Mean-Shift object tracking with a novel back-projection calculation method
作者： LingFeng Wang , HuaiYu Wu , ChunHong Pan
DOI: 10.1007/978-3-642-12307-8_8
关键词:
摘要: In this paper, we propose a mean-shift tracking method by using the novel back-projection calculation. The traditional calculation methods have two main drawbacks: either they are prone to be disturbed background when calculating histogram of target-region, or only consider importance pixel relative other pixels search-region. order solve drawbacks, carefully appearance based on priors, i.e., texture information background, and difference between foreground-target background. Accordingly, our consists basic steps. First, present approximation effectively reduce disturbance from Moreover, is used for instead target-region histogram. Second, proposed emphasizing probability that belongs foreground-target. Experiments show suitable various scenes appealing with respect robustness.
springer.com
core.ac.uk
sci-hub.st 参考文章(9)
Jung-ho Lee, Woong-hee Lee, Dong-seok Jeong, Object tracking method using back-projection of multiple color histogram models international symposium on circuits and systems. ,vol. 2, pp. 668- 671 ,(2003) , 10.1109/ISCAS.2003.1206062
D. Comaniciu, P. Meer, Mean shift: a robust approach toward feature space analysis IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 24, pp. 603- 619 ,(2002) , 10.1109/34.1000236
G.R. Bradski, Real time face and object tracking as a component of a perceptual user interface workshop on applications of computer vision. pp. 214- 219 ,(1998) , 10.1109/ACV.1998.732882
D. Comaniciu, V. Ramesh, P. Meer, Kernel-based object tracking IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 25, pp. 564- 575 ,(2003) , 10.1109/TPAMI.2003.1195991
J. Lin, Divergence measures based on the Shannon entropy IEEE Transactions on Information Theory. ,vol. 37, pp. 145- 151 ,(1991) , 10.1109/18.61115
Robert T Collins, Yanxi Liu, Marius Leordeanu, None, Online selection of discriminative tracking features IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 27, pp. 1631- 1643 ,(2005) , 10.1109/TPAMI.2005.205
M. Greiffenhagen, D. Comaniciu, H. Niemann, V. Ramesh, Design, analysis, and engineering of video monitoring systems: an approach and a case study Proceedings of the IEEE. ,vol. 89, pp. 1498- 1517 ,(2001) , 10.1109/5.959343
D. Comaniciu, V. Ramesh, P. Meer, Real-time tracking of non-rigid objects using mean shift computer vision and pattern recognition. ,vol. 2, pp. 142- 149 ,(2000) , 10.1109/CVPR.2000.854761
K. Fukunaga, L. Hostetler, The estimation of the gradient of a density function, with applications in pattern recognition IEEE Transactions on Information Theory. ,vol. 21, pp. 32- 40 ,(1975) , 10.1109/TIT.1975.1055330