation with cerebral ultrasound images from birth to term equivalent age will help clinicians assess these changes. This work proposes a semi-automatic GUI platform for segmenting the main cerebral sulci in the clinical setting from ultrasound images. This platform has been obtained from images of a cerebral ultrasound neonatal database images provided by two clinical researchers from the Hospital Sant Joan de Déu in Barcelona, Spain. The primary objective is to provide a user-friendly design platform for clinicians, for running and visualizing an atlas of images validated by medical experts. This GUI offers different segmentation approaches, pre-processing tools, and is friendly designed for running, visualizing images, and segmenting the principal sulci. The presented results are discussed in detail in this paper, providing an exhaustive analysis of the proposed approach’s effectiveness.

This article presents a method of segmenting images with gray levels that uses Onicescu's information energy calculated in the context of the neutrosophic theory. Starting from the information energy calculation for complete neutrosophic information, it is shown how to extend its calculation for incomplete and inconsistent neutrosophic information. The segmentation method is based on calculation of thresholds for separating the gray levels using the local maximum points of the Onicescu information energy.

Image processing is a field of which its popularity increases and continues and, that grows dynamically with new technologies. Nowadays, image processing finds itself in use in almost every field. One of these uses is undoubtedly in the field of medicine, where diagnosis and treatment planning are made from images and, which is constantly changing with newly developed techniques. Of course, the most important factor in using this so widely in the medical field is the acquisition of images on every medical field. With the help of these images, the complaints can be seen more easily and the doctor can follow a path in the treatment of the disease. In our study, we used the Region Growing segmentation method to detect the intestinal mass. This study compares the area determined by the specialist with the area obtained with the segmentation process and, it is seen that the created software system can be used as an auxiliary system to specialist doctors.

Assessment of the percentage of disease infected lung volume using computed tomography (CT) images can play an important role to detect lung diseases and predict disease severity. However, manual segmentation of disease infected regions from many CT image slices is tedious and not feasible in clinical practice. To help solve this clinical challenge, this study aims to investigate a new strategy to automatically segment disease infected regions and predict disease severity. We employed a public dataset acquired from 20 COVID-19 patients, which includes manually annotated lung and infections masks, to train a new ensembled deep learning (DL) model that combines the five customized residual attention UNet models to segment disease infected regions followed by a Feature Pyramid Network (FPN) model to classify severity stage of COVID-19 infection. To test potentially clinical utility of new model, we first gathered and processed another set of CT images acquired from 80 Covid-19 patients. Next, we asked two chest radiologists to read CT images of each patient and report the estimated percentage of infected lung volume and disease severity level. Additionally, we asked radiologists to rate acceptance of DL model-generated segmentation results using a 5-scale rating method. Data analysis results show that agreement between disease severity classification is >90% in 45 testing cases. Furthermore, >73% of cases received the high rating score from two radiologists (scored more than 4). This study demonstrates feasibility of developing a new DL-model to efficiently provide quantitative assessment of disease severity based on the automated segmentation of the disease infected regions to support improving efficacy of radiologists in disease diagnosis.

The task of weakly supervised point cloud semantic segmentation has received widespread attention and also has been widely used in autonomous driving, robotics, and modern industries. Due to the high dimensionality and large volume of point cloud data, many technical difficulties appeal to weakly supervised semantic processing, especially segmentation. However, weakly-supervised schemes usually provide only partial labelling information of the underlying point cloud data and thus need to effectively extract local features, geometric information, and contextual relationships only using these limited labelled data for supervised learning. To improve weakly-supervised semantic segmentation, we propose a novel segmentation network through the boundary-based feature aggregation based on a K-NN algorithm with down-sampling operation, and also introduce the smoothness loss and Siamese loss for effective segmentation. The experiments on public datasets demonstrate that our presented segmentation method exceeds most of the existing fully supervised and weakly-supervised methods in terms of mIoU. Specifically, our network has high segmentation accuracy on the labels of objects with similar geometrical structures, such as ceiling, wall, floor, chair and table, reaching 91.2%, 98.8%, 83.3%, 75.3% and 80.2%, respectively. Extensive experiments also illustrate its robustness, effectiveness, and generalization of the proposed weakly supervised segmentation network.

The segmentation of abnormal regions is vital in smart manufacturing. However, the existing segmentation system for detecting sauce-packet leakage on intelligent sensors encounters an issue of imaging blurring caused by uneven illumination. This issue adversely affects segmentation performance, thereby impeding the rapid production of industrial assembly lines. To alleviate this issue, we propose the two-stage Illumination-aware Sauce-packet Leakage Segmentation (ISLS) method for intelligent sensors. The ISLS comprises two main stages: Illumination-aware region enhancement and leakage region segmentation. In the first stage, YOLO-Fastestv2 is employed to capture the Region of Interest (ROI), which reduces redundancy computations. Additionally, we propose an image enhancement to relieve the impact of uneven illumination, enhancing the texture details of ROI. In the second stage, we propose a novel feature extraction network. Specifically, we propose the Multi-scale Feature Fusion Module (MFFM) and the Sequential Self-Attention Mechanism (SSAM) to capture discriminative representations of leakage. The multi-level features are fused by MFFM with a small number of parameters, which capture leakage semantics at different scales. The SSAM realizes the enhancement of valid features and the suppression of invalid features by adaptive weighting of spatial and channel dimensions. Furthermore, we generated a self-built dataset of sauce-packets, including 606 images with various leakage areas. Comprehensive experiments demonstrate that our ISLS method shows better results than several state-of-the-art methods, with additional performance analyses deployed on intelligent sensors to affirm the effectiveness of our proposed method. Our code is available at https://github.com/LSJ5106/SauceDetect.

Image segmentation is the process of partitioning an image into multiple segments where the goal is to simplify the representation of the image and make the image more meaningful and easier to analyze. In particular, semantic segmentation is an approach of detecting the classes of objects, based on each pixel. In the past, most semantic segmentation models were for only one single style, such as urban street views, medical images, or even Manga. In this paper, we proposed a semantic segmentation model called Dual-Pyramid Wide Residual Network (DPWRN) to solve the segmentation for cross-style datasets, which is suitable for diverse segmentation applications. The DPWRN integrated the Pyramid of Kernel paralleled with Dilation (PKD) and Multi-Feature Fusion (MFF) to improve the accuracy of segmentation. To evaluate the generalization of the DPWRN and its superiority over most state-of-the-art models, three datasets with completely different styles are tested in the experiments. Finally, the DPWRN verified its generalization and also showed its superiority over most state-of-the-art models.

As the oil industry increasingly turns to unconventional low-permeability and low-porosity reservoirs, precise post-fracture production prediction is a pivotal instrument in investment de-cision-making, formulation of energy policies, and promotion of environmental assessments. Nevertheless, despite extensive research spanning decades, the precise post-fracture production prediction based on logging parameters remains an intricate task. In this study, we gathered ex-tensive logging data and segmented the post-frac gas production during well testing on the first day to enrich the dataset. Nine pipelines were then architected using various techniques of data preprocessing, feature extraction, and advanced machine learning models. Hyperparameter op-timization was executed via the GridsearchCV. To assess the efficacy of diverse models, metrics including the coefficient of determination (R2), standard deviation (SD), and root mean square error (RMSE) were invoked. Among the several pipelines explored, the PS-NN exhibited excellent predictive capability in specific reservoir contexts (an R2 value of 0.94 and an RMSE of 48.15). In essence, integrating machine learning with logging parameters effectively assesses reservoir productivity at multi-meter formation scales. This strategy not only mitigates uncertainties en-demic to reservoir exploration but also equips petroleum engineers with monitoring on reservoir dynamics, thereby facilitating reservoir development. Additionally, this approach provides res-ervoir engineers with an efficient way of reservoir performance oversight.

Background Most of the Leber hereditary optic neuropathy (LHON) cases are bilateral and sequential, how-ever there are rare unilateral examples, or those in which the delay of onset of vision loss between one and the other eye is longer. In the case of presumed childhood amblyopia in one eye, the vision loss in the good eye may be the only symptom of bilateral disease, that was unnoticed in previ-ously amblyopic eye, or a preexisting episode of LHON on the “amblyopic” eye. Clinical decision in such cases may be difficult and suggestive for other forms of atypical optic neuropathy until confirmed by genetic testing. Case series We present three genetically confirmed (MT-ND1:m.3700G>A, MT-ND6:m14484 T>C, and MT-ND4:m.11778G>A) patients with subacute vision loss in previously good eye with the other eye believed to be amblyopic from the childhood, and their features different of what would be expected in true amblyopia. In all, electrophysiology testing showed bilaterally reduced ampli-tude of PERG with low VEP P100 wave amplitudes and prolonged peak time in both eyes, also unusual for amblyopia. During the follow-up, pallor of the optic discs progressed in all eyes. Significant thinning of the retinal nerve fiber layer around the optic disc (pRNFL) and ganglion cell complex (GCC) in the macular region was present. All three patients had peculiar history. First patient was treated for presumed hyperopic amblyopia that did not improve since child-hood and experienced visual loss on the good eye at the age of 17 and was negative for the three typical LHON mutations. Extended testing confirmed atypical pathogenic variant MT-ND1:m.3700G>A in homoplasmy. The second patient with presumed strabismic amblyopia had unusual presentation of vision loss only at the age of 61 and after exclusion of other causes, typical MT-ND4:m.11778G>A pathogenic variant was found in homoplasmy. The third case was peculiar as he had presumed strabismic amblyopia since childhood and had some degree of disc pallor in the amblyopic eye upon presenting with loss of vision on the good eye at the age of 21 and typical pathogenic variant m14484 T>C, p.Met64Val was subsequently confirmed. However, one year after the disease onset, he started to experience significant spontaneous functional im-provement in the non-amblyopic up to 1.0 Snellen, whilst improvement in the presumed amblyop-ic eye was modest, suggesting preexisting amblyopia. This interestingly extensive improvement was carefully followed by electrophysiology as well as visual acuity and fields. Conclusion This report shows three different scenarios of presentation of LHON in patients with presumed uniocular amblyopia from childhood. In such cases, the diagnosis may be difficult and detailed structural and functional evaluation of the optic nerve head is necessary to assess whether earlier LHON episode was misdiagnosed as amblyopia or whether LHON presented bilaterally on both eyes whilst only being noticed in the previously good eye.

Vein segmentation and projection correction constitute the core algorithms of auxiliary venipuncture device, responding to the accurate venous positioning to assist puncture and reduce the number of punctures and pain of patients. This paper proposes an improved U-Net for segmenting vein and a coaxial correction for image alignment in the self-build vein projection system. The proposed U-Net is embedded by Gabor convolution kernels in the shallow layers to enhance segmentation accuracy. Additionally, to mitigate the semantic information loss caused by channel reduction, the network model is lightweighted by the mean of replacing conventional convolutions with inverted residual blocks. During the visualization process, a method that combining coaxial correction and homography matrix is proposed to address the non-planarity of the dorsal hand in this paper. First, use a hot mirror to adjust the light paths of both projector and camera to be coaxial, and then align the projected image with dorsal hand using a homography matrix. Using this approach, the device requires only a single calibration before use. With the implementation of the improved segmentation method, an accuracy rate of 95.12% is achieved by the dataset. The intersection over union ratio between the segmented and original images is reached at 90.07%. The entire segmentation process is completed in a 0.09 second, and the largest distance error of vein projection onto dorsal hand is 0.53mm. Experiments show that the device has reached practical accuracy and has the value of research and application.

