Bisheng Yang， Wenxue Xu， Zhen Dong

Abstract：Automatic extracting building outlines from airborne laser scanning (ALS) point clouds has been an active topic in the field of photogrammetry, remote sensing, and computer vision. In this paper, a marked point process method was implemented to extract building outlines from ALS point clouds. First, the Gibbs energy model of building objects is defined to describe building points. Second, the defined Gibbs energy model is sampled within the framework of Reverse Jump Markov Chain Monte Carlo (RJMCMC) and optimized to find an optimal energy configuration by simulated annealing. Finally, the detected building objects are refined to eliminate the false detection, and the outlines of buildings are derived from the detected building objects by morphological operators. Three data sets were tested to verify the validity of the proposed method, showing the proposed method extracts building objects from the data sets with an average completeness of 84.2% and correctness of 99.1%.

Keywords：building outlines, marked point processes, airborne laser scanning

Download