Detecting Cadastral Boundary from Satellite Images Using U-Net model
This addresses land administration needs by automating boundary detection, but it is incremental as it applies an existing deep learning method to a specific domain.
The paper tackled the problem of detecting cadastral boundaries from satellite images using a U-Net model with a ResNet34 backbone, achieving precision, recall, and F-score of 88%, 75%, and 81%, respectively, on farmlands in Iran.
Finding the cadastral boundaries of farmlands is a crucial concern for land administration. Therefore, using deep learning methods to expedite and simplify the extraction of cadastral boundaries from satellite and unmanned aerial vehicle (UAV) images is critical. In this paper, we employ transfer learning to train a U-Net model with a ResNet34 backbone to detect cadastral boundaries through three-class semantic segmentation: "boundary", "field", and "background". We evaluate the performance on two satellite images from farmlands in Iran using "precision", "recall", and "F-score", achieving high values of 88%, 75%, and 81%, respectively, which indicate promising results.