Binocular Image Sequence Analysis: Integration of Stereo Disparity and Optic Flow for Improved Obstacle Detection and Tracking

Binocular vision systems have been widely used for detecting obstacles in advanced driver assistant systems (ADASs). These systems normally utilise disparity information extracted from left and right image pairs, but ignore the optic flows able to be extracted from the two image sequences. In fact, integration of these two methods may generate some distinct benefits. This paper proposes two algorithms for integrating stereovision and motion analysis for improving object detection and tracking. The basic idea is to fully make use of information extracted from stereo image sequence pairs captured from a stereovision rig. The first algorithm is to impose the optic flows as extra constraints for stereo matching. The second algorithm is to use a Kalman filter as a mixer to combine the distance measurement and the motion displacement measurement for object tracking. The experimental results demonstrate that the proposed methods are effective for improving the quality of stereo matching and three-dimensional object tracking.

[1]  Ye Zhang,et al.  On 3-D scene flow and structure recovery from multiview image sequences , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[2]  Yingping Huang.  Obstacle detection in urban traffic using stereovision , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[3]  W. Enkelmann,et al.  Robust obstacle detection and tracking by motion analysis , 1997, Proceedings of Conference on Intelligent Transportation Systems.

[4]  Wendong Wang,et al.  Recovering the Three-Dimensional Motion and Structure of Multiple Moving Objects from Binocular Image Flows , 1996, Comput. Vis. Image Underst..

[5]  Nasser M. Nasrabadi,et al.  Integration of stereo vision and optical flow using Markov random fields , 1988, IEEE 1988 International Conference on Neural Networks.

[6]  Yoshiki Ninomiya,et al.  STEREO VISION FOR OBSTACLE DETECTION , 2006 .

[7]  Allen M. Waxman,et al.  Binocular Image Flows: Steps Toward Stereo-Motion Fusion , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Christoph Stiller,et al.  Fusing optical flow and stereo disparity for object tracking , 2002, Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.

[9]  Shan Fu,et al.  Stereovision-Based Object Segmentation for Automotive Applications , 2005, EURASIP J. Adv. Signal Process..

[10]  Zhencheng Hu,et al.  Tracking cycle: a new concept for simultaneous tracking of multiple moving objects in a typical traffic scene , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[11]  James S. Duncan,et al.  3-D Translational Motion and Structure from Binocular Image Flows , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Tatsuya Suzuki,et al.  Measurement of vehicle motion and orientation using optical flow , 1999, Proceedings 199 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (Cat. No.99TH8383).

[13]  Kanad K. Biswas,et al.  Cooperative integration of stereopsis and optic flow computation , 1995 .

[14]  Nicola Ancona.  A Fast Obstacle Detection Method based on Optical Flow , 1992, ECCV.

[15]  Ramesh C. Jain,et al.  Dynamic Stereo with Self-Calibration , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Uwe Franke,et al.  Real-time stereo vision for urban traffic scene understanding , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[17]  Brendan McCane,et al.  On Benchmarking Optical Flow , 2001, Comput. Vis. Image Underst..