Visual Odometry for Accurate Vehicle Localization - An Assistant for GPS Based Navigation

This paper describes a new approach for improving the estimation of a vehicle motion trajectory in complex urban environments by means of visual odometry. A new strategy for compensating the heterodasticity in the 3D input data using a weighted non-linear least squares based system is presented. A Matlab simulator is used in order to analyze the error in the estimation and validate the new solution. The obtained results are discussed and compared to the previous system. The final goal is the autonomous vehicle outdoor navigation in large-scale environments and the improvement of current vehicle navigation systems based only on standard GPS. This research is oriented to the development of traffic collective systems aiming vehicle-infrastructure cooperation to improve dynamic traffic management. The authors provide examples of estimated vehicle trajectories using the proposed method and discuss the key issues for further improvement.

[1]  K. Upton,et al.  A modern approach , 1995 .

[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]  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..

[4]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[5]  John D. Worth,et al.  A Modern Approach , 2005 .

[6]  Douglas M. Bates,et al.  Nonlinear Regression Analysis and Its Applications , 1988 .

[7]  Zhengyou Zhang,et al.  Estimation of Displacements from Two 3-D Frames Obtained From Stereo , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Nicolas Simond.  Free Space in Front of an Autonomous Guided Vehicle in Inner-City Conditions , 2007, EUROCAST.

[9]  A. C. Aitken.  IV.—On Least Squares and Linear Combination of Observations , 1936 .

[10]  Mik Wisniewski,et al.  Applied Regression Analysis: A Research Tool , 1990 .

[11]  Ignacio Parra,et al.  Combination of Feature Extraction Methods for SVM Pedestrian Detection , 2007, IEEE Transactions on Intelligent Transportation Systems.