視覺影像追蹤近年來已成為研究發展的熱門課題，不僅使用於國防科技武器方面，更是越來越普及於我們日常生活當中；諸如居家安全監控系統、老年人的生活安全看護，車輛導航與安全輔助駕駛…等。因此本論文使用電腦視覺與影像處理的方法設計發展一套動態物體的自動偵測與追蹤系統應用於自走車上；以高斯混合模型建立背景模型，以背景濾除的方式來有效達到前景動態物體的偵測。首先運用K-means clustering將背景像素值做初步的分群，並利用最大期望值演算法(EM Algorithm)去估測和更新最佳的高斯混合模型參數，以找到與真正像素值最相似的分佈。當移動物體被偵測擷取出之後，將記錄並擷取出此物體的顏色資訊，利用樣板影像和候選影像之間的彩色分佈密度函數來計算出最高相似度的質心位置，再配合平均位移(Mean Shift Algorithm)演算法即可以精準且快速的算出所追蹤的移動物體。此追蹤系統將搭配自主式移動機器人，讓自主式移動機器人能夠自動搜查移動物體，再將此移動物位置訊息回傳給自主式移動機器人，達到及時監控與追蹤目標。

In recent years, visual tracking have became an important and popular research topic, it is not only applied in military application, but also in our regular life, such as security surveillance, care taking for elder and disabled person at home, vehicle tracking and aid to navigation on the roadway etc. Therefore, in this thesis, the technology of computer vision and image processing technology were used on mobile robot using PTZ camera to develop automatic object motion detection and tracking system. The Gaussian Mixture Model is used to build background and extract moving regions, the K-means clustering and EM Algorithm is used to estimate and renovate the optimization parameters. Follow by extracting and analyzing the color feature of moving object, and computing the similarity function of color probability density function between reference model and candidate target model. Then combine with Mean Shift Algorithm, it can find the position of moving object precise and quickly, then feedback the information of position and displacement to autonomous mobile robot, finally achieve real time surveillance and tracking.

[1] H. Weiming, T. Tieniu, W. Liang, and S. Maybank, "A survey on visual surveillance of object motion and behaviors," Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 34, pp. 334-352, 2004.
[2] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, "Detecting moving objects, ghosts, and shadows in video streams," Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 25, pp. 1337-1342, Oct 2003.
[3] O. Javed, K. Shafique, and M. Shah, "A hierarchical approach to robust background subtraction using color and gradient information," in Motion and Video Computing, 2002. Proceedings. Workshop on, 2002, pp. 22-27.
[4] A. Elgammal, R. Duraiswami, D. Harwood, and L. S. Davis, "Background and foreground modeling using nonparametric kernel density estimation for visual surveillance," Proceedings of the Ieee, vol. 90, pp. 1151-1163, Jul 2002.
[5] T. Meier and K. N. Ngan, "Automatic segmentation of moving objects for video object plane generation," Circuits and Systems for Video Technology, IEEE Transactions on, vol. 8, pp. 525-538, 1998.
[6] N. Ahuja and A. Briassouli, "Joint spatial and frequency domain motion analysis," in Automatic Face and Gesture Recognition, 2006. FGR 2006. 7th International Conference on, 2006, pp. 203-208.
[7] S. Birchfield, "Elliptical head tracking using intensity gradients and color histograms," in Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on, 1998, pp. 232-237.
[8] A. Cavallaro, O. Steiger, and T. Ebrahimi, "Tracking video objects in cluttered background," Circuits and Systems for Video Technology, IEEE Transactions on, vol. 15, pp. 575-584, 2005.
[9] S. A. El-Azim, I. Ismail, and H. A. El-Latiff, "An efficient object tracking technique using block-matching algorithm," in Radio Science Conference, 2002. (NRSC 2002). Proceedings of the Nineteenth National, 2002, pp. 427-433.
[10] Z. Xiaoqin, L. Zhiyong, and Q. Hong, "A Robust Multiple Cues Fusion based Bayesian Tracker," in Robotics and Automation, 2007 IEEE International Conference on, 2007, pp. 4614-4619.
[11] T. W. Yang, K. Zhu, Q. Q. Ruan, and J. D. Han, "Moving Target Tracking and Measurement with a Binocular Vision System," in Mechatronics and Machine Vision in Practice, 2008. M2VIP 2008. 15th International Conference on, 2008, pp. 85-91.
[12] T. Hayashi, S. Enokida, and T. Ejima, "A real-time target tracking method applicable to a robot's vision," in Robot and Human Interactive Communication, 2003. Proceedings. ROMAN 2003. The 12th IEEE International Workshop on, 2003, pp. 127-132.
[13] H. Kimura and H. Katano, "Vision-based motion recognition of the hexapod for autonomous assistance," in Intelligent Robots and Systems, 1998. Proceedings., 1998 IEEE/RSJ International Conference on, 1998, pp. 1-6 vol.1.
[14] S. Wybo, D. Tsishkou, C. Vestri, F. Abad, S. Bougnoux, and R. Bendahan, "Monocular vision obstacles detection for autonomous navigation," in Intelligent Robots and Systems, 2008. IROS 2008. IEEE/RSJ International Conference on, 2008, pp. 4190-4190.
[15] C. Diansheng, B. Feng, X. Yi, and W. Tianmiao, "Tracking system of motion object for scout robot," in Robotics and Biomimetics, 2008. ROBIO 2008. IEEE International Conference on, 2009, pp. 1111-1116.
[16] Y. Matsushita, K. Nishino, K. Ikeuchi, and M. Sakauchi, "Illumination normalization with time-dependent intrinsic images for video surveillance," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 26, pp. 1336-1347, 2004.