Effective marketing decision-making benefits from a rigorous, data-driven process that systematically evaluates alternatives based on insights and analysis. This study develops and evaluates a 5-stage decision-making process model integrating marketing engineering principles aimed to optimize marketing decisions. An experiment randomized 150 participants into groups following either the proposed model or an unaided approach. Results indicate the model-following group achieved significantly higher ROI from marketing decisions (19.3% vs 16.4%) and employed key elements like customer segmentation, experimentation, and optimization to a greater extent. However, limitations including the experiment's scenario, self-report measures, and cross-sectional design constrain implications. Future research employing probability sampling, multiple decision contexts, longitudinal designs, manipulation checks, and objective metrics can further validate the proposed model. Overall, the study advances the understanding of how structured decision processes based on marketing engineering principles may optimize marketing decisions and outcomes.

The rapid development of LiDAR technology has promoted great changes in forest resource surveys. The airborne LiDAR point cloud can provide precise tree height and detailed vertical structure of the tree stands. Coordinating some representative ground sample plots, LiDAR can be used to estimate key forest resource indicators such as forest stock volume, diameter at breast height, and forest biomass at a large scale. By establishing relationship models between the forest parameters of sample plots and the calculated parameters of LiDAR, these developments may eventually expand the models to large-scale forest resource surveys of entire areas. In this study, eight sample plots in northeast China are used to verify and update the information using point cloud obtained by the LiDAR scanner riegl-vq-1560i. Firstly, the tree crowns are segmented using the profile-rotating algorithm, and dominant trees height are used to check and rectify the tree locations. Secondly, considering the correlation between forestry parameters and tree species, we establish models to distinguish between species using geometric characteristics of tree crowns. Thirdly, when the tree species is known, parameters such as height, crown width, diameter at breast height, biomass and stock volume can be extracted from trees. The prediction models of forestry parameters can also be verified, which can be extended to accurate large-scale forestry surveys based on LiDAR data. Finally, experiment results demonstrate that the F-score of the eight plots in the tree segmentation exceed 0.95, the accuracy of tree species correction exceeds 90%, and the R2 of tree height, east-west canopy width, north-south canopy width, diameter at breast height, above-ground biomass and stock volume are 0.893, 0.757, 0.694, 0.840, 0.896 and 0.891, respectively. The above results indicate that the LiDAR-based estimation of forestry parameters is practical and that these forestry parameter prediction models can be widely applied in forest resource monitoring.

Reasonable trajectory planning is the precondition for the parafoil airdrop system to achieve autonomous accurate homing and safe landing. In order to successfully realize the self-homing of the parafoil airdrop system, a new trajectory optimization design scheme is proposed in this paper. The scheme is based on the parafoil's unique flight and control characteristics and adopts a segmented homing design. Compared with the current common trajectory design method, its core feature is to avoid the problem that the straight-line flight distance before landing is limited by the radius of the height-reducing area and ensure landing accuracy and safety. Firstly, the different starting states of the parafoil airdrop system and the landing requirements were comprehensively considered, and the homing trajectory is reasonably segmented. Based on the requirements of energy control, stable flight, and landing accuracy, the optimal objective function of the trajectory was established, and the trajectory parameters, calculation methods, and constraints were given. Secondly, the cuckoo search algorithm was applied to optimize the objective function to obtain the final home trajectory. Finally, the trajectory planning under different airdrop conditions was simulated and verified. The results showed that the planned trajectories could reach the target point accurately and meet the flight direction requirements, proving the proposed scheme's correctness and feasibility.

The analysis of microscopy images has always been an important yet time consuming process in in materials science. Convolutional Neural Networks (CNNs) have been very successfully used for a number of tasks, such as image segmentation. However, training a CNN requires a large amount of hand annotated data, which can be a problem for material science data. We present a procedure to generate synthetic data based on ad-hoc parametric data modelling for enhancing generalization of trained neural network models. Especially for situations where it is not possible to gather a lot of data, such an approach is beneficial and may enable to train a neural network reasonably. Furthermore, we show that targeted data generation by adaptively sampling the parameter space of the generative models gives superior results compared to generating random data points.

An autonomous concrete crack inspection system is necessary for preventing hazardous incidents arising from deteriorated concrete surfaces. In this paper, we represent a concrete crack detection framework to aid the process of automated inspection. The proposed approach employs a deep convolutional neural network architecture for crack segmentation from concrete image. The proposed network alleviates the effect of gradient vanishing problem present in deep neural network architectures. A feature silencing module is incorporated in the crack detection framework, for eliminating unnecessary feature maps from the network. The overall performance of the network significantly improves as a result. Experimental results support the benefit of incorporating feature silencing within a convolutional neural network architecture for improving the network’s robustness, sensitivity, and specificity. An added benefit of the proposed architecture is its ability to accommodate for the trade-off between specificity (positive class detection accuracy) and sensitivity (negative class detection accuracy) with respect to the target application. Furthermore, the proposed framework achieves a high precision rate and processing time than crack detection architectures present in literature.

Artificial Intelligence based on Deep Learning is opening new horizons in Biomedical research and promises to revolutionize the Microscopy field. Slowly, it now transitions from the hands of experts in Computer Sciences to researchers in Cell Biology. Here, we introduce recent developments in Deep Learning applied to Microscopy, in a manner accessible to non-experts. We overview its concepts, capabilities and limitations, presenting applications in image segmentation, classification and restoration. We discuss how Deep Learning shows an outstanding potential to push the limits of Microscopy, enhancing resolution, signal and information content in acquired data. Its pitfalls are carefully discussed, as well as the future directions expected in this field.

The continuous and precise mapping of glacier calving fronts is essential for monitoring and understanding rapid glacier changes in Antarctica and Greenland, which have the potential for significant sea level rise within the current century. This effort has been mostly restricted to the slow and painstaking manual digitalization of the calving front positions in thousands of satellite imagery products. Here, we have developed a machine learning toolkit to robustly and automatically detect glacier calving front margins in satellite imagery. The toolkit is based on semantic image segmentation using Convolutional Neural Networks (CNN) with a modified U-Net architecture to isolate the calving fronts from satellite images after having been trained with a dataset of images and their corresponding manually-determined calving fronts. As a case study we train our neural network on a varied set Landsat images with lowered resolutions from Jakobshavn, Sverdrup, and Kangerlussuaq glaciers, Greenland and test the results on novel images from Helheim glacier, Greenland to evaluate the performance of the approach. The neural network is able to identify the calving front in new images with a mean deviation of 96.3 m from the true fronts, equivalent to 1.97 pixels on average, while the corresponding error for manually-determined fronts on the same resolution images is 92.5 m. We find that the trained neural network significantly outperforms common edge detection techniques, and can be used to continuously map out calving-ice fronts with a variety of data products.

The use of unmanned aerial vehicle (UAV) during emergency response of a disaster has been widespread in recent years and the terrain images captured by the cameras on board these vehicles are significant sources of information for such disaster monitoring operations. Thus, analyzing such images are important for assessing the terrain of interest during such emergency response operations. Further, these UAVs are mainly used in disaster monitoring systems for the automated deployment of sensor nodes in real time. Therefore, deploying and localizing the wireless sensor nodes optimally, only in the regions of interest that are identified by segmenting the images captured by UAVs, hold paramount significance thereby effecting their performance. In this paper, the highly effective nature-inspired Plant Growth Simulation Algorithm (PGSA) has been applied for the segmentation of such terrestrial images and also for the localization of the deployed sensor nodes. The problem is formulated as a multi-dimensional optimization problem and PGSA has been used to solve it. Furthermore, the proposed method has been compared to other existing evolutionary methods and simulation results show that PGSA gives better performance with respect to both speed and accuracy unlike other techniques in literature.

Accurate detection of forest restoration sites using deep learning is crucial for effective ecosystem management, optimizing reforestation efforts, and ensuring environmental sustainability. While various deep learning-based systems have been developed for this purpose, the influence of different neural network architectures on model performance during the identification of forest restoration sites remains underexplored. This study aimed to address this gap by exploring the optimal methodology for extracting and classifying candidate sites for forest restoration based on Convolutional Neural Networks (CNNs), specialized for image recognition. Four categories—arable land, road and barren, quarry, and forest—were defined as candidate sites for forest restoration. A dataset comprising 17,043 samples was divided into training (11,929) and validation (5,114) sets at a ratio of 7:3 for model learning. Model accuracy was evaluated using pixel accuracy (PA) and mean intersection over union (mean IoU). The Resnet152-U-Net model demonstrated a pixel accuracy of 95.2% and a mean IoU of 61.3%, indicating excellent performance in extracting candidate sites for forest restoration. This approach offers spatial and temporal advantages over conventional field surveys or aerial image-based assessments, potentially serving as valuable data for selecting future forest restoration sites.

Water area segmentation in remote sensing is of great importance for flood monitoring. To overcome some challenges in this task, we construct the Water Index and Polarization Information (WIPI) multi-modality dataset and propose a multi-Modality Fusion and Gated multi-Filter U-Net (MFGF-UNet) convolutional neural network. The WIPI dataset enhances the water information and reduces the data dimension. In particular, the Cloud-Free label provided in the database effectively mitigates the issue of scarcity of labeled samples Since a single form or uniform kernel size cannot handle the variety in size and shape of water bodies, we proposed the gated multi-filter inception (GMF-Inception) module in our MFGF-UNet. Moreover, we utilize the attention mechanism by introducing the Gated Channel Transform (GCT) skip connection and integrating GCT into GMF- Inception to further improve model performance. Extensive experiments on three benchmarks, including WIPI, Chengdu and GF2020 datasets demonstrate that our method achieves favorable performance with lower complexity and better robustness against six competing approaches. For example, on WIPI, Chengdu and GF2020 datasets, the proposed MFGF-UNet model achieves F1 of 0.9191, 0.7410, and 0.8421, respectively, which average F1 on three datasets is 0.0045 higher than the U-Net model and reduces 62% average GFLOPs. New WIPI dataset, code and trained models have been released on GitHub

The Colony-Forming Unit (CFU) counting problem remains a complex issue without a universal solution in biomedical and food safety domains. A multitude of sophisticated heuristics and segmentation-driven approaches have been proposed by numerous researchers. Among those, U-Net is the most frequently cited and popular Deep Learning method. The latter approach provides a segmentation output map and requires an additional counting procedure which accounts for unique segmented regions and detected microbial colonies. However, because of pixel-based targets it tends to generate irrelevant artifacts or errant pixels, leading to inaccurate and mixed post-processing results. In response to these challenges, we propose a novel hybrid counting approach, incorporating a multi-loss U-Net reformulation and a post-processing Petri dish localization algorithm. First of all, our unique innovation lies in the multi-loss U-Net reformulation. We introduce an additional loss term at the bottleneck U-Net layer, focusing on delivering an auxiliary signal indicating where to look for distinct CFUs. Second, our novel localization algorithm accurately incorporates an agar plate and its bezel into the CFU counting routines. Finally, our proposition is further enhanced by the integration of a fully automated solution. This comprises a specially designed uniform Petri dish illumination system and a counting web application. The latter application is capable of directly receiving images from the camera, which are subsequently processed, and the segmentation results are sent back to the user. This feature provides an opportunity to correct the CFU counts, offering a feedback loop that contributes to the continued development of the Deep Learning model. Through extensive experimentation, we have found that all probed multi-loss U-Net architectures incorporated in our hybrid approach consistently outperform their single-loss counterparts which utilize exclusively the combination of Tversky and Cross-Entropy training losses at the output U-Net layer. We report further significant improvements by the means of our novel localization algorithm. This reaffirms the effectiveness of our proposed hybrid solution in addressing contemporary challenges of the precise in-vitro CFU counting.

