Can generalised relative pose estimation solve sparse 3D registration?

Popular 3D scan registration projects, such as Stanford digital Michelangelo or KinectFusion, exploit the high-resolution sensor data for scan alignment. It is particularly challenging to solve the registration of sparse 3D scans in the absence of RGB components. In this case, we can not establish point correspondences since the same 3D point cannot be captured in two successive scans. In contrast to correspondence based methods, we take a different viewpoint and formulate the sparse 3D registration problem based on the constraints from the intersection of line segments from adjacent scans. We obtain the line segments by modeling every horizontal and vertical scan-line as piece-wise linear segments. We propose a new alternating projection algorithm for solving the scan alignment problem using line intersection constraints. We develop two new minimal solvers for scan alignment in the presence of plane correspondences: 1) 3 line intersections and 1 plane correspondence, and 2) 1 line intersection and 2 plane correspondences. We outperform other competing methods on Kinect and LiDAR datasets.

[1]  Marc Pollefeys,et al.  A 4-point algorithm for relative pose estimation of a calibrated camera with a known relative rotation angle , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Kostas Daniilidis,et al.  Fully Automatic Registration of 3D Point Clouds , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  Dieter Schmalstieg,et al.  A Minimal Solution to the Generalized Pose-and-Scale Problem , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Jiaolong Yang,et al.  Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Xiaowei Zhou,et al.  Multi-image Matching via Fast Alternating Minimization , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Peter F. Sturm,et al.  Multi-view geometry for general camera models , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Ji Zhang,et al.  LOAM: Lidar Odometry and Mapping in Real-time , 2014, Robotics: Science and Systems.

[8]  Robert Pless,et al.  Using many cameras as one , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[9]  Wolfram Burgard,et al.  An evaluation of the RGB-D SLAM system , 2012, 2012 IEEE International Conference on Robotics and Automation.

[10]  J. D. Wegner,et al.  Globally consistent registration of terrestrial laser scans via graph optimization , 2015 .

[11]  Hongdong Li,et al.  Five-Point Motion Estimation Made Easy , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[12]  Jean-Emmanuel Deschaud,et al.  IMLS-SLAM: Scan-to-Model Matching Based on 3D Data , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Hongdong Li,et al.  The 3D-3D Registration Problem Revisited , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[14]  Roland Siegwart,et al.  A Review of Point Cloud Registration Algorithms for Mobile Robotics , 2015, Found. Trends Robotics.

[15]  Hongdong Li A Simple Solution to the Six-Point Two-View Focal-Length Problem , 2006, ECCV.

[16]  Hongdong Li,et al.  A linear approach to motion estimation using generalized camera models , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Karl Johan Åström,et al.  Solutions to Minimal Generalized Relative Pose Problems , 2005 .

[18]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[19]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[20]  Laurent Itti,et al.  Efficient Velodyne SLAM with point and plane features , 2018, Autonomous Robots.

[21]  Pascal Vasseur,et al.  A Homography Formulation to the 3pt Plus a Common Direction Relative Pose Problem , 2014, ACCV.

[22]  Roland Siegwart,et al.  Finding the Exact Rotation between Two Images Independently of the Translation , 2012, ECCV.

[23]  Uttaran Bhattacharya,et al.  Fast Multiview 3D Scan Registration Using Planar Structures , 2017, 2017 International Conference on 3D Vision (3DV).

[24]  Jonathan P. How,et al.  Efficient Global Point Cloud Alignment Using Bayesian Nonparametric Mixtures , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Henrik I. Christensen,et al.  RGB-D edge detection and edge-based registration , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[26]  H. Pottmann,et al.  Computational Line Geometry , 2001 .

[27]  Jiaolong Yang,et al.  Go-ICP: Solving 3D Registration Efficiently and Globally Optimally , 2013, 2013 IEEE International Conference on Computer Vision.

[28]  Patrick L. Combettes,et al.  On the effectiveness of projection methods for convex feasibility problems with linear inequality constraints , 2009, Computational Optimization and Applications.

[29]  Wolfram Burgard,et al.  3-D Mapping With an RGB-D Camera , 2014, IEEE Transactions on Robotics.

[30]  Stergios I. Roumeliotis,et al.  An Efficient Algebraic Solution to the Perspective-Three-Point Problem , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Ji Zhang,et al.  Low-drift and real-time lidar odometry and mapping , 2017, Auton. Robots.

[32]  Wolfram Burgard,et al.  A benchmark for the evaluation of RGB-D SLAM systems , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[33]  Jörg Stückler,et al.  CPA-SLAM: Consistent plane-model alignment for direct RGB-D SLAM , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[34]  Yan Lu,et al.  Robust RGB-D Odometry Using Point and Line Features , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[35]  Lars Petersson,et al.  GOGMA: Globally-Optimal Gaussian Mixture Alignment , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Jun Wang,et al.  Multi-View Point Registration via Alternating Optimization , 2015, AAAI.

[37]  K. S. Arun,et al.  Least-Squares Fitting of Two 3-D Point Sets , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Vladlen Koltun,et al.  Learning Compact Geometric Features , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[40]  Chen Liu,et al.  FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans , 2018, ECCV.

[41]  Vincent Lepetit,et al.  An Efficient Minimal Solution for Multi-camera Motion , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[42]  Ping Wang,et al.  An efficient solution to the perspective-three-point pose problem , 2018, Comput. Vis. Image Underst..

[43]  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.

[44]  David J. Hawkes,et al.  A Stochastic Iterative Closest Point Algorithm (stochastICP) , 2001, MICCAI.

[45]  Chen Feng,et al.  DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Torsten Sattler,et al.  Minimal Solvers for Generalized Pose and Scale Estimation from Two Rays and One Point , 2016, ECCV.

[47]  Marc Pollefeys,et al.  A Minimal Case Solution to the Calibrated Relative Pose Problem for the Case of Two Known Orientation Angles , 2010, ECCV.

[48]  Frederik Schaffalitzky,et al.  A minimal solution for relative pose with unknown focal length , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[49]  Yinlong Liu,et al.  Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search , 2018, ECCV.

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

[51]  Lipu Zhou,et al.  Automatic Extrinsic Calibration of a Camera and a 3D LiDAR Using Line and Plane Correspondences , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[52]  Roland Siegwart,et al.  A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation , 2011, CVPR 2011.

[53]  Torsten Sattler,et al.  Hybrid Camera Pose Estimation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[54]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[55]  Anath Fischer,et al.  3D Point Cloud Registration for Localization Using a Deep Neural Network Auto-Encoder , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[56]  Shree K. Nayar,et al.  A general imaging model and a method for finding its parameters , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[57]  Mikael Persson,et al.  Lambda Twist: An Accurate Fast Robust Perspective Three Point (P3P) Solver , 2018, ECCV.

[58]  P. Schönemann,et al.  A generalized solution of the orthogonal procrustes problem , 1966 .