[17] I. Haritaoglu, D. Harwood, and L. S. Davis, "W⁴: real-time surveillance of people and their activities," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 22, pp. 809-830, 2000.
[18] A. J. Lipton, H. Fujiyoshi, and R. S. Patil, "Moving target classification and tracking from real-time video," in Applications of Computer Vision, 1998. WACV '98. Proceedings., Fourth IEEE Workshop on, 1998, pp. 8-14.
[19] J. Chamorro-Martinez and J. Fernandez-Valdivia, "A New Approach to Motion Pattern Recognition and Its Application to Optical Flow Estimation," Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 37, pp. 39-51, 2007.
[20] D. Meyer, J. Denzler, and H. Niemann, "Model based extraction of articulated objects in image sequences for gait analysis," in Image Processing, 1997. Proceedings., International Conference on, 1997, pp. 78-81 vol.3.
[21] C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," in Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., 1999, p. 252 Vol. 2.
[22] S.-C. Jeng, "A GMM-based Mehtod for Dynamic Background Image Model Construction with Shadow Removal," Department of Electrical and Control Engineering, National Chiao Tung University 2005.
[23] 鐘國亮, "影像處理與電腦視覺," 3rd ed: 東華書局，台北, 2006.
[24] L. G. Moshe Blank, Eli Shechtman, Michal Irani and Ronen Basri, "Actions as Space-Time Shapes," Appeared first in the Tenth IEEE International Conference on Computer Vision (ICCV), 2005.
[25] M. Kilger, "A shadow handler in a video-based real-time traffic monitoring system," in Applications of Computer Vision, Proceedings, 1992., IEEE Workshop on, 1992, pp. 11-18.
[26] N. Paragios and R. Deriche, "Geodesic active contours and level sets for the detection and tracking of moving objects," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 22, pp. 266-280, 2000.
[27] N. Peterfreund, "Robust tracking of position and velocity with Kalman snakes," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 21, pp. 564-569, 1999.
[28] A. Mohan, C. Papageorgiou, and T. Poggio, "Example-based object detection in images by components," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 23, pp. 349-361, 2001.
[29] R. Polana and R. Nelson, "Low level recognition of human motion (or how to get your man without finding his body parts)," in Motion of Non-Rigid and Articulated Objects, 1994., Proceedings of the 1994 IEEE Workshop on, 1994, pp. 77-82.
[30] G. Baugh and A. Kokaram, "Feature-based object modelling for visual surveillance," in Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on, 2008, pp. 1352-1355.
[31] C. Jia-Ching and J. M. F. Moura, "Capture and representation of human walking in live video sequences," Multimedia, IEEE Transactions on, vol. 1, pp. 144-156, 1999.
[32] W. F. Gardner and D. T. Lawton, "Interactive model-based vehicle tracking," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 18, pp. 1115-1121, 1996.
[33] S. X. Ju, M. J. Black, and Y. Yacoob, "Cardboard people: a parameterized model of articulated image motion," in Automatic Face and Gesture Recognition, 1996., Proceedings of the Second International Conference on, 1996, pp. 38-44.
[34] S. A. Niyogi and E. H. Adelson, "Analyzing and recognizing walking figures in XYT," in Computer Vision and Pattern Recognition, 1994. Proceedings CVPR '94., 1994 IEEE Computer Society Conference on, 1994, pp. 469-474.
[35] Y. Hao, L. Jianguang, S. Hongzan, H. Weiming, and T. Tieniu, "Efficient and robust vehicle localization," in Image Processing, 2001. Proceedings. 2001 International Conference on, 2001, pp. 355-358 vol.2.
[36] S. Kamijo, Y. Matsushita, K. Ikeuchi, and M. Sakauchi, "Occlusion robust vehicle tracking for behavior analysis utilizing spatio-temporal Markov random field model," in Intelligent Transportation Systems, 2000. Proceedings. 2000 IEEE, 2000, pp. 340-345.
[37] Y. Changjiang, R. Duraiswami, and L. Davis, "Efficient mean-shift tracking via a new similarity measure," in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, pp. 176-183 vol. 1.
[38] R. T. Collins, "Mean-shift blob tracking through scale space," in Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, 2003, pp. II-234-40 vol.2.
[39] D. Comaniciu and V. Ramesh, "Mean shift and optimal prediction for efficient object tracking," in Image Processing, 2000. Proceedings. 2000 International Conference on, 2000, pp. 70-73 vol.3.
[40] D. Comaniciu and P. Meer, "Mean shift analysis and applications," in Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, 1999, pp. 1197-1203 vol.2.
[41] D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 25, pp. 564-577, 2003.
[42] R. C. G. a. R. E. Woods, "Digital Image Processing," 2001.
[43] D.W. Scott, "Multivariate Density Estimation " New York: Wiley,, 1992.
[44] T. Kailath, "The Divergence and Bhattacharyya Distance Measures in Signal Selection," Communication Technology, IEEE Transactions on, vol. 15, pp. 52-60, 1967.
[45] K. Fukunaga and L. Hostetler, "The estimation of the gradient of a density function, with applications in pattern recognition," Information Theory, IEEE Transactions on, vol. 21, pp. 32-40, 1975.
[46] Y.-C. Chung, "A Real-Time Motion Detection and Tracking System in the Dynamic Background," Industrial Technology R & D Master Program on IC Design, National Chiao Tung University, 2007.
[47] D. Comaniciu, V. Ramesh, and P. Meer, "Real-time tracking of non-rigid objects using mean shift," in Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on, 2000, pp. 142-149 vol.2.