Motivation: It is essential for the diagnosis and treatment of renal cancers to segment kidney tumours precisely and effectively. In medical image segmentation tasks, deep learning models have demonstrated promising results, and the UNet model is widely employed in this field. However, optimising the UNet model for kidney tumour segmentation further can improve its efficacy and deployment feasibility. Related Works: Previous works have explored various techniques to improve the efficiency of deep learning models in medical image segmentation. Image partitioning methods divides the input image into smaller regions, enabling parallel processing and reducing memory requirements. Pruning techniques eliminates redundant or insignificant weights, neurons and connections, resulting in a more compact and efficient model architecture. However, the UNet model architecture and its complexity in the context of kidney tumor segmentation using UNet remains unexplored. Methodology: The proposed methodology consists of adaptive partitioning and weight pruning. Adaptive partitioning divides the UNet model into smaller sub-models, facilitating parallel processing and accelerating inference without compromising segmentation accuracy. Weight pruning techniques remove redundant or less significant weights from the UNet-P model, reducing complexity and improving inference time by eliminating unnecessary computations. The adaptive partitioning and weight pruning processes are seamlessly integrated within the UNet-P architecture, resulting in an optimized model for kidney tumor segmentation. Results: We performed experiments utilising a dataset of KiT 23 CT scan images containing images of kidney malignancies. Compared to the standard UNet model, the optimised UNet-PWP model with adaptive partitioning and weight pruning obtained significant efficiency gains. The adaptive partitioning permitted parallel computation of sub-models, which accelerated inference times. Weight pruning decreased the UNet-PWP model’s complexity without compromising segmentation accuracy, thereby enhancing efficiency. The results of our experiments demonstrated the efficacy of the proposed method with 98% accuracy, demonstrating its potential for deployment in health sector.

Teeth segmentation plays a pivotal role in dental diagnosis, treatment, planning, and the development of computer-aided dental systems. It enables precise identification and analysis of dental structures, aiding in detecting dental abnormalities, measuring tooth dimensions, and assessing oral health conditions. Accurate teeth segmentation also facilitates the automation of dental workflows, leading to improved efficiency and reduced human error. Artificial Intelligence (AI) has witnessed rapid advancements, with various approaches developed or enhanced. While Convolutional Neural Networks (CNNs) have been widely used in medical image segmentation, the U-Net architecture has emerged as a standout performer due to its exceptional segmentation capabilities. This paper presents a proof of concept for the Attention U-Net architecture, as previously used in [1], applied to teeth segmentation. The study demonstrates the superior performance of this network in accurately segmenting teeth using a newly available benchmark dataset called Tufts Dental X-Ray Dataset. When trained and tested on 10-fold cross-validation, the model achieved an average dice coefficient of 95.01%, intersection over union of 90.6%, and pixel accuracy of 98.82%. These scores surpass those of all other networks implemented on the same dataset. By leveraging the Attention U-Net architecture, our research showcases the potential of advanced AI techniques in dental radiography. The findings contribute to the ongoing efforts to develop automated systems to assist dental professionals in their clinical practice.

Capsule endoscopy (CE) has been a widely used medical imaging tool for the diagnosis of gastrointestinal tract abnormalities like bleeding. But the CE captures a huge number of image frames that are time-consuming and tedious tasks for medical experts to diagnose manually. To address this issue, researchers focused on the computer-aided bleeding detection system to identify bleeding automatically in real-time. This paper presents a systematic review of the available state-of-the-art computer-aided bleeding detection algorithms for capsule endoscopy. The review was carried out by searching five different repositories: Scopus, PubMed, IEEE Xplore, ACM Digital Library, and ScienceDirect for all original publications on computer-aided bleeding detection published between 2001 and 2021. The PRISMA methodology was used to perform the review, and 112 full-texts of scientific papers were reviewed. The contributions of this paper are I) a taxonomy for computer-aided bleeding detection algorithms for capsule endoscopy is identified, II) the available state-of-the-art computer-aided bleeding detection algorithms including various color spaces (RGB, HSV, etc.), feature extraction techniques, and classifiers are discussed, and III) identify the most effective algorithm for practical use cases. Finally, the paper is concluded by providing future direction for computer-aided bleeding detection research.

Modern hyperspectral imaging technologies generate enormous datasets that could potentially transmit a wealth of information, but such a resource presents numerous difficulties for data analysis and interpretation. Deep learning techniques undoubtedly provide a wide range of potential for solving both traditional imaging tasks and exciting new problems in the spatial-spectral domain. This is true in the primary application area of remote sensing, where hyperspectral technology originated and has made the majority of its progress, but it may be even more true in the vast array of now existing and developing application areas that make use of these imaging technologies. The current review advances on two fronts: on the one hand, it is directed at domain experts who desire an updated overview of how deep learning architectures might work in conjunction with hyperspectral acquisition techniques to address specific tasks in various application sectors. On the other hand, by providing them with a picture of how deep learning technologies are applied to hyperspectral data from (near)real-time perspective. The contributions of this review include the existence of these two points of view and the inclusion of opportunities and important problems associated with the development of future CHIME mission to be launched by European Space Agency (ESA).

Cardiovascular disease is the leading cause of death worldwide. A key factor in assessing the risk of cardiovascular disease is left ventricular functional evaluation. Left ventricular (LV) systolic function is evaluated by measuring the left ventricular ejection fraction (LVEF) using echocardiography data. Therefore, quick and accurate left ventricle segmentation is important for estimating the LVEF. However, it is difficult to accurately segment the left ventricle due to changes in the shape and area of the left ventricle during cardiac cycles. In this study, we proposed a framework that considers changes in the shape and area of the left ventricle during the cardiac cycle by applying the convolutional long short-term memory (CLSTM) approach. In addition, we evaluated the left ventricular segmentation and multidimensional quantification of the proposed system in comparison to manual and automated segmentation methods. In addition, to assess the validity of CLSTM, the values of multi-dimensional quantification metrics were compared and analyzed using graphs and Bland–Altman plots on a frame-by-frame basis. We demonstrated that the CLSTM method effectively segments the left ventricle by considering the LV activity. In conclusion, we demonstrated that LV segmentation based on our framework may be utilized to accurately estimate LVEF values.

Object segmentation is still considered a challenging problem in autonomous driving, particularly in consideration of real world conditions. Following this line of research, this paper approaches the problem of object segmentation using LiDAR-camera fusion and semi-supervised learning implemented in a fully-convolutional neural network. Our method is tested on real-world data acquired using our custom vehicle iseAuto shuttle. The data include all-weather scenarios, featuring night and rainy weather. In this work, it is shown that LiDAR-camera fusion with only a few annotated scenarios and semi-supervised learning, it is possible to achieve robust performance on real-world data in a multi-class object segmentation problem. The performance of our algorithm is measured in terms of intersection over union, precision, recall and area-under-the-curve average precision. Our network achieves 82% IoU in vehicle detection in day fair scenarios and 64% IoU in vehicle segmentation in night rain scenarios.

In response to droughts, various media campaigns and water saving instructions are released, often however, with only temporary water conservation effects. A promising development is this regard are Digital Water Meters (DWM) that provide near real-time water-use feedback. Despite extensive DWM experience in some water-stressed regions, a profound understanding of the initial attitude towards DWM and message tailoring opportunities are rarely empirically explored. Therefore, we aim to obtain insights into the attitude towards the introduction of DWM and explore opportunities for message tailoring, a topic of extra relevance as we may be on the threshold of a large-scale implementation in many world regions. Messages tailored to (i) normative beliefs and attitudes on drinking water, (ii) water-use activity and (iii) phase of decision-making, seem particularly compatible with DWM. Through a survey (n=1037) in the Netherlands, we observe that 93% of respondents have no objections utility investments in DWM and that 78% would accept a free DWM because of improved leakage detection, lower costs and environmental considerations. Finally, instead of sociodemographic factors, we observed that an attitude-based customer segmentation approach proved an especially useful predictor of respondent’s motivation to endorse DWM and forms a promising basis for water conservation message-tailoring strategies.

Automatic methods for constructing navigation routes do not fully meet all requirements. The aim of this study was to modify the methodology for generating indoor navigation models based on the Medial Axis Transformation (MAT) algorithm. The simplified method for generating corridor axes relies on the Node-Relation Structure (NRS) methodology. The axis of the modeled structure (corridor) is determined based the points of the middle lines intersecting the structure (polygon). The proposed solution involves a modified approach to the segmentation of corridor space. Traditional approaches rely on algorithms to construct Triangulated Irregular Networks (TINs) by Delaunay triangulation or algorithms for generating Thiessen polygons known as Voronoi diagrams (VDs). In this study, both algorithms were used in the segmentation process. The edges of TINs intersect structures. Selected midpoints on TIN edges, which are located in the central part of the structure, are used to generate VDs. Polygon VDs segment corridor structures. The identifiers or structure nodes are the midpoints on TIN edges rather than the calculated centroids. The generated routes are not zigzag lines, and they approximate natural paths. The main advantage of the proposed solution is its simplicity which can be attributed to the use of standard tools for processing spatial data in a geographic information system.

In contrast to physical sustainable measures carried out in homes, such as insulation, the installation of a Home Energy Management System (HEMS) has no direct and immediate energy-saving effect. A HEMS gives insight into resident behaviour regarding energy use. When this is linked to the appropriate feedback, the resident is in a position to change his or her behaviour. This should result in reduced gas and/or electricity consumption. The aim of our study is to contribute towards the effective use of home energy management systems (HEMS) by identifying types of homeowners in relation to the use of HEMS. The research methods used were a literature review and the Q-method. A survey using the Q-method was conducted among 39 owners of single-family homes in various Rotterdam neighbourhoods. In order to find shared views among respondents, a principal component analysis (PCA) was performed. Five different types of homeowner could be distinguished: the optimists, the privacy-conscious, the technicians, the sceptics, and the indifferent. Their opinions vary as regards the added value of a HEMS, what characteristics a HEMS should have, how much confidence they have in the energy-saving effect of such systems, and their views on the privacy and safety of HEMS. The target group classification can be used as input for a way in which local stakeholders, e.g. a municipality, can offer HEMS that is in line with the wishes of the homeowner.

This paper presents the automation of the thin-layer chromatography technique whose separation and identification of molecules present in a mixture are currently done manually and laboriously [1]. We have therefore found an interest in automating this technique. In this part, the method implemented comprises 2 steps. First we proceeded to the segmentation of the spots obtained on the chromatographic plate. We then developed a program to identify families of molecules such as coumarins, terpenes, tannins, flavonoids, polyphenols, etc. by calculating segmentation parameters such as standard deviation, entropy, average pixel intensity from an algorithm on the matlab software. Finally our results have been compared to the results obtained by the traditional identification technique in laboratories. Some similarity between the two results obtained shows the reliability and the robustness of our technique.

In table tennis competitions the rule violation judgment with the greatest controversy is the height of the ball serve. This is because inaccuracy in the ball height judgment, which results in erroneous judgment, is unavoidable. Thus, we designed an automatic image judgment auxiliary system for table tennis ball height during service in this study. We used a high-speed camera to record the ball toss in the table tennis service. The designed algorithm architecture can automatically search for the ball and the position of the hand action under low light source conditions. The algorithm is mainly divided into hue-saturation-value color space processing and morphology processing using Hough transform to search for the circular ball. Experiment result shows that color segmentation can successfully and accurately determine the ball position under low light conditions. The morphology method can find the position of the hand and help determine the moment when the ball leaves the hand during the service ball toss. Finally, the actual size of the target is used to estimate the actual distance unit represented by the image pixel.

