RectMatch: A novel scan matching method using the rectangle-flattening representation for mobile LiDAR systems

Abstract Point cloud registration is a fundamental problem in 3D computer vision. This paper addresses scan matching for reliable Mobile LiDAR Systems (MLSs) that can traverse different environments and be robust against outliers and noise. High reliability in multiple scenarios is vital to many applications, such as autonomous driving, but poor feature representations often compromise it. This paper introduces an expressive feature called the rectangle-flattening representation to enhance reliability. First, we propose a clustering method based on density, direction and flattening that allows regions to grow in a “planes first, lines second, less flattened structures last” manner. This method can extract rectangles from environments where planes are scarce. Second, we develop a squared point-to-rectangle distance function that is piecewise yet continuously differentiable to leverage the rectangle-flattening representation for scan matching. Unlike the traditional point-to-plane or plane-to-plane residual functions that rely on planar surfaces in other directions to provide translational information, our point-to-rectangle distance function is intrinsically translation-aware. Extensive experiments are conducted on three aspects: scan matching accuracy, robustness, and odometry and mapping on MLSs. We compare our algorithm to several state-of-the-art methods using KITTI and Ford datasets in scan matching accuracy test with environments covering residential areas, highways, rural areas, downtown areas and campuses. Rigorous experiments show that among all of the methods compared, only RectMatch has an overall scan matching success rate surpassing 90% and even 95% across the two datasets. The robustness tests demonstrate that RectMatch can better deal with random outliers and Gaussian noise. For a comprehensive evaluation of RectMatch for MLSs, the third test incorporates five publicly available datasets using different laser scanners on multiple platforms traversing different environments. The results show high algorithm reliability and accuracy.

[1]  Long Quan,et al.  D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Andrew W. Fitzgibbon.  Robust registration of 2D and 3D point sets , 2003, Image Vis. Comput..

[3]  Tatsuo Arai,et al.  The generation of environmental map based on a NDT grid mapping -Proposal of convergence calculation corresponding to high resolution grid- , 2008, 2008 IEEE International Conference on Robotics and Automation.

[4]  Andrea Tagliasacchi,et al.  Sparse Iterative Closest Point , 2013, Comput. Graph. Forum.

[5]  Han Hu,et al.  Object-based incremental registration of terrestrial point clouds in an urban environment , 2020 .

[6]  Zheng Liu,et al.  BALM: Bundle Adjustment for Lidar Mapping , 2020, IEEE Robotics and Automation Letters.

[7]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[8]  Nanning Zheng,et al.  Accurate Mix-Norm-Based Scan Matching , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[9]  Paul Checchin,et al.  CICP: Cluster Iterative Closest Point for sparse-dense point cloud registration , 2018, Robotics Auton. Syst..

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

[11]  Vladlen Koltun,et al.  Fully Convolutional Geometric Features , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[12]  Jan Kautz,et al.  DeepGMR: Learning Latent Gaussian Mixture Models for Registration , 2020, ECCV.

[13]  Cheng Wang,et al.  Semantic line framework-based indoor building modeling using backpacked laser scanning point cloud , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[14]  Li Wang,et al.  SLAM integrated mobile mapping system in complex urban environments , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[15]  Ryan M. Eustice,et al.  University of Michigan North Campus long-term vision and lidar dataset , 2016, Int. J. Robotics Res..

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

[17]  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.

[18]  Steven Lake Waslander,et al.  Scan registration using segmented region growing NDT , 2014, Int. J. Robotics Res..

[19]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[20]  Martin Magnusson,et al.  The three-dimensional normal-distributions transform : an efficient representation for registration, surface analysis, and loop detection , 2009 .

[21]  Milad Ramezani,et al.  The Newer College Dataset: Handheld LiDAR, Inertial and Vision with Ground Truth , 2020, ArXiv.

[22]  I. Jolliffe.  Principal Component Analysis , 2005 .

[23]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  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.

