臺灣博碩士論文加值系統

隨著安全與隱私的日漸重視，視訊監控的需求也日漸增加。而在監控系統中，最基礎也最重要的是物件偵測技術，尤其是在很複雜繁忙的環境下。本論文提出一種無建背景式即時物件向量偵測演算法，並將所提出的演算法移植至低成本的DSP嵌入式平台，以及將其延伸應用，發展成人行計數系統。此向量偵測方法主要在於利用三步搜尋法來指定方向的向量，並且再透過新的向量分析演算法來分析。若是有物件順著我們指定的方向穿越過我們事先定義的閘門，我們的系統將會偵測出此物件。此外我們也改進與最佳化此向量偵測演算法，然後移植至德州儀器公司的Davinci DM6446和DM DSP EVM。在最後我們也將此方法擴展應用，此方法配合其他像是3 successive-frames differencing等演算法來建構出人行計數系統。在實驗結果中可看出我們所提出的方法能即時運行，而且也具有相當高的偵測準確率。

To ensure public and private safety and security, the demand of intelligent video surveillance has become overwhelmingly increasing. One of the fundamental and important processes of the surveillance system is motion detection especially under very complex situations. The objective of this thesis is to present a non-background motion based object detection algorithm, and to implement the proposed algorithm on a low-cost DSP platform and to extend it to the application of people counting. The proposed motion detection method convolves the estimation of the appointed motion with three step search and motion analysis by a novel motion vector analysis algorithm to detect moving objects passing through a pre-defined gate along the desired direction. We further improve and optimize this motion detection algorithm, and then implement it on TI Davinci DM6446 and DM6437 DSP EVM boards. Besides, in the last part for this thesis shows the extended application of people counting on PC by this algorithm along with 3 successive-frames differencing method and others. The experimental results reveal that the final system works in real-time and performs excellent correct detection accuracy.

Abstract i
Acknowledgements ii
Contents iii
1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.3 Thesis Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2 Literature Survey 4
3 Motion Detection with Motion Vector Analysis 8
3.1 Motion Estimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.2 Motion Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .. . . . 14
4 System Architecture and Implementation 17
4.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.2 Optimization Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .18
4.2.1 Compiler Level . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .20
4.2.2 Floating Point Operation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .21
4.2.3 Loop Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
4.2.4 Intrinsic Functions and Packing Data . . . . . . . . . . . . . . . . . . . . . . . .22
4.2.5 Memory Access Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
4.2.6 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .24
4.3 Implementation on TI DM6446 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .25
5 The Extended Application of People Counting 27
5.1 Object Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
5.1.1 3-Successive Video Frames Differencing and Fusion . . . . . . . . . . . 28
5.1.2 Hole Filling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
5.1.3 Separation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
5.2 Object Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
6 Experimental Results 38
6.1 Implementation Results on TI DM6446 . . . . . . . . . . . . . . . . . . . . . . . .38
6.2 Result of People Counting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
7 Conclusion and Future Work 45
Bibliography 46

