This paper is a follow-up to a previous study that was conducted in a research forest and identified the optimal method for Diameter at Breast Height (DBH) estimation as a circular scanning and fitting ellipses to 4cm stem cross-sections at breast height. The aim of this study was to determine whether the identified method is applicable to natural boreal forests as well. The iPad Pro LiDAR scanner was used to acquire point clouds for 15 sites representing a range of natural boreal forest conditions in Ontario, Canada, and estimate DBH. The secondary objective was to determine if tested stand (Species composition, age, density, understory) or tree (Species, DBH) factors affected the accuracy of estimated DBH. Overall, estimated DBH values were within 1cm of actual DBH values for 78 of 133 measured trees (59%). An RMSE of 1.5cm (8.6%) was achieved. Stand age had a large effect (>0.15) on the accuracy of estimated DBH values, while density, understory, and DBH had moderate effects (0.05-0.14). No trend was identified between accuracy and stand age. Accuracy improved as understory density decreased and as tree DBH increased. Inertial Measurement Unit (IMU) and positional accuracy errors with the iPad Pro scanner limit the feasibility of using this device for forest inventories.

Effective development of digital twins of real-world objects requires sophisticated data collection techniques and algorithms for automated modeling of individual objects. In City Information Modeling (CIM) systems, individual buildings can be modeled automatically at the second Level Of Detail or LOD 2. Similarly, automated solutions for 3D modeling of individual trees at different levels of details are required for Tree Information Modeling (TIM) and building Forest Digital Twins (FDT). The existing algorithms support the automated modeling of trees by generating models of the canopy and the lower part of the trunk. Our work in this paper is based on the assumption that, similar to the canopy shape, the structure of tree trunk and branches is also an important consideration. An algorithm for automated modeling of tree trunks is proposed. Aiming to generate 3D models of tree trunks, the suggested approach starts by extracting the trunk point cloud, which is then segmented into single stems. Finally, the individual stems are modeled by dividing them into slices. The geometry of the developed tree models is represented in a matrix format. This solution enables automatic comparisons of tree elements over time, which is necessary for monitoring changes in forest stands and promoting sustainable forest management. Despite the huge variation of trunk geometric forms, the proposed modeling approach can gain an accuracy of better than 4 cm in the constructed tree trunk models.

Early spaceborne laser altimetry mission development starts in pre-phase A design, where diverse ideas are evaluated against mission science requirements. A key challenge is predicting realistic instrument performance through forward modeling at arbitrary spatial scale. Analytical evaluations compromise accuracy for speed, while radiative transfer modeling is not applicable at global scale due to computational expense. Instead of predicting arbitrary properties of a lidar measurement, we develop a baseline theory to predict only the distribution of uncertainty specifically for the terrain elevation retrieval based on terrain slope and fractional canopy cover features through a deep neural network gaussian mixture model, also known as a mixture density network (MDN). Training data was created from differencing geocorrected GEDI L2B elevation measurements with 32 independent reference lidar datasets in the contiguous U.S. from the National Ecological Observatory Network. We trained the MDN and selected hyperparameters based on regional distribution predictive capability. On average, the relative error of equivalent standard deviation of predicted regional distributions was 15.9%, with some anomalies in accuracy due to generalization and insufficient feature diversity and correlation. As an application, we predict the percent of elevation residuals of a GEDI-like lidar within a given mission threshold from 60°S to 78.25°N, which correlate to qualitative understanding of prediction accuracy and instrument performance.

The current deformation and stable state of slopes with historical shatter signs is a concern for engineering construction. Suspected landslide scarps were discovered at the rear edge of the slope of the Genie in the Sichuan-Tibet transportation corridor during a field investigation. In order to qualitatively determine the current status of the surface deformation of this slope, this paper uses high-resolution optical remote sensing, airborne LiDAR and InSAR technologies for comprehensive analysis. The interpretation of high-resolution optical and airborne LiDAR data revealed that the rear edge of the slope exhibits three levels of scarps. However, no deformation was detected with the D-InSAR analysis of ALOS-1 radar images from 2007 to 2008 or with the Stacking-InSAR and SBAS-InSAR processing of Sentinel-1A radar images from 2017 to 2020. A geological model of the slope was established in combination with field investigation stipulating that the slope is composed of steep anti-dip layered dolomite limestone and that the scarps at the rear edge of the slope were caused by historical shallow toppling. Further research is recommended to determine the extent of toppling deformation and evaluate the slope stability under the disturbance of tunnel excavation.

Recently, the interest in silicon-based detectors capable of detecting single photons in the near-infrared is growing mainly due to LiDAR applications, autonomous driving in particular. Silicon single-photon avalanche diodes are one of the most interesting single-photon NIR technology available on the market, nevertheless, their efficiency is hindered by the low absorption coefficient of Si in the NIR. The idea is the integration of CMOS-compatible nanostructures, specifically, silver grating array supporting Surface Plasmons Polaritons (SPPs), to confine superficially the incoming NIR photons and therefore increase photons probability to generate an electron-hole pair. The plasmonic silver array is geometrically fine-tuned using time domain simulation software to achieve maximum detector performance at 950 nm. Then, the plasmonic silver array is integrated by means of the focused ion beam technique on the detector. Finally, the integrated detector is electro-optically characterized, demonstrating a quantum efficiency of 13 at 950 nm, 2,2 times more than the reference detector. This result suggests the production of a device capable of detecting single NIR photons, at a very low cost and compatible with CMOS, thus integrable on existing technology platforms.

Accurately quantifying the above-ground volume (AGV) and thus above-ground biomass (AGB) of forest stands is an important aspect in the conservation of mangrove ecosystem owing to their ecological and economic benefits. However, the number of studies focusing on quantifying mangrove forests’ biomass has been relatively low due to their marshy terrain, making exploratory studies challenging. In recent times, the use of LiDAR technologies in forest inventory studies has become increasingly popular, due to the reliability of LiDAR as a highly accurate means of 3D spatial data acquisition. In this study, we propose an end-to-end methodology for estimating AGV of mangrove forest stands from terrestrial LiDAR data. Many of the recent studies on this topic effectively employ machine learning algorithms such as multi layer perceptron, random forests, etc. for filtering foliage in the point cloud data of single trees. This study further extends that approach by incorporating the impact of class imbalance of forest point cloud data in a weighted random forest classifier. For the task of segmentation of wood/foliage points in a single tree point cloud, this approach yielded an average increase of 2.737% in the balanced accuracy score, 0.007 in the Cohen’s kappa score, 2.745% in the ROC AUC score and 0.857% in the F1 score. For the task of AGV estimation of a single tree, this approach resulted in an average coefficient of determination of 0.93 with respect to the ground truth volumes. For the task of counting pneumatophores in a plot-level point cloud, the proposed breadth-first searching method yielded an average coefficient of determination of 0.9391. Also, the machine learning classifier and geometric features used in this study were invariant to tree species and hence could be generalised for the classification of point clouds of other tree species as well. Finally, a breadth-first graph-search segmentation based approach is also proposed as part of this pipeline to estimate the contribution of pneumatophores to the AGB of mangrove forest stands. Since pneumatophores are a special adaptation of mangrove forests for gaseous exchange in marshy environments, this study aims to incorporate the detection and AGB estimation of pneumatophores in the inventory of mangrove forest stands. Studying the contribution of pneumatophores to the AGB of mangrove forest plots could also aid future mangrove forest inventory studies in modeling the underlying root network and estimating the below-ground biomass of mangrove trees.

