臺灣博碩士論文加值系統

在這篇論文中，我建構了一個以機率資料連結(PDA)為基礎之影像追蹤系統。它能夠以大於每秒20次的速度在普通家用電腦上執行。此系統能夠在凌亂複雜的環境下追蹤目標物而不受干擾。為了能夠長時間的追蹤目標，同時為了能將視線對準目標物，它的相機是架設在一個可以俯仰和旋轉的平台上。此系統由兩個功能上相輔相成的單元所組成：其一為影像偵測單元，其二為影像追蹤單元。影像偵測單元的功能是在畫面中找出一群最可疑目標物，並將這群最可疑目標物的位置及特徵傳送給影像追蹤單元。影像追蹤單元再以機率資料連結的理論計算出真實目標物之最佳位置估測值。此最佳位置估測值再傳送給相機平台作為控制之依據。本論文除了上述影像追蹤之數學理論外，另以實作部分證實其可行性及可靠性。

1 INTRODUCTION3
1.1MOTIVATION3
1.2BRIEF LITERATURE REVIEW4
1.3CONTRIBUTIONS5
1.4THESIS ORGANIZATION6
2 PRELIMINARIES8
2.1ARCHITECTURE OVERVIEW8
2.2SYSTEM MODEL AND COORDINATE TRANSFORMATIONS9
3 REAL-TIME TARGET DETECTION13
3.1REAL-TIME TARGET DETECTOR COMPONENTS13
3.2MOTION DETECTION16
3.3GRADIENT EDGE DETECTOR19
3.4TEMPLATE MATCHING20
3.4.1Challenging the Basic Assumption of Template Matching21
3.4.2Generating the Set of Target Candidates23
3.5COLOR-POSITION CLASSIFICATION BY SUPPORT VECTOR MACHINE25
3.5.1Motivation25
3.5.2Previous Color Classification Systems25
3.5.3Support Vector Machines26
3.5.4The SVM Air Target Detection System30
4 DATA ASSOCIATION FOR TRAJECTORY ESTIMATION40
4.1ESTIMATION WITH DISCRETE KALMAN FILTER40
4.2THE NEAREST-NEIGHBOR STANDARD FILTER42
4.3THE PROBABILISTIC DATA ASSOCIATION FILTER43
4.3.1The Validation Region44
4.3.2The Stochastic Model45
5 THE VISUAL PROBABILISTIC DATA ASSOCIATION FILTER48
5.1COMPONENTS OF THE VPDA FILTER48
5.2INCORPORATING IMAGE FEATURES49
5.3PERSISTENT NOISE REMOVAL51
5.4MOTION CONTROL OF VISION PLATFORM60
6 EXPERIMENTS69
7 CONCLUSION AND FUTURE RESEARCH75
REFERENCES77

