摘要
監視系統以及數位影像處理技術日益普及，即時監視系統成為重要的研究目標。本論文提出應用粒子濾波器與最佳估測技術於目標追蹤系統，並以影像處理技術作為量測方法，最佳估測技術則應用卡門濾波器，在影像追蹤時結合卡門濾波器及粒子濾波器技術， 本論文需要許多的影像處理技術做前置處理。在一般視覺影像下，影像很容易因為光照變化的影響，而改變目標的色彩特徵，本論文提出利用色彩空間轉換的方法，將原先RGB色彩空間轉換為HSV色彩空間，利用HSV色彩空間的特性以降低陰影的干擾，及光照變化所產生的影響。本文亦提出以動態調整偵測區域的具適應性濾波器方法來量測各種不同條件下的目標追蹤，實驗結果證實本文所提出的方法具有足夠的準確度，其適應性可以克服目標追蹤的問題，本研究所設計的追蹤系統可提升量測的準確度。

Because the surveillance system and the digital image processing technology is more popular today, therefore the real-time surveillance system has become an important research topic. In this dissertation, the particle filter algorithm and optimal estimation technology are applied to object tracking system. The system also uses image processing technology to process the object image. The Kalman filter is applied to make optimal estimation. This study combines some algorithms which include Kalman filter, particle filter, and image processing for solving object estimation and tracking problems. A set of image sequences from video views are applied to evaluate performance. In general, the color characteristic of image is easy to change because of the impact of illumination. Therefore, this dissertation proposed a method by using the color space transformation. In order to reduce the effect of shadow and impact of changing illumination, the RGB color space is transferred to HSV color space in this algorithm. Based on the experimental result, it indicates the proposed approach successfully tracks objects and the performance efficiency can be enhanced by using the proposed algorithm.

摘要 i
ABSTRACT ii
ACKNOLOGYMENT iii
TABLE OF CONTENTS iv
LIST OF FIGURES v

CHAPTER 1 INTRODUCTION 1
1. 1 Background and motivation 1
1. 2 Research contributions 3
1. 3 Dissertation contents 3
CHAPTER 2 IMAGE PROCESSING TECHNOLOGY 5
2. 1 Color space 6
2. 2 Image binarization 9
2. 3 Morphological algorithm 11
2. 4 Image filter 17
CHAPTER 3 OPTIMAL ESTIMATION ALGORITHM AND PARTICLE FILTER 19
3. 1 Optimal estimation algorithm 19
3. 2 Particle filter 23
CHAPTER 4 EXPERIMENTAL RESULTS AND ANALYSIS 29
4. 1 Object extract 29
4. 2 Experiment results 33
CHAPTER 5 CONCLUSIONS AND FUTURE WORK 39
5. 1 Conclusions 39
5. 2 Future work 39
REFERENCES 41

[1] Pushe Zhao, Hongbo Zhu, He Li, and Tadashi Shibata, “A Directional-Edge-Based Real-Time Object Tracking System Employing Multiple Candidate-Location Generation,” Transactions on Circuits and Systems for Systems for Video Technology, Vol. 23, No. 3, pp.503-517, March 2013.
[2] Chunlin Jiao, Mantun Gao, Yikai Shi, “Color Image Segmentation in a Novel Dynamic Color Space,” Proceedings of the 7th World Congress on Intelligent Control and Automation, Chongqing, China, pp. 5922 - 5927, June 2008.
[3] Jia Huajie, Wang Lichun, Sun Yanfeng, Hu Yongli, “Color Face Recognition Based on Color Space Normalization and Quaternion Matrix Representation,” Fourth International Conference on Digital Home, pp.133-137, 2012.
[4] Mohonder S. Grewal, Angus P. Andrews, Kalman Filtering: Theory and Practice with Matlab, John Wiley, 1993。
[5] Y. Bar-Shalom, and T.E. Formann, Tracking and Data Association, Artech House, 1988.
[6] Pau-Choo Chung, Ching-Tsorng Tsai, E-Ling Chen, and Yung-Nien Sun, “Polygonal Approximation Using A Competitive Hopfield Neural Network,” Patten Recognition, Vol. 27, No.11, pp.1505-1215, 1994.
