1.Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing 100871 2.Department of Computer Science and Technology, Tsinghua University, Beijing 100084
Abstract An Adaboost based algorithm for object tracking in image sequences is proposed. In this algorithm, tracking is considered as a binary classification problem. Firstly, the linear combination of R, G, and B with integer coefficients is used to generate the candidate features. Features are selected for the design of weak classifiers according to the two-class variance ratio. Then, a strong classifier is built on the weak classifiers. For each incoming frame, a likelihood image of the object is created according to the classification results of pixels by the strong classifier. The trust region method and the scale space theory are employed to locate the blobs in the likelihood image, and thus the object tracking is fulfilled. The changes of illumination often cause the changes of features. The adaptability of the proposed algorithm is improved by online integration of new weak classifiers and automated weights update of the used ones. Based on the tracking results of sequence examples, the proposed algorithm can adapt to feature changes, track object in cluttered background and describe the object accurately with better tracking precision.
[1] Shi Jianbo, Tomasi C. Good Features to Track // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Seattle, USA, 1994: 593-600 [2] Han Bohyung, Davis L. Object Tracking by Adaptive Feature Extraction // Proc of the International Conference on Image Processing. Singapore, Singapore, 2004, Ⅲ: 1501-1504 [3] Stern H, Efros B. Adaptive Color Space Switching for Face Tracking in Multi-Colored Lighting Environments // Proc of the 5th IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 249-254 [4] Avidan S. Subset Selection for Efficient SVM Tracking // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Madison, USA, 2003, Ⅰ: 85-92 [5] Comaniciu D, Ramesh V, Meer P. Real-Time Tracking of Non-Rigid Objects Using Mean Shift // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, USA, 2000, Ⅱ: 142-149 [6] Comaniciu D, Ramesh V, Meer P. Kernel-Based Object Tracking. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577 [7] Jia Jingping, Zhao Rongchun. Tracking of Objects in Image Sequences Using Bandwidth Matrix Mean Shift Algorithm // Proc of the 7th International Conference on Signal Processing. Beijing, China, 2004, Ⅲ: 918-921 [8] Liu T L, Chen H T. Real-Time Tracking Using Trust-Region Methods. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26(3): 397-402 [9] Berghen F V. Intermediate Report on the Development of an Optimization Code for Smooth, Continuous Objective Functions When Derivatives Are Not Available [EB/OL]. [2003- 08- 09]. http://www.optimization-online.org/DB_HTML/2003/08/704.html [10] Lindeberg T. Feature Detection with Automatic Scale Selection. International Journal of Computer Vision, 1998, 30(2): 79-116 [11] Duda R O, Hart P E, Stock D G. Pattern Classification. 2nd Edition. New York, USA: John Wiley & Sons, 2001: 385-386 [12] Leordeanu M, Collins R T, Liu Yanxi. Online Selection of Discriminative Tracking Features. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643 [13] Ren Jinchang, Zhang Wenzhe, Zhao Rongchun, et al. An Automatic Target Tracking Method Based on Self-Adaptive Threshold under Complex Background. Application Research of Computers, 2003, 20(4), 55-57 (in Chinese) (任金昌,张文哲,赵荣椿,等.一种基于自适应阈值的复杂背景下自动目标跟踪方法.计算机应用研究, 2003, 20(4): 55-57)
2009, Vol. 22 