Forest canopy structure (CS) controls many ecosystem functions and is highly variable across landscapes, but the magnitude and scale of this variation is not well understood. We used a portable canopy lidar system to characterize variation in five categories of CS along N = 3 transects (140–800 m long) at each of six forested landscapes within the eastern USA. The cumulative coefficient of variation was calculated for subsegments of each transect to determine the point of stability for individual CS metrics. We then quantified the scale at which CS is autocorrelated using Moran’s I in an Incremental Autocorrelation analysis. All CS metrics reached stable values within 300 m but varied substantially within and among forested landscapes. A stable point of 300 m for CS metrics corresponds with the spatial extent that many ecosystem functions are measured and modeled. Additionally, CS metrics were spatially autocorrelated at 40 to 88 m, suggesting that patch scale disturbance or environmental factors drive these patterns. Our study shows CS is heterogeneous across temperate forest landscapes at the scale of 10’s of meters, requiring a resolution of this size for upscaling CS with remote sensing to large spatial scales.

The application of 3D LiDAR technology has become increasingly extensive in tunnel monitoring due to the large density and high accuracy of the acquired spatial data. The proposed processing method aims at circle tunnels and provides a clear workflow to automatically process raw point data and easily interpretable results to analyze tunnel health state. The proposed automatic processing method employs a series of algorithms to extract point cloud of a single tunnel segment without obvious noise from entire raw tunnel point cloud mainly by three steps: axis acquisition, segments extraction and denoising. Tunnel axis is extracted by fitting boundaries of the tunnel point cloud rejection in plane with RANSAC algorithm. With guidance of axis, the entire preprocessed tunnel point cloud is segmented by equal division to get a section of tunnel point cloud which corresponds to a single tunnel segment. Then the noise in every single point cloud segment is removed by clustering algorithm twice, based on distance and intensity. Finally, clean point clouds of tunnel segments are processed by effective deformation extraction processor to get ovality and three-dimensional deformation nephogram.

Today, non-expensive remote sensing (RS) data from different sensors and platforms can be obtained at short intervals and be used for assessing several kinds of forest characteristics at the level of plots, stands and landscapes. Methods such as composite estimation and data assimilation can be used for combining the different sources of information to obtain up-to-date and precise estimates of the characteristics of interest. In composite estimation a standard procedure is to assign weights to the different individual estimates inversely proportional to their variance. However, in case the estimates are correlated, the correlations must be considered in assigning weights or otherwise a composite estimator may be inefficient and its variance be underestimated. In this study we assessed the correlation of plot level estimates of forest characteristics from different RS datasets, between assessments using the same type of sensor as well as across different sensors. The RS data evaluated were SPOT-5 multispectral data, 3D airborne laser scanning data, and TanDEM-X interferometric radar data. Studies were made for plot level mean diameter, mean height, and growing stock volume. All data were acquired from a test site dominated by coniferous forest in southern Sweden. We found that the correlation between plot level estimates based on the same type of RS data were positive and strong, whereas the correlations between estimates using different sources of RS data were not as strong, and weaker for mean height than for mean diameter and volume. The implications of such correlations in composite estimation are demonstrated and it is discussed how correlations may affect results from data assimilation procedures.

NASA’s ICESat-2space-borne photon-counting lidar mission is providing global elevation measurements that will provide significant benefits to a variety of bio-geoscience research applications. Given the novelty of elevation and the derived data products from the ICESat-2 mission, the research community needs software tools that can facilitate photon-level analyses to support product validation and development new analysis methods. Here, we describe PhotonLabeler, a free graphic user interface (GUI) for manual labeling and visualization of ICESat-2 Geolocated Photon data (ATL03). Developed in MATLAB, the GUI facilitates the reading and display of ATL03 Hierarchical Data Format (HDF) files, the manual labeling of individual photons into target classes of choice using a number of point selections tools and enables eventual saving of labeled data in ASCII format. Other capabilities include saving and loading of labeling sessions to manage labeling tasks over time. We expect labeled data generated using the application to serve two main purposes. First, serve as ground truth for validating various products from ICESat-2 mission, especially for study sites around the world that do not have existing reference datasets such as airborne lidar. Second, serve as training and validation data in the development of new algorithms for generating various ICESat-2 data products. We demonstrate the first use case through a validation case study for the land and vegetation product (ATL08), which provides canopy and terrain height estimates, over two sites. For the first site, located in northwestern Zambia, we used ICESat-2 ATL03 data acquired at night and for our second site in Texas, US, we used ATL03 data acquired during the day. The PhotonLabeler application is freely available as a compiled MATLAB binary to enable free access and utilization by interested researchers.

Gardens play a key role in the definition of the cultural landscape since they reflect the culture, identity and history of a people. They also contribute to the ecological balance of the city. Despite gardens have an historic and social value, they are not protected as much as the rest of the existing heritage, like architecture and archaeological sites. While methods of built-heritage mapping and monitoring are increasing and constantly improving to reduce built-heritage loss and the severe impact of natural disasters, the documentation and survey techniques for gardens are often antiquated, inventories are typically made by non-updated/updatable reports, and rarely they are on digital format and in 3D. This paper presents the preliminary results of a study on latest technology for gardens laser scanning. We compared static Terrestrial Laser Scanning and Mobile Laser Scanning point clouds, to evaluate their quality for documentation and the estimation of the tree attributes. The evaluation is based on visual observation and graphic comparison of the two point clouds acquired in different instances. Both methods produced useful outcomes for the research scope within their limitations. Terrestrial Laser Scanning is still the method that offers more accurate point clouds with a higher point density and less noise level. However, the more recent Mobile Laser Scanning is able to survey in less time, significantly reducing the costs for site activities, data post-production and registration. Both methods have their own restrictions that are amplified by site features, mainly the lack of plans for the geometric alignment of scans and for the Simultaneous Location and Mapping (SLAM) process. We also offer the results of a comparison of the functional range of the two machines, as well as for a comparison of their terrain information extraction capabilities.