[7] Franz Pernkopf, “Tracking of Multiple Targets Using Online Learning for Reference Model Adaptation,” IEEE Transactions on systems, Man, and Cybernetics-Part B: Cybernetics, Vol. 38, No. 6, pp. 1465-1475, December 2008.
[8] Matej Kristan, Stanislav Kovacic, Aleš Leonardis, and Janez Perš, “A Two-Stage Dynamic Model for Visual Tracking,” IEEE Transactions on systems, Man, and Cybernetics-Part B: Cybernetics, Vol. 40, No. 6, pp.1505-1520, December 2010.
[9] Zulfiqar Hasan Khan, Irene Yu-Hua Gu, and Andrew G. Backhouse, “Robust Visual Object Tracking Using Multi-Mode Anisotropic Mean Shift and Particle Filters,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 21, No. 1, 74-87, January 2011.
[10] Zsolt L. Husz, Andrew M. Wallace, and Patrick R. Green, “Tracking with a Hierarchical Partitioned Particle Filter and Movement Modeling,” IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, Vol. 41, No. 6, pp.1571-1584, December 2011.
[11] Hong Qin, Shoujue Wang, Huaxiang Lu, and Xinliang Chen, “Human-Inspired Order-based Block Feature in the HSI Color Space for Image Retrieval,” Proceedings of the 2009 IEEE International Conference on Robotics and Biomimetics, pp.1978-1982, December 2009.
[12] Wei-Ta Chen, Wei-Chuan Liu, and Ming-Syan Chen, Fellow, “Adaptive Color Feature Extraction Based on Image Color Distributions,” IEEE Transaction on Image Processing, Vol. 19, No. 8, pp.2005-2016, August 2010.
[13] Horng-Horng Lin, Tyng-Luh Liu, and Jen-Hui Chuang, “Learning a Scene Background Model via Classification,” IEEE Transactions on Signal Processing, Vol. 57, No. 5, pp.1641-1654, May 2009.
[14] J. Mike McHugh, Janusz Konrad, Fellow, Venkatesh Saligrama, and Pierre-Marc Jodoin, “Foreground-Adaptive Background Subtraction,” IEEE Signal Processing Letters, Vol. 16, No. 5, pp.390-393, May 2009.
[15] Jung Uk Cho, Seung Hun Jin, Xuan Dai Pham, Dongkyun Kim, and Jae Wook Jeon, “A Real-Time Color Feature Tracking System Using Color Histograms,” International Conference on Control, Automation and Systems, pp.1163-1167, October 2007.
[16] Wang Weihua, He Yan, Li Zhijun, and Chen Zengping, “A Real-time Target Detection Algorithm for Infrared Search and Track System Based on ROI Extraction,” National University of Defense Technology Changsha, China, pp.774-778, August 2012.
[17] Vincent Garcia, E´ric Debreuve, and Michel Barlaud, “Region-of –interest Tracking Based on Key Point Trajectories on a Group of Pictures,” International Workshop on Content-Based Multimedia Indexing, CBMI '07, pp.198-203, June 2007.
[18] Li Xu, Jiaya Jia, and Yasuyuki Matsushita, “Motion Detail Preserving Optical Flow Estimation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No. 9, pp.1293-1300, September 2012.
[19] Xiaojing Song, Lakmal D. Seneviratne, and Kaspar Althoefer, “A Kalman Filter-Integrated Optical Flow Method for Velocity Sensing of Mobile Robots,” IEEE/ASME Transactions on Mechatronics, Vol. 16, No. 3, pp.551-563, June 2011.
[20] Rouhollah Dianat and Shohreh Kasaei, “Change Detection in Optical Remote Sensing Images Using Difference-Based Methods and Spatial Information,” IEEE Geoscience and Remote Sensing Letters, Vol. 7, No. 1, pp.215-219, January 2010.
[21] Wonjun Kim, and Changick Kim, “Background Subtraction for Dynamic Texture Scenes Using Fuzzy Color Histograms,” IEEE Signal Processing Letters, Vol. 19, No. 3, pp.127-130, March 2012.
[22] Bohyung Han, and Larry S. Davis, “Density-Based Multifeature Background Subtraction with Support Vector Machine,” IEEE Transactions on Pattern analysis and Machine Intelligence, Vol. 34, No. 5, pp.1017-1023, May 2012.
