Real-Time Global Registration for Globally Consistent RGB-D SLAM

Real-time globally consistent camera localization is critical for visual simultaneous localization and mapping (SLAM) applications. Regardless the popularity of high efficient pose graph optimization as a backend in SLAM, its deficiency in accuracy can hardly benefit the reconstruction application. An alternative solution for the sake of high accuracy would be global registration, which minimizes the alignment error of all the corresponding observations, yet suffers from high complexity due to the tremendous observations that need to be considered. In this paper, we start by analyzing the complexity bottleneck of global point cloud registration problem, i.e., each observation (three-dimensional point feature) has to be linearized based on its local coordinate (camera poses), which however is nonlinear and dynamically changing, resulting in extensive computation during optimization. We further prove that such nonlinearity can be decoupled into linear component (feature position) and nonlinear components (camera poses), where the former linear one can be effectively represented by its compact second-order statistics, while the latter nonlinear one merely requires six degrees of freedom for each camera pose. Benefiting from the decoupled representation, the complexity can be significantly reduced without sacrifice in accuracy. Experiments show that the proposed algorithm achieves globally consistent pose estimation in real-time via CPU computing, and owns comparable accuracy as state-of-the-art that use GPU computing, enabling the practical usage of globally consistent RGB-D SLAM on highly computationally constrained devices.

[1]  Vladlen Koltun,et al.  Fast Global Registration , 2016, ECCV.

[2]  Vladlen Koltun,et al.  Robust reconstruction of indoor scenes , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Javier González,et al.  Cartan-Sync: Fast and Global SE(d)-Synchronization , 2017, IEEE Robotics and Automation Letters.

[4]  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.

[5]  Juan D. Tardós,et al.  ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras , 2016, IEEE Transactions on Robotics.

[6]  Dieter Fox,et al.  RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments , 2010, ISER.

[7]  Evangelos E. Milios,et al.  Globally Consistent Range Scan Alignment for Environment Mapping , 1997, Auton. Robots.

[8]  Robert B. Fisher,et al.  Estimating 3-D rigid body transformations: a comparison of four major algorithms , 1997, Machine Vision and Applications.

[9]  Amit Singer,et al.  Global Registration of Multiple Point Clouds Using Semidefinite Programming , 2013, SIAM J. Optim..

[10]  John J. Leonard,et al.  SE-Sync: A certifiably correct algorithm for synchronization over the special Euclidean group , 2016, Int. J. Robotics Res..

[11]  Andrew W. Fitzgibbon,et al.  Bundle Adjustment - A Modern Synthesis , 1999, Workshop on Vision Algorithms.

[12]  Nassir Navab,et al.  Model globally, match locally: Efficient and robust 3D object recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Daniel Cremers,et al.  Dense visual SLAM for RGB-D cameras , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Matthias Nießner,et al.  BundleFusion , 2016, TOGS.

[15]  Andrew J. Davison,et al.  A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Dorian Gálvez-López,et al.  Bags of Binary Words for Fast Place Recognition in Image Sequences , 2012, IEEE Transactions on Robotics.

[17]  Richard Szeliski,et al.  Pushing the Envelope of Modern Methods for Bundle Adjustment , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Andrew Owens,et al.  SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels , 2013, 2013 IEEE International Conference on Computer Vision.

[19]  Jose Luis Blanco,et al.  A tutorial on SE(3) transformation parameterizations and on-manifold optimization , 2012 .

[20]  Stefan Leutenegger,et al.  ElasticFusion: Real-time dense SLAM and light source estimation , 2016, Int. J. Robotics Res..

[21]  Frank Dellaert,et al.  Square Root SAM: Simultaneous Localization and Mapping via Square Root Information Smoothing , 2006, Int. J. Robotics Res..

[22]  Manolis I. A. Lourakis,et al.  SBA: A software package for generic sparse bundle adjustment , 2009, TOMS.

[23]  Khushali Deulkar,et al.  Google Project Tango - A Convenient 3D Modeling Device , 2014 .

[24]  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).

[25]  Wolfram Burgard,et al.  G2o: A general framework for graph optimization , 2011, 2011 IEEE International Conference on Robotics and Automation.

[26]  Christopher Zach,et al.  Robust Bundle Adjustment Revisited , 2014, ECCV.

[27]  Niloy J. Mitra,et al.  Super4PCS: Fast Global Pointcloud Registration via Smart Indexing , 2019 .

[28]  Andrea Fusiello,et al.  Global Registration of 3D Point Sets via LRS Decomposition , 2016, ECCV.

[29]  Lu Fang,et al.  Beyond SIFT using binary features in Loop Closure Detection , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[30]  Kuk-Jin Yoon,et al.  Joint Layout Estimation and Global Multi-view Registration for Indoor Reconstruction , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[31]  John B. Moore,et al.  Global registration of multiple 3D point sets via optimization-on-a-manifold , 2005, SGP '05.

[32]  John C. Tang,et al.  3D Collaboration Method over HoloLens™ and Skype™ End Points , 2015, ImmersiveME@ACM Multimedia.

[33]  Lu Fang,et al.  MILD: Multi-index hashing for appearance based loop closure detection , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).