Revising Cadastral Data on Land Boundaries Using Deep Learning in Image-Based Mapping

Abstract

One of the main concerns of land administration in developed countries is to keep the cadastral system up to date. The goal of this research was to develop an approach to detect visible land boundaries and revise existing cadastral data using deep learning. The convolutional neural network (CNN), based on a modified architecture, was trained using the Berkeley segmentation data set 500 (BSDS500) available online. This dataset is known for edge and boundary detection. The model was tested in two rural areas in Slovenia. The results were evaluated using recall, precision, and the F1 score—as a more appropriate method for unbalanced classes. In terms of detection quality, balanced recall and precision resulted in F1 scores of 0.60 and 0.54 for Ponova vas and Odranci, respectively. With lower recall (completeness), the model was able to predict the boundaries with a precision (correctness) of 0.71 and 0.61. When the cadastral data were revised, the low values were interpreted to mean that the lower the recall, the greater the need to update the existing cadastral data. In the case of Ponova vas, the recall value was less than 0.1, which means that the boundaries did not overlap. In Odranci, 21% of the predicted and cadastral boundaries overlapped. Since the direction of the lines was not a problem, the low recall value (0.21) was mainly due to overly fragmented plots. Overall, the automatic methods are faster (once the model is trained) but less accurate than the manual methods. For a rapid revision of existing cadastral boundaries, an automatic approach is certainly desirable for many national mapping and cadastral agencies, especially in developed countries.

Creating a dataset of historic roads in Sydney from scanned maps

“…Furthermore, there are a few state-of-the-art studies using machine learning methods for map digitization. For example, text detection in historic maps 38 , segmentation and digitization of historic maps 39 , 40 , feature recognition 41 , 42 , road extraction 43 , detecting road types 44 , and cadastral boundary extraction 45 , 46 using neural network, deep neural network, and convolutional neural network models.…”

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

“…It employs the spectral information in each pixel (pixel-based) or the geometry and spatial relationships of a group of pixels (object-based) to automatically extract parcel boundaries [12]. Studies prove that the object-based feature extraction provides 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 [5,12,[43][44][45]. Crommelinck et al [12] 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).…”

“…Validation of the interactively delineated cadastral boundaries ensures the reliability of the result for further cadastral applications. Furthermore, combining the automatic approach with manual interactive delineation is supposed to reduce time and resource consumption while maintaining the desired accuracy [45].…”

Smart Urban Cadastral Map Enrichment—A Machine Learning Method

“…Artificial intelligence methods, including machine learning and deep learning, have recently been used very much for map enrichment; updating; object, boundary and change detection; and spatial data fusion [14,15,[18][19][20]. In [18], a combination of data-level fusion and feature-level fusion was employed for natural object detection by multi-source geospatial data and deep learning.…”

“…In [18], a combination of data-level fusion and feature-level fusion was employed for natural object detection by multi-source geospatial data and deep learning. Deep learning methods have been implemented to align and update cadaster maps with satellite images [19], detect visible land boundaries automatically with aerial images and revise existing cadastral maps [20]. In [21], a comparison between manual approaches and machine learning algorithms for extracting visible cadaster boundaries from satellite images in rural and urban areas was made, and the authors showed that machine learning algorithms have lower costs, require less time and achieve a higher accuracy than manual approaches.…”