Point cloud segmentation with LIDAR reflection intensity behavior

Abstract

Light Detection and Ranging (LIDAR) scans are increasingly being used for 3D map construction and reverse engineering. The utility and benefit of the processed data maybe enhanced if the objects and geometry of the area scanned can be segmented and labeled. In this paper, we present techniques to model the intensity of the laser reflection return from a point during LIDAR scanning to determine diffuse and specular reflection properties of the scanned surface. Using several illumination models, the reflection properties of the surface are characterized by Lambertian diffuse reflection model and Blinn-Phong, Gaussian and Beckmann specular models. Experimental set up with eight different surfaces with varied textures and glossiness enabled measurement of algorithm performance. Examples of point cloud segmentation with the presented approach are presented.