Automatic 3D reconstruction of urban area from low resolution aerial LiDAR data

摘要

3D urban area model has a variety aspect of application. The most exist methods follows a three step pipeline. In this paper, we follow the pipeline to reconstruct the 3D model of urban area. An improved covariance analysis method is proposed to remove the irrelevant part of LiDAR. This preprocessing method is more robust than the original method for the low resolution LiDAR data. Also, a classification method based on the Markov Random Field on the connected component is proposed in this paper. The experiment shows our method can reconstruct 3D model of urban area from low resolution LiDAR data.