Pixel-line based clustering for the 3D point cloud generated by Kinect depth map

Abstract

A novel pixel-line based clustering algorithm for Kinect depth image data is proposed in this paper. The algorithm first clusters the three-dimensional points belonging to the same pixel row. Then the single row clusters coming from adjacent rows are compared and matched to fulfill the three-dimensional cluster growth. Experiments are carried out with both office scene and greenhouse scene. The clustering results show that the algorithm is good at highlighting small objects but is sensitive to uneven surfaces.