A Hybrid CamShift and l1-Minimization Video Tracking Algorithm

Authors: Clark Van Dam, Gagan Mirchandani

Abstract:

The Continuously Adaptive Mean-Shift (CamShift) algorithm, incorporating scene depth information is combined with the l1-minimization sparse representation based method to form a hybrid kernel and state space-based tracking algorithm. We take advantage of the increased efficiency of the former with the robustness to occlusion property of the latter. A simple interchange scheme transfers control between algorithms based upon drift and occlusion likelihood. It is quantified by the projection of target candidates onto a depth map of the 2D scene obtained with a low cost stereo vision webcam. Results are improved tracking in terms of drift over each algorithm individually, in a challenging practical outdoor multiple occlusion test case.

Keywords: CamShift, l1-minimization, particle filter, stereo vision, video tracking.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1055659

References:

[1] Bradski G., Kaehler A., "Learning OpenCV: Computer Vision with the OpenCV library", O'Reilly Media, Inc., 2008.
[2] Bruns E., Kurz D., Grundhiver A., and Bimber O., "Fast and robust CamShift tracking'', 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop, June 2010, pp. 9- 16.
[3] Wang Z., Yang X., Xu Y., Yu S., "CamShift Guided Particle Filter for Visual Tracking," Journal Pattern Recognition Letters, Vol. 30, Issue 4, March 2009, pp.407-13.
[4] Emami E., Fathy M., "Object Tracking Using Improved CAMShift Algorithm Combined with Motion Segmentation,"Conference on Machine Vision and Image Processing , 16-17 Nov. 2011, pp.1-4.
[5] Zou T., Tang X., Song B. , "Improved CamShift Tracking Algorithm Based on Silhouette Moving Detection," 2011 Third International Conference on Multimedia Information Networking and Security, 4-6 Nov. 2011, pp.11-15.
[6] Li J., Zhang J., Zhou Z.; Guo W., Wang B., Zhao Q. , "Object tracking using improved CamShift with SURF method," 2011 International Workshop on Open-Source Software for Scientific Computation, 12-14 Oct. 2011, pp.136-141.
[7] Kovacevic J., Juric-Kavelj S., Petrovic I., "An improved CamShift algorithm using stereo vision for object tracking," MIPRO 2011 Proceedings of the 34th International Convention, 23-27 May 2011, pp.707-710.
[8] Mei X. and Ling H., "Robust Visual Tracking and Vehicle Classification via Sparse Representation", IEEE Trans. PAMI, Nov. 2011, Vol.33, Isssue:11, pp.2259-2272.
[9] Deilamani, M.J. and Asli, R.N., "Moving object tracking based on mean shift algorithm and features fusion", Artificial Intelligence and Signal Processing, 2011, pp.48-53.
[10] Comaniciu D. and Meer P., "Mean Shift: A Robust Approach Towards Feature Space Analysis'', IEEE Trans. PAMI, May 2002, Vol.24, No.5, pp.603-619.
[11] Wright J., Yang A.Y., Ganesh A., Sastry S.S. and Ma Y., "Robust Face Recognition via Sparse Representation", IEEE Trans. PAMI, Feb. 2009, Vol.31, Issue:2, pp.210-227.
[12] Candes E., Romberg J. and Tao T., "Stable signal recovery from incomplete and inaccurate measurements'', Comm. on Pure and Applied Math,'' 59(8), 2006, pp.1207-1223.
[13] Donoho D., "Compressed Sensing", IEEE Trans. Information Theory, 52(4), 2006, pp.1289-1306.