Point-cloud registration using 3D shape contexts

The problem of aligning scans from a range sensor is central to 3D mapping for robots. In previous work we demonstrated a light-weight descriptor-based registration method that is suitable for creating maps from range images produced by devices such as the XBOX Kinect. For computational reasons, simple descriptors were used based only on the distribution of distances between points. In this paper, we present an alternative approach using 3D Shape Contexts that also retains angular information thereby producing descriptors that are more unique. Although this increases the computational load, intrinsic properties of the descriptor facilitate keypoint selection, leading to a more robust registration framework. This also provides greater flexibility when applying the method to sparse point clouds such as those produced by laser range scanners. Results are shown for registering new data acquired from an underground mine environment.