Prerpints.org logo
Preprint
Article

Furthering Automatic Feature Extraction for Fit-for-Purpose Cadastral Updating: Cases from Peri-Urban Addis Ababa, Ethiopia

Altmetrics

Downloads

164

Views

25

Comments

0

A peer-reviewed article of this preprint also exists.

Submitted:

28 June 2023

Posted:

29 June 2023

You are already at the latest version

Alerts
Abstract
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.
Keywords: 
Subject: Environmental and Earth Sciences  -   Remote Sensing

1. Introduction

Despite remote sensing and photogrammetry technologies now being increasingly common place in land administration, interest in emerging tools and technologies continue to rise [1]. Contemporary remote sensing technologies provide centimeter-level spatial resolution satellite images at a reasonable cost and time compared to aerial photography [2]. Unmanned Aerial Vehicles (UAVs) deliver high-resolution photographs and point cloud data for a parcel or parcels of interest quicker than traditional total station or GPS surveying [3,4]. GNSS-enabled mobile devices and web applications boost live data collection and facilitate cloud data storage [5].
Fit-for-purpose land administration (FFPLA) focuses on simplifying the preliminary work of the underpinning spatial framework for cadastral mapping. It prefers flexible, affordable, and upgradable technologies to stringent technical standards and sophisticated innovations for addressing current land administration issues (Enemark 2014). Emerging geospatial technologies provide efficient tools and techniques for cadastral mapping and registration of insecure tenure rights across the globe, as per the FFPLA requirement [6].
Focusing on cadastral mapping, this is the complex process that takes into account both technical and legal principles to determine parcel boundaries for new right registration or updating existing cadastral databases [3]. Maintaining the cadastre and keeping the data up-to-date is substantial, especially, for example, in rapidly urbanizing peri-urban areas of Ethiopia, where the farmers' land rights and tenure security are often jeopardized [7]. However, it is yet a challenge even for countries with well-established cadastral systems to track and update the dynamic nature of man-to-land relationships [4,8].
Thus, cadastral mapping is necessary for creating cadastral databases or updating existing ones; however, both hardly differ in methodological approach and materials used for the mapping [9]. While new creation is crucial for any country that seeks to establish a reliable land administration, updating is essential whenever land use or ownership changes occur. According to Bennett et al. [9], cadastral data subject to frequent changes include spatial data, party data, and rights data. Spatial or geographic data could involve subdivision, consolidation, or layering. A party or parties may be entitled to the land parcel by transfer, inheritance, or acquisition. Land use rights may vary with the time set: a specific period, ad-hoc, repeated, or continuous.
The overall cadastral database creation or updating process could be carried out systematically, covering the entire area plot by plot or sporadically triggered by the landholder [8,9]. However, sporadic cadastral mapping is usually for ground-based surveys; mapping with geospatial technologies or Automatic Feature Extraction (AFE) developments fit the systematic approach [10].
The primary concern of cadastral mapping is identifying the spatial extent of the boundary of the land parcel, the best unit to locate and define ownership rights in land management [11,12]. A parcel boundary is a spatially referenced demarcation line between two adjacent properties where one's land-use right ends and the other begins [13,14,15]. It can be physically marked and mapped using a fixed or general boundary approach [13]. A fixed boundary defines the property line precisely using accurate surveying equipment and techniques. A general boundary, on the other hand, is a rough determination of a parcel that typically uses existing artificial or natural features for demarcation such as hedges, ditches, walls, fences, roads, etc. [13,15,16]. The general boundary focuses more on the tenure security of individual owners than the spatial accuracy, and is often preferable for rural and peri-urban areas [17].
The nature and type of parcel boundaries matters when it comes to defining and applying methods and technologies for reliable cadastral mapping. In participatory mapping, parcel owners and concerned parties actively participate to delineate general boundaries on printed aerial/satellite imagery, which are later converted to digital format in the office using an on-screen digitization technique [13,18]. The approach is viable for acquiring reliable boundary information; however, the digitization process is time- and resource-consuming, less accurate, and difficult to repeat in case revision is required [19]. According to Chandrarathna [20], the digitization process took about 8% of the overall production time to delineate and map 500 plots from UAV imagery in Sri Lanka. Yagol et al. [21] also consumed 19% of the total time for digitizing and processing 102 parcels while making a cadastral map from high-resolution satellite imagery in Nepal. Moreover, it can deliver inconsistent results between individual experts: the experts may not delineate the same parcel uniformly, in addition to the subjectivity of image interpretation [5].
Although still in development, Automatic Feature Extraction (AFE) methods are suggested as a viable FFPLA alternative to map cadastral boundaries for registering and updating land records in a time and cost-efficient manner [19,22]. It is highly favored by the periodical improvements in the spatial resolution of the satellite/aerial images to extract general boundary objects without or with fewer human inputs [19]. AFE could eventually replace the labor and time-intensive on-screen digitization. The approach is tested in rural, peri-urban and urban settings and promising results are obtained [5,17,23]. Crommelinck et al. [23] advised the traditional surveying technique for urban areas since the smaller parcel sizes require fewer logistics than massive rural farmlands. The AFE approach is supposed to be economical in peri-urban areas where parcel boundaries are composed of both urban and (more of) rural characteristics.
Several authors illustrated the viability of the AFE approach in different ways, such as using open-source tools for image segmentation (e.g., Wassie et al. [17]), employing proprietary software solutions (e.g., Nyandwi et al. [5]), and developing codes for the complete process (e.g., Crommelinck [24]). Studies also evidenced the significance of emerging and freely available geospatial technologies for extracting cadastral boundaries automatically [2,19,25].
Thus, tenure security challenges due to the rapid (peri-) urbanization and the opportunities from emerging geospatial technologies for cost and time effective cadastral mapping are the basis for the overarching motivation and objectives of this research. Therefore, the purpose of the study is to explore the potential role of the AFE approach for extracting parcel boundaries in the peri-urban areas in Addis Ababa in a fast, affordable, and reliable manner, as required by FFPLA. It employs ready-to-use open-source software solutions for the (semi-) automatic extraction, classification, and delineation of cadastral boundaries, focusing on peri-urban areas in Addis Ababa. The approach is supposed to contribute to the overall endeavour to register land tenure rights and update cadastral records in a fit-for-purpose approach.
For further setting, the next section highlights the rapid urbanization of Addis Ababa peri-urban areas and automatic feature extraction practices and applications (Section 2). The methodology (Section 3) illustrates the study approach with a brief description of the study area and the datasets for the study. Then, the AFE test and processing results are presented (Section 4) and thoroughly discussed (Section 5). Finally, conclusions and recommendations for future improvements are made based on the study findings (Section 6).

