An On-Line Adaptive Product Fusion Tracking Algorithm Based on Multiple-Cue

Abstract:

To solve the poor robustness problem that object tracking only by fixation fusion based on multiple clues, an online adaptive fusion tracking algorithm based on multiple clues is proposed. the weighting of the different clues is online adjusting based on scene change , the more the feature contributes, the more a larger value, the less the feature contributes ,the less a smaller value. Simulation results show that this algorithm provides better robustness and stability.

• Periodical: Applied Mechanics and Materials (Volumes 303-306)
• Pages: 1536-1542
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.303-306.1536
• Online since: February 2013
• Authors: Jin Hua Wang, De Qiang Fu, Jie Cao
• Keywords: Adaptive Fusion, Histograms of Oriented Gradient (HOG), Object Tracking, Particle Filter (PF), Weighted Color Histogram

References

[1] HOU Zhi-Qiang，HAN Chong-Zhao. A Survey of Visual Tracking [J]. ACTA AUTOMATICA SINICA . Vol. 32, No. 4(2006): 603-617.

[2] Li P H, Chaumette F. Image cues fusion for object tracking based on particle filter[C]. Proceedings of the 3rd International Workshop on Articulated Motion and Deformable Objects. Palma de Mallorca, Spain: Springer, 2004, 99-107.

DOI: 10.1007/978-3-540-30074-8_11

[3] Bichfield S. Elliptical head tracking using intensity gradients and color histograms[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recongnition. Snata Barbara, USA: 1998, 232-237.

DOI: 10.1109/cvpr.1998.698614

[4] Shen C, Anton Van den Hengel, Dick A. Probabilistic multiple cue integration for particle filter based tracking[C]. Proceedings of the 7-th Digital Image Computing: Techniques and Appl; ications. 2003, 1: 399-408.

[5] Doucet A. On sequential simulation based methods for Bayesian filtering[R]. Technical Report University of Cambridge, Dept. of Engineerng, GUED-F-ENG TR310, (1998).

[6] P. Perez, C. Hue, J. Vermaak, M. Gangnet, Color-based probabilistic tracking[C], Proc. of the European Conference on Computer Vision, vol. 1, Copenhagen, Denmark, May-June 2002, 661-675.

DOI: 10.1007/3-540-47969-4_44

[7] Dalal N, Triggs B. Histogram of oriented gradients for human detection[C] Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2005: 886-893.

DOI: 10.1109/cvpr.2005.177

[8] WANG Yong-Zhong, LIANG Yan. Kernel-based Tracking Based on Adaptive Fusion of Multiple Cues[J]. ACTA AUTOMATICA SINICA . Vol. 34, No. 4(2008): 393-399.

DOI: 10.3724/sp.j.1004.2008.00393

[9] CAVIAR: context aware vision using image-based active recognition [EB/OL]. [2010-01-01]. http: /homepages. inf. ed. ac. uk/rbf/CAVIAR.