在電腦視覺物件追蹤領域中，以核函數為基礎搭配均值移動演算法已經被證實為有效率的方法，核函數為基礎追蹤演算法為將一塊區域量化成一個空間權重相關的直方圖等化模型，並且利用巴特查理亞(Bhattacharyya)係數當作量測相似程度之量測方法。這些方法已經證實為可靠的方法。

本論文即是採用一個新型的核函數追蹤器，利用HSV(Hue Saturation Value)空間中的一維H 空間來減少時間成本。但是巴特查理亞係數最大化均值移動方法在低階的特徵值方圖等化空間中有可能會造成物件位置的誤差。我們提出一個新的演算方法，我們利用兩個物件的點資訊來矯正因為均值移動所產生的誤差。實驗結果展現點角正比起傳統方法或是邊特徵為基礎的核函數追蹤方法達到較佳的精準度。

Kernel-based tracking with mean-shift algorithm has been demonstrated as an effective method on computer vision. Kernel-based tracking method tracks a region that is described as a spatially-weighted histogram, it using Bhattacharyya coefficient as similarity measure is shown to be a robust method.
This thesis demonstrates a kernel-based tracking using HSV (Hue Saturation Value) space with 1-D hue channel to reduce the time complexity. Because Bhattacharyya coefficient maximization using mean shift rule in low level feature of histogram may cause inaccuracy in target location, we proposed an new algorithm, we using the corner information between target to correct error cause by mean shift. Experimental results show the corner correction achieved more precise tracking results than original kernel-based tracking and edge feature based kernel tracking.

[1] Kung-Hao Liang and Tardi Tjahjadi, “Multiresolution segmentation of optical flow fields for object tracking,” Applied Signal Processing, vol. 4, no. 3, pp. 179–187, Springer-Verlag, London, 1997.

[2] Alireza Behard, Ali Shahrokni, Seyed Ahmad Motamedi, “A robust vision-based moving target detection and tracking system,” Proceeding of Image and Vision Computing conference, Dunedin, New Zeland 26th-28th, 2001.

[3] Benjamin Coifman and David Beymer, Jitendra Mailik, “A real-time computer vision system for vehicle tracking and traffic surveillance,” Trasportation Research: Part C, vol. 6, no. 4, pp. 271–288, 1998.

[4] M. Betke, E. Haritaoglu and L. S. Davis, “Real-time multiple vehicle detection and tracking from a moving vehicle,” Machine Vision and Applications, vol. 12, no. 2, pp. 69–83, 2000.

[5] Janguang Lou, Hao Yang,Weiming Hu, Tieniu Tan,“Vesual vehicle tracking using an improved ekf,” Asian Conference on Computer Vision, 2002.

[6] Dieter Koller, Joseph Weber, and Jitendra Malik, “Robust multiple car tracking with occlusion reasoning,” Third European Conference on Computer Vision, pp. 186–196, Springer-Verlag, 1994.

[7] Esther B. Meier and Frank Ade, “Using the condensation algorithm to implement tracking for mobile robots,” Third European Workshop on Advanced Mobile Robots, pp. 73–80, Zurich, Awitzerland, 1999.

[8] Andrea Giachetti, “Applications of contour tracking techniques,” citeseer. ist.psu.edu/7949.html.

[9] D. Comaniciu, V. Ramesh, P. Meer, ” Kernel-Based Object Tracking,” IEEE Trans. Pattern Analysis Machine Intell., Vol. 25, No. 5, 564-575, 2003

[10] K. Fukunaga and L. D. Hostetler, “The estimation of the gradient of a density function, with applications in pattern recognition,” IEEE Transactions on Information Theory, vol. 21, no.1, pp. 32–40, 1975

[11] Y. Cheng, “Mean shift, mode seeking, and clustering,” IEEE Trans. Pattern Analysis Machine Intelligence, vol. 17, no. 8, pp. 790–799, 1995

[12] D. Comaniciu, P. Meer,”Mean Shift: A Robust Approach toward Feature Space Analysis,” IEEE Trans. Pattern Analysis Machine Intell., Vol. 24, No. 5, 603-619,2002

[13] G.R. Bradski, “Computer video face tracking for use in a perceptual user interface,” Intel Technology Journal, Q2 1998.

[14] Q. A. Nguyen, A. Robles-Kelly and C. Shen, “Enhanced Kernel-based Tracking for Monochromatic and Thermographic Video.” In IEEE International Conference on Advanced Video and Signal Based Surveillance, 2006.

[15] H. Moravec.“Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover". Tech Report CMU-RI-TR-3 Carnegie-Mellon University, Robotics Institute, 1980.

[16] C. Harris and M.J. Stephens. “A combined corner and edge detector.” Alvey Vision Conference, 1988.

[17] K. She , G. Bebis , H. Gu , R. Miller ,“Vehicle Tracking Using On-Line Fusion of Color and Shape Features,” IEEE Int. Conf. on Intelligent Transportation Systems, 2004.

[18] http://www.cipr.rpi.edu/

[19] http://ftp.pets.rdg.ac.uk/PETS2000/