Fast Random Sample Matching of 3d Fragments

摘要: This paper proposes an efficient pairwise surface matching approach for the automatic assembly of 3d fragments or industrial components. The method rapidly scans through space all possible solutions by a special kind random sample consensus (RANSAC) scheme. By using normals and optionally simple features like curvatures, we can highly constrain initial 6 degrees freedom search relative transformations between two fragments. suggested is robust, very time memory efficient, easy to implement applicable kinds data where are available (e.g. range images, polygonal object representations, point clouds with neighbor connectivity, etc.).