臺灣博碩士論文加值系統

物件追蹤在電腦視訊應用中是一個重要的主題。在本研究裡將提出一個由運動預測和增大物件視窗這兩個主要的程序結合而成的改良式平均位移演算法為基礎之足球運動追蹤系統，目的是能有效率並準確的追蹤球員。在本研究提出的系統中，選用了對球員最具代表性的顏色來記錄球員，遮蔽問題以及球員在畫面中的進出問題也將被偵測並處理。從實驗結果可得本研究提出之系統的追蹤結果及查全率和精確度比起另三個作為對照的系統為佳。

Object tracking is an important topic in computer vision applications. In this study, an improved mean shift algorithm based tracking system with motion prediction and object window enlarging for soccer game analysis is proposed. The objective of the proposed system is to track soccer players efficiently and accurately. Discriminative color selection for modeling soccer players is employed in the proposed system. Occlusions are well handled in the proposed system, whereas incoming and outgoing players are also detected and handled in the proposed system. Based on the experimental results obtained in this study, the tracking results as well as the recall and precision rates of the proposed system are better than those of the three comparison systems.

摘 要 i
ABSTRACT ii
ACKNOWLEDGMENTS iii
TABLE OF CONTENTS iv
LIST OF FIGURES vi

CHAPTER 1 INTRODUCTION 1
1.1 Motivation 1
1.2 Survey of Related Researches 3
1.3 Thesis Organization 7

CHAPTER 2 OBJECT TRACKING METHODS 8
2.1 Introduction to Object Tracking 8
2.2 Brute Force Searching 8
2.3 Particle Filter 9
2.4 Mean Shift Algorithm 12
2.5 Continuously Adaptive Mean Shift 16

CHAPTER 3 THE PROPOSED TRACKING SYSTEM 19
3.1 System Architecture 19
3.2 Initialization 20
3.3 Tracking 22
3.4 Occlusion Handling 29
3.5 Handling for Incoming and Outgoing Players 34