Fundus image registration plays a crucial role in the clinical evaluation of ocular diseases, such as diabetic retinopathy and macular degeneration, necessitating meticulous monitoring. The alignment of multiple fundus images enables the longitudinal analysis of patient progression, widening the visual scope, or augmenting resolution for detailed examinations. Currently, prevalent methodologies rely on feature-based approaches for fundus registration. However, certain methods exhibit high feature point density, posing challenges in matching due to point similarity. This study introduces a novel fundus image registration technique integrating U-Net for the extraction of feature points employing FIVES for its training and evaluation, a novel and large dataset for blood vessels segmentation, prioritizing point distribution over abundance. Subsequently, the method employs medial axis transform and pattern detection to obtain feature points characterized by the Fast Retina Keypoint (FREAK) descriptor, facilitating matching for transformation matrix computation. Assessment of the vessel segmentation achieves 0.7559 for Intersection Over Union (IoU), while evaluation on the Fundus Image Registration Dataset (FIRE) demonstrates the method’s comparative performance against existing methods, yielding a registration error of 0.596 for area under the curve, refining similar earlier methods and suggesting promising performance comparable to prior methodologies.

(1) Background: OCT imaging has been used to assess enamel demineralization in dental research but is not yet developed enough to qualify as a diagnostic technique in clinics. The current capabilities of most commercial acquisition software allow for visual and qualitative assessment. There is a need for a fast and verified batch-processing algorithm for segmenting and analyzing the de-mineralized enamel. This study suggests a GUI MATLAB algorithm for processing and quantitative analysis of the demineralized enamel. (2) Methods: A group of artificially demineralized human enamels was in vitro scanned under the OCT, and ROI frames were extracted. By using a selected intensity threshold colormap, inter- (Ie) and intra- (Ia) prismatic demineralization can be segmented. A set of quantitative measurements for average demineralized depth, average line profile, and integrated reflectivity can be obtained for an accurate assessment. Real and simulated OCT frames were used for algorithm verification. (3) Results: A strong correlation between automated and known Excel measurements for the average demineralization depth was found (R² > 0.97). (4) Conclusions: OCT image segmentation and quantification of the enamel demoralization zones are possible. The algorithm can assess the future development of a real-time assessment of dental diagnostics using an oral probe OCT.

Bone metastasis detection and quantification on bone scintigraphy is challenging and clinical important for treatment and patient’s life quality. To develop a CNN based diagnostic system for automated segmentation on bone metastasis regions is non-trivial, especially for a small dataset. A dataset in house comprising 100 breast cancer patients and 100 prostate cancer patients is utilized for this research. The Double U-Net model is adapted through the integration of background removal, adding negative samples, and transfer learning methods for bone metastasis detection. The performance is investigated via 10-fold cross-validation and computed in pixel-wise scale. The best model we achieved has precision of 63.08%, sensitivity of 70.82%, and F1-score of 66.72%. The developed system has the potential to provide pre-diagnostic reports for physicians in final decisions and the calculation of the bone scan index (BSI) with the combination with bone skeleton segmentation.

Building Information Modelling (BIM) has gained significant relevance in civil engineering, particularly in the infrastructure sector. It offers the potential to increase efficiencies, optimize processes, and enhance sustainability throughout infrastructure projects’ life cycles. BIM consolidates information about asset components into a single model, enabling real-time updates, cost reduction, and improved consistency. Digital twins serve as valuable extensions of BIM in infrastructure, playing a crucial role during operation. By capturing real-time data from sensors and IoT devices, digital twins enabls continuous monitoring, proactive maintenance, efficient energy management, and informed decision-making for optimized operational efficiency. Advancements in 3D point cloud technologies, such as 3D laser scanning, have expanded BIM’s application in operation and maintenance. These technologies rapidly capture accurate and detailed three-dimensional information, prompting the exploration of automated alternatives to manual point cloud modeling. This paper demonstrates the application of supervised machine learning, specifically support vector machines, for analyzing and segmenting 3D point clouds, a crucial step in 3D modeling. Various approaches for semantic segmentation are introduced, investigated, and evaluated using diverse data sets. The results highlight the effectiveness of supervised machine learning techniques in achieving accurate segmentation of 3D point clouds.

The administration of regional neuraxial analgesia for pain relief during labor is widely recognized as a safe and effective method involving medication delivery into the epidural or subarachnoid space in the lower back. This study proposes an innovative semantic image segmentation methodology emphasizing enhanced interpretability using convolutional Random Fourier Features and layer-wise weighted class-activation maps tailored explicitly for foot segmentation in regional analgesia monitoring. Namely, our contribution is twofold: i) a novel Random Fourier Features layer is introduced to deal with image data to enhance three well-known architectures (FCN, UNet, and ResUNet); ii) three novel quantitive measures are presented to evaluate the interpretability of a given deep learning model devoted to segmentation tasks. Our approach is rigorously evaluated on a demanding dataset of foot thermal images from pregnant women who received epidural anesthesia. Its small size and considerable variability characterize the dataset. Our validation results demonstrate that the proposed methodology not only achieves competitive foot segmentation performance but also significantly enhances the explainability of the process, rendering it well-suited for applications such as epidural insertion during labor.

Industrial data scarcity is one of the largest factors holding back the widespread use of machine learning in manufacturing. To overcome this problem, the concept of transfer learning was developed and it achieved high attention in recent industrial research. Our paper focuses on the problem of time series segmentation and presents the first in-depth research about transfer learning for deep-learning based time series segmentation on the example of industrial end-of-line pump testing. In particularly, we investigate if the performance of deep learning models can be increased by pretraining the network with data from other domains. Three different scenarios are analyzed: source and target data being closely related, source and target data being distantly related, and source and target data being non-related. The results demonstrate that transfer learning can enhance the performance of time series segmentation models in respect to accuracy and training speed. The benefit is most clearly seen in scenarios where source and training data are closely related and the number of target training data samples is lowest. However, in the scenario of non-related datasets, cases of negative Transfer Learning were observed as well. Thus, the research emphasizes the potential, but also the challenges of industrial Transfer Learning.

Disorders of swallowing often lead to pneumonia when material enters the airways (aspiration). Flexible Endoscopic Evaluation of Swallowing (FEES) plays a key role in the diagnostics of aspiration but is prone to human errors. An AI-based tool could facilitate this process. Recent non-endoscopic/non-radiologic attempts to detect aspiration using machine-learning approaches have led to unsatisfying accuracy and show black box characteristics. Hence, for clinical users it is hard to trust in these model decisions. Our aim is to introduce an explainable artificial intelligence (XAI) approach to detect aspiration in FEES. Our approach is to teach the AI about the relevant anatomical structures like the vocal cords and the glottis based on 92 annotated FEES videos. Simultaneously, it is trained to detect bolus that passes the glottis and becomes aspirated. During testing, the AI successfully recognized glottis and vocal cords, but could not yet achieve satisfying aspiration detection quality. Albeit detection performance has to be optimized, our architecture results in a final model that explains its assessment by locating meaningful frames with relevant aspiration events and by highlighting the suspected bolus. In contrast to comparable AI tools, our framework is verifiable, interpretable and therefor accountable for clinical users.

Lesion studies are crucial in establishing brain-behavior relationships, and accurately segmenting the lesion represents the first step in achieving this. Manual lesion segmentation is the gold standard for chronic strokes. However, it is labor-intensive, subject to bias, and limits sample size. Therefore, our objective is to develop an automatic segmentation algorithm for chronic stroke lesions on T1-weighted MR images. Methods: To train our model, we utilized an open-source dataset: ATLAS v2.0 (Anatomical Tracings of Lesions After Stroke). We partitioned the dataset of 655 T1 images with manual segmentation labels into five subsets and performed a 5-fold cross-validation to avoid overfitting of the model. We used a deep neural network (DNN) architecture for model training. Results: To evaluate the model performance, we used three metrics that pertain to diverse aspects of volumetric segmentation including shape, location, and size. The Dice similarity coefficient (DSC) compares the spatial overlap between manual and machine segmentation. The average DSC was 0.65 (0.61- 0.67; 95% bootstrapped CI). Average symmetric surface distance (ASSD) measures contour distances between the two segmentations. ASSD between manual and automatic segmentation was 12mm. Finally, we compared the total lesion volumes and the Pearson correlation coefficient (ρ) between the manual and automatically segmented lesion volumes, which was 0.97(p-value < 0.001). Conclusions: We present the first automated segmentation model trained on a large multicentric dataset. This model will enable automated on-demand processing of MRI scans and quantitative chronic stroke lesion assessment.

A digital text abstract presents the essential information of an article, and we can find the trend and value of the research by analyzing it rigorously and digging up knowledge. Therefore, this study focuses on the abstracts of index journals in China and Taiwan from July 2010 to June 2020 (a total of 3,283 abstracts). Through the concepts of text mining and natural language processing (NLP), it constructs processes such as text retrieval, text segmentation and word cloud analysis, TF-IDF weight analysis, co-word analysis, network analysis, and trend analysis, and analyses a large amount of text data. The results show that the scope of research in China covers the fields of social sports and sports science, and research in Taiwan covers both natural and social sciences. The network diagram highlights the richness of sports-related research fields in the two regions, but research on sports philosophy is relatively rare. It is suggested that all disci-plines/departments should re-allocate the same resources, so as to show a balanced development trend and help expand a new chapter in the sports academic field.

The strategy of any organization is based on the growth of its customer base, and one of its principles is that selling a product to an existing customer is much more profitable than acquiring a new customer. However, this approach has several opportunities for improvement, since it usually has a totally reactive approach, which does not give opportunity to the areas specialized in customer experience and recovery, to give an effective response for that moment, since the customer is gone at the time of the intervention. This happens because usually a diagnostic analysis of customers who have stopped buying products or services in a defined period, commonly three (3) periods or months, is performed. This thesis work challenges the way to face this problem, and proposes the development of a complete solution, which does not focus exclusively on the prediction of churn, as is usually done in the state of the art research, but to intervene in different interactions that can be carried out with customers. The above focused not only to prevent customer churn, but to generate an added value of continuous improvement in sales processes, increase customer penetration, leading to an improvement in customer experience and consequently, an increase in customer loyalty.

Intertidal seagrass plays a vital role in estimating the overall health and dynamics of coastal environments due to its interaction with tidal changes. However, most seagrass habitats around the globe have been in steady decline due to human impacts, disturbing the already delicate balance in environmental conditions that sustain seagrass. Miniaturization of multi-spectral sensors has facilitated very high resolution mapping of seagrass meadows, which significantly improve the potential for ecologists to monitor changes. In this study, two analytical approaches used for classifying intertidal seagrass habitats are compared: Object-based Image Analysis (OBIA) and Fully Convolutional Neural Networks (FCNNs). Both methods produce pixel-wise classifications in order to create segmented maps, however FCNNs are an emerging set of algorithms within Deep Learning with sparse application towards seagrass mapping. Conversely, OBIA has been a prominent solution within this field, with many studies leveraging in-situ data and multiscale segmentation to create habitat maps. This work demonstrates the utility of FCNNs in a semi-supervised setting to map seagrass and other coastal features from an optical drone survey conducted at Budle Bay, Northumberland, England. Semi-supervision is also an emerging field within Deep Learning that has practical benefits of achieving state of the art results using only subsets of labelled data. This is especially beneficial for remote sensing applications where in-situ data is an expensive commodity. For our results, we show that FCNNs have comparable performance with standard OBIA method used by ecologists, while also noting an increase in performance for mapping ecological features that are sparsely labelled across the study site.

