Real-time stereo visual odometry for autonomous ground vehicles

This paper describes a visual odometry algorithm for estimating frame-to-frame camera motion from successive stereo image pairs. The algorithm differs from most visual odometry algorithms in two key respects: (1) it makes no prior assumptions about camera motion, and (2) it operates on dense disparity images computed by a separate stereo algorithm. This algorithm has been tested on many platforms, including wheeled and legged vehicles, and has proven to be fast, accurate and robust. For example, after 4000 frames and 400 m of travel, position errors are typically less than 1 m (0.25% of distance traveled). Processing time is approximately 20 ms on a 512times384 image. This paper includes a detailed description of the algorithm and experimental evaluation on a variety of platforms and terrain types.

[1]  Larry Matthies,et al.  Stereo vision and rover navigation software for planetary exploration , 2002, Proceedings, IEEE Aerospace Conference.

[2]  Kurt Konolige,et al.  Real-time Localization in Outdoor Environments using Stereo Vision and Inexpensive GPS , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

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

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

[5]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[6]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[7]  Larry H. Matthies,et al.  Two years of Visual Odometry on the Mars Exploration Rovers , 2007, J. Field Robotics.

[8]  Larry H. Matthies,et al.  Robust and Efficient Stereo Feature Tracking for Visual Odometry , 2008, 2008 IEEE International Conference on Robotics and Automation.

[9]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

[10]  Gaurav S. Sukhatme,et al.  Bias Reduction and Filter Convergence for Long Range Stereo , 2005, ISRR.

[11]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

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

[13]  Jonathan M. Garibaldi,et al.  Fast, unconstrained camera motion estimation from stereo without tracking and robust statistics , 2002, 7th International Conference on Control, Automation, Robotics and Vision, 2002. ICARCV 2002..

[14]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[15]  Saied Moezzi,et al.  Dynamic stereo vision , 1992 .