GPCO: An Unsupervised Green Point Cloud Odometry Method

Visual odometry aims to track the incremental motion of an object using the information captured by visual sensors. In this work, we study the point cloud odometry problem, where only the point cloud scans obtained by the LiDAR (Light Detection And Ranging) are used to estimate object’s motion trajectory. A lightweight point cloud odometry solution is proposed and named the green point cloud odometry (GPCO) method. GPCO is an unsupervised learning method that predicts object motion by matching features of consecutive point cloud scans. It consists of three steps. First, a geometry-aware point sampling scheme is used to select discriminant points from the large point cloud. Second, the view is partitioned into four regions surrounding the object, and the PointHop++ method is used to extract point features. Third, point correspondences are established to estimate object motion between two consecutive scans. Experiments on the KITTI dataset are conducted to demonstrate the effectiveness of the GPCO method. It is observed that GPCO outperforms benchmarking deep learning methods in accuracy while it has a significantly smaller model size and less training time.

[1]  Simon Lacroix,et al.  ICP-based pose-graph SLAM , 2016, 2016 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR).

[2]  C.-C. Jay Kuo,et al.  Pointhop++: A Lightweight Learning Model on Point Sets for 3D Classification , 2020, 2020 IEEE International Conference on Image Processing (ICIP).

[3]  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.

[4]  Roland Memisevic,et al.  Learning Visual Odometry with a Convolutional Network , 2015, VISAPP.

[5]  Suya You,et al.  FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method , 2020, ICPR Workshops.

[6]  Andras Majdik,et al.  LOL: Lidar-only Odometry and Localization in 3D point cloud maps* , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[7]  Ganning Zhao,et al.  TGHop: an explainable, efficient, and lightweight method for texture generation , 2021, APSIPA Transactions on Signal and Information Processing.

[8]  Gabriele Costante,et al.  LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation , 2017, IEEE Robotics and Automation Letters.

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

[10]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[11]  Konrad Schindler,et al.  FAST SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH STRONGLY VARYING DENSITY , 2016 .

[12]  Pranav Kadam,et al.  GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds , 2021, ArXiv.

[13]  Shan Liu,et al.  Unsupervised Point Cloud Registration via Salient Points Analysis (SPA) , 2020, 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP).

[14]  C.-C. Jay Kuo,et al.  Interpretable Convolutional Neural Networks via Feedforward Design , 2018, J. Vis. Commun. Image Represent..

[15]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[16]  Sen Wang,et al.  DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

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

[18]  C.-C. Jay Kuo,et al.  PointHop: An Explainable Machine Learning Method for Point Cloud Classification , 2019, IEEE Transactions on Multimedia.

[19]  Moncef Gabbouj,et al.  AnomalyHop: An SSL-based Image Anomaly Localization Method , 2021, 2021 International Conference on Visual Communications and Image Processing (VCIP).

[20]  Slobodan Ilic,et al.  PPFNet: Global Context Aware Local Features for Robust 3D Point Matching , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[21]  Ivan Markovic,et al.  Recalibrating the KITTI Dataset Camera Setup for Improved Odometry Accuracy , 2021, 2021 European Conference on Mobile Robots (ECMR).

[22]  Bo Yang,et al.  DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[23]  Paul J. Besl,et al.  Method for registration of 3-D shapes , 1992, Other Conferences.

[24]  C.-C. Jay Kuo,et al.  PixelHop: A successive subspace learning (SSL) method for object recognition , 2020, J. Vis. Commun. Image Represent..

[25]  Bin Yang,et al.  PIXOR: Real-time 3D Object Detection from Point Clouds , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[27]  Ye Duan,et al.  PointGrid: A Deep Network for 3D Shape Understanding , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[28]  Andreas E. Savakis,et al.  Flowdometry: An Optical Flow and Deep Learning Based Approach to Visual Odometry , 2017, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[29]  Geoffrey A. Hollinger,et al.  Deep Learning for Laser Based Odometry Estimation , 2016 .

[30]  Yue Wang,et al.  Dynamic Graph CNN for Learning on Point Clouds , 2018, ACM Trans. Graph..

[31]  Sen Wang,et al.  VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem , 2017, AAAI.

[32]  Joachim Hertzberg,et al.  Globally consistent 3D mapping with scan matching , 2008, Robotics Auton. Syst..

[33]  Suya You,et al.  DefakeHop: A Light-Weight High-Performance Deepfake Detector , 2021, 2021 IEEE International Conference on Multimedia and Expo (ICME).

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

[35]  Ji Zhang,et al.  Visual-lidar odometry and mapping: low-drift, robust, and fast , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[36]  Suya You,et al.  Pixelhop++: A Small Successive-Subspace-Learning-Based (Ssl-Based) Model For Image Classification , 2020, 2020 IEEE International Conference on Image Processing (ICIP).

[37]  C.-C. Jay Kuo,et al.  R-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method , 2021, ArXiv.

[38]  Shan Liu,et al.  Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation , 2020, 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP).

[39]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[40]  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).