The Coronavirus disease (COVID-19) caused by a novel coronavirus, SARS-CoV-2, has been declared as a global pandemic. Due to its infection rate and severity, it has emerged as one of the major global threats of the current generation. To support the current combat against the disease, this research aims to propose a Machine Learning based pipeline to detect the COVID-19 infection using the lung Computed Tomography scan images (CTI). This implemented pipeline consists of a number of sub-procedures ranging from segmenting the COVID-19 infection to classifying the segmented regions. The initial part of the pipeline implements the segmentation of the COVID-19 affected CTI using Social-Group-Optimization and Kapur’s Entropy thresholding, followed by k-means clustering and morphology-based segmentation. The next part of the pipeline implements feature extraction, selection and fusion to classify the infection. PCA based serial fusion technique is used in fusing the features and the fused feature vector is then employed to train, test and validate four different classifiers namely Random Forest, k-Nearest Neighbors (KNN), Support Vector Machine with Radial Basis Function, and Decision Tree. Experimental results using benchmark datasets show a high accuracy (> 91%) for the morphology-based segmentation task and for the classification task the KNN offers the highest accuracy among the compared classifiers (> 87%). However, this should be noted that this method still awaits clinical validation, and therefore should not be used to clinically diagnose the ongoing COVID-19 infection.

The driving force behind adopting the idea of ​​sustainable development are producers and retailers. Unfortunately, when preparing their product range for consumers, many of them still only pay attention to the size of the customers’ earnings, how often they shop and how much they buy when shopping. In consumer segmentation, sustainable values ​​that consumers apply when making their purchasing decisions are rarely taken into account. The aim of this article is to show that values ​​such as environmental protection, the ethical behaviour of producers, fair trade or maximising the utility function of consumption are so important in the purchasing process in the coffee market that they can be used as segmentation variables. The Polish coffee market was selected to carry out segmentation taking into account the consumers' sustainable values. The main source of the article is the results of a standardized online survey conducted on a nationwide sample of 800 coffee consumers in July 2018. Multi-dimensional analyses such as extrapolative factor analysis (EFA) and cluster analysis (CA) were used to describe the obtained results. As a result, six segments of coffee consumers were identified and described: “responsible, aspiring to be connoisseurs”, “loyal coffee enthusiasts”, “pragmatic users”, “coffee laypersons”, “sophisticated connoisseurs”, “consumerists, connoisseurs, but not at any price”. Among the identified segments, the sustainable consumption values ​​most often mentioned refer to "responsible, aspiring to be connoisseurs", and the least often - ”consumerists, connoisseurs, but not at any price”. The conclusions presented in the last part of the article may be used by manufacturing and trade enterprises, operating on the coffee market, in order to respond to the identified needs and expectations of consumers and by governmental and social organisations so as to determine the directions of pro-ecological education of consumers.

Degradation of environment quality is currently the prime cause of the recent occurrence of natural disasters; it also contributes in the increase of the area that is prone to natural disasters. This research is aimed to map the potential of areas around Pesanggrahan river in DKI Jakarta by segmenting the Digital Elevation Model derived from LIDAR data. The objective of this segmentation is to find the watershed lines of the DEM image. Data processing in this research is using LIDAR data which take the ground surface data, which is overlaid with Jakarta river map and subsequently, the data is then segmented the image. The expected result of the research is the flood potential area information, especially along the Pesanggrahan river in South Jakarta.

Semantic image segmentation has recently witnessed considerable progress by training deep convolutional neural networks (CNNs). The core issue of this technique is the limited capacity of CNNs to depict visual objects. Existing approaches tend to utilize approximate inference in a discrete domain or additional aides and do not have a global optimum guarantee. We propose the use of the multi-label manifold ranking (MR) method in solving the linear objective energy function in a continuous domain to delineate visual objects and solve these problems. We present a novel embedded single stream optimization method based on the manifold ranking (MR) model to avoid approximations without sacrificing expressive power. In addition, we propose a novel network, which we refer to as dual multi-scale manifold ranking (\textbf{DMSMR}) network, that combines the dilated, multi-scale strategies with the single stream MR optimization method in the deep learning architecture to further improve the performance. Experiments on high resolution images, including close-range and remote sensing datasets, demonstrate that the proposed approach can achieve competitive accuracy without additional aides in an end-to-end manner.

This research introduces a pioneering solution to the challenges posed by gastrointestinal tract (GI) cancer in radiation therapy, focusing on the imperative task of precise organ segmentation for minimizing radiation-induced damage. GI imaging has historically used manual demarcation, which is laborious and uncomfortable for patients. We address this by introducing the ResECA-U-Net deep learning model, a novel combination of the UNet and ResNet34 architectures. Furthermore, we further augment its functionality by incorporating the Efficient Channel Attention (ECA-Net) methodology. By utilizing data from the UW-Madison Carbone Cancer Centre, we carefully investigate several image processing techniques designed to capture critical local characteristics. With its foundation in computer vision concepts, the ResECA-U-Net model is excellent at extracting fine details from GI images. Sophisticated metrics such as intersection over union (IoU) and the dice coefficient are used to evaluate performance. Our study's outcomes demonstrate the effectiveness of the suggested method, yielding an impressive 96.27% Dice coefficient and 91.48% IoU. These results highlight the significant contribution that our strategy has made to the advancement of cancer therapy. Beyond its scientific merits, this work has the potential to significantly enhance cancer patients' quality of life and provide better long-term outcomes. Our work is a significant step towards automating and optimizing the segmentation process, which can potentially change how GI cancer is treated completely.

The importance of detecting and diagnosing the imminence of aneurysm rupture before it occurs cannot be overstated. However, this process is often time-consuming and challenging, with variability in conclusions not uncommon among experts. Furthermore, current state-of-the-art models in medical image segmentation suffer from limited availability of large annotated datasets for training, exacerbated by an immense data imbalance. In most segmentation tasks, 3D segmentation is preferred due to its capacity to leverage more contextual information. However, these models require more data, which is constrained by the aforementioned issues. In the realm of current diagnosis models, those lacking geographic context are notably ineffective. To address these issues, the aim is to develop a model pipeline to accurately detect cerebral intracranial aneurysms and diagnose rupture imminence through 3D magnetic resonance angiography (MRA) and tabular input, augmented with the implementation of neuro-symbolic ai. The utilization of data fusion to tackle the lack of context in tabular models is proposed, leveraging extracted geographical features from a segmentation model. To enhance segmentation results and tackle the data imbalance in aneurysm segmentation, a two-stage model pipeline that extracts contextual geographic features before aneurysm segmentation is suggested. Segmentation results are additionally improved through ensemble techniques and novel preprocessing techniques. Finally, a neuro-symbolic aspect is introduced to enhance model diagnosis, interpretability and performance. The multi-step Integrated Neuro-Symbolic Analysis Pipeline for Cerebral Aneurysm Rupture Diagnosis is introduced.

With the popularity of solar energy in the electricity market, demand arises for data such as precise locations of solar panels for efficient energy planning, management, and distribution. However, this data is not easily accessible and in some cases, information such as precise locations does not exist. Furthermore, existing data sets for training semantic segmentation models of PV installations are limited, and their annotation is time-consuming and labor-intensive. Therefore, for additional remote sensing (RS) data creation, the pix2pix generative adversarial network (GAN) is utilized, enriching the original resampled training data of varying GSDs without compromising its integrity. Experiments done with the DeepLabV3 model, ResNet-50 backbone, and pix2pix GAN architecture were conducted to find the optimal configuration for an accurate RS imagery segmentation model. The result is a fine-tuned solar panel semantic segmentation model, trained using transfer learning and utilizing an optimal amount – 60% of generated RS imagery for additional training data, increasing model accuracy. The findings demonstrate the benefits of using GAN-generated images as additional training data, increasing the size of small data sets, and improving the capabilities of the segmentation model for solar panel detection in RS images.

AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512x512 pixels were extracted using translation lesion boxes that encompass lesions in different positions and capture different contexts of perilesional skin. In total, 16488 translation augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings.

There is a need for cost-effective and non-invasive methods of monitoring feeding behavior in livestock operations, considering the significant impact of feed costs on economic efficiency and assisting in detecting health issues of group-fed animals. This paper proposes using deep learning-based computer vision techniques to detect pen-fed beef cattle feeding behavior using Mask Region-based Convolutional Neural Network (RCNN). A deep learning model was pre-trained on the Common Objects in Context (COCO) dataset to generate cattle instance segmentation. Manually defined feed bunk polygons are compared with these segmentation masks to derive feeding time for each bunk. A full day’s worth of video data and the corresponding physical sensor data are collected for the experiment. By benchmarking the computer vision detected data with physical ground truth over random time segments from morning to evening (thus various lighting conditions), the optimal thresholds for Mask RCNN are determined to be 0.7 for bounding boxes and 0.1 for masks. Using these parameters. The reports suggest that the computer vision system achieved a precision of 87.2% and a recall of 89.1%, signifying precise detection of feeding events. Our study, to the best of our knowledge, was one of the first investigations of instance segmentation on feeding time sense, which combines deep learning methods with traditional computer vision logistics, reporting on feeding time data collection and processing, camera testing and adjustment, and performance evaluation. Future research directions include computer vision applied in feed grading and animal re-identification for individual production analysis.

In response to the growing inspection demand exerted by process automation in component manufacturing, Non-destructive testing (NDT) continues to explore automated approaches that utilize deep learning algorithms for defect identification, including within digital X-ray radiography images. This necessitates a thorough understanding of the implication of image quality parameters on the performance of these deep learning models. This study investigates the influence of two image quality parameters, namely Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR), on the performance of U-net deep learning segmentation model. Input images were acquired with varying combinations of exposure factors such as kilovoltage, milli-ampere, and exposure time, which altered the resultant quality. The data was sorted into 5 different datasets according to their measured SNR and CNR values. The deep learning model was trained 5 distinct times, utilizing a unique dataset for each training session. Training the model with high CNR values yielded an intersection over Union (IoU) metric of 0.9594 on test data of the same category but drops to 0.5875 when tested on lower CNR test data. The result in this study emphasizes the importance of achieving a balance in training dataset according to the investigated quality parameters, to enhance the performance of deep learning segmentation models in NDT radiography applications.

Schistosomiasis is a debilitating parasitic disease of poverty that affects more than 200 million people worldwide, mostly in sub-Saharan Africa, and is clearly associated with the construction of dams and water resource management infrastructure in tropical and subtropical areas. Changes to hydrology and salinity linked to water infrastructure development may create conditions favorable to the aquatic vegetation that is suitable habitat for the intermediate snail hosts of schistosome parasites. With thousands of small and large water reservoirs, irrigation canals, and dams developed or under construction in Africa, it is crucial to accurately assess the spatial distribution of high-risk environments that are habitat for freshwater snail intermediate hosts of schistosomiasis in rapidly changing ecosystems. Yet, standard techniques for monitoring snails are labor-intensive, time-consuming, and provide information limited to the small areas that can be manually sampled. Consequently, in low-income countries where schistosomiasis control is most needed, there are formidable challenges to identify potential transmission hotspots for targeted medical and environmental interventions. In this study, we developed a new framework to map the spatial distribution of suitable snail habitat across large spatial scales in the Senegal River Basin by integrating satellite data, high-definition, low-cost drone imagery, and an artificial intelligence (AI)-powered computer vision technique called semantic segmentation. A deep learning model (U-Net) was built to automatically analyze high-resolution satellite imagery to produce segmentation maps of aquatic vegetation, with a fast and robust generalized prediction that proved more accurate than a more commonly used random forest approach. Accurate and up-to-date knowledge of areas at highest risk for disease transmission can increase the effectiveness of control interventions by targeting habitat of disease-carrying snails. With the deployment of this new framework, local governments or health actors might better target environmental interventions to where and when they are most needed in an integrated effort to reach the goal of schistosomiasis elimination.