[25]  Steven Lake Waslander,et al.  Scan registration with multi-scale k-means normal distributions transform , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[26]  Brendan Englot,et al.  LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[27]  Subhransu Maji,et al.  Multi-view Convolutional Neural Networks for 3D Shape Recognition , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[29]  Yusheng Xu,et al.  Registration of large-scale terrestrial laser scanner point clouds: A review and benchmark , 2020 .

[30]  Shiyu Song,et al.  DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[31]  Jian Zhang,et al.  Feature-Metric Registration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration Without Correspondences , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Michael Felsberg,et al.  Density Adaptive Point Set Registration , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[33]  John Lewis,et al.  Java Software Structures: Designing and Using Data Structures , 2003 .

[34]  Daniel Eggert,et al.  OCTREE-BASED SIMD STRATEGY FOR ICP REGISTRATION AND ALIGNMENT OF 3D POINT CLOUDS , 2012 .

[35]  Michael A. Greenspan,et al.  Approximate k-d tree search for efficient ICP , 2003, Fourth International Conference on 3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings..

[36]  Yuchao Dai,et al.  Deep learning based point cloud registration: an overview , 2020, Virtual Real. Intell. Hardw..

[37]  Szymon Rusinkiewicz,et al.  A symmetric objective function for ICP , 2019, ACM Trans. Graph..

[38]  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).

[39]  Leonidas J. Guibas,et al.  SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Dietrich Paulus,et al.  MC2SLAM: Real-Time Inertial Lidar Odometry Using Two-Scan Motion Compensation , 2018, GCPR.

[41]  Yasuhiro Aoki,et al.  PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[43]  Shenghai Yuan,et al.  MILIOM: Tightly Coupled Multi-Input Lidar-Inertia Odometry and Mapping , 2021, IEEE Robotics and Automation Letters.

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

[45]  Frédéric Bosché,et al.  Plane-based registration of construction laser scans with 3D/4D building models , 2012, Adv. Eng. Informatics.

[46]  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).

[47]  Chenglu Wen,et al.  Toward Efficient 3-D Colored Mapping in GPS-/GNSS-Denied Environments , 2020, IEEE Geoscience and Remote Sensing Letters.

[48]  Patrick J. Flynn,et al.  A Survey Of Free-Form Object Representation and Recognition Techniques , 2001, Comput. Vis. Image Underst..

[49]  Bo Wu,et al.  Image-Guided Registration of Unordered Terrestrial Laser Scanning Point Clouds for Urban Scenes , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[50]  Yi Lin,et al.  A low-cost multi-sensoral mobile mapping system and its feasibility for tree measurements , 2010 .

[51]  Takashi Tsubouchi,et al.  A 3-D Scan Matching using Improved 3-D Normal Distributions Transform for Mobile Robotic Mapping , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[52]  Ryan M. Eustice,et al.  Ford Campus vision and lidar data set , 2011, Int. J. Robotics Res..

[53]  Zi Jian Yew,et al.  3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration , 2018, ECCV.

[54]  Sebastian Scherer,et al.  VoxNet: A 3D Convolutional Neural Network for real-time object recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[55]  Gérard G. Medioni,et al.  Object modeling by registration of multiple range images , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[56]  Andrea Censi,et al.  An ICP variant using a point-to-line metric , 2008, 2008 IEEE International Conference on Robotics and Automation.

[57]  Roland Siegwart,et al.  Point Clouds Registration with Probabilistic Data Association , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[58]  Radu Horaud,et al.  A Generative Model for the Joint Registration of Multiple Point Sets , 2014, ECCV.

[59]  Jianru Xue,et al.  Precise 2D point set registration using iterative closest algorithm and correntropy , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

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

[61]  Wenzhong Shi,et al.  A Novel Method for Plane Extraction from Low-Resolution Inhomogeneous Point Clouds and its Application to a Customized Low-Cost Mobile Mapping System , 2019, Remote. Sens..

[62]  Radu Horaud,et al.  Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximization , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.