Online self-supervised monocular visual odometry for ground vehicles

This paper presents an online self-supervised approach to monocular visual odometry and ground classification applied to ground vehicles. We solve the motion and structure problem based on a constrained kinematic model. The true scale of the monocular scene is recovered by estimating the ground surface. We consider a general parametric ground surface model and use the Random Sample Consensus (RANSAC) algorithm for robust fitting of the parameters. The estimated ground surface provides training samples to learn a probabilistic appearance-based ground classifier in an online and self-supervised manner. The appearance-based classifier is then used to bias the RANSAC sampling to generate better hypotheses for parameter estimation of the ground surface model. Thus, without relying on any prior information, we combine geometric estimates with appearance-based classification to achieve an online self-learning scheme from monocular vision. Experimental results demonstrate that online learning improves the computational efficiency and accuracy compared to standard sampling in RANSAC. Evaluations on the KITTI benchmark dataset demonstrate the stability and accuracy of our overall methods in comparison to previous approaches.

[1]  J. Little,et al.  Inverse perspective mapping simplifies optical flow computation and obstacle detection , 2004, Biological Cybernetics.

[2]  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.

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

[4]  Roland Siegwart,et al.  Real-time monocular visual odometry for on-road vehicles with 1-point RANSAC , 2009, 2009 IEEE International Conference on Robotics and Automation.

[5]  Dimitrios G. Kottas,et al.  Camera-IMU-based localization: Observability analysis and consistency improvement , 2014, Int. J. Robotics Res..

[6]  J. M. M. Montiel,et al.  Indoor robot motion based on monocular images , 2001, Robotica.

[7]  Peter I. Corke,et al.  A tutorial on visual servo control , 1996, IEEE Trans. Robotics Autom..

[8]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Harry Zhang,et al.  The Optimality of Naive Bayes , 2004, FLAIRS.

[10]  Karl Iagnemma,et al.  Self‐supervised terrain classification for planetary surface exploration rovers , 2012, J. Field Robotics.

[11]  Sanjiv Singh,et al.  Monocular Visual Odometry using a Planar Road Model to Solve Scale Ambiguity , 2011, ECMR.

[12]  Friedrich Fraundorfer,et al.  Visual Odometry Part I: The First 30 Years and Fundamentals , 2022 .

[13]  Allan D. Jepson,et al.  Visual Perception of Three-Dimensional Motion , 1990, Neural Computation.

[14]  Davide Scaramuzza,et al.  Exploiting motion priors in visual odometry for vehicle-mounted cameras with non-holonomic constraints , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Roland Siegwart,et al.  Fusion of IMU and Vision for Absolute Scale Estimation in Monocular SLAM , 2011, J. Intell. Robotic Syst..

[16]  Sebastian Thrun,et al.  Self-supervised Monocular Road Detection in Desert Terrain , 2006, Robotics: Science and Systems.

[17]  Jaehyun Park,et al.  Resolving scale ambiguity for monocular visual odometry , 2013, 2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[18]  Ashutosh Saxena,et al.  Learning Depth from Single Monocular Images , 2005, NIPS.

[19]  Yuichi Taguchi,et al.  Monocular Visual Odometry and Dense 3D Reconstruction for On-Road Vehicles , 2012, ECCV Workshops.

[20]  Ji Hoon Joung,et al.  What does ground tell us? Monocular visual odometry under planar motion constraint , 2011, 2011 11th International Conference on Control, Automation and Systems.

[21]  James R. Bergen,et al.  Visual odometry for ground vehicle applications , 2006, J. Field Robotics.

[22]  Roland Siegwart,et al.  Onboard IMU and monocular vision based control for MAVs in unknown in- and outdoor environments , 2011, 2011 IEEE International Conference on Robotics and Automation.

[23]  Sebastian Thrun,et al.  Stanley: The robot that won the DARPA Grand Challenge , 2006, J. Field Robotics.

[24]  Yutaka Kanayama,et al.  Two dimensional wheeled vehicle kinematics , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[25]  Ben Taskar,et al.  Online, self-supervised terrain classification via discriminatively trained submodular Markov random fields , 2008, 2008 IEEE International Conference on Robotics and Automation.

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

[27]  Giulio Reina,et al.  A Self‐learning Framework for Statistical Ground Classification using Radar and Monocular Vision , 2015, J. Field Robotics.

[28]  Julius Ziegler,et al.  StereoScan: Dense 3d reconstruction in real-time , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[29]  James R. Bergen,et al.  Visual odometry , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[30]  Kerem Ozkan.  Background surfaces and the horizon in the perception of the 3-D world , 2009 .

[31]  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.

[32]  Shiyu Song,et al.  Robust Scale Estimation in Real-Time Monocular SFM for Autonomous Driving , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.