Image segmentation is a new challenge prob- lem in medical application. The use of medical imaging has become an integral part of research, as it allows us to see inside the human body without surgical intervention. Many researcher have studied brain segmentation. One stage method is used to segment the brain tissues. In this paper, we proposed the multi-stage generative ad- versarial network to solve the problem of information loss in the one-stage. We utilize the coarse-to-fine to improve brain segmentation using multi-stage generative adversar- ial networks (GAN). In the first stage, our model generated a coarse outline for (i) background and (ii) brain tissues. Then, in the second stage, the model generated outline for (i) white matter (WM), (ii) gray matter (GM) and (iii) cerebrospinal fluid (CSF). A good result can be achieved by fusing the coarse outline and refine outline. We conclude that our model is more efficient and accu- rate in practice for both infant and adult brain segmenta- tion. Moreover, we observe that multi-stage model is faster than prior models. To be more specific, the main goal of multi-stage model is to see the performance of the model in a few shot learning case where a few labeled data are available. For medical image, this proposed model can work in a wide range of image segmentation where the convolution neural networks and one-stage methods have failed.

The strategy of any organization is based on the growth of its customer base, and one of 5 its principles is that selling a product to an existing customer is much more profitable than acquiring 6 a new customer. However, this approach has several opportunities for improvement, since it usu- 7 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 8 customer experience and recovery, to give an effective response for that moment, since the customer 9 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 10 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 11 riods or months, is performed. This thesis work challenges the way to face this problem, and pro- 12 poses the development of a complete solution, which does not focus exclusively on the prediction 13 of churn, as is usually done in the state of the art research, but to intervene in different interactions 14 that can be carried out with customers. The above focused not only to prevent customer churn, but 15 to generate an added value of continuous improvement in sales processes, increase customer pene- 16 tration, leading to an improvement in customer experience and consequently, an increase in cus- 17 tomer loyalty.

The strategy of any organization is based on the growth of its customer base, and one of 5 its principles is that selling a product to an existing customer is much more profitable than acquiring 6 a new customer. However, this approach has several opportunities for improvement, since it usu- 7 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 8 customer experience and recovery, to give an effective response for that moment, since the customer 9 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 10 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 11 riods or months, is performed. This paper challenges the way to face this problem, and proposes 12 the development of a complete solution, which does not focus exclusively on the prediction of 13 churn, as is usually done in the state of the art research, but to intervene in different interactions 14 that can be carried out with customers. The above focused not only to prevent customer churn, but 15 to generate an added value of continuous improvement in sales processes, increase customer pene- 16 tration, leading to an improvement in customer experience and consequently, an increase in cus- 17 tomer loyalty.

Autonomous driving systems are increasingly becoming a necessary trend towards building smart cities of the future. Numerous proposals have been presented in recent years to tackle particular aspects of the working pipeline towards creating a functional end-to-end system, such as object detection, tracking, path planning, sentiment or intent detection. Nevertheless, few efforts have been made to systematically compile all of these systems into a single proposal that effectively considers the real challenges these systems will have on the road, such as real-time computation, hardware capabilities, etc. This paper has reviewed various techniques towards proposing our own end-to-end autonomous vehicle system, considering the latest state on the art on computer vision, DSs, path planning, and parallelization.

Breast cancer is the leading cause of cancer deaths worldwide in women. This aggressive tumour can be categorized into two main groups: in situ and infiltrative, with the latter being the most common malignant lesions. The current use of Magnetic Resonance Imaging (MRI) was shown to provide highest sensitivity in the detection and discrimination between benign vs. malignant lesions, when interpreted by expert radiologists. In this article, we present the prototype of a Computer-Aided Detection/Diagnosis (CAD) system that could provide valuable assistance to the radiologist for the discrimination between in situ and infiltrating tumours. The system consists of two main processing levels: 1) Localization of possibly tumoral regions of interest (ROIs) through an iterative procedure based on intensity values (ROI Hunter) followed by a deep-feature extraction and classification method for false-positive rejection; 2) Characterization of the selected ROIs and discrimination between in situ and invasive tumour, consisting of Radiomics feature extraction and classification through a machine-learning algorithm. The CAD system was developed and evaluated using a DCE-MRI image database, containing at least one confirmed mass per image, as diagnosed by an expert radiologist. When evaluating the accuracy of the ROI Hunter procedure with respect to the radiologist-drawn boundaries, sensitivity to mass detection was found to be 75%. The AUC of the ROC curve for discrimination between in situ and infiltrative tumors was 0.70.

In this paper, we use a machine learning method, known as Nonnegative Matrix Factorization, to extract from a given image some new information obtained from a number of color space representations. Such kind of information, termed ``metacolor'', can be considered as a particular color space representation of the image, which can be used to obtain a binary segmentation of the investigated image by distinguishing foreground and background pixels. Some numerical experiments prove that the proposed method shows improved results when compared with common simpler thresholding algorithms.

U-Net, based on a deep convolutional neural network (CNN), has been clinically used to au-to-segment normal organs and potentially target volumes. However, CNNs with local geometric dependencies may limit the accuracy of segmentation. Additionally, the performance of CNNs can vary depending on the selection of network hyper-parameters, which was mitigated by the proposition of nnU-Net. We chose a vision transformer architecture called VT U-Net, which features a self-attention excluding the convolution layer, to overcome the limitations of CNNs by utilizing global geometric information of images. The VT U-Net v.2 became more powerful thanks to the adaptive hyper-parameter optimizer embedded in nnU-Net. However, despite leveraging the benefits of nnU-Net, VT U-Net v.2 still had additional network hyper-parameters that needed to be optimally chosen. Accordingly, among various hyper-parameters, this study attempted to find the optimal combination of the patch size and the embedded dimension regarding the transformer. From the 4-fold cross-validation, the modified VT U-Net v.2 showed the highest average performance for planning target volume (PTV) segmentation among the investigated networks. Though nnU-Net was based on convolution layers, the adaptive hyper-parameter optimizers turned out to enhance the performance. It was also confirmed that network hyper-parameters affected the segmentation accuracy of vision transformers.

An automatic recognizing system of white blood cells can assist hematologists in the diagnosis of many diseases, where accuracy and efficiency are paramount for computer-based system. In this paper, we present a new image processing system to recognize the five types of white blood cells in peripheral blood with marked improvement in efficiency when juxtaposed against mainstream methods. The prevailing deep learning segmentation solutions often utilize millions of parameters to extract high-level image features and neglect the incorporation of prior domain knowledge, which consequently consume substantial computational resources and increase the risk of overfitting, especially when limited medical image samples are available for training. To address these challenges, we propose a novel memory-efficient strategy that exploits graph structures derived from the images. Specifically, we introduce a lightweight superpixel-based Graph Neural Network (GNN) and break new ground by introducing superpixel metric learning to segment nucles and cytoplasm. Remarkably, our proposed segmentation model (SMGNN) achieves state-of-the-art segmentation performance while utilizing at most 10000$\times$ less than the parameters compared to existing approaches. The subsequent segmentation-based cell type classification processes show satisfactory results that such automatic recognizing algorithms are accurate and efficient to execeute in hematological laboratories.

This paper presents an Edge-based color image segmentation derived from the method of Particle Motion in a Vector Image Fields (PMVIF) that could previously be applied only to monochrome images. Instead of using an edge vector field derived from a gradient vector field and a normal compressive vector field derived from a Laplacian-gradient vector field, two novel orthogonal vector fields, directly computed from a color image, one parallel and another orthogonal to the edges, were used in the model to force a particle to move along the object edges. The normal compressive vector field is derived from the center-to-centroid vectors of local color distance images. Next, the edge vector field is derived by taking the normal compressive vector field, multiplied by differences of auxiliary image pixels to obtain a vector field analogous to a Hamiltonian gradient vector field. Using the PASCAL Visual Object Classes Challenge 2012 (VOC2012) and the Berkeley Segmentation Data Set and Benchmarks 500 (BSDS500), the benchmark score of the proposed method is provided in comparison with those of the traditional PMVIF, Watershed, SLIC, K-means, Mean shift, and JSEG. The proposed method yields better RI, GCE, NVI, BDE, Dice coefficients, faster computation time, and noise resistance.

Cold-water coral reefs are rich, yet fragile ecosystems found in colder oceanic waters. Knowledge of their spatial distribution on continental shelves, slopes, seamounts and ridge systems is vital for marine spatial planning and conservation. Cold-water corals frequently form conspicuous carbonate mounds of varying sizes, which are identifiable from multibeam echosounder bathymetry and derived geomorphometric attributes. However, the often large number of mounds makes manual interpretation and mapping a tedious process. We present a methodology that combines image segmentation and random forest spatial prediction with the aim to derive maps of carbonate mounds and an associated measure of confidence. We demonstrate our method based on multibeam echosounder data from Iverryggen on the mid-Norwegian shelf. We identified the image-object mean planar curvature as the most important predictor. The presence and absence of carbonate mounds is mapped with high accuracy (overall accuracy = 84.4%, sensitivity = 0.827 and specificity = 0.866). Spatially-explicit confidence in the predictions is derived from the predicted probability and whether the predictions are within or outside the modelled range of values and is generally high. We plan to apply the showcased method to other areas of the Norwegian continental shelf and slope where MBES data have been collected with the aim to provide crucial information for marine spatial planning.

Object segmentation on remotely-sensed images: aerial (or very high resolution, VHS) images and satellite (or high resolution, HR) images, has been applied to many application domains, especially road extraction in which the segmented objects are served as a mandatory layer in geospatial databases. Several attempts in applying deep convolutional neural network (DCNN) to extract roads from remote sensing images have been made; however, the accuracy is still limited. In this paper, we present an enhanced DCNN framework specifically tailored for road extraction on remote sensing images by applying landscape metrics (LMs) and conditional random fields (CRFs). To improve DCNN, a modern activation function, called exponential linear unit (ELU), is employed in our network resulting in a higher number of and yet more accurate extracted roads. To further reduce falsely classified road objects, a solution based on an adoption of LMs is proposed. Finally, to sharpen the extracted roads, a CRF method is added to our framework. The experiments were conducted on Massachusetts road aerial imagery as well as THEOS satellite imagery data sets. The results showed that our proposed framework outperformed Segnet, the state-of-the-art object segmentation technique on any kinds of remote sensing imagery, in most of the cases in terms of precision, recall, and F1.