[1] Texas Instruments. sprue66c-DVEVM Getting Started Guide, March 2007.
[2] Texas Instruments Incorporated. TMS320C6000 Optimization Workshop, August 2005.
[3] Texas Instruments Incorporated. DM644x davinci technology workshop, February 2007.
[4] Cheng-Hui Wu. An Efficient Moving Shadow Removal Algorithm and Its Application of Traffic Flow Detection. 2009.
[5] C.R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland. Pfinder: Real-Time
Tracking of the Human Body. 19:780-785, 1997.
[6] C. Stauffer and W.E.L. Grimson. Adaptive background mixture models for real-time tracking. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:246-252, 1999.
[7] A.L. Hironobu, A.J. Lipton, H. Fujiyoshi, and R.S. Patil. Moving Target Classification and Tracking From Real-Time Video. 1998.
[8] Y. Kameda and M. Minoh. A human motion estimation method using 3-successive video frames. In International Conference on Virtual Systems and Multimedia, pages 135-140, 1996.
[9] R. Collins, A. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, O. Hasegawa, P. Burt, et al. A system for video surveillance and monitoring. In Proc. American Nuclear Society (ANS) Eighth International Topical Meeting on Robotics and Remote Systems, pages 25-29. Citeseer, 1999.
[10] M.Y. Shih, Y.J. Chang, B.C. Fu, and C.C. Huang. Motion-based background modeling for moving object detection on moving platforms. In Computer Communications and Networks, 2007. ICCCN 2007. Proceedings of 16th International Conference on, pages 1178-1182, 2007.
[11] C.H. Cheung and L.M. Po. A novel cross-diamond search algorithm for fast block motion estimation. IEEE Transactions on Circuits and Systems for Video Technology, 12(12):1168-1177, 2002.
[12] M. Ghanbari. The cross-search algorithm for motion estimation [image coding]. IEEE Transactions on Communications, 38(7):950-953, 1990.
[13] T. Koga, K. Iinuma, A. Hirano, Y. Iijima, and T. Ishiguro. Motion-compensated inter-frame coding for video conferencing. Teleconferencing, page 63, 1985.
[14] L.M. Po and W.C. Ma. A novel four-step search algorithm for fast block motion estimation. IEEE Transactions on Circuits and Systems for Video Technology, 6(3):313-317, 1996.
[15] J.Y. Tham, S. Ranganath, M. Ranganath, and AA Kassim. A novel unrestricted center-biased diamond search algorithm forblock motion estimation. IEEE Transactions on Circuits and Systems for Video Technology, 8(4):369-377, 1998.
[16] S. Zhu and K.K. Ma. A new diamond search algorithm for fast block matching motion estimation. In Information, Communications and Signal Processing, 1997. ICICS.,Proceedings of 1997 International Conference on, volume 1, 1997.
[17] D. Turaga and M. Alkanhal. Search Algorithms for Block-Matching in Motion Estimation. 1998.
[18] JL Barron, DJ Fleet, and SS Beauchemin. Performance of optical flow techniques. International journal of computer vision, 12(1):43-77, 1994.
[19] A. Meygret, M. Thonnat, I.S. Autipolis, and R. des Lucioles. Segmentation of optical flow and 3D data for the interpretation of mobile objects. In Proceedings: Third International Conference on Computer Vision, December 4-7, 1990, Osaka, Japan, page 238. IEEE Computer Society Press, 1990.
[20] H. Sidenbladh. Detecting human motion with support vector machines. In International Conference on Pattern Recognition, Cambridge, UK. Citeseer, 2004.
[21] P. Sangi, J. Heikkila, and O. Silvén. Extracting motion components from image sequences using particle filters. In PROCEEDINGS OF THE SCANDINAVIAN CONFERENCE ON IMAGE ANALYSIS, pages 508-514. Citeseer, 2001.
[22] D.T. Lin and L.W. Liu. Real-Time Detection of Passing Objects Using Virtual Gate and Motion Vector Analysis. Lecture Notes in Computer Science, 5061:710-719, 2008.
[23] C. Sacchi, G. Gera, L. Marcenaro, and C.S. Regazzoni. Advanced image-processing tools for counting people in tourist site-monitoring applications. Signal Processing, 81(5):1017-1040, 2001.
[24] O. Sidla, Y. Lypetskyy, N. Brandle, and S. Seer. Pedestrian detection and tracking for counting applications in crowded situations. In IEEE International Conference on Video and Signal Based Surveillance, 2006. AVSS'06, pages 70-70, 2006.
[25] A. Mittal and L.S. Davis. M 2 Tracker: a multi-view approach to segmenting and track- ing people in a cluttered scene. International Journal of Computer Vision, 51(3):189- 203, 2003.
[26] D.B. Yang, H.H. González-Baños, and L.J. Guibas. Counting people in crowds with a real-time network of simple image sensors. In Proceedings of the Ninth IEEE International Conference on Computer Vision, page 122. Citeseer, 2003.
[27] S.J. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, and H. Wechsler. Tracking groups of people. Computer Vision and Image Understanding, 80(1):42-56, 2000.
[28] K. Terada, D. Yoshida, S. Oe, and J. Yamaguchi. A counting method of the number of passing people using a stereocamera. In Industrial Electronics Society, 1999. IECON'99 Proceedings. The 25th Annual Conference of the IEEE, volume 3, 1999.
[29] S.F. Lin, J.Y. Chen, and H.X. Chao. Estimation of number of people in crowded scenes using perspectivetransformation. IEEE Transactions on Systems, Man and Cybernetics, Part A, 31(6):645-654, 2001.
[30] D. Huang and T.W.S. Chow. A people-counting system using a hybrid RBF neural network. Neural Processing Letters, 18(2):97-113, 2003.
[31] A. Albiol, V. Naranjo, and I. Mora. Real-time high density people counter using morphological tools. In Pattern Recognition, 2000. Proceedings. 15th International Conference on, volume 4, 2000.
[32] T.H. Chen, T.Y. Chen, and Z.X. Chen. An intelligent people-°ow counting method for passing through a gate. In 2006 IEEE Conference on Robotics, Automation and Mechatronics, pages 1-6, 2006.
[33] J.W. Kim, K.S. Choi, B.D. Choi, and S.J. Ko. Real-time vision-based people counting system for the security door. In Proc. of 2002 International Technical Conference On Circuits Systems Computers and Communications, Phuket (July 2002).
[34] L. Snidaro, C. Micheloni, and C. Chiavedale. Video security for ambient intelligence. IEEE Transactions on Systems, Man and Cybernetics, Part A, 35(1):133-144, 2005.
[35] S. Yu, X. Chen, W. Sun, and D. Xie. A robust method for detecting and counting people. In Audio, Language and Image Processing, 2008. ICALIP 2008. International Conference on, pages 1545-1549, 2008.
[36] A. McAndrew. An Introduction to Digital Image Processing With Matlab. Course Technology Press Boston, MA, United States, 2004.
[37] R. C. Gonzalez and R. E. Woods. Digital Image Processing 2/e. Prentice Hall, 2002.
[38] Texas Instruments Incorporated. TMS320DM6446 digital media system-on-chip. Lit. Number: SPRS283F, 2008.
[39] Texas Instruments Incorporated. TMS320DM6437 digital media processor. Lit. Number: SPRS345D, 2008.
[40] Texas Instruments Incorporated. Code Composer Studio Development Tools v3.3 Getting Started Guide (Rev. H). Lit. Number: spru509h, 2008.
[41] Texas Instruments Incorporated. Hand-Tuning Loops and Control Code on the TMS320C6000. Lit. Number: SPRA666, 2006.
[42] Texas Instruments Incorporated. TMS320C6000 Optimizing Compiler v 6.1 User's Guide (Rev. O). Lit. Number: spru187o, 2008.
[43] Texas Instruments Incorporated. TMS320C64x+ IQmath Library User's Guide. Lit. Number: sprugg9, 2008.
[44] Z. Nikolic, H.T. Nguyen, and G. Frantz. Design and implementation of numerical linear algebra algorithms on fixed point DSPs. EURASIP Journal on Advances in Signal Processing, 2007:1-22, 2007.
[45] Texas Instruments Incorporated. Common Object File Format. Lit. Number: SPRAAO8, 2009.
[46] M.C. Lin. Finding text on natural scene video and DSP implementation. 2009.
[47] Pets 2006 benchmark data. http://www.cvg.rdg.ac.uk/PETS2006/data.html.