[1] Yalamanchili, S., W. N. Martin, and J. K. Aggarwal. “Extraction of moving object description via differencing,” CGIP, Vol. 18, pp.188-201, 1982.
[2] Lipton, A., H. Fujiyoshi, and R. Patil, "Moving Target Classification and Tracking from Real-time Video," Proc. of the DARPA Image Understanding Workshop, 1998.
[3] Brunelli, R., T. Poggio, “Template Matching: Matched Spatial Filters And Beyond,” MIT AI Memo 1549, July 1995.
[4] Lew, M.S., N. Sube, T.S. Huang, “Improving visual matching,” IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 58 —65, 2000.
[5] Kang, H. S., “Motion estimation algorithm with low complexity for video compression,” Electronics Letters, Vol. 36, pp. 1533 —1535, 2000.
[6] Chen, M. J., L. G. Chen, T. D. Chiueh, Y. P. Lee, “A new block-matching criterion for motion estimation and its implementation,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 5 No. 3, pp. 231 —236, 1995.
[7] Chen, Y. S., Y. P. Hung, and C. S. Fuh, “A Fast Block Matching Algorithm Based on the Winner-Update Strategy,” Proceedings of the Fourth Asian Conference on Computer Vision, Vol. 2, pp. 977-982, Jan. 2000.
[8] Bilal Ahmad, M., T. S. Choi, “Edge detection-based block motion estimation,” Electronics Letters, Vol. 37, No. 1,pp. 17-18, 2001.
[9] Cox, I.J., “A Review of Statistical Data Association Techniques for Motion Correspondence,” Intl. Journal of Computer Vision, Vol. 10, pp. 53-66, 1993.
[10] Bar-Shalom, Y., E. Tse, “Tracking in a Cluttered Environment with Probabilistic Data Association,” Automatica, Vol. 11, pp. 451-460, 1975.
[11] Bar-Shalom, Y., T. E. Fortmann, Tracking and Data Association, Academic Press, 1988.
[12] Fortmann, T.E., Y. Bar-Shalom, and M. Scheffe, “Sonar Tracking of Multiple Targets Using Joint Probabilistic Data Association,” IEEE Journal of Oceanic Engineering, Vol. 8, No. 3, 1983.
[13] Reid, D.B., “An Algorithm for Tracking Multiple Targets,” IEEE Trans. On Automatic Control, Vol. 24, No. 6, pp. 843-854, 1979.
[14] Deriche, R., O. Faugeras, “Tracking Line Segments,” European Conf. On Computer Vision, pp. 259-268, Springer-Verlag, 1990.
[15] Broida, T.J., S. Chandrashekhar, and R. Chellappa, “Recursive 3-d motion estimation from a monocular image sequence,” IEEE Trans. Aerospace and Electronic Systems, Vol.26, No. 4, pp.639-656, 1990.
[16] Minsky, M. L. Minsky, The Society of Mind. New York, NY: Simon and Schuster, 1986.
[17] Halevy, G., and D. Weinshall, “ Motion of Disturbances: Detection and Tracking of Multi-Body Non-Rigid Motion,” Machine Vision and Applications, Vol. 11, pp. 122-137, 1999.
[18] Haralick, R.M., and L.G. Shapiro, Computer and Robot Vision, Vol.1, Addison-Wesley Inc., 1992.
[19] Haworth, C., A.M. Peacock, D. Renshaw, “Performance of Reference Block Updating Techniques when Tracking with the Block Matching Algorithm,” to appear on Proc. Intl. Conf. Image Processing, 2001
[20] Goshtasby, A., “Template Matching in Rotated Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, No. 3, pp. 338-344, 1985.
[21] Caelli, T.M., Z.Q. Liu, “On the Minimum Number of Templates Required for Shift, Rotation and Size Invariant Pattern Recognition,” Pattern Recognition, pp. 205-216, 1988.
[22] Park, J., J. Seo, D. An, “Detection of human faces using skin color and eyes,” IEEE International Conference on Multimedia and Expo, Vol. 1, pp.133 -136, 2000.
[23] Yang, M. H., N. Ahuja, “Detecting human faces in color images,” International Conference on Image Processing, Vol. 1 , pp. 127-130, 1998.
[24] Yang, J., W. Lu, and A. Waibel, "Skin-color modeling and adaptation," Technical Report CMU-CS-97-146, CS department, CMU, 1997.
[25] Liu, J., and Y.H. Yang, “Multiresolution color image segmentation,” IEEE Trans. Pattern Anal. Mach. Intel., Vol.16, pp. 689-700, July 1994.
[26] Wren, C., A. Azarbayejani, T. Darrell, A. Pentland, “Pfinder: Real-Time Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No.7, pp. 780-785, 1997.
[27] Saber, E., A.M. Tekalp, “Integration of color, shape, and texture for automatic image annotation and retrieval," J. Electronic Imaging (special issue), Vol. 7, No. 3, pp. 684-700, 1998.
[28] Vapnik, V. N., Statistical Learning Theory, John Wiley & Sons, Inc., 1998.
[29] Cortes, C., V. Vapnik, “Support vector networks,” Machine Learning, Vol. 20, pp. 273—297, 1995.
[30] Cover, T.M., “Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition,” IEEE Transactions on Electronic Computers, EC-14, pp. 326-334, 1965.
[31] Osuna, E. E., “Support Vector Machines: Training and Applications,” Ph.D. thesis, Dept. of EECS, Massachusetts Institute of Technology, 1998.
[32] Nelson, B., N.P. Papanikolopolous, and P. Khosla, "Visual Servoing for Robotic Assembly," Visual Servoing Real-Time Control of Robot Manipulators Based on Visual Sensory Feedback, K. Hashimoto, ed., World Scientific Publishing, River Edge, NJ, 1993, pp. 139 - 164.
[33] Papanikolopoulos, N. P., and P. K. Khosla, “Adaptive Robotic Visual Tracking: Theory and Experiments,” IEEE Trans. Automatic Control, Vol. 38, No. 3, pp. 429-445, Mar 1993.
[34] Feddema, J. T., C. S. G. Lee, “Adaptive image feature prediction and control for visual tracking,” IEEE Trans. Systems, Man and Cybernetics, Vol. 20, No. 5, pp. 1172-1183, 1990.
[35] Feddema, J. T., C. S. G. Lee, “Adaptive image feature prediction and control for visual tracking with a moving camera,” Proc. IEEE Int. Conf. Systems, Man and Cybernetics, pp. 20-24, Nov 1990.
[36] Chiou, W. G., “Design and Implementation of Visual Servoing System for Realistic Air Target Tracking,” Master Thesis, Dept. of Electrical Eng., National Taiwan University, 2000.
[37] Colegrove, S. B., and S. J. Davey, “The Probabilistic Data Association Filter with Multiple Nonuniform Clutter Regions,” IEEE Int. Radar Conf., pp. 65-70, 2000.
[38] Boshra, M., and B. Bhanu, “Predicting Performance of Object Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 22, No. 9, pp. 956-969, 2000.
[39] Sarachik, K. B,, “The Effect of Gaussian Error in Object Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 4, pp. 289-301, 1997.
[40] Chen, J., H. Leung, T. Lo, J. Litva, M. Blanchette, “A Modified Probabilistic Data Association in a Real Clutter Environment,” IEEE Trans. Aerospace and Electronic Systems, Vol. 32, No. 1, pp. 300-313, 1996.
[41] Liu, D., L. C. Fu, T. K. Kuo, J. W. Yeh, “PDA Filter Based on the Winner-Update Strategy for Visual Tracking,” Vol. 1, pp. 13-17, R.O.C. Conference on Automatic Control, 2001. (First Prize Student Paper Award)
[42] Slotine, J. J., W. Li, Applied Nonlinear Control, 1st Ed., Prentice Hall, 1991.
[43] Emerson Inc., E-Series Drives Reference Manual, Rev. A3, May 9, 2000.
[44] Ridler, T. W., S. Calvard, “Picture Thresholding using an Iterative Selection Method,” IEEE Trans. Systems, Man and Cybernetics, Vol. 8, No. 8, pp. 630-632, 1978.
[45] Liu, D. and L. C. Fu, “Target Tracking in an Environment of Nearly Stationary and Biased Clutter,” to appear on IEEE International Conference on Intelligent Robots and Systems, 2001.