Point cloud registration is an essential step in the process of 3D reconstruction.In this paper,a fast registration algorithm of rock mass point cloud is proposed based on the improved iterative closest point (ICP)alg...Point cloud registration is an essential step in the process of 3D reconstruction.In this paper,a fast registration algorithm of rock mass point cloud is proposed based on the improved iterative closest point (ICP)algorithm.In our proposed algorithm,the point cloud data of single station scanner is transformed into digital images by spherical polar coordinates,then image features are extracted and edge points are removed,the features used in this algorithm is scale-invariant feature transform (SIFT).By analyzing the corresponding relationship between digital images and 3D points,the 3D feature points are extracted,from which we can search for the two-way correspondence as candidates. After the false matches are eliminated by the exhaustive search method based on random sampling,the transformation is computed via the Levenberg-Marquardt-Iterative Closest Point (LM-ICP)algorithm.Experiments on real data of rock mass show that the proposed algorithm has the similar accuracy and better registration efficiency compared with the ICP algorithm and other algorithms.展开更多
基金the National Natural Science Foundation of China (Grant No.61471338)Youth Innovation Promotion Association CAS (2015361)+2 种基金Key Research Program of Frontier Sciences,CAS (QYZDY-SSW-SYS004)Beijing Nova Program (z171100001117048)President Fund of UCAS.
文摘Point cloud registration is an essential step in the process of 3D reconstruction.In this paper,a fast registration algorithm of rock mass point cloud is proposed based on the improved iterative closest point (ICP)algorithm.In our proposed algorithm,the point cloud data of single station scanner is transformed into digital images by spherical polar coordinates,then image features are extracted and edge points are removed,the features used in this algorithm is scale-invariant feature transform (SIFT).By analyzing the corresponding relationship between digital images and 3D points,the 3D feature points are extracted,from which we can search for the two-way correspondence as candidates. After the false matches are eliminated by the exhaustive search method based on random sampling,the transformation is computed via the Levenberg-Marquardt-Iterative Closest Point (LM-ICP)algorithm.Experiments on real data of rock mass show that the proposed algorithm has the similar accuracy and better registration efficiency compared with the ICP algorithm and other algorithms.
