A novel approach based on cluster-group for classification of 3D residential scene

To understand scenes and help autonomous robots and cars, researchers' attention is directed through the problem of classifying 3D point cloud. In this paper, we present a novel approach to semantically segment 3D point cloud of residential scenes captured by a lidar sensor. Our approach is based on a dual-scale analysis: a small-scale clustering and a large-scale grouping. Features used to train our AdaBoost classifier are then extracted from clusters and groups. We evaluate our method with a challenging lidar data set. The result shows our approach can classify scene objects accurately.