臺灣博碩士論文加值系統

在本篇論文中，提出了一個有效地運用貝氏理論進行以核心函數為基礎的視訊物件追蹤方法。物件追蹤在許多視訊處理中扮演重要的角色，例如視訊監視系統、物件式視訊資料庫檢索、或是自動化視訊操作等。而視訊物件的變化則增加了追蹤上的困難度，其中主要的變化來自於視訊物件比例的改變以及遮蔽的發生。
為了解決這些困難，我們將視訊物件追蹤表示成運用貝氏理論分析的問題。在此架構上，我們使用現在視訊格與參考視訊格間的差異定義出機率模組，再藉由機率的最大化得到最佳視訊追蹤結果。因此，我們運用梯度法獲得每個參考視訊格所對應的最佳結果；然後，再採用線性合併的策略以及修改過的衰退參數來整合所有參考視訊格所對應的最佳結果，並且根據此統整出的結論得到正確的追蹤物件。
實驗結果可以顯示出我們提出的方法與mean-shift演算法之間效能的比較。我們的方法比起mean-shift演算法顯然更為有效且可信賴，即使當物件已經被嚴重的遮蔽，提出的方法仍然可以正確的追蹤物件。

This thesis proposes an effective approach for kernel-based video object tracking. Video object tracking plays an important role in many applications of multimedia, such as video surveillance, object-based video database search, and automatic video manipulation. The main difficulty comes from the scaling change of a video object and occlusion.
We formulate the tracking problem as a Bayesian learning framework and define the probabilistic models in terms of the distance between current frame and reference frame. We thus take the gradient method to obtain an optimized result with respect to a number of reference frames. Then we adopt the linear combination strategy and the modified decay rate to integrate the information from each reference frame and obtain the tracking result.
In our experiments, we show the comparison of our method and the mean-shift algorithms. The tracking results of our method are more effective and reliable than the mean-shift algorithms. Even when the target object is severely occluded, our method tracks the reappeared object correctly.

[1] A. R. Mansour, “Region Tracking via Level Set PDEs Without Motion Computation”, IEEE Trans. Pattern Anal. Machine Intell., vol. 24, No. 7, pp. 947-961, July 2002.
[2] A. D. Jepson, D. J. Fleet ,and T. F. El-Maraghi, “Robust Online Appearance Models for Visual Tracking ”, IEEE Trans. Pattern Anal. Machine Intell., Vol. 25, No. 10, pp. 1296-1311, October 2003.
[3] D. Comaniciu, V. Ramesh, and P. Meer, “Kernel Based Object Tracking”, IEEE Trans. Pattern Anal. Machine Intell., Vol. 25, No. 5, pp. 564-577, May 2003.
[4] D. Comaniciu, and P. Meer, “Mean Shift: A Robust Approach Toward Feature Space Analysis”, IEEE Trans. Pattern Anal. Machine Intell., Vol. 24, No. 5, pp. 603-619, May 2002.
[5] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, “Detecting Moving Objects, Ghosts, and Shadows in Video Streams”, IEEE Trans. Pattern Anal. Machine Intell., Vol. 25, No. 10, pp. 1337-1342, October 2003.
[6] T. L. Liu, and H. T. Chen, “Real-time tracking using trust-region methods”, IEEE Trans. Pattern Anal. Machine Intell., Vol. 26 , No. 3 , pp. 397-402, March 2004.
[7] R. T. Collins, “Mean-shift Blob Tracking through Scale Space”, IEEE CVPR, Madison, June 2003.
[8] A. Yilmaz, X. Li, and M. Shah, “Object contour tracking using level sets”, Asian Conference on Computer Vision, ACCV 2004, Jaju Islands, Korea, January 2004.
[9] J. O. Berger, “Statistical Decision Theory and Bayesian Analysis”, Springer-Verlag, New York, 1985.
[10] Z.Zivkovic, and B.Krose, “A probabilistic model for an EM-like object tracking algorithm using color-histograms” 6th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, May, 2004.
[11] K. Nummiaro, E. Koller-Meier, and L. V. Gool, “Color Features for Tracking Non-rigid Objects”, Chinese Journal of Automation, Vol. 29, No. 3, pp. 345-355, May 2003
[12] Y. Wang, J. Ostermann, and Y. Q. Zhang, “Video Processing and Communications”, 2001.
[13] M. J. Lucena, J. M. Fuertes, N. P. D. L. Blanca, and A. Garrido “An Optical Flow Probabilistic Observation Model for Tracking”, ICIP 2003, Barceloma, Spain, Sep. 2003.
[14] D. Comaniciu, V. Ramesh, and P. Meer, “The Variable Bandwidth Mean Shift and Data-Driven Scale Selection”, International Conference on Computer Vision, Vol. I, pp. 438-445, July 2001.
[15] T. Kailath, “The divergence and Bhattacharyya distance measures in signal selection”, IEEE Trans. Commun. Tech. Vol. 15, pp. 52-60, 1976.