ABSTRACT Purpose: Tongue image analysis for disease diagnosis is an ancient traditional non-invasive diagnosis technique widely used by traditional medicine practitioners. Deep Learning based multi-label disease detection models offer tremendous potential to clinical decision support systems, by facilitating preliminary diagnosis. Methods: In this work, we propose a multi-label disease detection pipeline, where in observation and analysis of tongue images captured and received via smartphones assist in predicting the health status of an individual. All images are voluntarily given by subjects consulting collaborating physicians. Images thus acquired are first and foremost classified either into a diseased or a normal category by a 5-fold cross-validation algorithm using a convolution neural network (MobileNetV2) model for binary classification. Once the diseased label is predicted, the image is used to diagnose multiple diseases using the prediction algorithm based on DenseNet121. Results: Average accuracy of 93 % was achieved in classifying diseased from normal healthy tongue by detection model with MobileNetV2 architecture. Multilabel disease classification produced more than 90% accurate results for the seven class labels considered. Conclusion: AI based image analysis shows promising results and an extensive dataset could provide further improvements to this approach. Rather than employing high-cost sophisticated image capturing setup, experimenting with smartphone images opens opportunity to provide preliminary health status to individuals on smartphone prior to further line of treatment and diagnosis.

In today’s competitive landscape, achieving customer-centricity is paramount for the sustainable growth and success of organisations. This research is dedicated to understanding customer preferences in the context of the Internet of Things (IoT) and employs a two-part modeling ap-proach tailored in this digital era. In the first phase, we leverage the power of the Self-Organizing Map (SOM) algorithm to segment IoT customers based on their connected device usage patterns. This segmentation approach reveals three distinct customer clusters, with the second cluster demonstrating the highest propensity for IoT device adoption and usage. In the second phase, we introduce a robust Decision Tree methodology designed to prioritize various factors influencing customer satisfaction in the IoT ecosystem. We employ the Classification and Regression Tree (CART) technique to analyze 17 key questions that assess the significance of factors impacting IoT device purchase decisions. By aligning these factors with the identified IoT customer clusters, we gain profound insights into customer behaviour and preferences in the rapidly evolving world of connected devices. This comprehensive analysis delves into the factors contributing to customer retention in the IoT space, with a strong emphasis on crafting logical marketing strategies, en-hancing customer satisfaction, and fostering customer loyalty in the digital realm. Our research methodology involves surveys and questionnaires distributed to 207 IoT users, categorizing them into three distinct IoT customer groups. Leveraging analytical statistical methods, regression analysis, and IoT-specific tools and software, this study rigorously evaluate the factors influencing IoT device purchases. Importantly, this approach not only effectively clusters the IoT Customer Relationship Management (IoT-CRM) dataset but also provides valuable visualizations that are essential for understanding the complex dynamics of the IoT customer landscape. Our findings underscore the critical role of logical marketing strategies, customer satisfaction, and customer loyalty in enhancing customer retention in the IoT era. This research makes a significant contri-bution to businesses seeking to optimize their IoT -CRM strategies and capitalize on the oppor-tunities presented by the IoT ecosystem.

In today's world it is very much important to maintain the security of information and its risks. The biometric-based techniques are very much useful in these problems. Among the several kinds of biometric-based technique, face detection is much complex and much more important. Due to the age and several other problems, a human face structure changes over time, again a human has lots of expressions. Sometimes due to the lighting condition or the variation of the angle of an input device, the pattern of a human face structure also changed. As a result, the face cannot be detected properly. In this paper, a method is proposed that can detect the human faces both automatically and manually very efficiently. In manual mode, a user can select the input faces referred by the system according to their choice. In automated mode, the system detected all possible face areas using the Kohonen Self-Organizing Feature Map technique. This method reduced the complex color image into a vector quantized image with desired colors. Then a color segmentation technique is used to detect the possible face skin areas from the vector quantized image. Then the Histogram Oriented Gradient technique used to detect the feature from the faces and K-Nearest Neighbour Classifier is used to compare both face images detected by the two modes. The automated method prosed better accuracy than the manual method.

Segmentation of a region of interest is an important pre-processing step for many colour image analysis techniques. Similarly segmentation of plant in digital images is an important preprocessing step in phenotying plants by image analysis. In this paper we present an analytical study to statistically determine the suitability of colour space representation of an image to best detect plant pixels and separate them from background pixels. Our hypothesis is that the colour space representation in which the separation of the distributions representing plant pixels and background pixels is maximized would be the best for detection of plant pixels. The two classes of pixels are modelled as a Gaussian mixture model (GMM). In our GM modelling we don't make any prior assumption about the number of Gaussians in the model. Rather a constant bandwidth mean-shift filter is used to cluster the data and the number of clusters and hence the number of Gaussians is automatically determined. Here we have analysed following representative colour spaces like $RGB$, $rgb$, $HSV$, $Ycbcr$ and $CIE-Lab$. This is because these colour spaces represent several other similar colour spaces and also an exhaustive study of all the colour space will be too voluminous. We also analyse the colour space feature from the two-class variance ratio perspective and compare the results of our hypothesis with this metric. The dataset for this empirical study consist of 378 digital images of plants and their manual segmentation. Dataset consist of various species of plants (arabidopsi, tobacco, wheat, rye grass etc.) imaged under different lighting conditions, indoor and outdoor, controlled and uncontrolled background. In results we obtain better segmentation of the plants in $HSV$ colour space, which is supported by its Earth mover distance (EMD) on the GMM distribution of plant and background pixels.

Remote sensing technology is crucial for accurate rooftop detection, benefiting urban planning, disaster management, and solar resource estimation. This study employs Efficient Interactive Segmentation (EISEG) to enhance the efficiency of remote sensing image labeling, with a particular focus on rooftop detection. It is necessary to use modern technology because traditional manual labelling methods are labor-intensive and complicated. The study introduces a novel framework on deep learning semantic segmentation models, facilitating an efficient approach to rooftop identification using high-resolution UAV remote sensing datasets. Large dataset of labeled UAV rooftop building images, in which each superpixel region is assigned a binary label indicating rooftop presence. Advanced methods including Asymmetric Neural Network (ANN), Dual At-tention Network (DANet), PP-LiteSeg, and Deeplab3 are implemented for automatic rooftop detection due to their higher performance and advanced architectures. These models are executed on the Baidu deep learning platform PaddlePaddle, generating initial rooftop segmentation maps crucial for estimating photovoltaic resources. The ANN model emerges with the highest accuracy at 96%, followed by DANet at 95.09%, PP-LiteSeg at 94.54%, and Deeplab3 at 81.61%. The outcomes presenting efficient models for automated rooftop identification, and demonstrating the continuous need for improving deep learning techniques in smart and sustainable cities.

Fit-for-purpose land administration (FFPLA) seeks to simplify cadastral mapping via lowering the costs and time associated with conventional surveying methods. The approach can be applied to both initial establishment and on-going maintenance of system. In Ethiopia, cadastral maintenance remains an on-going challenge, especially in rapidly urbanizing peri-urban areas, where farmers' land rights and tenure security are often jeopardized. Automatic Feature Extraction (AFE) is an emerging FFPLA approach, proposed as an alternative for mapping and updating cadastral boundaries. This study explores the role of the AFE approach for updating cadastral boundaries in the vibrant peri-urban areas of Addis Ababa. Open-source software solutions are utilized to assess the (semi-) automatic extraction of cadastral boundaries from orthophotos (segmentation), designation of 'boundary' and 'non-boundary' outlines (classification), and delimitation of cadastral boundaries (interactive delineation). Both qualitative and quantitative assessments of the achieved results (validation) are undertaken. A high-resolution orthophoto of the study area and a reference cadastral boundary shape file are used, respectively, for extracting the parcel boundaries and validating the interactive delineation results. Qualitative (visual) assessment verified the completed extraction of newly constructed cadastral boundaries in the study area, although non-boundary outlines such as footpaths and artefacts are also retrieved. For the buffer overlay analysis, the interactively delineated boundary lines and the reference cadastre were buffered within the spatial accuracy limits for urban and rural cadasters. As a result, the quantitative assessment delivered 52% correctness and 32% completeness for a buffer width of 0.4m and 0.6m, respectively, for the interactively delineated and reference boundaries. The study further demonstrated the potentially significant role AFE could assist in delivering fast, affordable, and reliable cadastral mapping. Further investigation, based on user input and expertise evaluation, could help to improve the approach and apply it to a real-world setting.

Hand gestures are an essential part of human-to-human communication and interaction, and therefore for technical applications, the aim is increasingly to achieve interaction between humans and computers that is as natural as possible, for example by means of natural language or hand gestures. In the context of human-machine interaction research, these methods are consequently being explored more and more. However, the realization of natural communication between humans and computers is a major challenge. In the field of hand gesture recognition, research approaches are being pursued that use additional hardware such as special gloves to classify gestures with high accuracy. Recently, deep learning techniques using artificial neural networks have been increasingly proposed for the problem of gesture recognition without using such tools. In this context, in our approach convolutional neural network (CNN) will be explored in detail for the task of hand gesture recognition. CNN is a deep neural network that can be used in the field of visual object processing and classification. The goal of this work is to recognize ten types of static hand gestures in front of complex backgrounds and different hand sizes based on raw images without the use of extra hardware. We achieved good results with a CNN network architecture consisting of seven layers. Through data augmentation and skin segmentation, a significant increase of the model accuracy was achieved. On public benchmarks the ten gestures have been classified almost perfectly with a testing accuracy of 96.5%

Thresholding is considered as a statistical-decision making theory which can lessen the average error incurred in allocating pixels to two or more groups. The traditional Bayes decision rule can be applied with the prior knowledge of the Probability Density Function (PDF) of each class. It is surmised that a threshold resulting in the best class separation is the optimal one. In this paper, Otsu’s thresholding for image segmentation has been implemented. The well-known Otsu’s method is to learn a threshold that can maximize the between-class variance or equivalently make light of the within-class variance of the entire image. At first, a color image of a tree is taken. After that, the image is transformed into a grayscale image. Then in the first part, two-level thresholding is conducted, and later on, three-level thresholding is also applied. Again, two-level thresholding, as well as three level thresholding, are also applied to some other images. Finally, the comparison is made between two level thresholding and three level thresholding

In the remote sensing domain, it is crucial to complete semantic segmentation on the raster images, e.g., river, building, forest, etc, on raster images. A deep convolutional encoder--decoder (DCED) network is the state-of-the-art semantic segmentation method for remotely sensed images. However, the accuracy is still limited, since the network is not designed for remotely sensed images and the training data in this domain is deficient. In this paper, we aim to propose a novel CNN for semantic segmentation particularly for remote sensing corpora with three main contributions. First, we propose applying a recent CNN called a global convolutional network (GCN), since it can capture different resolutions by extracting multi-scale features from different stages of the network. Additionally, we further enhance the network by improving its backbone using larger numbers of layers, which is suitable for medium resolution remotely sensed images. Second, "channel attention'' is presented in our network in order to select the most discriminative filters (features). Third, "domain-specific transfer learning'' is introduced to alleviate the scarcity issue by utilizing other remotely sensed corpora with different resolutions as pre-trained data. The experiment was then conducted on two given datasets: (i) medium resolution data collected from Landsat-8 satellite and (ii) very high resolution data called the ISPRS Vaihingen Challenge Dataset. The results show that our networks outperformed DCED in terms of $F1$ for 17.48% and 2.49% on medium and very high resolution corpora, respectively.

