Stereo Visual Odometry Based on Motion Decoupling and Special Feature Screening for Navigation of Autonomous Vehicles

Visual odometry uses image information to estimate the ego-motion of a camera and is a practical technique for the navigation of autonomous vehicles. This paper presents a novel stereo-based ego-motion estimation method for this purpose. The proposed method employs a motion decoupling strategy that uses a set of distant feature points to estimate the camera’s rotation and a set of close feature points to estimate the translation. The set of feature points used for the motion estimation is carefully screened with bucketing plus aging techniques by considering their spatial distribution and temporal evolution. It has been found that the age of the tracked features has a significant impact on motion estimation. Older features generate less tracking error and should be selected for motion estimation. The proposed method is tested on the KITTI benchmark dataset and evaluated by comparing it with the existing visual odometry systems. The experimental results demonstrate that the proposed method can significantly improve the calculation efficiency and, meanwhile, guarantee a satisfactory accuracy.

[1]  Paul Timothy Furgale,et al.  Stereo mapping and localization for long-range path following on rough terrain , 2010, 2010 IEEE International Conference on Robotics and Automation.

[2]  Fabio Bellavia,et al.  Robust Selective Stereo SLAM without Loop Closure and Bundle Adjustment , 2013, ICIAP.

[3]  Andreas Geiger,et al.  Visual SLAM for autonomous ground vehicles , 2011, 2011 IEEE International Conference on Robotics and Automation.

[4]  Kun Qian,et al.  Wearable-Assisted Localization and Inspection Guidance System Using Egocentric Stereo Cameras , 2018, IEEE Sensors Journal.

[5]  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.

[6]  Andreas Kolb,et al.  Robust Range Camera Pose Estimation for Mobile Online Scene Reconstruction , 2018, IEEE Sensors Journal.

[7]  Ivan Petrovic,et al.  Stereo odometry based on careful feature selection and tracking , 2015, 2015 European Conference on Mobile Robots (ECMR).

[8]  Frank Dellaert,et al.  Flow separation for fast and robust stereo odometry , 2009, 2009 IEEE International Conference on Robotics and Automation.

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

[10]  Volker Willert,et al.  How to distinguish inliers from outliers in visual odometry for high-speed automotive applications , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).

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

[12]  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.

[13]  Frank Dellaert,et al.  Stereo Tracking and Three-Point/One-Point Algorithms - A Robust Approach in Visual Odometry , 2006, 2006 International Conference on Image Processing.

[14]  Volker Willert,et al.  Flow-decoupled normalized reprojection error for visual odometry , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[15]  Larry H. Matthies,et al.  Error modeling in stereo navigation , 1986, IEEE J. Robotics Autom..

[16]  Peirong Ji.  StereoScan : Dense 3 D Reconstruction in Real-time , 2016 .

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

[18]  Wei Lu,et al.  High-performance visual odometry with two-stage local binocular BA and GPU , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[19]  Sinisa Segvic,et al.  Improving the Egomotion Estimation by Correcting the Calibration Bias , 2015, VISAPP.

[20]  Nabil Aouf,et al.  Thermal Stereo Odometry for UAVs , 2015, IEEE Sensors Journal.