GPO: Global Plane Optimization for Fast and Accurate Monocular SLAM Initialization

Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems. This paper focuses on a novel initialization method for monocular SLAM based on planar features. The algorithm starts by homography estimation in a sliding window. It then proceeds to a global plane optimization (GPO) to obtain camera poses and the plane normal. 3D points can be recovered using planar constraints without triangulation. The proposed method fully exploits the plane information from multiple frames and avoids the ambiguities in homography decomposition. We validate our algorithm on the collected chessboard dataset against baseline implementations and present extensive analysis. Experimental results show that our method outperforms the ne-tuned baselines in both accuracy and real-time.

[1]  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).

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

[3]  H. Jin Kim,et al.  Linear RGB-D SLAM for Planar Environments , 2018, ECCV.

[4]  Sei Ikeda,et al.  Visual SLAM algorithms: a survey from 2010 to 2016 , 2017, IPSJ Transactions on Computer Vision and Applications.

[5]  Shaojie Shen,et al.  Robust initialization of monocular visual-inertial estimation on aerial robots , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

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

[7]  Fei-Yue Wang,et al.  An efficient coordinate frame calibration method for 3-D measurement by multiple camera systems , 2005, IEEE Trans. Syst. Man Cybern. Part C.

[8]  Zhanyi Hu,et al.  Geographic, geometrical and semantic reconstruction of urban scene from high resolution oblique aerial images , 2019, IEEE/CAA Journal of Automatica Sinica.

[9]  E. Malis,et al.  Deeper understanding of the homography decomposition for vision-based control , 2007 .

[10]  Shichao Yang,et al.  Pop-up SLAM: Semantic monocular plane SLAM for low-texture environments , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

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

[12]  Jana Kosecka,et al.  Dense piecewise planar RGB-D SLAM for indoor environments , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[13]  Fei-Yue Wang A simple and analytical procedure for calibrating extrinsic camera parameters , 2004, IEEE Trans. Robotics Autom..

[14]  Leif Kobbelt,et al.  A Surface-Growing Approach to Multi-View Stereo Reconstruction , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  V. Lepetit,et al.  EPnP: An Accurate O(n) Solution to the PnP Problem , 2009, International Journal of Computer Vision.

[16]  Steven M. Seitz,et al.  Photo tourism: exploring photo collections in 3D , 2006, ACM Trans. Graph..

[17]  Simon Baker,et al.  Lucas-Kanade 20 Years On: A Unifying Framework , 2004, International Journal of Computer Vision.

[18]  Ronald Azuma,et al.  A Survey of Augmented Reality , 1997, Presence: Teleoperators & Virtual Environments.

[19]  Olivier Faugeras,et al.  Motion and Structure from Motion in a piecewise Planar Environment , 1988, Int. J. Pattern Recognit. Artif. Intell..

[20]  G. Ros,et al.  Visual SLAM for Driverless Cars : A Brief Survey , 2012 .

[21]  Hong Wang,et al.  Parallel planning: a new motion planning framework for autonomous driving , 2019, IEEE/CAA Journal of Automatica Sinica.

[22]  Elie A. Shammas,et al.  Keyframe-based monocular SLAM: design, survey, and future directions , 2016, Robotics Auton. Syst..

[23]  Onur Özyesil,et al.  Robust camera location estimation by convex programming , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  U SaputraMuhamad Risqi,et al.  Visual SLAM and Structure from Motion in Dynamic Environments , 2018 .

[25]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[26]  Laurent Kneip,et al.  Direct Optimization of Frame-to-Frame Rotation , 2013, 2013 IEEE International Conference on Computer Vision.

[27]  José Ruíz Ascencio,et al.  Visual simultaneous localization and mapping: a survey , 2012, Artificial Intelligence Review.

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

[29]  Éric Marchand,et al.  Improving monocular plane-based SLAM with inertial measures , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[30]  Leif Kobbelt,et al.  Iterative multi - view plane fitting , 2006 .

[31]  Noah Snavely,et al.  Robust Global Translations with 1DSfM , 2014, ECCV.

[32]  Ernesto Damiani,et al.  Augmented reality technologies, systems and applications , 2010, Multimedia Tools and Applications.

[33]  Zhe Chen,et al.  Progressive LiDAR adaptation for road detection , 2019, IEEE/CAA Journal of Automatica Sinica.

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

[35]  Bing He,et al.  Image analysis by two types of Franklin-Fourier moments , 2019, IEEE/CAA Journal of Automatica Sinica.

[36]  Seongdo Kim,et al.  Multi-planar Monocular Reconstruction of Manhattan Indoor Scenes , 2018, 2018 International Conference on 3D Vision (3DV).

[37]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[38]  Davide Scaramuzza,et al.  SVO: Fast semi-direct monocular visual odometry , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[39]  Zihan Zhou,et al.  Robust plane-based structure from motion , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[40]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Jun Wang,et al.  A Submap Joining Based RGB-D SLAM Algorithm Using Planes as Features , 2017, FSR.

[42]  Saeid Nahavandi,et al.  Deep imitation learning for autonomous vehicles based on convolutional neural networks , 2020, IEEE/CAA Journal of Automatica Sinica.

[43]  Guofeng Zhang,et al.  Keyframe-based dense planar SLAM , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[44]  Tat-Jun Chin,et al.  A Fast Resection-Intersection Method for the Known Rotation Problem , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[46]  Ping Tan,et al.  Global Structure-from-Motion by Similarity Averaging , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[47]  Shaojie Shen,et al.  VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator , 2017, IEEE Transactions on Robotics.

[48]  Roland Siegwart,et al.  Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback , 2017, Int. J. Robotics Res..

[49]  K. Madhava Krishna,et al.  Top Down Approach to Detect Multiple Planes from Pair of Images , 2014, ICVGIP.