2. Background of the study

2.1. Urbanization, a threat to tenure security of peri-urban areas of Addis Ababa

Peri-urbanization refers to the dynamic and complex transformation of peri-urban areas into a mix of rural and urban landscapes and socioeconomic activities [26]. Urbanization could stimulate economic growth, expand infrastructure, improve public and private amenities, and enhance the lifestyles of peri-urban occupants [27]. On the other hand, the unplanned expansion of established cities towards the peri-urban areas threatens the farmers' land rights and tenure security [7,28]. Land-related fraud and corruption may also arise due to inefficient and slow land administration and management services that fail to cope with the dynamic changes [29].
Ethiopia is experiencing haphazard urbanization towards the peri-urban outskirts in response to the high growth rate of the population [7,30]. Due to the absence of a demarcated administrative boundary between the rural and urban in Ethiopia, as in the case of many African countries, the highly dynamic peri-urbanization process is uncontrolled [31]. Most of Ethiopia's large cities, including the capital Addis Ababa, arose without proper planning, and urban centres continue to do so to this day [32]. What is peri-urban currently will be changed to a complete urban system within a few years. The small cities and towns across the country are the outcomes of such undetermined peri-urbanization [33].
The peri-urban areas are in high demand, both legally, as part of government-led development projects, and illegally, in informal settlements [34]. Ethiopia strategically fosters peri-urbanization by evicting agricultural land from peri-urban farmers for residential house building or private investment [35]. According to the World Bank Group [36], well-managed urbanization might boost Ethiopia's economic growth; otherwise, loss of land rights and rural-urban migration would be the adverse effects that reduce productivity.
The consequence of the unplanned rapid urbanization is manifested in the peri-urban areas of the country's capital, Addis Ababa, the hub of numerous national and international organizations. The spontaneous expansion of the city, at an approximate rate of 2% per year, appeared to be its distinctive characteristic and a threat to the peri-urban land rights [7,34,37]. Teklemariam et al. [7] demonstrated that changes in the tenure system due to rapid urbanization highly endangered the Addis Ababa peri-urban farmers' land rights. An efficient cadastral and land registration system is vital to manage the consequences of rapid urbanization and ensure tenure security problems [38].
A real property registration proclamation was enacted in Ethiopia a century ago in 1907, which allows land transactions in Addis Ababa [39,40]. The 1960 property registration article and the 1975 urban land and extra housing reform are remarkable developments in the country's land tenure system history [39,40]. Since the 1994 urban land lease holding regulation, the Addis Ababa City Administration has initiated a cadastral project and worked to register properties for taxation and tenure security purposes [39]. It was a pilot project designed to serve as the basis for a national solution and a model for other regional cities and urban areas. However, inefficient integration and updating mechanisms have rendered the cadastre unable to control the informal settlements and land encroachments that threaten tenure security [41]. Studies further declared that the urban cadastral system of Addis Ababa is not functioning as expected [42,43] for a variety of factors, including a lack of broad strategic orientations [44], technical shortcomings, legal gaps, and insufficient institutional structures [45].
Nonetheless, according to Metaferia et al. [46], the legal, spatial, and institutional frameworks for the undergoing cadastral project favour emerging geospatial technologies to boost the efforts in a fit-for-purpose manner. International aid and financial organizations also advocate utilization of freely available cutting-edge open-source software technologies for quick tenure registration and cadastral updating [47].

2.2. AFE practices

The AFE method is commonly used to delineate patterns with predictable arrangements, and it has been applied in various disciplines more reliably than the manual approach [48]. It employs the spectral information in each pixel (pixel based) or the geometry and spatial relationships of group of pixels (object based) to automatically extract parcel boundaries [13]. Studies prove that the object based feature extraction provide more reliable results than the pixel based approach for it considers the image texture, pixel proximity, feature size and shape in addition to the spectral information [5,13,49,50,51]. Crommelinck et al. [13] summarized the steps involved in extracting object-based boundary features as image segmentation (segmenting the image into spectrally similar features), line extraction (identifying edge lines or boundary features), and connecting edge or boundary lines (contour generation) (Figure 1).
Several scholars have practiced and proved the potential of different machine learning algorithms to fully or semi-automatically extract boundary features from satellite or aerial images. Although the methodological approaches and the applied algorithms vary, promising results are obtained for detecting and semi-automatically extracting farmland boundaries, which could enhance the rural cadastre [5,17,24,52,53].
Babawuro et al. [52] employed edge detection, morphological operations and Hough Transform (HT) algorithms for detecting and extracting farmland cadastral boundaries from high resolution satellite imagery. Turker et al. [53] applied a rule-based perceptual grouping algorithm to automatically extract agricultural field boundaries from SPOT5 and SPOT4 images, which performed better on high-resolution imagery (SPOT5) than the coarser one (SPOT4). Mean-shift image segmentation algorithm is used for semi-automatic boundary extraction in rural areas from 0.5m resolution pan-sharpened and orthorectified WorldView-2 satellite images [17]. Similarly Nyandwi et al. [5] used the World View-2 images to extract general parcel boundaries by Object-Based Image Analysis (OBIA) approach that delivers Geographic Information System (GIS) compatible vector files. The approach involves breaking the image into objects (Segmentation) and grouping them based on the spectral properties and contextual information (Classification). The authors tested both fully automated and expert knowledge techniques using commercial software (eCognition) and the Estimate Scale Parameter (ESP2) tool to set optimal parameterization values. Crommelinck [24] has developed a procedure for boundary feature extraction that takes advantage of visible cadastral boundaries on high-resolution aerial/satellite images. First, it employed Multi-resolution Combinational Grouping (MCG), an extended version of globalized probability of boundary (gPb) algorithm, for identifying closed boundaries between objects or segments based on the image texture, colour, and brightness information. Then, training dataset is generated labelling the contour lines with 'boundary' and 'not boundary' to train a classifier algorithm and predict boundary likelihoods for unseen testing data without a boundary label. The third step encompasses interactively delineating lines with highest boundary likelihoods to create final cadastral boundaries. A Quantum GIS (QGIS) 'BoundaryDelineation' plugin is created to guide the interactive delineation by determining a least-cost-path between user-selected nodes, or connecting around selection of lines or end points of selected lines generated in the first step.
Despite the problem of determining an appropriate threshold value to avoid over- or under-segmentation, which could provide extra boundary features [17,53], statistical validation of the achieved results confirms the potential of the AFE approach for mapping cadastral boundaries. Turker et al. [53] attained 82.6% for the SPOT5 and 76.2% for the SPOT4 images matching between the automatically extracted agricultural field boundaries and the reference dataset. With a sample set of images that possessed haystacks and bushes, Wassie et al. [17] obtained 55.4% completeness, 16.3% correctness, and 14.4% quality, buffering the extracted and reference lines by 0.5m and 3 m, respectively. The OBIA approach implemented by Nyandwi et al. [5] extracted 45% of visible boundaries in rural areas (completeness) and 47.4% correctness, although it failed in urban areas due to the features' complexity and spectral reflectance ambiguity.
The accuracy assessment of interactively delineated cadastral boundaries in Crommelinck's [24] study delivered 67% spatial correctness and 37% completeness. Additionally, compared to manual on-screen digitizing, the interactive boundary delineation approach reduced the time required to extract boundary lines by 38% and the number of clicks by about 80%. Koeva et al. [54] also evaluated the boundary delineator QGIS plugin against the seven characteristic elements of FFPLA. The tool is proved to be attainable and upgradable for it is freely available and open for further improvement. +
In summary, the AFE approach uses fewer resources and produces results faster than traditional methods and manual digitization, but with less absolute and relative accuracy, for both individual parcels and the breadth of the cadastral area being mapped. Fetai et al. [51] advised combining the automatic approach with the manual interactive delineation to reduce the time and resource consumption while maintaining the desired accuracy. Thus, the 'BoundaryDelineation' QGIS plugin, which supports an interactive, semi-automatic delineation of parcel boundaries, would speed up the process and minimize both human resources and infrastructure costs [55,56]. The plugin is supposed to enhance cadastral mapping where visible cadastral boundaries are predominant and fit-for-purpose land administration is favored [57]. However, it needs more attention and further investigation to refine the technology and employ it in practical uses [15,23]. Crommelinck et al. [58] proposed utilization of the technology for real world cadastral mapping scenarios.

3. Methods and Materials

3.1. Study area

Addis Ababa is one of the most rapidly growing cities in Sub-Saharan Africa. Its geographic location is roughly 9o2'N Latitude and 38o45'E Longitude, at an average altitude of 2,400 meters above sea level. Addis Ababa covers 540 square kilometres of territory and contains ten administrative divisions known as "sub-cities" (recently restructured to eleven). The six peripheral sub-cities (Akaki-Kitaly, Bole, Kolfe-Keranio, Gulele, Nifas-Silk-Lafto, and Yeka) account for 92% of the total area [34]. These sub-cities are subject to a high rate of urbanization in the peri-urban areas of the neighbouring Oromia special zone cities, resulting in chaos like farmers' displacement and environmental deterioration [59]. The Akaki-Kality sub-city is chosen as the case study region because it demonstrates the influence of increasing urbanization on the tenure system of peri-urban areas of Addis Ababa (Figure 2).
Akaki-Kality is one of the city's largest sub-city, covering 156 square kilometres of land, the majority of which are industrial zones and agricultural fields [60]. It is located in the southeast of Addis Ababa, where substantial urbanization has occurred in recent years at the expense of its peri-urban agrarian communities [61]. For instance, while condominium housing occupied 11% of the city in 2016, the majority of the land was acquired from the peri-urban areas of the Akaki-Kality sub-city [34]. According to Koroso et al. [61], the built-up area of the sub-city increased by 115 percent within fifteen years (from 2004 to 2019). Several scholarly articles also revealed the severe impact of unplanned rapid urbanization on land tenure security generally in Addis Ababa [7,34,59,62,63,64], notably in the Akaki-Kality sub-city peri-urban areas [60,61,65].
The study specifically determined a peri-urban village in Woreda 9, locally called Feche (Figure 2), where many condominium houses are developed, and rapid urbanization is still occurring. One of the researchers also has better familiarity with the area, which might help with visual inspection and field verification of the results. Furthermore, due to the high rate of urbanization in the surrounding area and perceptible variability between the image and the reference data, it helps validate the approach for cadastral map updating.

