即時目標影像追蹤對於機器人視覺、監控系統等工業應用極為重要，因此本論文提出一種以粒子群聚最佳化演算法(Particle Swarm Optimization, PSO)為基礎之多目標物體追蹤法。作法上係以待追蹤物體之灰階直方圖做為物體的特徵，並產生多個粒子群體，再利用各個粒子所選取到之影像區間的灰階直方圖與目標物的灰階直方圖之差距作為適應值，利用PSO演算法具有記憶及全域搜尋和同步處理等優點，來搜尋各個目標物體。由於直方圖建模是由其目標物體影像大小來做建模，但是當目標物體因尺度(scale)變化時，其直方圖便不會跟著尺度變化而改變，所以會造成追蹤錯誤，因此本文將利用影像中之加速穩健特徵(Speeded Up Robust Features, SURF)，在PSO演算法中嵌入SURF演算法以提取目標物體影像並重新建模取得直方圖，使得PSO不會因為目標物體因尺度變化時得到錯誤的直方圖，而造成追蹤錯誤。

This paper presents a particle swarm optimization (PSO) based approach for multiple object tracking based on histogram matching. To start with, gray-level histograms are calculated to establish feature model for each of the target object. The difference between the gray-level histogram corresponding to each particle in the search space and the target object is used as the fitness value of the PSO algorithm. Multiple swarms are created, depending on the number of the target objects under tracking. Because of the efficiency and simplicity of the PSO algorithm for global optimization, target objects can be tracked as iterations continue. Experimental results confirm that the proposed PSO algorithm can rapidly converge, allowing real-time tracking of each target object. It is observed that tracking performance based on histogram modeling seriously deteriorates if the image size of the target objects varies in scale. To solve this problem, Speeded Up Robust Features (SURF) is embedded into the tracking algorithm extract the accurate position of the target objects in the image, where histogram models of the target objects are re-generated for tracking during the evolution of the PSO algorithm. As a result, tracking performance is significantly improves, as demonstrated in the experimental results.

[1]http://140.113.87.112/vol_2/skill_6.htm
[2]Ernesto Luiz Andrade, John Charles Woods, Ekram Khan, and Mohammed Ghanbari, “Region-Based Analysis and Retrieval for Tracking of Semantic Objects and Provision of Augmented Information in Interactive Sport Scenes,” IEEE Transactions on Multimedia, vol. 7, no. 6, pp. 1084-1096, 2005.
[3]Surendra Gupte, Osama Masoud, Robert F. K. Martin, and Nikolaos P. Papanikolopoulos, “Detection and Classification of Vehicles,” IEEE Teansacyions on Intelligent Transportation Systems, vol. 3, no. 1, 2002.
[4]Hamed Kiani Galoogahi, “Tracking Groups of People in Presence of Occlusion,” Fourth Pacific-Rim Symposium on Image and Video Technology, pp. 438-443, Nov. 2010.
[5]Hironobu Fujiyoshi and Alan J. Lipton, “Tracking Groups of People in Presence of Occlusion,” Proceedings Fourth IEEE Workshop on Applications of Computer Vision, pp. 15-21, Oct. 1998.
[6]Nikos Paragios and Rachid Deriche, “Geodesic active contours and level sets for the detection and tracking of moving objects,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 3, pp. 266-280, Mar. 2000.
[7]Tomoaki Kobayashi, Keita Nakagawa, Joe Imae and Guisheng Zhai, “Real time object tracking on video image sequence using particle swarm optimization,” International Conference on Control, Automation and Systems, pp. 1773-1778, Oct. 2007.
[8]I. A. Karaulova, P. M. Hall, and A. D. Marshall, “A hierarchical model of dynamics for tracking people with a single video camera,” In Proc. British Machine Vision, pp. 262–352, 2000.
[9] Fukunaga, Keinosuke, Larry 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.
[10]Veronica Vilaplana and Ferran Marques, “The estimation of the gradient of a density function, with applications in pattern recognition,” 15th IEEE International Conference on Image Processing, pp. 2712-2715, Oct. 2008.
[11]Katja Nummiaro, Esther Koller-Meier and Luc Van Gool, “An Adaptive Color-Based Particle Filter,” Image and Vision Computing, vol. 21, pp. 99-110, 2003.
[12]Fukunaga, Keinosuke, Larry 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.
