Flexible Feature Optimization Based Robust Object Tracking
WANG Jiang-Tao1, CHEN De-Bao1, YANG Jing-Yu2
1. School of Physical and Electronic Information,Huaibei Normal University,Huaibei 235000 2.School of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing 210094
Abstract To overcome the disadvantages of single feature that often fails in describing the object reliably under dynamic environment, a flexible feature optimization based particle filter tracking algorithm is proposed. Firstly, the concept of sharpness factor is introduced to objectively elevate the discriminant ability for different features. Then, based on the features tracking property, the optimal feature under current scene is adaptively generated by combining the weighted features. Finally, the optimal feature is applied in the particle filter scheme to execute the object tracking task. The proposed algorithm is flexible and it can be extended to any feature represented by histogram. The experimental results on various videos demonstrate the effectiveness and robustness of the proposed method in multi-features fusion and object tracking.
[1] Yilmaz A,Javed O,Shah M.Object Tracking: A Survey.ACM Computing Surveys,2006,38(4): 1-45 [2] Wang H,Suter D,Schindler K,et al.Adaptive Object Tracking Based on an Effective Appearance Filter.IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29(9): 1661-1667 [3] Avidan S.Ensemble Tracking.IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29 (2): 261-271 [4] Li Shuxiao,Chang Hongxing,Zhu Chengfei.Adaptive Pyramid Mean Shift for Global Real-Time Visual Tracking.Image and Vision Computing,2010,28(3): 424-437 [5] Liu Hong,Yu Ze,Zha Hongbin,et al.Robust Human Tracking Based on Multi-Cue Integration and Mean-Shift.Pattern Recognition Letters,2009,30(9): 827-837 [6] Yu Dan,Wei Wei,Zhang Yuanhui.Mean Shift Tracking Algorithm Based on Multi-Feature Space.Pattern Recognition and Artificial Intelligence,2009,22(4): 666-672 (in Chinese) (虞 旦,韦 巍,张远辉.基于多特征空间的均值漂移算法.模式识别与人工智能,2009,22(4): 666-672) [7] Li P,Chaumette F.Image Cues Fusion for Object Tracking Based on Particle Filter // Proc of the 3rd International Workshop on Articulated Motion and Deformable Object.Palma de Mallorca,Spain,2004: 99-107 [8] Wang H,Suter D.Efficient Visual Tracking by Probabilistic Fusion of Multiple Cues // Proc of the 18th International Conference on Pattern Recognition.Hong Kong,China,2006,IV: 892-895 [9] Triesch J,Malsburg C.Democratic Integration: Self-Organized Integration of Adaptive Cues.Neural Computation,2001,13(9): 2049-2074 [10] Spengler M,Schiele B.Towards Robust Multi-Cue Integration for Visual Tracking.Machine Vision and Applications,2003,14(1): 50-58 [11] Shen C,Hengel A,Dick A.Probabilistic Multiple Cue Integration for Particle Filter Based Tracking // Proc of the 7th International Conference on Digital Image Computing: Techniques and Applications,Sydney,Australia,2003: 399-408 [12] Pérez P,Vermaak J,Blake A.Data Fusion for Visual Tracking with Particles.Proc of the IEEE,2004,92(3): 495-513 [13] Comaniciu D,Ramesh V,Meer P.Kernel-Based Object Tracking.IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(5): 564-577 [14] Nummiaro K,Koller-Meier E,Gool L V.An Adaptive Color-Based Particle Filter.Image and Vision Computing,2003,21(1): 99-110 [15] Ning Jifeng,Zhang Lei,Zhang D,et al.Robust Mean Shift Tracking with Corrected Background-Weighted Histogram[EB/OL].[2011-04-10].http://www4.comp.polyu.edu.hk/~cslzhang/paper/IET_CV_2010.pdf
2012, Vol. 25 