3.2. Data

A high-resolution (0.25 m by 0.25 m) orthophoto is used for extracting the study area peri-urban parcel boundaries. The aerial photograph is acquired by the Ethiopian Mapping Agency (EMA) (recently named as Space Science and Geospatial Institute, SSGI) in 2016. A cadastral boundary shape file, obtained from the Akaki-Kality sub-city land administration office, is used as reference data for the AFE result validation (Table 1). It is produced from aerial photograph acquired in 2010, and is used as a base map for cadastral survey work and planning purposes [41]. Both datasets are subsetted to the identified area of interest for extraneous data removal and manageability for boundary extraction and validation purposes.

3.3. AFE approach

The study intends to explore the outstanding role of the AFE approach for fast, inexpensive, and reliable cadastral mapping by validating the result with cadastral reference data. It adopted the AFE approach developed by Crommelinck et al. [23] that involved image segmentation, boundary classification, interactive delineation, and validation (buffer overlay accuracy assessment). Segmentation delivers available boundary outlines from the image. Classification helps determine conceivable cadastral boundaries from the set of extracted outlines. Interactive delineation enhances the precise delimitation of the identified cadastral boundaries. Validation of the interactively delineated cadastral boundaries ensures the reliability of the result for further cadastral applications. Thus, the study outlines a workflow to utilize publicly available and ready-to-use open-source software tools for each process that demonstrates the outstanding role of the AFE approach for fast, affordable, and reliable cadastral mapping.
Based on Crommelinck et al. [23] and GitHub [66], each step is further described below, along with the proposed open-source software solutions:-
i) 
Image segmentation:- at this stage, the orthoimage pixels are grouped into segments to deliver the outlines of the visible boundary features. The study employs the mean-shift image segmentation algorithm implemented in Orfeo ToolBox1 (OTB), an open-source state-of-the-art image processing library freely available for use [67,68]. The OTB is integrated in QGIS for ease of use and further analysis of the extracted parcel boundaries.
ii) 
Boundary classification:- this step requires training a machine learing model with a training dataset to enable it predict most probable boundary lines from the vector files obtained through image segmentation. The training and validation datasets are extracted from the segmentation result by mannually selecting and assigning 1 and 0 attribute values respectively to boundary and non-boundary line features. The study applied the Random Forest (RF) machine learning algorithms for the parcel boundary prediction. Although, Crommelinck et al. [23] tested and found that Convolutional Neural Networks (CNN) machine learning algorithms provide better precision and accuracy boundary likelihoods, various studies also proved that RF could provide good accuracy in image classification [2,69,70]. Moreover, it is one of the various machine learing models implemented in the OTB.
iii) 
Interactive delineation:- at this stage, the final cadastral boundaries are created by interactively delineating the boundary outlines based on the classification result. The line segments classified as parcel boundary further visually inspected and interactively delineated using the QGIS 'BoundaryDelineation' plugin. The plugin is developed by Its4land 2 initiative, the European Horizon 2020-funded project, for quick cadastral mapping and land rights registration [71]. It is one of the six tools created by the initiative to support Sub-Saharan African countries with innovative technologies and consulting services in order to improve the time- and cost-consuming field surveying procedure for cadastral mapping. The 'BoundaryDelineation' plugin provides six different interactive functionalities (Table 2) which facilitate precise delineation of the parcel boundaries as demonstrated in Figure 3.

3.4. Accuracy Assessment

Accuracy assessment provides confidence to apply the adopted AFE approach in a real-world scenario for peri-urban cadastral mapping and updating. The study employs both qualitative (visual inspection) and quantitative (buffer overlay) assessment methods. The qualitative assessment visually compares the interactively delineated cadastral features with ground reality. The quantitative validation uses the buffer overlay method to compare the interactively delineated boundary lines with the cadastral reference boundary. The buffer overlay method creates a buffer around a more-accurate spatial feature to assess the positional accuracy of a less accurate test line by computing the percentage of its length that lies within the buffer [72]. Several studies applied the buffer overlay method to assess classification results quantitatively [5,17,23,73].
Studies used different radii buffer sizes for the extracted and reference boundary lines for a buffer overlay analysis. Crommelinck et al. [23] used a 30cm buffer size for validating automatically extracted and interactively delineated cadastral boundaries from UAV datasets for both rural and peri-urban areas in Rwanda and Kenya. Fetai et al. [4] performed the accuracy assessment with buffer widths of 0.25, 0.50, 1.0, and 2.0 meters for cadastral boundaries extracted from UAV image. Wassie et al. [17] used 0.5, 1.0, and 2.0m buffer radii to validate automatically extracted boundary lines from high-resolution satellite images for rural areas of Ethiopia. A study for the FFPLA implementation model suggested 1m accuracy for rural area cadastral mapping from an orthophoto of 0.3m resolution [74].
Considering that the test case is a peri-urban area where the urban-to-rural transition is undetermined, the study prompts validation of the interactively delineated boundary lines with different buffering sizes (from high to coarse). Thus, three moderate buffer radii for the extracted (0.4, 0.5, and 1.0m) and the reference (0.6, 1.0, and 1.5m) lines are arbitrarily selected within the limits of the FDRE's [75] minimum spatial accuracy for urban cadastre (0.4m) and the IAAO's [76] suggested accuracy level for rural boundaries (2.4m).
The QGIS 'LineComparison' plugin developed by Its4land project is employed for the buffer overlay accuracy assessment of the interactive delineation result. It needs rasterizing and buffering the reference dataset (Figure 4, Green), and overlaying it with the interactively delineated boundary lines (Figure 4, Red). Thus, number of correctly extracted (True Positive (TP)) (Figure 4a), incorrectly retrieved (False Positive (FP)) (Figure 4b), and missing (False Negative (FN)) (Figure 4c) boundary features are used to statically compute completeness, correctness, and quality of the interactive delineation result.
As discussed briefly in Heipke et al. [73], Crommelinck et al. [77], and others:
  • Completeness is the percentage of the reference boundary that lies within the buffered extracted data (the reference data explained by the extracted data) and is given as:
C o m p l e t e n e s s   ≈ TP TP   +   FN × 100 %
  • Correctness refers the percentage of the extracted boundary that lies within the buffered reference data (the extracted data explained by the reference data), and is given as:
C o r r e c t n e s s   ≈ TP TP   +   FP × 100 %
  • Quality is derived from the completeness and correctness of the extracted data for these two metrics are complimentary and computed concurrently in order to indicate the quality or the overall accuracy of the extraction approach [78].
Q u l a i t y   ≈ TP TP   +   FP + FN × 100 %
For ease of visualization and the statistical computation, the 'Expected' and 'Extracted' number of pixels that belong to the TP, FP, FN, and TN categories are organized in a table (error matrix) as shown in Table 3.
The overall research methodology for the cadastral boundary extraction, classification, interactive delineation and result validation is depicted in Figure 5.

4. Results

The adopted methodology for the study is procedurally implemented to automatically extract boundary outlines from the orthophoto and classify the segmentation outlines into cadastral 'boundary' and 'non-boundary' features. The segmentation outlines classified as 'boundary' are further delineated interactively for precisely determining the cadastral boundaries. The interactively delineated boundary lines are validated to confirm the adopted AFE approach encouraging results. In this section, the processing outputs from the image segmentation, boundary classification, interactive delineation, and validation are presented in order.