In this paper, an intelligent blind guide system based on 2D LiDAR and RGB-D camera sensing is proposed, and the system is mounted on the smart cane. The intelligent guide system relies on 2D LiDAR, RGB-D camera, IMU, GPS, Jetson nano B01, STM32 and other hardware. The main advantage of the intelligent guide system proposed by us is that the distance between the smart cane and obstacles can be measured by 2D LiDAR based on Cartographer algorithm, thus achieving Simultaneous localization and mapping (SLAM). At the same time, through the improved yolov5 algorithm, pedestrians, vehicles, pedestrian crosswalks, traffic lights, warning posts, stone piers, tactile paving and other objects in front of the visually impaired can be quickly and effectively identified. Laser SLAM and improved yolov5 obstacle identification tests were carried out inside a teaching building on the campus of Hainan Normal University and on a pedestrian crossing on Longkun South Road in Haikou City, Hainan Province. The results show that the intelligent guide system developed by us can drive the wheels and omnidirectional wheels at the bottom of the smart cane, and give the smart cane a self-leading blind guide function like a "guide dog", which can effectively guide the visually impaired to avoid obstacles and reach the predetermined destination, and can quickly and effectively identify the obstacles on the way out. The laser SLAM speed of this system is 25~31FPS, which can realize the short-distance obstacle avoidance and navigation function both in indoor and outdoor envionments. The improved yolov5 helps to identify 86 types of objects, the recognition rate for pedestrian crosswalks and for vehicles are 84.6% and 71.8%, respectively; the overall recognition rate for 86 types of objects is 61.2%, and the obstacle recognition rate of the intelligent guide system is 25-26FPS.

This research is focused on two key areas. The first is mapping the 2022 flood in the Red River of the North near Grafton, North Dakota, US, and the second is evaluating the scour potential of the Grafton Bridge. Local scour of bridge piers can cause hydraulic structures such as bridge piers and abutments to fail during floods, making it a crucial area of investigation. To collect bathymetry and discharge data during low and high flow conditions, including a flood event with a 16.5-year return period in 2022, an Autonomous Surface Vehicle (ASV) incorporated with LiDAR DEM (Digital Elevation Model) data obtained from the US Geological Survey (USGS) National Map was used. Flood mapping and evaluation of local scour around the bridge pier were conducted using the HEC-RAS 6.0.0 software, which utilizes the Colorado State University method as a default equation. This research demonstrates the potential of ASVs in collecting critical data and LiDAR DEM data is an efficient method for flood mapping and determining scour potential, as it integrates bathymetry, flow velocity, and flood prediction.

The 21st century has seen the launch of new space-borne sensors based on LiDAR (light detection and ranging) technology developed in the second half of the 20th century. LiDAR was initially developed to integrate laser-focused imaging with the capability to determine distances through the measurement of signal return times, utilizing suitable sensors and data acquisition electronics. Nowadays, these sensors have transformed into robust instruments, offering novel opportunities for mapping terrain, canopy heights, and estimating above-ground biomass (AGB) across local to regional scales. This work aims to analyze the scientific impact of these sensors on large-scale for-est mapping to retrieve 3D canopy information, monitor forest degradation, estimate AGB, and model key ecosystem variables such as primary productivity and biodiversity. In this way, a worldwide bibliometric analysis of this topic was carried out based on up to 412 publications in-dexed in the Scopus database during the period 2004-2022. The results showed that the number of published documents increased exponentially in the last five years, coinciding with the commis-sioning of two new LiDAR space missions: Ice, Cloud and Land Elevation Satellite (ICESat-2) and Global Ecosystem Dynamics Investigation (GEDI). These missions are providing data since 2018 and 2019, respectively. The journal that demonstrated the highest productivity in this field was "Remote Sensing," and among the leading contributors, the top five countries in terms of publica-tions were the USA, China, the UK, France, and Germany. In the realm of prominent research in-stitutions, France boasted six, the USA had four, China had three, while the UK and Canada each had one. The upward trajectory in the number of publications recorded from 2004 to 2022 catego-rizes the subject under investigation as a highly trending research topic, particularly within the context of enhancing the administration of forest resources and engaging in global climate treaty frameworks mandating the surveillance and reporting of carbon stocks in forests. The recent launch in August 2022 of the Terrestrial Ecosystem Carbon Monitoring Satellite (TECMS; China State Administration of Forestry and Grassland), along with the planned launch in the coming years of up to three new space sensors, such as the Multi-footprint Observation LiDAR and Im-ager (Japan Aerospace Exploration Agency), the BIOMASS P-band Synthetic Aperture Radar (SAR) (European Space Agency), and the LiDAR Surface Topography (LIST; NASA), will greatly contribute to expanding the ability to map and monitor forest systems at very large scales. In this context, the integration of space-borne data, including imagery, SAR, and LiDAR, is anticipated to steer the trajectory of this research in the upcoming years.

Traffic signal control plays a key role in managing urban traffic flow, enhancing safety, and minimizing congestion and conflicts. Effective green time allocation is a critical element of this control process. This research explores the utilization of LiDAR sensor technology in the optimization of green time allocation for one phase of a traffic signal at a signalized intersection. LiDAR sensors provide precise and real-time data on vehicle presence and traffic patterns, enabling a data-driven approach to traffic signal control. The study begins with an analysis of the limitations of traditional traffic signal control strategies, which often rely on fixed-time plans or rudimentary vehicle detection systems. These approaches can lead to suboptimal green time allocation, resulting in inefficient traffic management and increased vehicle delays.The integration of LiDAR sensors provides detailed information on vehicle queues, arrival rates, and vehicle types. The research presents a practical framework for green time allocation optimization, considering factors such as intersection geometry, traffic volumes, and signal coordination. An intelligent control algorithm was developed that uses LiDAR data to determine the optimal green time for a specific phase, thereby reducing unnecessary waiting times and enhancing intersection efficiency. The effectiveness of the proposed LiDAR-based green time allocation strategy is demonstrated through extensive field tests. The results indicate significant improvements in intersection throughput, reduced delays, and enhanced traffic safety. In conclusion, this research highlights the transformative potential of LiDAR sensor technology in traffic signal control, specifically in the context of optimizing green time allocation. The findings support the notion that adaptive and data-driven strategies, when integrated with LiDAR sensors, can contribute to more efficient, sustainable, and safe urban traffic management. This research aims to provide valuable insights for transportation engineers, policymakers, and researchers seeking innovative solutions for modern urban traffic control.

Multiple social and environmental justice concerns are linked to urban form such as the distribution of socioeconomic class populations, healthcare spending, air pollution exposure, and human mobility. This study used 1m resolved LIDAR data to characterize land use in Salt Lake County, Utah and associate it with sociodemographic and air quality data at the census block group and zip code levels. We found that increasing tree cover was associated with higher per capita income and lower minority populations while increasing built cover was linked to lower per capita income and higher minority populations. Air quality showed less strong correlations, however, decreased non irrigated cover, increased built cover, and higher amounts of households living under poverty was related to higher long-term PM2.5 exposure. Several policy efforts have been undertaken to improve air quality and reduce negative health outcomes in Utah which are being informed by regulatory and research grade air quality sensors.

