Intensity Histogram Based Segmentation of 3D Point Cloud Using Growing Neural Gas

This paper proposes a 3D point cloud segmentation method using a reflection intensity of Laser Range Finder LRF. In this paper, we use LRF and tilt unit for acquiring a 3D point cloud. First of all, we apply Growing Neural Gas GNG to the point cloud for learning a topological structure of the point cloud. Next, we proposed a segmentation method based on an intensity histogram that is composed of the nearest data of each node. Finally, we show experimental results of the proposed method and discuss the effectiveness of the proposed method.