4.1. Image segmentation

Image segmentation is the process of grouping image pixels that have some visual characteristics in common [79]. Visible parcel boundaries have such common characteristics and reflectance values, which favour the image segmentation algorithms. The OTB mean- shift segmentation algorithm with few changes to some of its default parameter values is applied. The spatial radius, the region size, and the object size parameters are respectively set to 50, 1000, and 100 by repetitive try and error to merge smaller region sizes with the neighbouring closest radiometry cluster and to disregard small areas (in pixels) during vectorization.
Running the OTB segmentation algorithm automatically extracted a total of 2,652 polygon features over the study area, which includes visible boundaries bounded by vegetation and fences. There are also several boundary features that fall inside the reference cadastral boundary, which is buffered by 0.4m, the minimal spatial accuracy for the urban legal cadastre set by regulation [75]. Figure 6 shows automatically extracted outlines (yellow) and boundary features that fall in a 0.4m buffer width of the reference cadastre (Green).
The AFE approach quite detected condominium buildings (Figure 7a), ditches and cobblestone roads (Figure 7b) in the newly built-up areas due to their different reflectance from the surrounding. However, it also produced non-boundary objects within cadastral parcels due to the spectral differences and linear artefacts (horizontal and vertical straight lines) in the image areas where there are no boundaries or spectral differences (Figure 7c).
The polygons are checked and fixed to meet the geometry properties and converted into lines using the QGIS 'Fix Geometry' and 'Polygon to Lines' built-in plugins. The length, azimuth, and vertexes on each line feature is computed for later use to train the RF model and predict boundary likelihoods of the segmentation result [24].

4.2. Boundary classification

The boundary classification approach requires training dataset to train the classifier for the prediction of the boundary and non-boundary line features. Random field inspection is carried out to be familiar with the surrounding parcel boundary types and identify 'boundary' and 'non-boundary' segmentation lines. The datasets are thus arbitrarily selected by visual appraisal of the segmentation lines with the features on the orthophoto based on ground reality and the coincident of the extracted boundaries with the reference parcel boundary. Thus, lines ostensibly representing cadastral boundaries are randomly selected and labelled (1) to denote 'boundary', whilst sample lines that do not describe parcel boundaries or artefacts are allocated (0), denoting 'non-boundary'. Consequently, a total of 300 lines are identified equally for 'boundary' and 'non-boundary' features as proposed in the work of Crommelinck [24]. Figure 8 shows the distribution of the randomly selected training dataset over the study area.
The OTB RF model with the default parameter setting classified the overall AFE segmentation lines (2,652) into 'boundary' (1,811) and 'non-boundary' (841) line segments. The classification result is visually inspected and observed that the RF model classified the automatically extracted outlines into 'boundary' and 'non-boundary' lines, but sometimes with a mix of the two. Figure 9 shows the AFE segmentation outlines classified as 'boundary' (Yellow) and 'non-boundary' (Blue) lines by the RF model.

4.3. Interactive delineation

The QGIS 'BoundaryDelineation' plugin automatically generates information from the orthophoto that helps to interactively delineate cadastral boundaries [24]. It takes the study area image /orthophoto/ and the probable boundary lines (identified by the RF classifier in this case). The lines are simplified at an appropriate scale to eliminate unnecessary details [80]. The interactive delineation needs careful visual inspection the classified segmentation outlines based on the familiarity of the delineator with the study area. This makes easy to use either of the 'BoundaryDelineation' tool functionalities as appropriate (Table 2) for precise delineation. Thus, the cadastral boundaries and the building footprints are interactively delineated by snapping to the input lines and vertices, which can be accepted as final or rejected for re-edition (Figure 10).
For validation and further processing the interactively delineated boundaries are converted to polygons and checked to address the fundamental topological concerns using the QGIS 'Topology Checker' plugin. That said, appropriate corrections are made for topological errors which could break the relationship between boundary features [81], especially for overshoots, undershoots, and dangles.

4.4. Validation

The interactively delineated boundary lines are validated both qualitatively and quantitatively by comparison with cadastral reference data. The visual inspection of the 'BoundaryDelineation' result is satisfactory for it was possible to exhaustively delineate cadastral boundaries and building footprints in the study area. However, dense vegetation and footpaths are extracted as cadastral boundaries. There are also extracted lines that do not match with- and a significant deviation from the reference cadastral boundary lines. This is further quantified using the QGIS 'LineComparison' plugin, which compares the interactively delineated boundary lines to the reference cadastral dataset and computes the error of commission (false positives) and omission (false negatives). Accordingly, the 'LineComparison' tool generated error matrices for the three buffering sizes of the input (0.4 m, 0.5 m, and 1 m) and the reference (0.6 m, 1 m, and 1.5 m) lines, and computed the correctness, completeness, and quality of the interactively delineated boundaries for each buffer size as shown in Table 4.
The validation result for the selected three buffer sizes is graphically depicted in Figure 11.

5. Discussion

The study explored freely available software tools and plugins for automatically extracting cadastral boundaries. An orthophoto and a reference cadastre for the case study peri-urban area in Addis Ababa, Ethiopia, are used for the demonstration. The orthophoto and the reference cadastre datasets are generated from aerial photographs acquired in 2016 and 2010, respectively. Publicly available open-source tools and plugins are identified and employed for image segmentation, boundary classification, interactive delineation, and validation. The OTB mean-shift image segmentation and classification tools are employed to segment the image and classify cadastral and non-cadastral boundaries. The identified cadastral boundaries are interactively delineated and validated using the QGIS 'BoundaryDelineation' and 'LineComparison' plugins, respectively. The discussion clarifies the adopted approach and elucidates the outstanding role of the AFE approach in extracting parcel boundaries for cadastral mapping and refresh in a fit-for-purpose manner.

5.1. Image segmentation and classification contribute to cadastral mapping and refresh

Image segmentation and classification are well-established techniques in remote sensing application studies. Segmentation is useful for detecting objects and boundaries, whereas classification is important to identify land cover types [82]. Nowadays, image segmentation and further classification of the segmentation result into 'boundary' and 'non-boundary' cadastral features is providing promising results for rural and peri-urban area cadastral mapping and updating [24].
The OTB mean-shift segmentation algorithm automatically extracted 2,652 boundary features which include visible boundaries such as fences and vegetation (Figure 6). The number of extracted boundary outlines (2,652) is much greater than the reference cadaster (131), partly due to new built-up areas between 2010 and 2016. There are also boundary outlines (Figures 6a and 6b) that fall within a reference cadastral boundary buffered by 0.4m, the minimal accuracy for urban cadastral boundaries set by the Ethiopian Council of Ministers Regulation [75]. This could show the significant role of the AFE approach in automatically extracting cadastral boundaries, although it may require additional manual editing. Furthermore, the boundary lines of condominium buildings, cobblestone roads, and ditches are also precisely extracted (Figure 7), which did not exist in the reference cadastre.
According to the Addis Ababa context, the condominium building footprints are the basic spatial information for issuing condominium house ownership certificates that mention the block, the floor, and the house number of the individual room in the block. Thus, precise identification of the condominium building footprints aids significantly to the cadastral mapping and refreshing of the peri-urban areas where a large number of condominium houses have been built in the past several years and still are. Automatic extraction of the cobblestone roads and ditches would also enhance delineating the spatial boundaries of building blocks surrounded by them.
Despite the fact that the RF model classified some 'boundary' features as 'non-boundary' and vice versa (Figure 9), the classification approach minimized the number of segmentation outlines by 32% in the subsequent processing. Thus, the RF classification is useful to exclude non cadastral boundary features from the set of extracted boundary outlines. Furthermore, using only the outlines classified as 'boundary' would be better than exploring the entire set of segmentation with a lot of artefacts and non-cadastral boundary features that have no relevance.
Various scholars have revealed image segmentation and classification prospects for extracting cadastral boundaries. However, the adaptations and implementations may not be as straightforward as with the open-source tools and plugins used for this study. For instance, Nyandwi et al. [5] used proprietary software (ENVI, eCognition) for image pre-processing and cadastral boundary extraction and found encouraging results in rural areas. While proprietary software may yield better in image pre-processing and cadastral boundary extraction, its use could come at a higher cost. Wassie et al. [17] applied an open-source mean-shift image segmentation algorithm and automatically extracted rural boundaries and found it encouraging, especially compared to on-screen digitization. However, the iterative segmentation to identify the cadastral boundary from the entire set of extracted outlines looks time- and resource-intensive. Crommelinck [24] employed the MCG method for image segmentation and a CNN algorithm for boundary classification to identify more probable cadastral boundaries. Although the source code is publicly available on GitHub3, it demands a certain level of technical expertise in programming for the necessary configuration and modification to adapt the approach.

