Automated road extraction from LiDAR data based on intensity and aerial photo

Abstract

A clustering method based on intensity data is used to extract road from LiDAR data in this paper. And the result is refined by using the spectrum information of aerial images. An experiment is performed with a group of LiDAR data in BeiJing. The results presented in this paper have shown that clustering method based on intensity could extract road in some extent, but many error points exist at the same time. When fusing the spectrum information of aerial images, the experiment result is improved obviously. Large amount of error points is removed, while the point cloud of road keep down.