CHAPTER 4 EXPERIMENTAL RESULTS 37

CHAPTER 5 DISCUSSIONS AND CONCLUSIONS 70
5.1 Discussions 70
5.2 Conclusions 71

REFERENCES 72

[1] J. Zhou and J. Hoang, “Real time robust human detection and tracking system,” in Proc. IEEE Conf. on Comput. Vision Pattern Recognit., vol. 3, Jun. 2005, pp. 149.
[2] C. Hua, H. Wu, Q. Chen, and T. Wada, “A pixel-wise object tracking algorithm with target and background sample,” in Proc. IEEE Int. Conf. on Pattern Recognit., vol. 1, 2006, pp. 739-742.
[3] Q. Zhao, J. Kang, H. Tao, and W. Hua, “Part based human tracking in a multiple cues fusion framework,” in Proc. IEEE Int. Conf. on Pattern Recognit., vol. 1, 2006, pp. 450-455.
[4] K. Sato and J. K. Aggarwal, “Temporal spatio-velocity transform and its application to tracking and interaction,” Comput. Vision and Image Understanding, vol. 96, pp. 100-128, Nov. 2004.
[5] T. Yang, S. Z. Li, Q. Pan, and J. Li, “Real-time multiple objects tracking with occlusion handling in dynamic scenes,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., vol. 1, Jun. 2005, pp. 970-975.
[6] W. T. Chu, C. W. Wang, and J. L. Wu, “Extraction of baseball trajectory and physics-based validation for single-view baseball video sequences,” in Proc. IEEE Int. Conf. on Multimedia and Expo, Jul. 2006, pp. 1813-1816.
[7] L. Wu, X. Meng, X. Liu and S. Chen, “A new method of object segmentation in the basketball videos,” in Proc. IEEE Int. Conf. on Pattern Recognit., vol. 1, 2006, pp. 319-322.
[8] H. Miyamori and S. I. Iisaku, “Video annotation for content-based retrieval using human behavior analysis and domain knowledge,” in Proc. IEEE Int. Conf. on Autom. Face Gesture Recognit., Mar. 2000, pp. 320-325.
[9] M. Bertini, A. D. Bimbo, and W. Nunziati, “Model checking for detection of sports highlights,” in Proc. ACM Int. Workshop on Multimedia Inf. Retrieval, Nov. 2003, pp. 215-222.
[10] D. Reid, “An algorithm for tracking multiple targets,” IEEE Trans. on Autom. Control, vol. AC-24, no. 6, pp. 843-854, Dec. 1979.
[11] M. Han, A. Sethi, W. Hua, and Y. Gong, “A detection-based multiple object tracking method,” in Proc. IEEE Int. Conf. on Image Process., vol. 5, 2004, pp. 3065-3068.
[12] A. Mohan, C. Papageorgiou, and T. Poggio, “Example based object detection in images by components,” IEEE Trans. on Pattern Anal. Mach. Intell., vol. 23, no. 4, pp. 349-361, Apr. 2001.
[13] B. Wu and R. Nevatia, “Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors,” in Proc. IEEE Int. Conf. on Comput. Vision, vol. 1, Oct. 2005, pp. 90-97.
[14] S. J. McKenna, “Tracking groups of people,” Comput. Vision and Image Understanding, vol. 80, no. 1, pp. 42-56, Oct. 2000.
[15] D. S. Lee, “Effective Gaussian mixture learning for video background subtraction,” IEEE Trans. on Pattern Anal. Mach. Intell., vol. 27, no. 5, pp. 827-832, May 2005.
[16] J. Rittscher, J. Kato, S. Joga, and A. Blake, “A probabilistic background model for tracking,” in Proc. Eur. Conf. on Comput. Vision II, vol. 1843, Jan. 2000, pp. 336-350.
[17] N. M. Oliver, B. Rosario, and A. P. Pentland, “A Bayesian computer vision system for modeling human interactions,” IEEE Trans. on Pattern Anal. Mach. Intell., vol. 22, no. 8, pp. 831-843, Aug. 2000.
[18] A. Elgammal, R. Duraiswami, D. Harwood, and L. S. Davis, “Background and foreground modeling using nonparametric kernel density estimation for visual surveillance,” Proc. the IEEE, vol. 90, pp. 1151-1163, Jul. 2002.
[19] A. Yilmaz, O. Javed, and M. Shah, “Object tracking: a survey,” ACM Comput. Surv., vol. 38, no. 4, p. 13, 2006.
[20] P. Gabriel, J. –B. Hayet, J. Piater, and J. Verly, “Object tracking using color interest points,” in Proc. IEEE Conf. on Adv. Video and Signal Based Surveillance, Sept. 2005, pp. 159-164.
[21] C. J. Veenman, M. J. T. Reinders, and E. Backer, “Resolving motion correspondence for densely moving points,” IEEE Trans. on Pattern Anal. Mach. Intell., vol. 23, pp. 54-72, Jan. 2001.
[22] D. P. Huttenlocher, J. J. Noh, and W. J. Rucklidge, “Tracking non-rigid objects in complex scenes,” in Proc. IEEE Int. Conf. on Comput. Vision, May 1993, pp. 93-101.
[23] J. Kang, I. Cohen, and G. Medioni, “Object reacquisition using invariant appearance model,” in Proc. IEEE Int. Conf. on Pattern Recognit., vol. 4, Aug. 2004, pp. 759-762.
[24] H. Schweitzer, J. W. Bell, and F. Wu, “Very fast template matching,” in Proc. Eur. Conf. on Comput. Vision IV, 2002, pp. 358-372.
[25] A. Adam, E. Rivlin, and I. Shimshoni, “Robust fragments-based tracking using the integral histogram,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., vol. 1, Jun. 2006, pp. 798-805.
[26] F. Porikli, “Integral histogram: a fast way to extract histogram in Cartesian spaces,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., vol. 1, Jun. 2005, pp. 829-836.
[27] P. Fieguth and D. Terzopoulos, “Color-based tracking of heads and other mobile objects at video frame rates,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., Jun. 1997, pp. 21-27.