5.2. Interactive delineation enhances the traditional on-screen digitization

On-screen digitization is a traditional interactive process in geographic information systems to generate a digital map from several image sources [83]. The advancement in computer processing capabilities and machine learning algorithms enhanced the traditional on-screen digitization for better and precise identification and delineation of cadastral boundary lines. The Its4land 'BoundaryDelineation' tool is an example of such a powerful tool that enhances the manual on-screen digitization technique. It facilitates semi-automated boundary line delineation, recording automatically while indicating the boundary lines interactively. The tool generates vertices along each line that would help interactively delineate cadastral boundaries precisely; making use of the different options it possessed (Table 2).
Both the qualitative (visual inspection) and quantitative (buffer overlay) assessments favor the interactive delineation approach over manual on-screen digitization. Visual assessment validated the complete extraction of cadastral boundary lines in the research area, while excluding non-boundary outlines such as footpaths and artefacts. Dense vegetation along parcel borders is approximated and demarcated with less departure to the probable center. Significant cadastral changes in the study area between 2010 and 2016 are easily detectable visually. However, it is also worth considering the possible effect of the changes on the quantitative buffer overlay assessment results.
Nonetheless, the quantitative validation of the interactively delineated boundary lines is also promising, especially for less accuracy-demanding rural and peri-urban areas. Assuming possible shifts both to the interactively delineated lines and the cadastral reference boundary, the buffer overlay analysis provided auspicious results (Table 4, Figure 11).
Buffering the input lines by 0.4m and the reference boundary by 0.6m provided 52% correctness and 32% completeness. Increasing the buffer size of the input lines to 0.5m and the reference cadastre to 1m changes the correctness and completeness percentages to 72 and 33, respectively. An additional increase in the input and reference lines to 1m and 1.5m increases the correctness to 72% and the completeness to 49%. The rise in correctness and completeness percentages with increasing buffer size might indicate possible cadastral boundary shifts due to the unplanned peri-urban expansion.
The quality of the interactively delineated boundaries needs to be improved, although there is an increase in each scenario (24%, 29%, and 42%). Quality is derived from the completeness and correctness of the interactively delineated boundary lines. It requires maximizing the number of correctly extracted (TP) boundary lines and minimizing the errors of commission (FP) and omission (FN) (Figure 4, Table 3).
Whilst the results are quite good - in cadastral applications, it seems much higher achievements, e.g., 80–90% - are still a long way off with these results. That said, incremental improvements are visible, and the method does allow for a rough-cut cadastre. Careful visual inspection of the extracted boundary outlines and familiarity of the delineator with the study area is also likely to increase the quality of the interactive delineation result [2].
Earlier works' statistical validations demonstrated the possibility of better improvements. Wassie et al. [17] attained 16.3% correctness and 54.4% completeness with the mean-shift image segmentation algorithm. Nyandwi et al. [5] applied OBIA and demonstrated the potential of the AFE approach over traditional on-screen digitization, extracting 45% of the visible boundaries in the study area and achieving 47.4% correctness. Crommelinck's [24] interactive delineation approach performed better, delivering 67% correctness and 37% completeness for peri-urban areas in Rwanda.
Thus, the validation results indicated the possibility of attaining higher levels of correctness and completeness with improvement in the AFE approach. Accordingly, improving the image segmentation and classification algorithms used in this study could enhance the efficiency of the 'BoundaryDelineation' tool to correctly extract cadastral boundaries found in the vicinity of the mapping area. Koeva et al. [2] anticipated the superiority of interactive delineation over the traditional on-screen digitization approach if some extra functionalities, such as line geometry checking and creating polygon attributes, are incorporated. Alternative image segmentation and classification techniques may improve the correctness of the 'Boundary Delineation' tool.
Besides, unlike manual digitization which visually depicts and digitizes the probable boundary lines, interactive delineation is guided by the vertices generated along the RF-classified boundary (input) lines. This makes the interactive delineation approach repeatable in case revision is required, saves time to digitize (fewer clicks than manual digitization [24]), and precisely delineates the boundaries despite some differences with the reference boundary. Although the approach tends to improve manual digitalization-based indirect surveying, user feedback and expertise evaluation are expected to improve it further for real-world scenario applications.

5.3. Open-source software tools and plugins enhance the implementation of the AFE approach for cadastral mapping and refresh

Open-source software tools and plugins provide a range of functionalities that help automate and streamline the cadastral mapping process. These made the traditional cadastral mapping and updating process faster, more affordable, and more reliable than conventional ground surveying. The study by Ajayi et al. [84] approximated the AFE approach as 2.5 times faster and nine times cheaper than traditional ground surveying. There are various proprietary and freely available open-source software solutions to implement the AFE approach for cadastral mapping and refresh. This study explored the readily available QGIS tools and plugins that could be used to automatically extract cadastral boundary features.
The automatic cadastral boundary extraction is done by the OTB mean-shift segmentation tool, which segments the input image and delivers the feature boundary outlines in vector format. The 'TrainVectorClassifier' and 'VectorClassifier' tools are used to train the RF model and classify the extracted boundary outlines into 'boundary' and 'non-boundary' lines. The Its4land 'BoundaryDelineation' tool is employed to interactively delineate cadastral boundaries and building footprints, simplifying the RF-classified boundary lines to an appropriate scale. The 'LineComparison' plugin is another tool from It4sland that rasterizes and buffers the interactively delineated boundary lines to carry out the validation. The QGIS built-in plugins are used to manipulate the input image and the extracted lines for further processing, as depicted in the methodology.
Both the OTB and the Its4land tools provided the intended result for cadastral mapping and refresh. However, there were unconditional interruptions and breaks while running the algorithms behind the tools. This might be resolved by future enhancements and updates to the source code; being open-source is an advantage. Nonetheless, the study proved the availability of the necessary free and open-source tools and plugins to implement the AFE approach for real cadastral mapping and refresh.
Even though expertise and experience with geospatial technologies are necessary, the implementations and applications of the open-source tools and plugins are not complex. Thus, the study demonstrated the potential of publicly available software solutions to accelerate systematic cadastral boundary mapping, enhancing AFE applications in compliance with the FFPLA requirement.

