UAV measurements and AI-driven algorithms fusion for real estate good governance principles support

Abstract

The paper introduces an original method for effective spatial data processing, particularly important for land administration and real estate governance. This approach integrates Unmanned Aerial Vehicle (UAV) data acquisition and processing with Artificial Intelligence (AI) and Geometric Transformation algorithms. The results reveal that: (1) while the separate applications of YOLO and Hough Transform algorithms achieve building detection rates up to 77% and 83%, respectively, (2) a novel methodology is proposed to combine spatial data and assess their quality of the detected buildings by comparing the generated building polygons with existing cadastral maps. The evaluation uses a polygon-based comparison approach, which computes metrics such as Precision, Recall, F1-Score, and Accuracy based on the spatial relationships between predicted and reference building contours, (3) the weighted model showed about 7 % improvement in accuracy compared to cadastral data. This innovative approach substantially improves spatial data processing, aiding in implementing principles for real estate good governance and offering a valuable asset for various land administration applications.

Keywords

• Remote Sensing
• UAV
• YOLO
• Hough Transform
• Validation
• Cadastre