The retrieval of tree height percentiles with satellite lidar waveforms over the mountainous ar-eas is greatly challenged due to slanted and rugged topographic relief of underlying ground. A novel algorithm is proposed to extract the height percentiles based on the target response waveform (TRW) that is resolved by using a Richardson–Lucy deconvolution algorithm with an adaptive iterative time. The height metrics of the energy percentiles of 25%, 50%, 75% and 95% for the cumulative TRW distribution are determined by their vertical distances relative to the ground elevation in this study. To validate the proposed algorithm, we select the received waveforms of the Global Ecosystem Dynamics Investigation (GEDI) lidar over the Pahvant Mountains of central Utah, USA. The results reveal that the resolved TRWs resemble closely to the actual target response waveforms from the coincident airborne lidar data, with the mean values of the coefficient of correlation, total bias and root mean square error (RMSE) taking val-ue of 0.92, 0.0813 and 0.0016. In addition, the accuracies of the derived height percentiles from the proposed algorithm have been greatly improved compared with the conventional Gaussian de-composition method and the slope-adaptive waveform metrics method. The RMSE values de-crease by the mean values of 1.96 m and 2.72 m, respectively. It demonstrates that the proposed algorithm has good potential in the extraction of forest structure parameter over rugged moun-tainous areas.

This study investigates the application of Light Detection and Ranging (LiDAR) sensor technology for data collection at signalized intersections characterized by a high rate of traffic crashes. The research aims to provide valuable insights into the potential of LiDAR-based data analysis to enhance road safety and traffic management at signalized intersections. The research methodology involved the deployment of LiDAR sensors at Marlboro Pike & Brooks Dr. signalized intersection in Coral Hills, Maryland. Two LiDAR sensors installed in this intersection to collect high-resolution, three-dimensional data of the intersection area from June, 1^st to July, 7^th 2023. The data included information on vehicle trajectories, speeds, and behaviors, as well as pedestrian and cyclist movement patterns. Concurrently, historical traffic crashes recorded and traffic flow data were obtained for the same intersection.The analysis of LiDAR data involved several key aspects including LiDAR data allowed for a precise evaluation of traffic flow patterns, including congestion points, traffic volume fluctuations, and peak-hour behavior. This information provided insights into potential factors contributing to crashes. By analyzing LiDAR data, the study identified near-miss incidents, which are often precursors to actual crashes. This proactive approach could assist in identifying crash-prone areas within the intersection. The LiDAR data analysis also focused on pedestrian and cyclist movements, including jaywalking and bike lane usage. The aim was to identify areas where infrastructure improvements could enhance safety for vulnerable road users. LiDAR data was compared with historical crash data to identify specific locations within the intersection that exhibited a high frequency of crashes. This information can guide targeted safety interventions. Last but not least, the study explored opportunities to optimize traffic signal timings based on real-time traffic data from LiDAR. Adaptive signal control could help mitigate congestion and reduce the risk of crashes.The results of this study demonstrated the potential of LiDAR sensor technology in collecting detailed data for traffic analysis in signalized intersections. By combining LiDAR data with historical crash records and traffic flow data, traffic engineers and urban planners can develop evidence-based strategies to reduce the frequency and severity of crashes in high-risk areas. Ultimately, this research contributes to a comprehensive understanding of how LiDAR technology can be employed to enhance road safety and traffic management, providing valuable insights for traffic engineers, urban planners, and policymakers seeking to improve the safety and efficiency of signalized intersections with a history of high traffic crashes.

The wind observations for multiple levels (40–200 m) have been conducted for a long time (2016–2020) on Jeju Island of South Korea. This study aims at understanding the vertical and temporal characteristics of lower atmosphere. Jeju Island is a region located at mid-latitude and is affected by seasonal monsoon wind. The maximum wind speed appears in the lower layer during day time and is delayed in the upper layer during latter time in diurnal cycle. In summer season, the surface layer increases up to 160 m during day time via dominant solar radiation effect, which is higher than those for other seasons. However, the maximum wind speed in winter season appears irregularly among altitudes, and the surface layer is ~100 m, which is lower than that in summer season. It can be attributed to the increase in the mean wind speed in diurnal cycle caused by the strong northwestern wind for winter season. These results imply that the relationship between near-surface and higher altitudes is primarily affected by solar radiation and seasonal monsoon winds. These results are expected to contribute to site selection criteria for wind farms and to the assessment concerning planetary boundary layer modeling.

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.

The accuracy of wind field simulation and prediction is one of the most significant parameters in the field of atmospheric science and wind energy. Limited by the observation data, there are few researches on wind energy development. A 3D Doppler wind lidar (DWL) providing the high-vertical-resolution wind data over the urban complex underlying surface in February 2018 was employed to evaluated the accuracy of vertical wind field simulation systematically for the first time. 11 PBL schemes of the Weather Research and Forecasting Model (WRF) were employed in simulation. The model results were evaluated in groups separated by weather (sunny days, haze days and windy days), observation height layers, and various observation wind speeds. The test results presented that the vertical layer altitude of the observation point position was the most important factor. The simulation is fairly well at a height of 1000-2000m, as most of the relative mean bias of wind speed and wind direction are less than 20% and 6% respectively. Below 1000 m, the wind speed and direction biases are about 30%-150% m.s-1 and 6%-30% respectively. Moreover, when the observed wind speed was lower than 5 m.s-1, the bias were usually large, and the wind speed relative mean bias is up to 50-300%. In addition, the accuracy of simulated wind profile is better in 10-15m.s-1 than other speed ranges, and is better up 1000m than below 1000m in the boundary layer. We see that the WRF boundary layer schemes have different applicability to different weather conditions. The WRF boundary layer schemes have significant differences in wind field simulation with larger error under the complex topography. A PBL scheme is not likely to maintain its advantages in the long term under different conditions including altitude and weather conditions.

In terrain analysis and hydrological modeling, surface depressions (or sinks) in a digital elevation model (DEM) are commonly treated as artifacts and thus filled and removed to create a depressionless DEM. Various algorithms have been developed to identify and fill depressions in DEMs during the past decades. However, few studies have attempted to delineate and quantify the nested hierarchy of actual depressions, which can provide crucial information for characterizing surface hydrologic connectivity and simulating the fill-merge-spill hydrological process. In this paper, we present an innovative and efficient algorithm for delineating and quantifying nested depressions in DEMs using the level-set method based on graph theory. The proposed level-set method emulates water level decreasing from the spill point along the depression boundary to the lowest point at the bottom of a depression. By tracing the dynamic topological changes (i.e., depression splitting/merging) within a compound depression, the level-set method can construct topological graphs and derive geometric properties of the nested depressions. The experimental results of two fine-resolution LiDAR-derived DEMs show that the raster-based level-set algorithm is much more efficient (~150 times faster) than the vector-based contour tree method. The proposed level-set algorithm has great potential for being applied to large-scale ecohydrological analysis and watershed modeling.