Full waveform (FW) LiDAR holds great potential for retrieving vegetation structure parameters at a high level of detail, but this prospect is constrained by practical factors such as lack of available handy processing tools and technical intricacy of waveform processing. This study introduces a new product, named the Hyper Point Cloud (HPC) derived from FW LiDAR data, and explore its potential applications such as tree crown delineation using the HPC-based intensity and percentile height (PH) surfaces, which show a promising solution to the constraints of using FW LiDAR data. Results of the HPC present a new direction to handle FW LiDAR data and offer prospects for studying the mid-story and understory of vegetation with high point density (~ 182 points/m2). The intensity-derived digital surface model (DSM) generated from the HPC shows that the ground region has larger maximum intensity (MAXI) and mean intensity (MI) than the vegetation region while having smaller total intensity (TI) and number of intensities (NI) at the given grid cell. Our analysis of intensity distribution contours at individual tree level exhibit similar patterns, indicating that the MAXI and MI are decreasing from the tree crown center to tree boundary while a rising trend is observed for TI and NI. These intensity variable contours provide a theoretical justification for using HPC-based intensity surfaces to segment tree crowns and exploit their potential for extracting tree attributes. The HPC-based intensity surfaces and the HPC-based PH Canopy Height Models (CHM) demonstrate promising tree segmentation results comparable to the LiDAR derived CHM for estimating tree attributes such as tree locations, crown widths and tree heights. We envision that products such as the HPC and the HPC-based intensity and height surfaces introduced in this study can open new perspectives to use FW LiDAR data and alleviate the technical barrier of exploring FW LiDAR data for detailed vegetation structure characterization.

Abstract: The Micro-Electro-Mechanical System (MEMS) LiDAR point cloud in autonomous vehicles has a large deflection range, which results in slow registration speed and poor applicability. To maximize speed, an improved NDT (Normal Distribution Transform) method that integrates point cloud density features has been proposed. First, the point cloud is reduced using a modified voxel filter and a pass-through filter. Next, the ISS (Intrinsic Shape Signature) algorithm is utilized to analyze the point cloud features and extract keypoints, the 4PCS (4-Point Congruent Sets) algorithm is then employed to calculate the initial pose under the constraints of the keypoint set to complete the coarse registration. Finally, the self-adaptive segmentation model is constructed by using KD-tree to obtain the density features of keypoints, and the NDT algorithm is combined with this model to form an SSM-NDT algorithm, which is used for fine registration. Each algorithm was compared on the autonomous vehicle dataset PandaSet and actual collected data sets, the results show that the novel method increases the speed by at least 60% and takes into account good registration accuracy and strong anti-interference.

Digital Twin Cities (DTCs) play a fundamental role in city planning and management. They allow three-dimensional modeling and simulation of cities. 3D semantic segmentation is the foundation for automatically creating enriched DTCs, as well as their updates. Past studies indicate that prior level fusion approaches demonstrate more promising precisions in 3D semantic segmentation compared to point level fusion, features level fusion, and decision level fusion families. In order to improve point cloud enriched semantic segmentation outcomes, this article proposes a new approach for 3D point cloud semantic segmentation through developing and benchmarking three prior level fusion scenarios. A reference approach based on point clouds and aerial images was proposed to compare it with the different developed scenarios. In each scenario, we inject a specific prior knowledge (geometric features,classified images ,etc) and aerial images as attributes of point clouds into the neural network’s learning pipeline. The objective is to find the one that integrates the most significant prior knowledge and enhances neural network knowledge more profoundly, which we have named the "smart fusion approach". The advanced Deep Learning algorithm "RandLaNet" was adopted to implement the different proposed scenarios and the reference approach, due to its excellent performance demonstrated in the literature. The introduction of some significant features associated with the label classes facilitated the learning process and improved the semantic segmentation results that can be achievable with the same neural network alone. Overall, our contribution provides a promising solution for addressing some challenges, in particular more accurate extraction of semantically rich objects from the urban fabric. An assessment of the semantic segmentation results obtained by the different scenarios is performed based on metrics computation and visual investigations. Finally,the smart fusion approach was derived based on the obtained qualitative and quantitative results.

In the context of autosomal dominant polycystic kidney disease (ADPKD), total kidney volume (TKV) plays a key role as biomarker of disease progression and response to therapy and has been recently recognized as enrichment biomarker and possible surrogate endpoint. Several imaging modalities and methods are available to calculate TKV, and the choice depends on the purpose of use. Technological advancements have made it possible to accurately assess cyst burden, that can be crucial to assess the disease state and help identifying rapid progressors. Moreover, the development of automated algorithms has increased the efficiency of total kidney and cyst volume measurements. Beyond total kidney and cyst volume, the quantification and characterization of non-cystic kidney tissue show potential to early stratify ADPKD patients, monitor disease progression, and possibly predict renal function loss. A broad spectrum of kid-ney MRI techniques are available to characterize kidney tissue, showing promise to non-invasively pick up early signs of ADPKD progression. Radiomics has been used to extract tex-tural features from ADPKD images, providing valuable information about the heterogeneity of the cystic and non-cystic components. This review provides an overview of ADPKD imaging bi-omarkers, focusing on quantification methods, potential, and necessary steps towards successful translation to clinical practice.

The aerospace industry develops prognosis and health management algorithms to ensure better safety on board. Particularly for in-flight controls where jamming is dreaded. For that, vibration signals are monitored to predict future defect occurrences. However, time series are not labeled according to severity level, and the user can only assess the system health from the data mining procedure. To that extent, we developed a clustering algorithm using a deep neural network core. We encoded the time series into pictures to be feed into an artificially trained neural network: U-NET. From the segmented output, one-dimensional information on cluster frontiers is extracted and filtered without any parameter selection. Then, a kernel density estimation finally transforms the signal into an empirical density. Ultimately, a Gaussian mixture model extracts the latter independent components. The method empowered us to reveal different degrees of severity faults in the studied data, with their respective likelihood without prior knowledge. We compared it to state-of-the-art machine learning algorithms. However, internal clustering results evaluation for time series is an open question. As state-of-the-art indexes were not producing relevant results, we built a new indicator to fulfill this task. We applied the whole method to an actuator consisting of an induction machine linked to a ball screw. This study lays the groundwork for future training of diagnosis and prognosis structures in the health management framework.

Sunn pest is one of the most crucial noxious species in agriculture. As the sunn pest penetrates and makes damage to the grains, they can no longer be utilized to make bakery goods like bread, pasta, and other baked foods since they become unusable. Therefore, analysis and detection of damaged wheat grains are necessary for production to continue. We recommend that the dataset could be used for analysis and segmentation of the wheat grains, detection of the sunn pest damage condition, and classification of the 6 species of which the dataset consists. As mentioned, in our dataset, there are 6 different species of wheat, including Bezostaja, Müfitbey, Nacibey, Sönmez-2001, Tosunbey, and Ekiz, which are the species that were made in Türkiye. Our dataset differs from the others due to its various species and the condition, whether it is healthy or sunn pest damaged or broken wheat grain, and because the dataset is a multiclass one, it can be used for the classification of the varieties. On the other hand, when the sunn pest damage condition is taken into account, the dataset is suitable for the detection of the sunn pest damage. In addition to that, the dataset includes grains that touch each other which makes it more applicable to problems that arise in real-life. The dataset consists of 83 sunn pest damaged and 87 healthy wheat images. In addition, there are 170 images that contain 3565 wheat grains. As can be observed, the dataset contains a variety of wheat species with sunn pest affected which displays that the promised dataset is suitable for numerous machine learning problems such as classification, segmentation, and detection.

Forest canopy gaps are important for the ecosystem dynamics. Depending on tree species, small canopy openings might be also associated to intra-crown porosity and to space between crowns. Yet, little is known on the relationships between the fine-scaled pattern of canopy openings and biodiversity features. This research explored the possibility of i)- mapping forest canopy gaps from a very high resolution orthomosaic (10 cm), processed from a versatile imaging platform such as unmanned aerial vehicles (UAV), ii)- to derive patch metrics that can be tested as covariates of variables of interest for forest biodiversity monitoring. This is attempted in a test area of 240 ha covered by temperate deciduous forest types in Central Italy and containing 50 forest inventory plots of about 530 m². Correlation and linear regression techniques were used to explore relationships between patch metrics and understorey (density, development and species diversity) or forest habitat biodiversity variables (density of micro-habitat bearing trees, vertical species profile, tree species diversity). The results revealed that small openings in the canopy cover (75% smaller than 7 m²) can be faithfully extracted from UAV RGB imagery, using the red band and contrast split segmentation. Highest correlations were observed in the mixed forest (beech and turkey oak), while beech forest had the poorest ones and turkey oak forest displayed intermediate results. Moderate to strong linear relationships were found between gap metrics and understorey variables in mixed forest type, with adjusted R² from linear regression ranging from 0.52 to 0.87. Equally good results, in the same forest types, were observed for forest habitat biodiversity variables (0.52<adjusted R²<0.79) with highest values found for density of trees with microhabitats and vertical species profile. In conclusion, this research highlights that UAV remote sensing can potentially provide covariate surfaces of variables of interest for forest biodiversity monitoring, conventionally collected in forest inventory plots. By integrating the two sources of data, these variables can be mapped over small forest areas with satisfactory levels of accuracy, at a much higher spatial resolution than would be possible by field-based forest inventory solely.

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that makes digitization of documents viable. Since the advent of deep learning, the performance of deep learning-based object detection has improved many folds. In this work, we outline and summarize the deep learning approaches for detecting graphical page objects in the document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.

The safe and reliable operation of autonomous vehicles in complex and dynamic environments is heavily dependent upon exteroceptive and proprioceptive sensors. A LiDAR system generates accurate 3D point clouds, which are crucial for the detection, classification, and tracking of multiple targets. LiDAR data, however, presents significant challenges due to its density, noise, and varying sampling rates. In this study, various clustering and MTT techniques for LiDAR point clouds will be identified and classified within the context of autonomous driving to assess the state-of-the-art methods’ key challenges and their performances. We have categorized clustering and MTT methods used in AV applications, identified research gaps and challenges and analyzed existing algorithms and their challenges in detail. Researchers and practitioners in the field of autonomous driving will find this review to be a valuable resource.

Densely urbanized areas, with a low percentage of green vegetation, are highly exposed to Heat Waves (HW) which nowadays are increasing in terms of frequency and intensity also in the middle-latitude regions, due to ongoing Climate Change (CC). Their negative effects may combine with those of the UHI (Urban Heat Island), a local phenomenon where air temperatures in the compact built up cores of towns increase more than those in the surrounding rural areas, with significant impact on the quality of urban environment, on citizens health and energy consumption and transport, as it has occurred in the summer of 2003 on France and Italian central-northern areas. In this context this work aims at designing and developing a methodology based on aero-spatial remote sensing (EO) at medium-high resolution and most recent GIS techniques, for the extensive characterization of the urban fabric response to these climatic impacts related to the temperature within the general framework of supporting local and national strategies and policies of adaptation to CC. Due to its extension and variety of built-up typologies, the municipality of Rome was selected as test area for the methodology development and validation. First of all, we started by operating through photointerpretation of cartography at detailed scale (CTR 1: 5000) on a reference area consisting of a transect of about 5x20 km, extending from the downtown to the suburbs and including all the built-up classes of interest. The reference built-up vulnerability classes found inside the transect were then exploited as training areas to classify the entire territory of Rome municipality. To this end, the satellite EO HR (High Resolution) multispectral data, provided by the Landsat sensors were used within a on purpose developed "supervised" classification procedure, based on data mining and “object-classification” techniques. The classification results were then exploited for implementing a calibration method, based on a typical UHI temperature distribution, derived from MODIS satellite sensor LST (Land Surface Temperature) data of the summer 2003, to obtain an analytical expression of the vulnerability model, previously introduced on a semi-empirical basis.