Detecting and tracking moving targets on omnidirectional vision

Abstract

A method was presented to implement the detecting and tracking of moving targets through omnidirectional vision. The method combined optical flow with particle filter arithmetic, in which optical flow field was used to detect and locate moving targets and particle filter was used to track the detected moving objects. According to the circular image character of omnidirectional vision, the calculation equation of optical flow field and the tracking arithmetic of particle filter were improved based on the polar coordinates at the omnidirectional center. The edge of a randomly moving object could be detected by optical flow field and was surrounded by a reference region in the particle filter. A dynamic motion model was established to predict particle state. Histograms were used as the features in the reference region and candidate regions. The mutual information (MI) and Gaussian function were combined to calculate particle weights. Finally, the state of tracked object was computed by the total particle states with weights. Experiment results show that the proposed method could detect and track moving objects with better real-time performance and accuracy.

Keywords

omnidirectional vision / optical flow / particle filter / mutual information

References

[1] Li Jin, Xu Junhong, Cong Wang et al. Research on real-time detection of moving target using gradient optical flow [C]. In: Proceedings of IEEE International Conference on Mechatronics and Automation, ICMA 2005. Canada, 2005. 1796–1801.

[2] Ha Jincheol, Alvino Christopher, Pryor Gallagher et al. Active contours and optical flow for automatic tracking of flying vehicles [C]. In: Proceedings of the 2004 American Control Conference. Boston, MA, United States, 2004. 3441–3446.

[3] Yamamoto S, Mae Y, Shirai Y et al. Real-time multiple object tracking based on optical flows[C]. In: Proceedings of 1995 IEEE International Conference on Robotics and Automation. Nagoya, Japan, 1995. 2328–2333.

[4] Tsutsui Hideki, Miura Jun, Shirai Yoshiaki. Optical flowbased person tracking by multiple cameras [C]. In: Proceedings of IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. Baden-Baden, 2001. 91–96.

[5] Perez P, Hue C, Vermaak J et al. Color-based probabilistic tracking[C]. In: Proceedings of the 7th European Conference on Computer Vision. Copenhagen, Denmark, 2002. 661–675.

[6] Nummiaro K., Koller-Meier E., Gool L. V. An adaptive color-based particle filter[J]. Image and Vision Computing, 2003, 21(1): 1-12.

[7] Guo R., Qin Z. An unscented particle filter for ground maneuvering target tracking[J]. Journal of Zhejiang University, 2007, 8(10): 1588-1595.

[8] Delahoche L, Pegard C, Marhic B et al. A navigation system based on an omnidirectional vision sensor [C]. In: Proceedings of 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Grenoble, France, 1997. 718–724.

[9] Wang Mingliang, Huang Chichang, Lin Hueiyung. An intelligent surveillance system based on an omnidirectional vision sensor[C]. In: Proceedings of 2006 IEEE Conference on Cybernetics and Intelligent Systems. Bangkok, Thailand, 2006. 4017871.

[10] Denman Simon, Chandran Vinod, Sridharan Sridha. Adaptive optical flow for person tracking[C]. In: Proceedings of Digital Imaging Computing: Techniques and Applications DICTA 2005. Cairns, Australia, 2005. 44–50.