LSG-CPD: Coherent Point Drift with Local Surface Geometry for Point Cloud Registration

Probabilistic point cloud registration methods are becoming more popular because of their robustness. However, unlike point-to-plane variants of iterative closest point (ICP) which incorporate local surface geometric information such as surface normals, most probabilistic methods (e.g., coherent point drift (CPD)) ignore such information and build Gaussian mixture models (GMMs) with isotropic Gaussian covariances. This results in sphere-like GMM components which only penalize the point-to-point distance between the two point clouds. In this paper, we propose a novel method called CPD with Local Surface Geometry (LSG-CPD) for rigid point cloud registration. Our method adaptively adds different levels of point-to-plane penalization on top of the point-to-point penalization based on the flatness of the local surface. This results in GMM components with anisotropic covariances. We formulate point cloud registration as a maximum likelihood estimation (MLE) problem and solve it with the Expectation-Maximization (EM) algorithm. In the E step, we demonstrate that the computation can be recast into simple matrix manipulations and efficiently computed on a GPU. In the M step, we perform an unconstrained optimization on a matrix Lie group to efficiently update the rigid transformation of the registration. The proposed method outperforms state-of-the-art algorithms in terms of accuracy and robustness on various datasets captured with range scanners, RGBD cameras, and LiDARs. Also, it is significantly faster than modern implementations of CPD. The source code is available at https://github.com/ ChirikjianLab/LSG-CPD.git.

[1]  Scott P. Cryan,et al.  A Survey of LIDAR Technology and Its Use in Spacecraft Relative Navigation , 2013 .

[2]  Alejandro F. Frangi,et al.  Generalised Coherent Point Drift for Group-Wise Registration of Multi-dimensional Point Sets , 2017, MICCAI.

[3]  Markus H. Gross,et al.  Efficient simplification of point-sampled surfaces , 2002, IEEE Visualization, 2002. VIS 2002..

[4]  Aleksandr V. Segal,et al.  Generalized-ICP , 2009, Robotics: Science and Systems.

[5]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Emanuele Menegatti,et al.  Robust Intrinsic and Extrinsic Calibration of RGB-D Cameras , 2017, IEEE Transactions on Robotics.

[7]  Wei Gao,et al.  FilterReg: Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist Parameterization , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Chen Li,et al.  Improved Techniques for Multi-view Registration with Motion Averaging , 2014, 2014 2nd International Conference on 3D Vision.

[9]  Radu Horaud,et al.  Rigid and Articulated Point Registration with Expectation Conditional Maximization , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[11]  Vladlen Koltun,et al.  Dense scene reconstruction with points of interest , 2013, ACM Trans. Graph..

[12]  Stefan Leutenegger,et al.  ElasticFusion: Dense SLAM Without A Pose Graph , 2015, Robotics: Science and Systems.

[13]  Baba C. Vemuri,et al.  Robust Point Set Registration Using Gaussian Mixture Models , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Zhe Min,et al.  Robust Non-Rigid Point Set Registration Algorithm Considering Anisotropic Uncertainties Based on Coherent Point Drift , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[15]  Markus Vincze,et al.  An Empirical Evaluation of Ten Depth Cameras: Bias, Precision, Lateral Noise, Different Lighting Conditions and Materials, and Multiple Sensor Setups in Indoor Environments , 2019, IEEE Robotics & Automation Magazine.

[16]  Achim J. Lilienthal,et al.  Fast and accurate scan registration through minimization of the distance between compact 3D NDT representations , 2012, Int. J. Robotics Res..

[17]  Giorgio Grisetti,et al.  NICP: Dense normal based point cloud registration , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[18]  Marc Levoy,et al.  A volumetric method for building complex models from range images , 1996, SIGGRAPH.

[19]  Javier González,et al.  Convex Global 3D Registration with Lagrangian Duality , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  New York Dover,et al.  ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM , 1983 .

[21]  James S. Duncan,et al.  A Robust Point Matching Algorithm for Autoradiograph Alignment , 1996, VBC.

[22]  King-Sun Fu,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence Publication Information , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  G. Chirikjian Stochastic Models, Information Theory, and Lie Groups, Volume 2 , 2012 .

[24]  Jan Kautz,et al.  HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration , 2018, ECCV.

[25]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

[27]  Max Q.-H. Meng,et al.  Robust Generalized Point Cloud Registration With Orientational Data Based on Expectation Maximization , 2020, IEEE Transactions on Automation Science and Engineering.

[28]  Russell H. Taylor,et al.  Iterative Most Likely Oriented Point Registration , 2014, MICCAI.

[29]  Sethu Vijayakumar,et al.  A Probabilistic Approach to Robust Shape Matching , 2006, 2006 International Conference on Image Processing.

[30]  Dieter Fox,et al.  DART: Dense Articulated Real-Time Tracking , 2014, Robotics: Science and Systems.

[31]  Lars Petersson,et al.  An Adaptive Data Representation for Robust Point-Set Registration and Merging , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[32]  Tony DeRose,et al.  Surface reconstruction from unorganized points , 1992, SIGGRAPH.

[33]  Heng Yang,et al.  TEASER: Fast and Certifiable Point Cloud Registration , 2021, IEEE Transactions on Robotics.

[34]  Edwin R. Hancock,et al.  A unified framework for alignment and correspondence , 2003, Comput. Vis. Image Underst..

[35]  HoraudRadu,et al.  An overview of depth cameras and range scanners based on time-of-flight technologies , 2016 .

[36]  Xavier Pennec,et al.  Multi-scale EM-ICP: A Fast and Robust Approach for Surface Registration , 2002, ECCV.

[37]  Andriy Myronenko,et al.  Point Set Registration: Coherent Point Drift , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Nathan Michael,et al.  On-Manifold GMM Registration , 2018, IEEE Robotics and Automation Letters.

[39]  Joachim Hertzberg,et al.  6D SLAM—3D mapping outdoor environments , 2007, J. Field Robotics.

[40]  G. Chirikjian Stochastic models, information theory, and lie groups , 2012 .

[41]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .

[42]  Jihua Zhu,et al.  Registration of Multi-View Point Sets Under the Perspective of Expectation-Maximization , 2020, IEEE Transactions on Image Processing.

[43]  Osamu Hirose,et al.  A Bayesian Formulation of Coherent Point Drift , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[45]  Pavel Krsek,et al.  The Trimmed Iterative Closest Point algorithm , 2002, Object recognition supported by user interaction for service robots.