[13]J. Kennedy and R. C. Eberhart, “Particle Swarm Optimization,” Proc. IEEE Int. Conf. Neural Network, Piscataway , vol. 4, pp. 1942-1948, 1995.
[14]H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded up robust features,” Proceedings of European Conference on Computer Vision, pp. 404-417, 2006.
[15]P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features, ” Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1403-14102, 2003.
[16]吳怡明，手勢辨識應用於遙控音樂播放系統， 國立台灣科技大學電機工程系碩士論文，2010年。
[17]韓承翰，以降維SURF為基礎的手勢辨識，國立台灣科技大學碩士電機工程系碩士論文，2010年。
[18]李和謙，應用溫度層技術之人臉辨識系統設計，國立台灣師範大學工業教育系碩士論文，2011年。
[19]鄭明育，演化式物體影像追蹤與傾斜定位，淡江大學電機工程學系碩士論文，2008年。
[20]Yuhua Zheng and Yan Meng, “Swarm intelligence based dynamic object tracking,” IEEE Congress on Evolutionary Computation, pp. 405-412, 2008.
[21]Zwe-Lee Gaing, “A particle swarm optimization approach for optimum design of PID controller in AVR system,” IEEE Transactions on Energy Conversion, vol. 19, no. 2, pp. 384-391, June. 2004.
[22]Maurice Clerc and James Kennedy, “The Particle Swarm Explosion, Stability, and Convergence in a Multidimensional Complex Space,” IEEE Transactions on Evolutionary Computation, vol. 6, no. 6, pp. 58-73, Fed. 2002.
[23]Xiaoqin Zhang, Weiming Hu, Wei Qu, Steve Maybank, “Multiple Object Tracking Via Species-Based Particle Swarm Optimization,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 20, no. 11, pp. 1590-1602, Nov. 2010.
[24]Payam Saisan, Swarup Medasani, and Yuri Owechko, “Multi-View Classifier Swarms for Pedestrian Detection and Tracking,” IEEE Computer Society Conference on omputer Vision and Pattern Recognition, pp. 18, June. 2005.
[25]Jung Uk Cho, Seung Hun Jin, Xuan Dai Pham, and Jae Wook Jeon, “Multiple Objects Tracking Circuit using Particle Filters with Multiple Features,” IEEE International Conference on Robotics and Automation, pp. 4639-4644, April. 2007.
[26]Wei He, Takayoshi Yamashita, Hongtao Lu, and Shihong Lao, “SURF Tracking,” IEEE 12th International Conference on Computer Vision, pp. 1586-1592, Oct. 2009.
[27]Jing Wen, Xinbo Gao, Xuelong Li, Dacheng Tao, “Incremental Learning of Weighted Tensor Subspace for Visual Tracking,” SMC 2009 IEEE International on Systems, Man and Cybernetics, pp. 3688-3693, Oct. 2009.
[28]Myo Thida, Paolo Remagnino, and How-lung Eng, “A particle swarm optimization approach for multi-objects tracking in crowded scene,” IEEE 12th International Conference on Computer Vision Workshops, pp. 1209-1215, Oct. 2009.
[29]Ying Fang, Huiyuan Wang, Shuang Mao, and Xiaojuan Wu, “Multi-object Tracking Based on Region Corresponding and Improved Color-Histogram Matching,” IEEE International Symposium on Signal Processing and Information Technology, pp. 1-4, Dec. 2007.
[30]Saira Saleem Pathan, Ayoub Al-Hamadi, and Bernd Michaelis, “Intelligent Feature-guided Multi-object Tracking Using Kalman Filter,” International Conference on Computer, Control and Communication, pp. 1-6, Feb. 2009.
[31]Jung Uk Cho, Seung Hun Jin, Xuan Dai Pham, and Jae Wook Jeon, “IMultiple Objects Tracking Circuit using Particle Filters with Multiple Features,” IEEE International Conference on Robotics and Automation, pp. 4639-4644, April. 2007.
[32]D.G.Lowe, “Object recognition from local scale-invariant,” International Conference of Computer Vision, vol. 60, pp. 1150-1157, 1999.
[33]劉韋辰，基於FPGA之單移動目標物 歷史軌跡方向即時辨識系統，國立台灣師範大學應用電子科技學系系碩士論文，2011年。
[34]翁志維，嵌設有NM區域搜尋法之多目標粒子群聚最佳化法及其在最佳PID控制器設計之應用，江大學電機工程學系碩士論文，2010年。