Impervious surface mapping with high-resolution remote sensing imagery has attracted increasing interest as it can provide detailed information for urban structure and distribution. Previous studies have suggested that the combination of LiDAR data and high-resolution imagery for impervious surface mapping performs better than using only high-resolution imagery. However, due to the high cost of the acquisition of LiDAR data, it is difficult to obtain the multi-sensor remote sensing data acquired at the same acquisition time for impervious surface mapping. Consequently, real landscape changes between multi-sensor remote sensing data at different acquisition times would lead to the error of misclassification in impervious surface mapping. This issue has mostly been neglected in previous works. Furthermore, the observation differences generated from multi-sensor data, including the problems of misregistration, missing data in LiDAR data, and shadow in high-resolution images would also challenge the final mapping result in the fusion of LiDAR data and high-resolution images. In order to conquer these problems, we propose an improved impervious surface mapping method incorporating both LiDAR data and high-resolution imagery at different acquisition times in consideration of real landscape changes and observation differences. In the proposed method, a multi-sensor change detection by supervised multivariate alteration detection is employed to obtain changed areas and misregistration areas. The no-data areas in the LiDAR data and the shadow areas in the high-resolution imagery are extracted by independent classification yielded by its corresponding single sensor data. Finally, an object-based post-classification fusion is proposed to take advantage of independent classification results with single-sensor data and the joint classification result with stacked multi-sensor data. Experiments covering the study site in Buffalo, NY, USA demonstrate that our method can accurately detect landscape changes and obviously improve the performance of impervious surface mapping.

Historical forest management practices in the southwestern US have left forests prone to high intensity, stand-replacement fires. Effective management to reduce the cost and impact of forest-fire management and allow fires to burn freely without negative impact depends on detailed knowledge of stand composition, in particular, above-ground biomass (AGB). Lidar-based modeling techniques provide opportunities to reduce costs and increase ability of managers to monitor AGB and other forest metrics. Using Bayesian Model Averaging (BMA), we develop a regionally applicable lidar-based statistical model for Ponderosa pine and mixed conifer forest systems of the southwestern USA, using previously collected field data. The selected regional model includes a mid and low canopy height metric, a canopy cover, and height distribution term. It explains 72% of the variability in field estimates of AGB, and the RMSE of the two independent validation data sets are 23.25 and 32.82 Mg/ha. The regional model developed is structured in accordance with previously described models fit to local data, and performs equivalently to models designed for smaller scale application. Developing regional models for broad scale application provides a cost-effective, robust approach for managers to monitor and plan adaptively at the landscape scale.

The amount and spatial distribution of foliage in a tree canopy have fundamental functions in ecosystems as they affect energy and mass fluxes through photosynthesis and transpiration. They are usually described by the Leaf Area Index (LAI) and the Leaf Area Density (LAD), which can be measured through a variety of methods, including voxel-based methods applied to LiDAR point clouds. A theoretical study recently compared the numerical errors arising from different voxel-based estimation methods for Plant Area Density (PAD) based on Beer’s law-based, contact frequency and Maximum-Likelihood Estimation, showing that the bias-corrected Maximum Likelihood Estimator was theoretically the most efficient. However, this earlier study i) ignored wood volumes; ii) neglected vegetation clumping inside the voxel; iii) ignored instrument characteristics in terms of effective footprint, iv) was limited to a single viewpoint. In practice, retrieving LAD from PAD is not straightforward, vegetation is not randomly distributed in volumes of interest, beams are divergent and forestry plots are usually sampled from more than one viewpoint, to mitigate the effect of occlusion. In the present short communication, we extend the previous efficient formulation to actual field conditions to i) account for the presence of both wood volumes and wood hits, ii) rigorously include correction terms for vegetation and instrument characteristics, iii) integrate multiview data. A numerical comparison with other methods commonly used to combine information from different viewpoints led to error reduction, especially in poorly-explored volumes, which are frequent in actual canopies. Beyond its concision, completeness and efficiency, this new formulation -which can be applied to multiview TLS, but also UAV LiDAR scanning - can help reducing errors in LAD estimation.

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.

This study explores the intricate relationship between the angle of vehicle-to-vehicle (V2V) conflicts and the severity of conflicts at signalized intersections during traffic signal failures, leveraging the advanced capabilities of LiDAR sensor technology. The research delves into the impact of conflict angles on collision outcomes and introduces LiDAR as a novel and precise tool for capturing spatial dynamics during unregulated traffic movements. Findings reveal that as the angle of V2V conflicts increases, indicating a wider approach between vehicles, the severity of conflicts tends to decrease. This reduction in severity is attributed to the detailed spatial data provided by LiDAR, enabling the identification of glancing impacts rather than direct head-on collisions. The mitigation of forces involved in collisions at increased angles contributes to a decreased likelihood of severe consequences, such as extensive vehicle damage and serious injuries to occupants.Conversely, as the angle of V2V conflicts decreases, signifying a narrower approach between vehicles, the potential for severe collisions tends to increase. LiDAR technology facilitates precise measurements of spatial coordinates and temporal dynamics, revealing that collisions occurring at smaller angles involve more direct and concentrated impact forces. This heightened risk of extensive damage to vehicles and increased injury severity is crucially captured by LiDAR, providing valuable insights into the relationship between conflict angles and collision outcomes during traffic signal failures. This study underscores the efficacy of LiDAR sensor technology in understanding the nuanced dynamics of V2V conflicts and highlights its role in developing targeted safety interventions. The integration of LiDAR data into traffic safety analyses offers a sophisticated approach to mitigating the impact of conflicts and enhancing overall safety at signalized intersections during signal failures. The research also highlighted that as the angle of V2P conflicts widens, PET experiences a proportional increase. A larger conflict angle signifies a more complex interaction between vehicles and pedestrians, leading to prolonged PET values. Conversely, a decrease in the angle of V2P conflicts is associated with a reduction in PET during traffic signal failures.The study commences with an examination of traffic characteristics at the E Cold Spring Ln – Hillen Rd intersection in Baltimore City, MD, utilizing a deployed LiDAR sensor. When the signal at this intersection experienced a temporary malfunction on a regular working day in September 2023, the LiDAR captured data related to vehicle and pedestrian volumes, as well as V2V and V2P conflicts. The primary objective of the research is to evaluate the repercussions of traffic signal failures on both traffic flow and safety, specifically V2V and V2P conflicts, occurring during periods of improper signal functionality. Additionally, this investigation delves into various factors that impact traffic signal performance, encompassing traffic demand, geometric layout, pedestrian interactions, and the incorporation of emerging technologies.

