Algorithm of land surface points extraction from airborne laser scanning data

Abstract

The authors propose a new algorithm for classifying point clouds. It enables them to be separated according to the surface to which they belong. We present a brief analysis of existing methods for solving the problem considered, classifying them and indicating their advantages and disadvantages. The offered algorithm is based on iterative searching for points with a significant difference in height from the digital elevation model that approximates their cloud. In the course of processing, the formulated technique achieves a consistent adjustment of the approximating surface to the actual relief, which helps natural object detection on the ground. The results are demonstrated compared with the classification of point clouds by the CSF algorithm implemented in the widely used corresponding software. The juxtaposition of the obtained results shows that the proposed algorithm allows achieving a better classification quality in areas with irregular terrain, preserving also a greater number of points under the forested areas of the surface