[28] Y. Rubner, C. Tomasi, and L. J. Guibas, “The earth mover’s distance as a metric for image retrieval,” Int. J. Comput. Vision, vol. 40, no. 2, pp. 99-121, Nov. 2000.
[29] M. Kristan, et al., “Multiple interacting targets tracking with application to team sport,” in Proc. IEEE Int. Conf. on Image and Signal Process. and Anal., Sept. 2005, pp. 322-327.
[30] S. Birchfield, “Elliptical head tracking using intensity gradients and color histograms,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., Jun. 1998, pp. 23-25.
[31] M. Isard and J. MacCormick, “BraMBLe: a Bayesian multiple-blob tracker,” in Proc. IEEE Int. Conf. on Comput. Vision, vol. 2, Jul. 2001, pp. 34-41.
[32] K. Nummiaro, E. Koller-Meier, and L. V. Gool, “An adaptive color-based particle filter,” Image and Vision Comput., vol. 21, no. 1, pp. 99-110, Jan. 2003.
[33] D. Comaniciu, V. Ramesh, and P. Meer, “Real-time tracking of non-rigid objects using mean shift,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., vol. 2, Jun. 2000, pp. 142-149.
[34] D. Comaniciu, V. Ramesh, and P. Meer, “Kernel-based object tracking,” IEEE Trans. on Pattern Anal. Mach. Intell., vol. 25, pp. 564-577, May 2003.
[35] Y. Jin and F. Mokhtarian, “Variational particle filter for multi-object tracking,” in Proc. IEEE Int. Conf. on Comput. Vision, Oct. 2007, pp. 1-8.
[36] R. R. Hwang and M. Huber, “A particle filter approach for multi-target tracking,” in Proc. IEEE Int. Conf. on Intell. Rob. Syst., Nov. 2007, pp. 2753-2760.
[37] R. T. Collins, “Mean-shift blob tracking through scale space,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., vol. 2, Jun. 2003, pp. 234-240.
[38] C. Yang, R. Duraiswami, and L. Davis, “Efficient mean-shift tracking via a new similarity measure,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., vol. 1, Jun. 2005, pp. 176-183.
[39] H. Guo, P. Guo, and H. Lu, “A fast mean shift procedure with new iteration strategy and re-sampling,” in Proc. IEEE Int. Conf. on Syst. Man Cybern., vol. 3, Oct. 2006, pp. 2385-2389.
[40] A. Yilmaz, “Object tracking by asymmetric kernel mean shift with automatic scale and orientation selection,” in Proc. IEEE Conf. on Comput. Vision and Pattern Recognit., Jun. 2007, pp. 1-6.
[41] C. Shan, Y. Wei, T. Tan, and F. Ojardias, “Real time hand tracking by combining particle filtering and mean shift,” in Proc. IEEE Int. Conf. on Autom. Face Gesture Recognit., May 2004, pp. 669-674.
[42] K. Bai and W. Liu, “Improved object tracking with particle filter and mean shift,” in Proc. IEEE Int. Conf. on Autom. Logistics, Aug. 2007, pp. 431-435.
[43] M. Isard and A. Blake, “Condensation – conditional density propagation for visual tracking,” Int. J. Comput. Vision, vol. 29, no. 1, pp. 5-28, Aug. 1998.
[44] K. Fukunaga and L. D. Hostetler, “The estimation of the gradient of a density function with applications in pattern recognition,” IEEE Trans. on Inf. Theory, vol. 21, pp. 32-40, Jan. 1975.
[45] Y. Cheng, “Mean shift, mode seeking, and clustering,” IEEE Trans. on Pattern Anal. Mach. Intell., vol. 17, pp. 790-799, Aug. 1995.
[46] D. Comaniciu and P. Meer, “Mean shift analysis and applications,” in Proc. IEEE Int. Conf. on Comput. Vision, vol. 2, Sept. 1999, pp. 1197-1203.
[47] D. Comaniciu and P. Meer, “Mean shift: a robust approach toward feature space analysis,” IEEE Trans. on Pattern Anal. Mach. Intell., vol. 24, pp. 603-619, May 2002.
[48] G. R. Bradski, “Computer vision face tracking for use in a perceptual user interface,” Intel Technol. J., vol. 2, pp. 12-21, 1998.
[49] G. R. Bradski, “Real time face and object tracking as a component of a perceptual user interface,” in Proc. IEEE Workshop on Appl. of Comput. Vision, Oct. 1998, pp. 214-219.
[50] Intel Corporation, “Open source computer vision library reference manual,” 2001.
[51] J. G. Allen, R. Y. D. Xu, and J. S. Jin, “Object tracking using CamShift algorithm and multiple quantized feature spaces,” in Proc. Pan-Sydney Area Workshop on Visual Inf. Process., 2004, pp. 3-7.
[52] H. Zhai, X. Wu, and H. Han, “Research of a real-time hand tracking system,” in Proc. IEEE Int. Conf. on Neural Network and Brain, vol. 2, Oct. 2005, pp. 1233-1235.
[53] O. –D. Nouar, G. Ali, and C. Raphael, “Improved object tracking with camshift algorithm,” in Proc. IEEE Int. Conf. on Acoust. Speech Signal Process., vol. 2, May 2006, pp. 657-660.
[54] H. Chu, S. Ye, Q. Guo, and X. Liu, “Object tracking algorithm based on camshaft algorithm combinating with difference in frame,” in Proc. IEEE Int. Conf. on Autom. Logistics, Aug. 2007, pp. 51-55.
[55] Q. Liu, C. Cai, K. N. Ngan, and H. Li, “Camshift based real-time multiple faces match tracking,” IEEE Int. Symp. Intell. Signal Process. Commun. Syst., Nov. 2007, pp. 726-729.
[56] J. H. Lee, W. H. Lee, and D. S. Jeong, “Object tracking method using back-projection of multiple color histogram models,” in Proc. IEEE Int. Symp. Circuits Syst., vol. 2, May, 2003, pp. 25-28.