Mapping vegetation species is critical to facilitate related quantitative assessment, and for invasive plants mapping their distribution is important to enhance monitoring and controlling activities. Integrating high resolution multispectral remote sensing (RS) image and lidar (light detection and ranging) point clouds can provide robust features for vegetation mapping. However, using multiple source of high-resolution RS data for vegetation mapping at large spatial scale can be both computationally and sampling intensive. Here we designed a two-step classification workflow to decrease computational cost and sampling effort, and to increase classification accuracy by integrating multispectral and lidar data to derive spectral, textural, and structural features for mapping target vegetation species. We used this workflow to classify kudzu, an aggressive invasive vine, in the entire Knox County (1,362 km2) of Tennessee, the United States. Object-based image analysis was conducted in the workflow. The first-step classification used 320 kudzu samples and extensive coarsely labeled samples (based on national land cover) to generate an overprediction map of kudzu using random forest (RF). For the second step, 350 samples were randomly extracted from the overpredicted kudzu and labeled manually for the final prediction using RF and support vector machine (SVM). Computationally intensive features were only used for the second-step classification. SVM had constantly better accuracy than RF, and the Producer’s Accuracy, User’s Accuracy, and Kappa for the SVM model on kudzu was 0.94, 0.96, and 0.90, respectively. SVM predicted 1010 kudzu patches covering 1.29 km2 in Knox County. We found the sample size of kudzu used for algorithm training impacted the accuracy and number of kudzu predicted. The proposed workflow could also improve sampling efficiency and specificity. Our workflow had much higher accuracy than the traditional method conducted in this research, and could be easily implemented to map kudzu in other regions or other vegetation species.

As a critical transmitter, the compact 532 nm lasers operating on high repetition and narrow pulse widths have been used widely for airborne or space-borne laser active remote sensing. We developed a free space pumped TEM₀₀ mode sub-nanosecond 532 nm laser that occupied a volume of less than 125 mm × 50 mm × 40 mm (0.25 liters). The fundamental 1064 nm laser consists of a passively Q-switched composite crystal microchip laser and an off-axis, two-pass power amplifier. The pump sources were two single-emitter semiconductor laser diodes (LD) of 808 nm with a maximum continuous wave (CW) power of 10 W each. The average power of fundamental 1064 nm laser was 1.26 W with the laser operating at 16 kHz repetition rates, and 857ps pulse widths. Since the beam distortion would be severe in microchip lasers in terms of the increase in heat load, for obtaining a high beam quality of 532 nm, the beam distortion was compensated by adjusting the distribution of pumping beam in our experiment of fundamental amplification. Furthermore, better than 0.6 W average power, 770 ps, beam quality of M² ＜1.2, and 16 kHz pulse output at 532 nm was obtained by a Type I LiB₃O₅ (LBO) crystal in the critical phase matching (CPM) regime for second harmonic generation (SHG).

Collision avoidance is an important feature in advanced driver-assistance systems, aiming at providing correct, timely and reliable warnings before an imminent collision (objects, vehicles, pedestrians, etc.). A co-simulation framework is proposed in this paper to address the design and evaluation of collision avoidances in a cyber-physical system. The co-simulation framework is supported on the interaction between SCANeR and Matlab/Simulink. From the best of authors’ knowledge, two main contributions are reported in this paper. Firstly, the modelling and simulation of virtual on-chip LIDAR sensors in a cyber-physical system (CPS) considering traffic scenarios is presented. The CPS is designed and implemented in SCANeR. Secondly, an obstacle recognition library with three specific Artificial Intelligence-based methods is also designed based on sensory information database provided by SCANeR. Three methods for collision avoidance detection are considered, i.e.; a multi-layer perceptron neural network, a self-organization map and a support vector machine. Finally, a comparison among these methods for detecting obstacles before different weather conditions is done with very promising results in terms of accuracy. The best results are achieved using the multi-layer perceptron in sunny and fog conditions, the support vector machine in rainy and self-organized map in snowy conditions.

Mobile Mapping System (MMS) plays a crucial role in generating high-precision 3D maps for various applications. However, the traditional MMS that uses tilted LiDAR (light detection and ranging) has limitations in capturing complete information of the environment. To overcome these limitations, we propose a panoramic vision-aided Cartographer simultaneous localization and mapping (SLAM) system for MMS, named "PVL-Cartographer". The proposed system integrates multiple sensors to achieve accurate and robust localization and mapping. It contains two sub-systems, early fusion and middle fusion. In the early fusion, range-maps are created from LiDAR points in a panoramic image space, facilitating the incorporation of visual features. The SLAM system works with both visual features with and without augmented ranges. In the middle fusion, a pose graph combines camera and LiDAR nodes, with IMU (Inertial Measurement Unit) data providing constraints between each node. Extensive experiments in challenging outdoor scenarios demonstrate the effectiveness of the proposed SLAM system in producing accurate results, even in conditions with limited features. Overall, our proposed PVL Cartographer system offers a robust and accurate solution for MMS localization and mapping.

This article proposes the use of a multi-scale and multi-sensor approach to collect and modelling 3D data concerning wide and complex areas in order to obtain a variety of metric information in the same 3D archive, based on a single coordinate system. The employment of these 3D georeferenced products is multifaceted and the fusion or integration among different sensors data, scales and resolutions is promising and could be useful for the generation of a model that could be defined as hybrid. The correct geometry, accuracy, radiometry and weight of the data models are hereby evaluated comparing integrated processes and results from Terrestrial Laser Scanner (TLS), Mobile Mapping System (MMS), Unmanned Aerial Vehicle (UAV), terrestrial photogrammetry, using Total Station (TS) and Global Navigation Satellite System (GNSS) as topographic survey. The entire analysis underlines the potentiality of the integration and fusion of different solutions and is a crucial part of the “Torino 1911” project whose main purpose is mapping and virtually reconstructing the 1911 Great Exhibition settled in the Valentino Park in Turin (Italy).

The Greenland Ice Sheet is now the largest land ice contributor to global sea level rise, largely driven by increased surface meltwater runoff from the ablation zone, i.e. areas of the ice sheet where annual mass losses exceed gains. This small but critically important area of the ice sheet has expanded in size by ~50% since the early 1960s, and satellite remote sensing is a powerful tool for monitoring the physical processes that influence its surface mass balance. This review synthesizes key remote sensing methods and scientific findings from satellite remote sensing of the Greenland Ice Sheet ablation zone, covering progress in 1) radar altimetry, 2) laser (lidar) altimetry, 3) gravimetry, 4) multispectral optical imagery and, 5) microwave and thermal imagery. Physical characteristics and quantities examined include surface elevation change, gravimetric mass balance, reflectance, albedo, and mapping of surface melt extent and glaciological facies and zones. The review concludes that future progress will benefit most from methods that combine multi-sensor, multi-wavelength, and cross-platform datasets designed to discriminate the widely varying surface processes in the ablation zone. Specific examples include fusing laser altimetry, radar altimetry, and optical stereophotogrammetry to enhance spatial measurement density, cross-validate surface elevation change, and diagnose radar elevation bias; fusing optical imagery, radar imagery, and microwave scatterometry to discriminate between snow, liquid water, refrozen meltwater, and bare ice near the equilibrium line altitude; combining optical reflectance with laser altimetry to map supraglacial lake, stream, and crevasse bathymetry; and monitoring the inland migration of snowlines, surface melt extent, and supraglacial hydrologic features.

