基于融合策略自适应的多线索跟踪方法

钟小品; 薛建儒; 郑南宁; 平林江

doi:10.3724/SP.J.1146.2005.01350

基于融合策略自适应的多线索跟踪方法

doi: 10.3724/SP.J.1146.2005.01350

基金项目:

创新群体研究资助计划(60021302)，国家自然科学基金(60405004)和西安交通大学电信学院青年教师科研基金资助课题

计量
- 文章访问数: 3061
- HTML全文浏览量: 90
- PDF下载量: 934
- 被引次数: 0
出版历程
- 收稿日期: 2005-10-25
- 修回日期: 2006-06-30
- 刊出日期: 2007-05-19

An Adaptive Fusion Strategy Based Multiple-Cue Tracking

摘要

摘要: 基于多线索融合的跟踪是跟踪领域近年来的研究热点之一，该文结合两种常用的线索融合方式：乘性融合及加权和融合，提出一种融合策略自适应的鲁棒跟踪方法。该方法使用粒子滤波技术，统计样本的二阶中心矩并求Frobenius范数以表征线索的受噪声污染程度，最后适时切换两种融合策略。实践证明，新的融合策略比传统单一的融合方式更鲁棒。
- 跟踪;粒子滤波;多线索;融合
Abstract: Multiple cue fusion based tracking is one of the most active research in tracking literature. In this paper, a novel adaptive fusion strategy is proposed for multiple cue fusion, base on two common used fusion rules: product rule and weighted sum rule. This strategy employs particle filtering technique, estimating second order moment of the weighted sample set and computing its Frobenius norm to denote how cues are reliable, and then switch the two fusion rules in time. In practice, the new fusion strategy shows more robustness than traditional single fusion rule.

HTML全文

参考文献(1)

Shen C H, Hengel A, and Dick A. Probabilistic multiple cue integration for particle filter based tracking. Proc. VIIth Digital Image Computing: Techniques and Applications, Melbourne, Australia, 2003, I: 399-408.[2]Li P H and Chaumette F. Image cues fusion for object tracking based on particle filter. F J Perales and B A Draper (Eds.): AMDO 2004, LNCS 3197: 99-107.[3]Leichter I, Lindenbaum M, and Rivlin E. A Probabilistic framework for combining tracking algorithms. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Washington, USA, 2004, (2): 445-451.[4]Spengler M and Schiele B. Towards robust multi-cue integration for visual tracking. International Journal of Machine Vision and Applications, 2003, (14): 50-58.[5]Collins R and Liu Y. On-line selection of discriminative tracking features. Proceedings of International Conference on Computer Vision, Nice, France, 2003: 346-352.[6]Toyama K and Hager G. Incremental focus of attention for robust vision-based tracking[J].International Journal of Computer Vision.1999, 35(1):45-63[7]Kittler J and Hatef M, et al.. On combining classifiers. IEEE Trans. on PAMI, 1998, 20: 226-238.[8]Triesch J and Malsburg C. Democratic integration: self-organized integration of adaptive cue[J].Neural Computation.2001, 13:2049-2074[9]Jacobs R. What determines visual cue reliability? Trends in Cognitive Sciences, 2002, 6(8): 345-350.[10]Arulampalam S, Maskell S, Gordon N, and Clapp T. A tutorial on particle filters for on-line nonlinear/non-Gaussian Bayesian tracking[J].IEEE Trans. on Signal Processing.2002, 50(2):174-188[11]Comaniciu D, Ramesh V, and Meer R. Real-time tracking of non-rigid objects using mean shift. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, USA, 2000, Vol.2: 142-149.[12]Perez P, Hue C, Vermaak J, and Gangnet M. Color-based probabilistic tracking. Proc. European Conf. Computer Vision, Copenhagen, Denmark, 2002, Vol(I): 661-675.[13]Huttenlocher D, Klanderman G, and Rucklidge W. Comparing images using the Hausdorff distance. IEEE Trans. on PAMI, 1993, 15(9): 850-863.

施引文献

资源附件(0)

访问统计