6. Conclusions

The study investigated the outstanding role of the AFE approach for mapping and updating cadastral boundaries, considering one of the vibrant peri-urban areas in Addis Ababa as a case study. It looked into the publicly accessible and open-source QGIS software tools and plugins for implementing the AFE approach.
Although several studies have demonstrated the potential of the AFE technique for cadastral boundary extraction, either by using proprietary software solutions or developing codes, the approaches seem expensive or require expertise for immediate use. This study, therefore, streamlined publicly available and ready-to-use geospatial software solutions and demonstrated the potential of the AFE approach for cadastral data extraction, complying with FFPLA requirements.
The OTB mean-shift segmentation and RF classification tools are used for extracting cadastral boundary outlines from the study area orthophoto and classifying into cadastral 'boundary' and 'non-boundary' features. The Its4land 'BoundaryDelineation' and 'LineComparison' plugins are applied to outline boundary lines interactively and evaluate the results.
The classification into cadastral 'boundary' and 'non-boundary' features minimized the number of automatically retrieved outlines by about 32%. This helped with the identification and interactive delineation of boundary lines from the set of classified boundary features, which contains fewer artefacts and non-cadastral boundary features.
Visual inspection confirms the extraction of the most probable visible boundary lines from the orthophoto with complete coverage of the study area. Whereas, the buffer overlay analysis provided 52% correctness and 32% completeness compared to the reference cadastre. Precise extraction of the building footprints favors systematic updating of the peri-urban cadastre, where multiple condominium houses have been developed in recent years. The spatial boundaries of the blocks of buildings can also be delineated from precisely extracted cobblestone pathways and ditches.
Overall, it was possible to demonstrate the potential of the AFE approach by interactively delineating the newly built-up cadastral boundaries within the six years (2010–2016) and updating the reference cadastre. Furthermore, the interactive delineation process can be repeated with a relevant accuracy in case rework is required. It also saves the time needed to extract the boundary lines compared to the manual digitization approach.
Nonetheless, as incremental refinements are seen in previous works, improving the image segmentation and classification algorithms behind the tools could enhance the efficiency of the approach and achieve better accuracies. Careful extraction of the training dataset and computation of more line attributes might reduce the misclassification of 'boundary' lines into 'non-boundary' features and vice versa. Besides, the delineator's acquaintance with the study area and careful visual inspection of the orthophoto would help precisely delineate cadastral boundaries.
Despite the encouraging results of utilizing free and open-source software solutions for the AFE implementation, the challenge of determining threshold values to avoid over- and under-segmentation needs attention. The unconditional interruptions and breakouts while using the tools also highlight the need for future enhancements, with the open source being a benefit.
In summary, the study is expected to contribute to the overall endeavor for cadastral mapping and refresh in peri-urban areas in a fit-for-purpose manner: fast, cheap, and reliable. However, the general methodological procedure and the technical approach for the AFE implementation need users' feedback and expertise evaluation to enhance further and apply it to the real-world scenario.

Author Contributions

Conceptualization, M.T.M.; methodology, M.T.M., R.M.B., B.K.A. and M.K.; formal analysis, M.T.M.; investigation, M.T.M.; data curation, M.T.M.; writing—original draft preparation, M.T.M.; writing—review and editing, M.T.M., R.M.B., B.K.A. and M.K.; visualization, M.T.M., R.M.B., B.K.A. and M.K. All authors have read and agreed to this version of the manuscript.

Funding

This research received no external funding.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Not applicable.

Conflicts of Interest

The authors declare no conflict of interest.

Notes

1
https://www.orfeo-toolbox.org/, accessed on January 9/2023
2
https://Its4land.com/, accessed on September 29, 2022
3
https://github.com/Its4land/delineation-tool/wiki/2b)-Convolutional-Neural-Network-Classification, accessed on November 15, 2022