[23] Stephen S. Wilson, “Theory of Matrix Morphology,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 6, pp.636-652, June 1992.
[24] Takeshi Ikenaga, and Takeshi Ogura, “Real-Time Morphology Processing Using Highly Parallel 2-D Cellular Automata CAM,” IEEE Transactions on Image Processing, Vol. 9, No. 12, pp.2018-2026, December 2000.
[25] Jun Zhou, Kui Li, Ting-qi Wang, “Algorithm of Compensating Loss of Round Color Mark Based on Circle Fitting,” Proceedings of the IEEE International Conference on Mechatronics & Automation Niagara Falls, Canada, Vol. 3, pp.1397-1401, July 2005.
[26] Junliang Xing, Haizhou Ai, Liwei Liu, and Shihong Lao, “Multiple Player Tracking in Sports Video: A Dual-Mode Two-Way Bayesian Inference Approach with Progressive Observation Modeling,” IEEE Transactions on Image Processing, Vol. 20, No. 6, pp.1652-1667, June 2011.
[27] Ning Yang, Bin Ding, Jiaming Zhang, “Improved Sampling Importance Resampling Particle Filter Optimized by Tabu Search,” International Conference on Artificial Intelligence and Computational Intelligence, pp.359-363, October 2010.
[28] Xiuzhi Li, Songmin Jia, and Wei Cui, “On Sample Diversity in Particle Filter based Robot SLAM,” International Conference on Robotics and Biomimetics, IEEE, pp.1072-1077, December 2011.
[29] S. O. Warner and B. L. Smith, “Autocorrelation-based Estimate of Particle Image Density for Diffraction Limited Particle Images,” Measurement Science and Technology, Vol. 25, No. 6, 065201, pp. 1-10, April 2014.
[30] H. T. Huang, H. E. Fiedler, and J. J. Wang, “Limitation and Improvement of PIV Part II: Particle Image Distortion, a Novel Technique,” Experiments in Fluids, Vol. 15, Issue 4, pp. 263-273, Sep. 1993.
[31] J. Zhao, Y. Heng, X. Gu, and S. Wang, “The Edge Detection of River Model Based on Self-Adaptive Canny Algorithm and Connected Domain Segmentation,” 2010 8th World Congress. Intelligent Control and Automation (WCICA), pp. 1333-1336, July 2010.
[32] R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital Image Processing Using MATLAB, 2nd edition, Gatesmark Publishing, 2009.
[33] J. C. Russ, The Image Processing Handbook, CRC press, 3rd edition, 1998.
[34] S. Singh, A. Godara, and Gaurav, “Detection of Partial Invisible Objects in Images using Histogram Equalization,” International Journal of Computer Applications, Vol. 85, No. 9, pp. 40-44, Jan. 2014.
[35] J. S. Lim, Two-Dimensional Signal and Image Processing, Prentice Hall PTR, Englewood Cliffs, NJ, pp. 536-540, 1990.
[36] I. T. Young, J. J. Gerbrands, L. J. van Vliet, Fundamentals of Image Processing, Delft University of Technology, Version 2.3, 2007.
[37] H. Hatze, “High-precision Three-dimensional Photogrammetric Calibration and Object Space Reconstruction Using a Modified DLT-approach,” Journal of Biomechanics, Vol. 21, No. 7, pp. 533-538, 1988.
[38] I. Yoon, S. Kim, D. Kim, M. H. Hayes, and J. Paik, “Adaptive Defogging with Color Correction in the HSV Color Space for Consumer Surveillance System,” IEEE Transactions on Consumer Electronics, Vol. 58, No. 1, pp. 111 – 116, Feb. 2012.
[39] H. T. Niknejad, A. Takeuchi, S. Mita, and D. McAllester, “On-Road Multivehicle Tracking Using Deformable Object Model and Particle Filter with Improved Likelihood Estimation,” IEEE Transactions on Intelligent Transportation Systems, Vol. 13, No. 2, pp. 748-758, June 2012.
[40] H. Qin, S. Wang, H. Lu, and X. Chen, “Human-Inspired Order-based Block Feature in the HSI Color Space for Image Retrieval,” Proceedings of the 2009 IEEE International Conference on Robotics and Biomimetics, pp. 1978-1982, Dec. 2009.
