Mean Shift Tracking with Advanced Background-Weighted Histogram

Abstract:

Tracking objects in videos using mean shift technique has brought to public attention. In background-weighted histogram (BWH) algorithm proposed by Kernel-Based Object tracking attempts to reduce the interference of background target localization in mean shift tracking. However, in this paper we prove that the weights assigned to pixels in the target candidate region by BWH are proportional to those without background information, i.e. BWH does not introduce any new information because the mean shift iteration formula is invariant to the scale transformation of weights. We then propose an Advanced BWH (ABWH) formula by transforming only the target model but not the target candidate model. The ABWH scheme can effectively reduce background’s interference in target localization and for the target not well initialized, it can still robustly track the object, which is hard to achieve by the conventional target representation and it lead to faster convergence and more accurate localization than the usual target representation in mean shift tracking.

• Periodical: Applied Mechanics and Materials (Volume 302)
• Pages: 706-710
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.302.706
• Online since: February 2013
• Authors: Abebe Yirga Alemu, Zhi Jun Pei, Jun Zhang
• Keywords: Advanced BWH, Background Information, Background Weighted Histogram, Object Tracking, Target Initialization, Target Model

References

[1] Hu J., Juan C., and Wang J.: A spatial-color mean-shift object tracking algorithm with scale and orientation estimation, Pattern Recogniti on Letters, 2008, 29, (16), pp.2165-2173.

DOI: 10.1016/j.patrec.2008.08.007

[2] Comaniciu D., Ramesh V. and Meer P.: Kernel-Based Object Tracking, IEEE Trans. Pattern Anal. Machine Intell., 2003, 25, (2), pp.564-577.

DOI: 10.1109/tpami.2003.1195991

[3] Paris S. and Durand F A Topological Approach to Hierarchical Segmentation using Mean Shift,. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Minnesota, USA, June 2007, pp.1-8.

DOI: 10.1109/cvpr.2007.383228

[4] Tu J., Tao H., and Huang T. Online updati ng appearance generative mixture model for mean shift tracking, Machine Vision and Applications, 2009, 20, (3), p.163–173.

DOI: 10.1007/s00138-007-0115-x

[5] Park J., Lee G., and Park S.: Color image segmentation using adaptive mean shift and statistical model-based methods, Computers & Mathemati cs with Applications, 2009, 57, (6), pp.970-980.

DOI: 10.1016/j.camwa.2008.10.053