References

  1. Bennett, R., et al., Remote sensing for land administration. Remote sensing, 2020. 12(15): p. 2497. [CrossRef]
  2. Koeva, M., et al., Innovative remote sensing methodologies for Kenyan land tenure mapping. Remote Sensing, 2020. 12(2): p. 273. [CrossRef]
  3. Šafář, V., et al., The Use of UAV in Cadastral Mapping of the Czech Republic. ISPRS International Journal of Geo-Information, 2021. 10(6): p. 380. [CrossRef]
  4. Fetai, B., et al., Extraction of visible boundaries for cadastral mapping based on UAV imagery. 2019. 11(13): p. 1510. [CrossRef]
  5. Nyandwi, E., et al., Comparing human versus machine-driven cadastral boundary feature extraction. Remote sensing, 2019. 11(14): p. 1662. [CrossRef]
  6. Enemark, S., R. McLaren, and C. Lemmen, Fit-for-purpose land administration guiding principles. Global Land Tool Network (GLTN): Copenhagen, Denmark, 2015.
  7. Teklemariam, A.T. and L. Cochrane, The Rush to the Peripheries: Land Rights and Tenure Security in Peri-Urban Ethiopia. Land, 2021. 10(2): p. 193. [CrossRef]
  8. Biraro, M., J. Zevenbergen, and B.K. Alemie, Good Practices in Updating Land Information Systems That Used Unconventional Approaches in Systematic Land Registration. Land, 2021. 10(4): p. 437. [CrossRef]
  9. Bennett, R.M., et al., Land Administration Maintenance: A Review of the Persistent Problem and Emerging Fit-for-Purpose Solutions. Land, 2021. 10(5): p. 509. [CrossRef]
  10. Enemark, S., R. Mclaren, and C. Lemmen, Fit-for-purpose land administration: Guiding principles for country implementation. GLTN reference, 2016.
  11. Lin, L. and C. Zhang, Land parcel identification, in Agro-geoinformatics. 2021, Springer. p. 163-174. [CrossRef]
  12. Bennett, R., et al., Remote sensing for land administration. 2020, Multidisciplinary Digital Publishing Institute.
  13. Crommelinck, S., et al., Review of Automatic Feature Extraction from High-Resolution Optical Sensor Data for UAV-Based Cadastral Mapping. Remote Sensing, 2016. 8, 689. [CrossRef]
  14. Kaufmann, J. The boundary concept: Land management opportunities for sustainable development provided by the cadastre 2014 approach. in FIG Working week. 2008.
  15. Zevenbergen, J. and R. Bennett. The visible boundary: More than just a line between coordinates. in In Proceedings of the GeoTechRwanda, Kigali, Rwanda; 8–20 November 2015; pp. 1–4. 2015.
  16. Luo, X., et al., Quantifying the Overlap between Cadastral and Visual Boundaries: A Case Study from Vanuatu. Urban Science, 2017. 1(4): p. 32. [CrossRef]
  17. Wassie, Y.A., et al., A procedure for semi-automated cadastral boundary feature extraction from high-resolution satellite imagery. Journal of Spatial Science, 2017. 63(1): p. 75-92. [CrossRef]
  18. Ali, Z. and S. Ahmed. Extracting parcel boundaries from satellite imagery for a Land Information System. in 2013 6th International conference on recent advances in space technologies (RAST). 2013. IEEE.
  19. Kohli, D., et al. Validation of a cadastral map created using satellite imagery and automated feature extraction techniques: A case of Nepal. in XXVI FIG Congress 2018: Embracing our smart world where the continents connect: enhancing the geospatial maturity of societies. 2018. International Federation of Surveyors (FIG).
  20. Chandrarathna, G., Comparative study on Cadastral Surveying using Total Station and High Resolution UAV Image (HRUAVI). 2016, Sri Lanka: Institute of surveying and mapping (Diyatalawa), Suvey Department.
  21. Yagol, P., et al. Comparative study on cadastral surveying using total station and high resolution satellite image. in Proceedings of the FIG-ISRPS workshop, 2015. 2015. Kathamandu, Nepal, 25th - 27th November, 2015.
  22. Lemmen, C., et al., A New Era in Land Administration Emerges. GIM International 2015: p. pp 22- 25.
  23. Crommelinck, S., et al., Application of deep learning for delineation of visible cadastral boundaries from remote sensing imagery. Remote sensing, 2019. 11(21): p. 2505. [CrossRef]
  24. Crommelinck, S.C., Automating image-based cadastral boundary mapping, in Faculty of Geo-Information Science and Earth Observation (ITC). 2019, University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC).
  25. Molendijk, M., J.M. Guarin, and C.J.G.i. Lemmen, Light mobile collection tools for land administration: proof of concept from Colombia. 2015. 27(1): p. 20-23.
  26. Follmann, A., Geographies of peri-urbanization in the global south. Geography Compass, 2022. 16(7): p. e12650. [CrossRef]
  27. Shaw, B.J., et al., The peri-urbanization of Europe: A systematic review of a multifaceted process. 2020. 196: p. 103733. [CrossRef]
  28. Gebremichael, D., et al., Building urban resilience: Assessing urban and peri-urban agriculture in Addis-Ababa, Ethiopia. Nairobi, Kenya, UNEP, 2014.
  29. Wubie, A.M., W.T. de Vries, and B.K. Alemie, A Socio-Spatial Analysis of Land Use Dynamics and Process of Land Intervention in the Peri-Urban Areas of Bahir Dar City. Land, 2020. 9(11): p. 445. [CrossRef]
  30. Adam, A.G., Understanding competing and conflicting interests for peri-urban land in Ethiopia’s era of urbanization. Environment and Urbanization, 2020. 32(1): p. 55-68. [CrossRef]
  31. Adam, A.G., Urban built-up property formation process in the peri-urban areas of Ethiopia, in Land Use Change and Sustainability. 2020, IntechOpen. [CrossRef]
  32. Wubie, A.M., W.T. de Vries, and B.K. Alemie, Synthesizing the dilemmas and prospects for a peri-urban land use management framework: Evidence from Ethiopia. Land Use Policy, 2021. 100: p. 105122. [CrossRef]
  33. Tesfaye, E.K., Peri-urban Land in Ethiopia: Genesis, Dynamics and Planning. 2019, Universität.
  34. Larsen, L., et al., The impact of rapid urbanization and public housing development on urban form and density in Addis Ababa, Ethiopia. Land, 2019. 8(4): p. 66. [CrossRef]
  35. Mohammed, I., A. Kosa, and N. Juhar, Economic linkage between urban development and livelihood of peri-urban farming communities in Ethiopia (policies and practices). Agricultural and Food Economics, 2020. 8(1): p. 21. [CrossRef]
  36. World Bank Group, Ethiopia Urbanization Review : Urban Institutions for a Middle-Income Ethiopia. 2015: Washington, DC. © World Bank Group.
  37. Wubneh, M.J.C., Addis Ababa, Ethiopia–Africa’s diplomatic capital. 2013. 35: p. 255-269. [CrossRef]
  38. van der Molen, P., CADASTRE 2014: a beacon in turbulent times, in FIG Congress 2014 - Engaging the Challenges – Enhancing the Relevance. 2014: Kuala Lumpur, Malaysia 16-21 June 2014.
  39. Yehun, A., et al. Evaluation of Current Urban Cadaster Practice in Ethiopia: Case of Bahir Dar, Gondar & Dessie. in FIG Working Week. 2017.
  40. Alemie, B.K., R.M. Bennett, and J. Zevenbergen, Evolving urban cadastres in Ethiopia: The impacts on urban land governance. Land Use Policy, 2015. 42: p. 695-705. [CrossRef]
  41. Zein, T., P. Hartfiel, and Z.A. Berisso. Addis Ababa: the road map to progress through securing property rights with real property registration system. in Proceedings of the World Bank Conference on Land and Poverty, Washington, DC, USA. 2012.
  42. Deininger, K., et al., Rural land certification in Ethiopia: Process, initial impact, and implications for other African countries. World development, 2008. 36(10): p. 1786-1812. [CrossRef]
  43. Chekole, S.D., W.T. de Vries, and G.B. Shibeshi, An Evaluation Framework for Urban Cadastral System Policy in Ethiopia. Land, 2020. 9(2): p. 60. [CrossRef]
  44. Tadesse, D., Reflections on the situation of urban cadaster in Ethiopia, in The Municipal Development Partnership (Eastern and Southern Africa) Africa Local Government Action Forum (ALGAF) 2006.
  45. Tigistu, G. Experience and future direction in Ethiopian rural land administration. in Proceedings of the Annual World Bank Conference on Land and Property, Washington, DC, USA. 2011.
  46. Metaferia, M.T., et al., The peri-urban cadastre of Addis Ababa: Status, challenges, and fit-for-purpose prospects. Land Use Policy, 2023. 125: p. 106477. [CrossRef]
  47. FAO and IFAD, GeoTech4Tenure – Technical guide on combining geospatial technology and participatory methods for securing tenure rights. 2022: Rome, FAO.
  48. Mather, P. and B. Tso, Classification methods for remotely sensed data. 2nd edition ed. 2009: CRC press.
  49. Thakur, V., et al., Cadastral Boundary Extraction and Image Classification Using OBIA and Machine Learning for National Land Records Modernization Programme in India. J Remote Sens GIS 8: J Remote Sens GIS, an open Access., 2019. Volume 8 (2 • 1000264). [CrossRef]
  50. Musleh, A.A. and H.S. Jaber, Comparative Analysis of Feature Extraction and Pixel-based Classification of High-Resolution Satellite Images Using Geospatial Techniques. E3S Web of Conferences, 2021. 318: p. 04007. [CrossRef]
  51. Fetai, B., D. Grigillo, and A.J.I.I.J.o.G.-I. Lisec, Revising Cadastral Data on Land Boundaries Using Deep Learning in Image-Based Mapping. 2022. 11(5): p. 298. [CrossRef]
  52. Babawuro, U. and Z. Beiji, Satellite Imagery Cadastral Features Extractions using Image Processing Algorithms : A Viable Option for Cadastral Science. International Journal of Computer Science Issues, 2012. 9(4): p. 30-38.
  53. Turker, M. and E.H. Kok, Field-based sub-boundary extraction from remote sensing imagery using perceptual grouping. ISPRS journal of photogrammetry and remote sensing, 2013. 79, 106-121. [CrossRef]
  54. Koeva, M., et al., Geospatial tool and geocloud platform innovations: A fit-for-purpose land administration assessment. Land, 2021. 10(6): p. 557. [CrossRef]
  55. Xia, X., C. Persello, and M.J.R.s. Koeva, Deep fully convolutional networks for cadastral boundary detection from UAV images. 2019. 11(14): p. 1725. [CrossRef]
  56. Luo, X., et al., Investigating semi-automated cadastral boundaries extraction from airborne laser scanned data. 2017. 6(3): p. 60. [CrossRef]
  57. Crommelinck, S., et al., Towards Automated Cadastral Boundary Delineation from UAV data. arXiv preprint arXiv:1709.01813., 2017.