[41] W. T. Chen, W. C. Liu, and M. S. Chen, “Adaptive Color Feature Extraction Based on Image Color Distributions,” IEEE Transaction on Image Processing, Vol. 19, No. 8, pp. 2005-2016, Aug. 2010.
[42] P. Gamba, M. Lilla, and A. Mecocci, “A Fast Algorithm for Target Shadow Removal in Monocular Color Sequences,” Proc. Of Int’l Conf. On Image Processing, Vol.1, pp. 436-447, Oct. 1997.
[43] S. Zhu and L. Ma, “An Adaptive Shadow Elimination Algorithm Using Shadow Position and Edges Attributes,” 2010 3rd International Congress on Image and Signal Processing (CISP2010), pp. 77-80, Oct. 2010.
[44] R. Cucchiara, C. Grana, M. Piccardi, A. Prati, and S. Sirotti, “Improving Shadow Suppression in Moving Object Detection with HSV Color Information”, Proceedings of IEEE Intelligent Transportation Systems, pp. 334 - 339, Aug. 2001.
[45] S. Singh and T. Patnaik, “An Efficient Shadow Removal Method Using HSV Color Space for Video Surveillance,” 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 1454-1460, Aug. 2015.
[46] L. W. Tsai, J. W. Hsieh, and K. C. Fan, “Vehicle Detection Using Normalized Color and Edge Map,” IEEE Transactions on Image Processing, Vol. 16, No. 3, pp. 850-864, March 2007.
[47] B. Zhang, “Reliable Classification of Vehicle Types Based on Cascade Classifier Ensembles,” IEEE Transactions on Intelligent Transportation Systems, Vol. 14, No. 1, pp. 322-332, March 2013.
[48] Q. Tian, T. Zhong, and H. Li, “A New Method for Vehicle Detection Using Mexican Hat Wavelet and Moment Invariants,” IEEE Workshop on Signal Processing Systems (SiPS), pp. 289-294, Oct. 2013.
[49] 朱志宇，粒子濾波算法及其應用，科學出版社，2010。
[50] 胡士強，粒子濾波原理及其應用，科學出版社，2010。
[51] 連國珍，數位影像處理，儒林書局， 2008。
[52] Ming-Tsung Yeh, Tun-Chang Lu, Chao-Hsing Hsu, Yu-Xian Huang, Long-Yi Chang, and Yi-Nung Chung. “Applying an Adjustable Image Color System to Track Multiple Crossing Objects,” ICIC Express Letters, 7(5), pp.1023-1030, 2016.
[53] Yi-Nung Chung, Tun-Chang Lu, Chao-Hsing Hsu, and Shu-Yu Wu. “Applying Real Time Image Recognition Technology to Apartment Park Lot Security System,” ICIC Express Letters, 10(4), pp. 877-882, 2016.
[54] Yi-Nung Chung, Tun-Chang Lu, Ming-Tsung Yeh, Yu-Xian Huang, and Chun-Yi Wu, “Applying the Video Summarization Algorithm to Surveillance Systems,” Journal of Image and Graphics, Vol. 3, Number 1, pp. 20-24, 2015.
[55] Yi-Nung Chung, Ming-Tsung Yeh, Tun-Chang Lu, Chao-Hhsing Hsu, and Yu-Xian Huang. “Applying a Novel Overlap Splitting Method and Wavelet Transformation to Vehicle Detection,” ICIC Express Letters, Vol. 9, Number 10, pp. 2873-2878, 2015.
[56] Tun-Chang Lu, Shun-Peng Hsu, Yu-Xian Huang, Yi-Nung Chung, and Shi-Ming Chen, “Applying Particle Filter Technology to Object Tracking,” Lecture Note in Electrical Engineering, Vol. 345, pp.105-111, 2014.
[57] Yi-Nung Chung, “Applying Image Processing and Neural Network Techniques to Data Association Algorithm,” International Journal of Innovative Computing, Information and Control,” International Journal of Innovative Computing, Information and Control, Volume 7, Number 5(A), May 2011, pp. 2427-2440, 2011.
[58] Joy Iong-Zong Chen, Yi-Nung Chung, “A Data Fusion Methodology for Wireless Sensor Systems,” International Journal of Computers Communications & Control, Vol. VII, No.1, pp.39-52, March. 2012.