我們提出了一個以統計模型為基礎的輪廓追蹤的方法，這個模型包含了一個新穎的預測模型和兩個統計物體模型，物體模型是由灰階色彩分佈和輪廓形狀的PCA模型而組成。利用漸進式的SVD技巧，這些模型都可以很有效率地在追蹤的時後學習並更新。我們經由實驗顯示了我們的預測方法比仿射的預測方法好，並且實驗結果顯示了我們的追蹤方法在各種不同情形下的人臉輪廓(放大、旋轉、部分遮蔽、整體環境亮度變化)都可以非常穩定的追蹤。

In this thesis, we propose a statistical model-based contour tracking method based on the Condensation framework. The models include a novel contour prediction model and two statistical object models. The object models consist of the grayscale histogram and contour shape PCA models computed from the previous tracking results. With the incremental singular value decomposition (SVD) technique, these three models are learned and updated very efficiently during tracking. We show that the proposed shape prediction model performs better than the affine predictor though experiments. Experimental results show the proposed contour tracking algorithm is very stable in tracking human heads on real videos with object scaling, rotation, partial occlusion, and illumination changes.

[1] D. A. Forsyth, J. Ponce, Computer Vision: A Modern Approach, pp. 373-396, Prentice Hall; 1st edition, August 14, 2002.
[2] M. Isard and A. Blake, “CONDENSATION - Conditional Density Propagation for Visual Tracking,” International Journal of Computer Vision, 29(1):5-28, 1998.
[3] A. Levy and M. Lindenbaum, “Sequential KarhunenLoeve Basis Extraction and its Application to image,” IEEE Transactions on Image Processing, 9(8):1371-1374, 2000.
[4] J. Lim, D. Ross, R.S. Lin, and M.H. Yang, “Incremental Learning for Visual Tracking,” Neural Information Processing Systems 17 (NIPS 2004), December 2004.
[5] B. K. P. Horn and B. G. Schunck, “Determining Optical Flow,” Artificial Intelligence, 17:185-203, 1981.
[6] B. D. Lucas and T. Kanade, “An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences,” Proc. DARPA Image Understanding Workshop, pp.121-130, 1981.
[7] J. Shi and C. Tomasi, “Good Features to Track,” In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 593-600, 1994.
[8] M. Irani, “Multi-Frame Optical Flow Estimation Using Subspace Constraints,” In Int. Conf. on Computer Vision, pp 626-633, 1999.
[9] L. Torresani and C. Bregler, “Space-Time Tracking,” European Conference on Computer Vision, pp. 801-812, 2002.
[10] A. Rahimi, L.-P. Morency and T. Darrell, “Reducing Drift in Parametric Motion Tracking,” In Int. Conf. on Computer Vision, 2001.
[11] G.. Golub and C. Van Loan, Matrix Computations, Johns Hopkins Univ. Press, 1992.
[12] M. Sonka, V. Hlavac and R. Boyle, Image Processing, Analysis, and Machine Vision, 2nd edition, pp.380-384, Thomson-Engineering, 1998.
[13] T.-L. Liu and H.-T. Chen, “Real-Time Tracking Using Trust-Region Methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 3, pp. 397-402, March 2004.
[14] D. Comaniciu, V. Ramesh and P. Meer, “Real-Time Tracking of Non-rigid Objects Using Mean Shift,” In Proc. Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 142-149, 2000.
[15] D. Comaniciu, V. Ramesh and P. Meer, “Kernel-Based Object Tracking,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 5, pp. 564-575, 2003.
[16] Y. Rui and Y. Chen, “Better Proposal Distributions: Object Tracking Using Unscented Particle Filter,” In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 786-793, 2001.
[17] E. Maggio and A. Cavallaro, “Hybrid Particle Filter and Mean Shift tracker with adaptive transition model,” Proc. of IEEE Signal Processing Society International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 19-23, 2005.
[18] K. Okuma, A. Taleghani, N. de Freitas, J. J. Little and D. G. Lowe, “A Boosted Particle Filter: Multitarget Detection and Tracking,” European Conference on Computer Vision, pp. 28-39, 2004.
[19] K. Nummiaro, E. Koller-Meier and L. Van Gool, “An Adaptive Color-Based Particle Filter,” International Journal of Image and Vision Computing, vol. 21, no. 1, pp. 99-110, 2003.