  58. Crommelinck, S., et al., INTERACTIVE CADASTRAL BOUNDARY DELINEATION FROM UAV DATA. ISPRS Annals of Photogrammetry, Remote Sensing & Spatial Information Sciences, 2018. 4(2). [CrossRef]
  59. Weldeghebrael, E.H. (2021). ADDIS ABABA: CITY SCOPING STUDY. Available online https://www.african-cities.org/wp-content/uploads/2021/12/ACRC_Addis-Ababa_City-Scoping-Study.pdf Accessed on: November 22, 2022.
  60. Nasser, N., The Socio-Economic Impact of Addis Ababa City Expansion on Farmers: The Case of Akaki Kality Sub City in Public Administration and Development Management. 2020, Addis Ababa University: Addis Ababa. p. 108.
  61. Koroso, N.H., J.A. Zevenbergen, and M.J.L.U.P. Lengoiboni, Urban land use efficiency in Ethiopia: An assessment of urban land use sustainability in Addis Ababa. 2020. 99: p. 105081. [CrossRef]
  62. Terfa, B.K., et al., Urban expansion in Ethiopia from 1987 to 2017: Characteristics, spatial patterns, and driving forces. Sustainability, 2019. 11(10): p. 2973. [CrossRef]
  63. Mohamed, A., H. Worku, and T. Lika, Urban and regional planning approaches for sustainable governance: The case of Addis Ababa and the surrounding area changing landscape. City and Environment Interactions, 2020. 8: p. 100050. [CrossRef]
  64. Mohamed, A. and H.J.J.o.U.M. Worku, Quantification of the land use/land cover dynamics and the degree of urban growth goodness for sustainable urban land use planning in Addis Ababa and the surrounding Oromia special zone. 2019. 8(1): p. 145-158. [CrossRef]
  65. Tufa, D.E. and T.L.J.L.U.P. Megento, The effects of farmland conversion on livelihood assets in peri-urban areas of Addis Ababa Metropolitan city, the case of Akaki Kaliti sub-city, Central Ethiopia. 2022. 119: p. 106197. [CrossRef]
  66. GitHub. GitHub Delineation-Tool wiki 2019 Accessed on: cited 2022 November 15, 2022; Available from: https://github.com/its4land/delineation-tool/wiki.
  67. Michel, J. and M. Grizonnet, State of the Orfeo Toolbox IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy, 2015: p. 1336-1339.
  68. Orfeo ToolBox. Open Source processing of remote sensing images. 2022 Accessed on: January 9, 2023; Available from: https://www.orfeo-toolbox.org/.
  69. Oo, T.K., et al., Comparing Four Machine Learning Algorithms for Land Cover Classification in Gold Mining: A Case Study of Kyaukpahto Gold Mine, Northern Myanmar. 2022. 14(17): p. 10754. [CrossRef]
  70. Uddin, S., et al., Comparing different supervised machine learning algorithms for disease prediction. 2019. 19(1): p. 1-16. [CrossRef]
  71. Its4land. What is its4land all about? 2016 Accessed on: cited 2022 September 29, 2022; Available from: https://its4land.com/.
  72. Goodchild, M.F. and G.J.J.I.j.o.g.i.s. Hunter, A simple positional accuracy measure for linear features. 1997. 11(3): p. 299-306. [CrossRef]
  73. Heipke, C., et al., Evaluation of automatic road extraction. 1997. 32(3 SECT 4W2): p. 151-160.
  74. Zein, T., Fit-For-Purpose Land Administration: An Implementation Model for Cadastre and Land Administration Systems, in 2016 World Bank Conference on Land and Poverty. 2016, The World Bank Washington DC.
  75. FDRE, Regulation to Provide for Urban Cadastral Surveying Council of Ministers Regulation. 2014, Addis Ababa, Ethiopia: Federal Negarit Gazeta p. 7669.
  76. IAAO, Standard on Digital Cadastral Maps and Parcel Identifiers. 2015, International Association of Assessing Officers Kansas City, MO, USA.
  77. Crommelinck, S., et al., Robust object extraction from remote sensing data. arXiv preprint arXiv:1904.12586., 2019.
  78. Salehi, B., et al., Well site extraction from Landsat-5 TM imagery using an object-and pixel-based image analysis method. International Journal of Remote Sensing, 2014. 35(23): p. 7941-7958. [CrossRef]
  79. Singh, K.K. and A. Singh, A study of image segmentation algorithms for different types of images. International Journal of Computer Science Issues, 2010. 7(5): p. 414.
  80. Garrido, A., N. Pérez de la blanca, and M. Garcia-Silvente, Boundary simplification using a multiscale dominant-point detection algorithm. Pattern Recognition, 1998. 31(6): p. 791-804. [CrossRef]
  81. Muller, A., O. Gericke, and J.J.J.o.t.S.a.i.o.c.e. Pietersen, Methodological approach for the compilation of a water distribution network model using QGIS and EPANET. 2020. 62(4): p. 32-43. [CrossRef]
  82. Sathya, P., L.J.I.J.o.M.L. Malathi, and Computing, Classification and segmentation in satellite imagery using back propagation algorithm of ann and k-means algorithm. 2011. 1(4): p. 422. [CrossRef]
  83. Sapkota, R.K. and G.P.J.J.o.G. Bhatta, Nepal, Technical Aspects of Digitization of Cadastral Maps. 2014. 13: p. 42-50.
  84. Ajayi, O.G. and E. Oruma, On the applicability of integrated UAV photogrammetry and automatic feature extraction for cadastral mapping. Advances in Geodesy Geoinformation, 2022: p. e19-e19. [CrossRef]
Preprints 77906 g001
Figure 1. Object based AFE workflows [1].
Figure 1. Object based AFE workflows [1].
Preprints 77906 g001
Preprints 77906 g002
Figure 2. Study area location map.
Figure 2. Study area location map.
Preprints 77906 g002
Preprints 77906 g003
Figure 3. Examples of the interactive delineation functionalities: (a) connect lines surrounding a click, or (b) a selection of lines. (c) Close endpoints of selected lines to a polygon. (d) Connect lines along least-cost-path [66].
Figure 3. Examples of the interactive delineation functionalities: (a) connect lines surrounding a click, or (b) a selection of lines. (c) Close endpoints of selected lines to a polygon. (d) Connect lines along least-cost-path [66].
Preprints 77906 g003
Preprints 77906 g004
Figure 4. Examples of correctly extracted (a), incorrectly retrieved (b), and missing (c) boundary lines.
Figure 4. Examples of correctly extracted (a), incorrectly retrieved (b), and missing (c) boundary lines.
Preprints 77906 g004
Preprints 77906 g005
Figure 5. AFE approach for cadastral mapping using open-source software tools.
Figure 5. AFE approach for cadastral mapping using open-source software tools.
Preprints 77906 g005
Preprints 77906 g006
Figure 6. Figure 6 AFE results: a) Automatically extracted outlines (yellow) and the reference cadastre (Green) buffered by 0.4m (b) Extracted boundary outlines that fall in 0.4m buffer width of the reference cadastre.
Figure 6. Figure 6 AFE results: a) Automatically extracted outlines (yellow) and the reference cadastre (Green) buffered by 0.4m (b) Extracted boundary outlines that fall in 0.4m buffer width of the reference cadastre.
Preprints 77906 g006
Preprints 77906 g007
Figure 7. AFE results: Condominium buildings (a), Ditches and Cobblestone Roads (b), Non-boundary lines (c).
Figure 7. AFE results: Condominium buildings (a), Ditches and Cobblestone Roads (b), Non-boundary lines (c).
Preprints 77906 g007
Preprints 77906 g008
Figure 8. Distribution of the training dataset over the study area.
Figure 8. Distribution of the training dataset over the study area.
Preprints 77906 g008
Preprints 77906 g009
Figure 9. RF Classification result.
Figure 9. RF Classification result.
Preprints 77906 g009
Preprints 77906 g010
Figure 10. Interactively delineated building and parcel boundaries.
Figure 10. Interactively delineated building and parcel boundaries.
Preprints 77906 g010
Preprints 77906 g011
Figure 11. Completeness, Correctness, and Quality of the interactively delineated boundaries.
Figure 11. Completeness, Correctness, and Quality of the interactively delineated boundaries.
Preprints 77906 g011
Table 1. Description of the data for the study.
Table 1. Description of the data for the study.
S/N Data Source Description Purpose
1 Aerial photograph of the study area (Orthophoto) Space Science and Geospatial Institute The orthophoto is produced by SSGI from an aerial photograph acquired in 2016 To extract parcel boundaries automatically
2 Cadastral parcel map of the study area (Shape file) Akaki-Kality
sub-city land administration office		 The shape file is extracted from an aerial photograph acquired in 2010 To validate
automatically
extracted parcel boundaries
Table 2. Description of the 'BoundaryDelineation' interactive functionalities [23,66].
Table 2. Description of the 'BoundaryDelineation' interactive functionalities [23,66].
Data Description
Aerial photograph of the study area (Orthophoto) Connect lines surrounding a click or selection of lines
Cadastral parcel map of the study area (Shape file) Connect endpoints of selected lines to a polygon
Connect along optimal path Connect vertices along least-cost-path based on a selected attribute, e.g. Boundary likelihood
Connect manual clicks Manual delineation with the option to snap to input lines and vertices
Update edits Update input lines based on manual edits
Polygonize results Convert created boundary lines to polygons
Table 3. Error matrix.
Table 3. Error matrix.
Expected
Boundary lines (1) nonBoundary lines (0)
Extracted Boundary lines
(1) 		  True Positive (TP)
/Extracted boundaries that coincide with the reference boundaries, Figure 4a /		   False Positive (FP)
/Extracted boundaries that do not concide with the reference boundaries, Figure 4b /
nonBoundary lines
(0) 		  False Negative (FN)
/Reference boundaries that are not extracted, Figure 4c /		   True Negative (TN)
/nonBoundaries identified as nonBoundaries/
Table 4. Validation of the interactively delineated boundaries with different buffer sizes.
Table 4. Validation of the interactively delineated boundaries with different buffer sizes.
0.4m by 0.6m Buffer size 0.5m by 1m Buffer size 1m by 1.5m Buffer size
Boundary (1) Non-Boundary (0) Boundary (1) Non-Boundary (0) Boundary (1) Non- Boundary (0)
Boundary (1) 25788 23631 28245 11151 15322 4124
Non-Boundary (0) 55955 1625056 58328 1009960 16810 241980
Completeness 32% 33% 48%
Correctness 52% 72% 79%
Quality 24% 29% 42%
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.
Prerpints.org logo

Preprints.org is a free preprint server supported by MDPI in Basel, Switzerland.

facebook logotwitter logolinkedin logo
MDPI Initiatives
Important Links
Subscribe

Disclaimer

Terms of Use

Privacy Policy

© 2024 MDPI (Basel, Switzerland) unless otherwise stated