In this article, we combine datasets from multiple research projects and remote sensing tech-nologies to evaluate the conservation conditions of La Fortaleza de Kuelap, a pre-Hispanic monument in Peru’s northeastern Andes that suffered significant damage during historically high seasonal rains in April 2022. Our analyses seek to identify the main causes of the collapse and locate places where the monument is likely at risk of further deterioration. To do so, we model surface hydrology using a digital elevation model (DEM) derived from drone LiDAR data, re-construct a history of previous collapses, and calculate the volume of the most recent by fusing terrestrial LiDAR and photogrammetric datasets. In addition, we examine subsurface water ac-cumulation through electrical resistivity data, reconstruct the stratification of the monument from seismic refraction data, and analyze vegetation loss and ground moisture accumulation using high resolution satellite imagery. Our results point to water accumulation as the most significant source of risk for La Fortaleza’s perimeter walls. Combined with adverse contemporary conser-vation interventions and natural conditions, this led to the collapse of April 2022. This integration of analytical results demonstrates how multi-scalar and multi-instrumental approaches provide comprehensive and timely assessments of conservation needs.

Imaging lidars are one of the hottest topics in the optronics industry. The need to sense the surroundings of every autonomous vehicle has pushed forward a career to decide the final solution to be implemented. The diversity of state-of-the art approaches to the solution brings, however, a large uncertainty towards such decision. This results often in contradictory claims from different manufacturers and developers. Within this paper we intend to provide an introductory overview of the technology linked to imaging lidars for autonomous vehicles. We start with the main single-point measurement principles, and then present the different imaging strategies implemented 8 in the different solutions. An overview of the main components most frequently used in practice is also presented. Finally, a brief section on pending issues for lidar development has been included, 10 in order to discuss some of the problems which still need to be solved before an efficient final implementation.Beyond this introduction, the reader is provided with a detailed bibliography containing both relevant books and state of the art papers.

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.

The vulnerability of alpine environments to climate change presses an urgent need to accurately model and understand these ecosystems. Popularity in use of digital elevation models (DEMs) to derive proxy environmental variables has increased over the past decade, particularly as DEMs are relatively cheaply acquired at very high resolutions (VHR; <1m spatial resolution). Here, we implement a multiscale framework and compare DEM-derived variables produced by Light Detection and Ranging (LiDAR) and stereo-photogrammetry (PHOTO) methods, with the aims of assessing their relevance and utility in species distribution modelling (SDM). Using a case study on the arctic-alpine plant Arabis alpina in two valleys in the western Swiss Alps, we show that both LiDAR and PHOTO technologies can be relevant for producing DEM-derived variables for use in SDMs. We demonstrate that PHOTO DEMs rivalled the accuracy of LiDAR, putting the current paradigm of LiDAR being the more accurate of the two methods into question. We obtained DEMs at spatial resolutions of 6.25cm-8m for PHOTO and 50cm-32m for LiDAR, where we determined that the optimal spatial resolutions of DEM-derived variables in SDM were between 1 and 32m, depending on the variable and site characteristics. We found that the reduced extent of PHOTO DEMs altered the calculations of all derived variables, which had particular consequences on their relevance at the site with heterogenous terrain. However, for the homogenous site, we found that SDMs based on PHOTO-derived variables generally had higher predictive powers than those derived from LiDAR at matching resolutions. From our results, we recommend carefully considering the required DEM extent to produce relevant derived variables. We also advocate implementing a multiscale framework to appropriately assess the ecological relevance of derived variables, where we caution against the use of VHR-DEMs finer than 50cm in such studies.

Over a billion people around the world are disabled, among them, 253 million are visually impaired or blind, and this number is greatly increasing due to ageing, chronic diseases, poor environment, and health. Despite many proposals, the current devices and systems lack maturity and do not completely fulfill user requirements and satisfaction. Increased research activity in this field is required to encourage the development, commercialization, and widespread acceptance of low-cost and affordable assistive technologies for visual impairment and other disabilities. This paper proposes a novel approach using a LiDAR with a servo motor and an ultrasonic sensor to collect data and predict objects using deep learning for environment perception and navigation. We adopted this approach in a pair of smart glasses, called LidSonic V2.0, to enable the identification of obstacles for the visually impaired. The LidSonic system consists of an Arduino Uno edge computing device integrated into the smart glasses and a smartphone app that transmits data via Bluetooth. Arduino gathers data, operates the sensors on smart glasses, detects obstacles using simple data processing, and provides buzzer feedback to visually impaired users. The smartphone application collects data from Arduino, detects and classifies items in the spatial environment, and gives spoken feedback to the user on the detected objects. In comparison to image processing-based glasses, LidSonic uses far less processing time and energy to classify obstacles using simple LiDAR data, according to several integer measurements. We comprehensively describe the proposed system's hardware and software design, construct their prototype implementations, and test them in real-world environments. Using the open platforms, WEKA and TensorFlow, the entire LidSonic system is built with affordable off-the-shelf sensors and a microcontroller board costing less than $80. Essentially, we provide designs of an inexpensive, miniature, green device that can be built into, or mounted on, any pair of glasses or even a wheelchair to help the visually impaired. Our approach affords faster inference and decision-making using relatively low energy with smaller data sizes as well as faster communications for the edge, fog, and cloud computing.

Coastal resources in Lian, Batangas, have undergone significant degradation due to a combination of human activities and natural factors, including sea-level rise, changes in sea-surface temperature, fluctuations in rainfall, increased storm frequency, and sedimentation. This has led to adverse effects on key ecosystems such as corals, mangroves, and seagrasses. To assess the extent of climate change hazards on these coastal resources, a Vulnerability Assessment was conducted in the municipality of Lian, Batangas. The assessment employed a combination of the Coastal Integrity Vulnerability Assessment Toolkit (CIVAT) and Integrated Coastal Sensitivity, Exposure, and Adaptive Capacity to Climate Change (ICSEA-C) guidelines. Additionally, the analysis incorporated detailed mapping using Light Detection and Ranging (LiDAR) data for mangroves and LandSat 8 imagery for corals and seagrasses. The findings at the municipal scale revealed that a staggering 90% of mangroves in Lian, Batangas, were highly vulnerable. This vulnerability was attributed to a high score in intrinsic characteristics and a low adaptive capacity. Similarly, a majority of seagrasses in the area were classified as medium and highly vulnerable at the municipal level. Only 10–20% of seagrasses received low to medium vulnerability scores. Shockingly, almost 100% of the coral reefs in Lian, Batangas, were deemed highly vulnerable, indicating a critical threat to this crucial marine ecosystem.

