Moving Object Detection and Tracking Using Particle Filter

Abstract:

Moving human detection and tracking are challenging tasks in computer vision. Human motion is usually non-linear and non-Gaussian, and thus many common algorithms are not appropriate for tracking. In this paper we propose a robust tracking algorithm based on particle filter. Multiple moving human in a video sequence are detected using frame difference and morphological operation. Then feature points of every person are extracted using a Harris Corner detection algorithm. Finally, Histogram of Oriented Gradient (HOG) is calculated for each feature point and feature points of the corresponding person are tracked using particle filter. Experimental results demonstrate that our method is efficient to improve the performance of tracking.

• Periodical: Applied Mechanics and Materials (Volumes 321-324)
• Pages: 1200-1204
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.321-324.1200
• Online since: June 2013
• Authors: M.M. Naushad Ali, M. Abdullah-Al-Wadud, Seok Lyong Lee
• Keywords: Harris Corner Detection, Histograms of Oriented Gradient (HOG), Human Tracking, Moving Object Detection, Particle Filter (PF)

References

[1] A. E. Dubois and A. Mitiche, Real-time system for high-level video representation: application to video surveillance, Proc. of SPIE Int. Symp. on Electronic Imaging, Conf. on Visual Comm. and Image Proc. (VCIP), Santa Clara, USA, 5022 (2003), 530-541.

DOI: 10.1117/12.476352

[2] K. H. Liang and T. Tjahjadi, Multiresolution segmentation of optical flow fields for object tracking, Appl. Sig. Proc..4, 3 (1997), 179-187.

[3] D. Beymer and K. Konolige, Real-time tracking of multiple people using continuous detection, ICCV, (1999)

[4] A. Doucet, N. D. Freitas, and N. Gordon, Sequential Monte Carlo methods in practice. Springer-Verlag, 2001.

[5] Dockstader et al., Multiple camera tracking of interacting and occluded human motion, Proc. of the IEEE, 89, 10 (2001), 1441-1455.

DOI: 10.1109/5.959340

[6] Z. Duan and Z. Cai, Adaptive Evolutionary Particle Filter Based Object Tracking with Occlusion Handling, Proc. of 5th Fifth Int. Conf. on Natural Computation, (2009), 358-361.

DOI: 10.1109/icnc.2009.623

[7] C. Harris and M. Stephens, A combined corner and edge detector, Proc. of 4th Alvey Vision Conf., (1988), 147–151.

DOI: 10.5244/c.2.23

[8] A. Dalal and B. Triggs, Histograms of oriented gradients for human detection. Proc. of Int. Conf. Comp. Vision and Pattern Recognition, 2 (2005), 86–893.

DOI: 10.1109/cvpr.2005.177

[9] A. Bhattacharyya, On a measure of divergence between two statistical populations defined by their probability distributions, Bulletin of the Calcutta Mathematical Society, 35 (1943), 99–109.

[10] M. Zhao, J. Zhao, S. Zhao, and Y. Wang, A Novel Method for Moving Object Detection in Intelligent Video Surveillance Systems, Proc. of IEEE Int. Conf. Comp. Intelligence and Security, Guangzhou, China, 2 (2006), 1797-1800.

DOI: 10.1109/iccias.2006.295372

[11] O. R. Vincent and O. Folorunso, A Descriptive Algorithm for Sobel Image Edge Detection, Proc. of Inf. Sci. & IT Edu. Conf., (2009).