Abstract: This paper first introduces the concept of a geogram that captures richer features to represent the objects. The spatiogram contains some moments upon the coordinates of the pixels corresponding to each bin, while the geogram contains information about the perimeter of grouped regions in addition to features in the spatiogram. Then we consider that a convergence process of mean shift is divided into obvious dynamic and steady states, and introduce a hybrid technique of feature description, to control the convergence process. Also, we propose a spline resampling to control the balance between computational cost and accuracy of particle filtering. Finally, we propose a boosting-refining approach, which is boosting the particles positioned in the ill-posed condition instead of eliminating the ill-posed particles, to refine the particles. It enables the estimation of the object state to obtain high accuracy. Experimental results show that our approach has promising discriminative capability in comparison with the state-of-the-art approaches.

[1]Arulampalam, M.S., Maskell, S., Gordon, N., et al., 2002. A tutorial on particle filter for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans. Signal Process., 50(2):174-188.

[2]Bai, K., Liu, W., 2007. Improved object tracking with particle filter and mean shift. Proc. IEEE Int. Conf. on Automation and Logistics, p.431-435.

[3]Comaniciu, D., Ramesh, V., Meer, P., 2003. Kernel based object tracking. IEEE Trans. Pattern Anal. Mach. Intell., 25(5):564-577.

[4]Fan, Z., Yang, M., Wu, Y., et al., 2006. Efficient optimal kernel placement for reliable visual tracking. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.658-665.

[5]Gao, C., Chen, W., 2011. Ground moving target tracking with VS-IMM using mean shift unscented particle filter. Chin. J. Aeronaut., 24(5):622-630.

[6]Han, B., Comaniciu, D., Zhu, Y., et al., 2004. Incremental density approximation and kernel-based Bayesian filtering for object tracking. Proc. IEEE Computer Vision and Pattern Recognition, p.638-644.

[7]Isard, M., Blake, A., 1998. Condensation-conditional density propagation for visual tracking. Int. J. Comput. Vis., 29(1):5-28.

[8]Jia, J., Wang, Q., Chai, Y., et al., 2006. Object tracking by multi-degrees of freedom mean shift procedure combined with the Kalman particle filter algorithm. Proc. IEEE Int. Conf. on Machine Learning and Cybernetics, p.3793-3797.

[9]Khan, Z.H., Gu, I.Y.H., Backhouse, A.G., 2011. Robust visual object tracking using multi-mode anisotropic mean shift and particle filters. IEEE Trans. Circ. Syst. Video Technol., 21(1):74-87.

[10]Le, P., Duong, A.D., Vu, H.Q., et al., 2009. An adaptive mean shift particle filter for moving objects tracking. Int. Conf. on Adaptive Hybrid Mean Shift and Particle Filter, Computing and Communication Technologies, p.1-4.

[11]Liu, H., Li, J., Qian, Y., et al., 2008. Robust multi-target tracking using mean shift and particle filter with target model update. Proc. 3rd Int. Conf. on Computer Vision Theory and Applications, p.605-610.

[12]Maggio, E., Cavallaro, A., 2005. Hybrid particle filter and mean shift tracker with adaptive transition model. Proc. IEEE Signal Processing Society Int. Conf. on Acoustics, Speech, and Signal Processing, p.221-224.

[13]Wang, F., Lin, Y., 2009. Improving particle filter with a new sampling strategy. Proc. 4th Int. Conf. on Computer Science and Education, p.408-412.

[14]Wang, H., Yang, B., Tian, G., et al., 2009. Object tracking by applying mean-shift algorithm into particle filtering. 2nd IEEE Int. Conf. on Broadband Network & Multimedia Technology, p.550-554.

[15]Wang, J., Liang, W., 2011. Robust tracking algorithm using mean-shift and particle filter. 4th Int. Conf. on Machine Vision: Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies, p.1-5.

[16]Wang, X., Zha, Y., Bi, D., 2007. An adaptive mean shift particle filter for moving objects tracking. SPIE, 6279:1-7.

[17]Yang, W., Hu, S., Li, J., et al., 2009. Robust tracking in FLIR imagery by mean shift combined with particle filter algorithm. IEEE Int. Symp. on Knowledge Acquisition and Modeling Workshop, p.761-764.

[18]Yao, A., Wang, G., Lin, X., et al., 2010. An incremental Bhattacharyya dissimilarity measure for particle filtering. Pattern Recogn., 43(4):1244-1256.

[19]Yao, A., Lin, X., Wang, G., et al., 2012. A compact association of particle filtering and kernel based object tracking. Pattern Recogn., 45(7):2584-2597.

[20]Yilmaz, A., Javed, O., Shah, M., 2006. Object tracking: a survey. ACM Comput. Surv., 38(4):13.1-13.45.