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.

Drought-induced plant mortality has increased globally during the last decades and is forecasted to influence global vegetation dynamics. Timely information on plant water dynamics is essential for understanding and anticipating drought-induced plant mortality. The most common metric that has been used for decades for measuring water stress is leaf water potential (Ψ_L), which is measured destructively. To obtain information on water dynamics from trees and forested landscapes, remote sensing methods have been developed. However, the spatial and temporal resolution of the existing methods have limited our understanding of water dynamics and diurnal variation of Ψ_L within single trees. Thus, we investigated the capability of terrestrial laser scanning (TLS) intensity in observing diurnal variation in Ψ_L during a 50 hour monitoring period and aimed to improve understanding on how large part of the diurnal variation in Ψ_L can be captured using intensity observations. We found that TLS intensity at 905 nm wavelength was able to explain 78% of the variation in Ψ_L for three trees of two tree species with a root-mean square error of 0.137 MPa. Based on our experiment with three trees, time-series of TLS intensity measurements can be used in detecting changes in Ψ_L, and thus it is worthwhile to expand the investigations to cover a wider range of tree species and forests and further increase our understanding of plant water dynamics at wider spatial and temporal scales.

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.

Monitoring crown closure evolution using multi-temporal Light Detection and Ranging (LiDAR) surveys is a method that we expect to be increasingly adopted given the availability of LiDAR sensors and the accumulating survey archives. However, little attention was devoted to comparing crown closure estimates from independent surveys. Although survey parameters cannot be modified after the data collection, we speculate that the error associated to crown closure estimates comparison can be reduced by selecting optimal post-survey parameters. In this study, we compared crown closure estimates of three airborne LiDAR surveys from 2018 (40 pt/m²) used as a reference, and two lower-density surveys from 2016 (4.5 pt/m²) and 2018 (2 pt/m²). We studied the effect of the height threshold used to separate canopy points and the grid resolution, using skewness and variance of lagged difference of crown closure. Crown closure estimates using low height thresholds were more different across surveys, resulting in higher root mean squared error (RMSE), bias and more different variograms. Results show that optimal height threshold was 3 m and grid resolution was 25 m, although there was room for decision (RMSE of 7% and 5%, and bias of 4% and 0% for 2016 and 2018 low-density surveys).

This research paper investigates ultra-wideband (UWB) localization systems by focusing on the use of average filter (AVG), Kalman filter (KF), and extended Kalman filter (EKF) algorithms, as well as a novel integrated filtering method that incorporates low-pass filter (LPF) into AVG, KF, and EKF. The study aims to improve localization loss in indoor environments using a TurtleBot robot equipped with a camera to observe ground truth positions. To evaluate the effectiveness of the proposed algorithms, a comprehensive comparison of the raw and filtered data with the camera-based ground truth observations is performed. Quantitative analyses of the results, including max, min, max-min, and mean error, are performed to evaluate the localization performance of the algorithms and the integrated filtering method. The results reveal that the integrated filtering method has performed better accuracy in comparison with existing methods.

Automated extraction of buildings from earth observation (EO) data is important for various applications, including updating of maps, risk assessment, urban planning, policy making. Combining data from different sensors such as high-resolution multispectral (HRI) and light detection and ranging (LiDAR) has shown great potential in building extraction. Deep learning (DL) is increasingly used in multimodal data fusion and urban object extraction. However, DL-based multimodal fusion networks may underperform due to insufficient learning of “joint features” from multiple sources and oversimplified approaches to fusing multimodal features. Recently, an hybrid attention-aware fusion network (HAFNet) has been proposed for building extraction from a dataset including co-located Very-High-Resolution (VHR) optical images and Light Detection And Ranging (LiDAR) joint data. The system reported good performances thanks to the adaptivity of the attention mechanism to the features of the information content of the three streams but suffered from model overparametrization, which inevitably leads to long training times and heavy computational load. In this paper the authors propose a restructuring of the scheme, which involved replacing VGG-16-like encoders with the recently proposed EfficientNet, whose advantages counteract exactly the issues found with the HAFNet scheme. The novel configuration was tested on multiple benchmark datasets, reporting great improvements in terms of processing times, and also in terms of accuracy. The new scheme, called HAFNetE (HAFNet with EfficientNet integration), appears indeed capable of achieving good results with less parameters, translating into better computational efficiency. Based on these findings, we can conclude that, given the current advancements in single-thread schemes, the classical multi-thread HAFNet scheme could be effectively transformed by the HAFNetE scheme by replacing VGG-16 with EfficientNet blocks on each single thread. The remarkable reduction achieved in computational requirements moves the system one step closer to on-board implementation in a possible, future “urban mapping” satellite constellation.

Currently, the most important challenge in any assessment of state-of-the-art sensor technology and its reliability is to achieve road traffic safety targets. The research reported in this paper is focused on the design of a procedure for evaluating the reliability of Internet-of-Things (IoT) sensors and the use of a Cyber-Physical System (CPS) for the implementation of that evaluation procedure to gauge reliability. An important requirement for the generation of real critical situations under safety conditions is the capability of managing a co-simulation environment, in which both real and virtual data sensory information can be processed. An IoT case study that consists of a LiDAR-based collaborative map is then proposed, in which both real and virtual computing nodes with their corresponding sensors exchange information. Specifically, the sensor chosen for this study is a Ibeo Lux 4-layer LiDAR sensor with IoT added capabilities. Implementation is through an artificial-intelligence-based modeling library for sensor data-prediction error, at a local level, and a self-learning-based decision-making model supported on a Q-learning method, at a global level. Its aim is to determine the best model behavior and to trigger the updating procedure, if required. Finally, an experimental evaluation of this framework is also performed using simulated and real data

The complexity of urban spatial configuration, which affects human-well being and landscape functioning, needs acquisition and 3d visualisation data to inform decision-making process better. One of the main challenges in sustainability research is to conceive spatial models which are capable of adapting to changes in scale and recalibrating the related indicators depending on the degree of detail and data availability. In this perspective, the inclusion of the third dimension into Urban Ecosystem Services (UES) assessment studies highlights the details of urban structure-function relationships, improves modelling and visualisation of data and impacts, aiding decision-makers to localise, assess and manage urban development strategies. The main goal of the proposed framework concerns mapping, evaluating and planning of the UES within a 3d-virtual environment to improve the visualisation of the spatial relationships among the services allocation and the urban fabric density.