隨著車載資通訊系統(Telematics Industry)越趨成熟，且車載裝置的架設也更加完善，在行車上的安全考量是越加重視。然而在一般車輛的後視鏡照視常會出現死角及盲點，於是便有很多針對此一問題進行改善的研究，發展出環視攝影系統(Around View Monitor)，然而系統僅做攝影監看，並無物體偵測的功能。在本研究中，利用裝置在車上的攝影機所拍攝到的畫面，尤其針對車身後方攝影機，提出一套偵測方法，不論車子在靜止或行進時，皆能將其背景抑制，偵測到移動物體，更利用模糊理論來減少每秒處理的畫面。
在移動物體偵測方面，因為背景為動態，我們須把移動背景抑制，故我們透過動作估計中(motion estimation)的區塊搜尋法找出移動向量，再做影像補償，最後利用影像相減法來抑制背景的區域。再以區塊為基礎，計算相減後的影像其像素值與標準差，判斷此兩種數值與臨界值關係，我們便可偵測出移動物體。但在做區塊搜尋法時，會產生龐大的運算量，我們發覺在一般的動態偵測中，計算幀幅的數量是由影片本身的每秒幀幅率所決定，故我們使用回授機制來減少多餘的幀幅數，進而降低運算量。由實驗結果我們可以發現，在車子移動速度不快的情況下，可節省超過50%的運算量。

The mature development of Telematics industry and the progress on its setup technique indicate that people place more and more importance on traffic safety. One of proposed approaches to enhance traffic safety is around view monitoring system (AVM). However, the system only has the function of monitoring with no detection at all. Therefore, this thesis proposes an approach that is able to detect moving objects in real time for the rearview of a vehicle based on the image taken by the rear camera. There are two issues getting involved in this research: (1) motion detection function to be able to detect any moving objects inside the designated area; and (2) a feedback system that is able to decide an appropriate number of image frames to be processed per second.
For motion detection, a moving vector is calculated by the search algorithm of blocking motion estimation and then is used to perform image compensation in order to mitigate the influence of moving background, and compensate the frame to reduce moving background effect. The standard deviation and maximum of each block can then be calculated. A moving object can therefore be detected by comparing these two values against respective threshold.
However, if every frame needs to be processed by above-mentioned procedures, it would be impossible to perform the detection function in real time due to heavy computations. Thus a feedback mechanism based on fuzzy theory is proposed in this thesis to decide the appropriate number of frames to be extracted and processed per second. That is, the number of frames being processed could be varying for every second. By doing so, the computations can be reduced without sacrificing the performance of moving object detection. The conducted experiments have shown that the number of computations is reduced by over 50% for a slow-moving vehicle while maintaining relatively good detection performance when being compared with other approaches.

[1] S. Tsugawa, N. Watanabe and H. Fujii, "Super smart vehicle system—Its concept and preliminary works," Vehicle Navigation and Information Systems Conference, 1991 , vol.2, no., pp. 269- 277, 20-23 Oct. 1991
[2] G. K. Santhalia and S. Singh, "An efficient approach to lane tracking system vehicular telemetics," Communication Systems Software and Middleware and Workshops, 2008. COMSWARE 2008. 3rd International Conference on , vol., no., pp.657-661, 6-10 Jan. 2008
[3] R. Li, Q. Shi and W. Shen, "Development of integrated information platform for intelligent transportation systems," Intelligent Transportation Systems, 2003. Proceedings. 2003 IEEE , vol.1, no., pp. 54- 59 vol.1, 12-15 Oct. 2003
[4] S. F. Gregson, J. McCormick and C. G. Parini, "Histogram equalisation as a method for making an objective comparison between antenna patterns functions," Antennas and Propagation, 2006. EuCAP 2006. First European Conference on , vol., no., pp.1-5, 6-10 Nov. 2006
[5] S. J. Ko and Y. H. Lee , "Center weighted median filters and their applications to image enhancement," Circuits and Systems, IEEE Transactions on , vol.38, no.9, pp.984-993, Sep 1991
[6] 鐘國亮編著，"影像處理與電腦視覺"，第三版，東華書局，2006
[7] P. S. Windyga, "Fast impulsive noise removal," Image Processing, IEEE Transactions on , vol.10, no.1, pp.173-179, Jan 2001
[8] W. Brand, "Morphable 3D models from video," Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on , vol.2, no., pp. II-456- II-463 vol.2, 2001
[9] N. Weng; Y. H. Yang and R. Pierson, "3D surface reconstruction using optical flow for medical imaging ," Nuclear Science Symposium, 1996. Conference Record., 1996 IEEE , vol.3, no., pp.1845-1849 vol.3, 2-9 Nov 1996
[10] J. F. Cohn, A. J.Zlochower, J.J. Lien and T. Kanade, "Feature-point tracking by optical flow discriminates subtle differences in facial expression," Automatic Face and Gesture Recognition, 1998. Proceedings. Third IEEE International Conference on , vol., no., pp.396-401, 14-16 Apr 1998
[11] A. J. Lipton, “Local application of optic flow to analyze rigid versus non-rigid motion,” Technical Report, CMU-RI-TR-99-13, Robotics Institute, Carnegie Mellon University, 1999.
[12] J. L. Barron, D. J. Fleet, S. S. Beauchemin and T. A. Burkitt, "Performance of optical flow techniques," Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on , vol., no., pp.236-242, 15-18 Jun 1992
[13] 王韻婷，"The implementation of a real-time object estimating system using the binocular stereo vision based on DSP"，國立台灣科技大學電機工程系，2007
[14] K. Dawson-Howe, “Active surveillance using dynamic background subtraction,” Technical Report, TCD-CS-96-06, Trinity College, 1996.
[15] R. T. Collins, A. J. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, O. Hasegawa, P. Burt and L. Wixson, “A system for video and monitoring,” Technical Report, CMU-RI-TR-00-12, Robotics Institute, Carnegie Mellon University, 2000.
[16] N. Ohta, "A statistical approach to background subtraction for surveillance systems," Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on , vol.2, no., pp.481-486 vol.2, 2001
[17] B. Gloyer, H. K. Aghajani, and T. Kailath, “Video-based freeway monitoring system using recursive vehicle tracking,” in Proc. in IS&T-SPIE Symposium on Electronic Imaging: Image and video Processing, 1995.
[18] D. Guo, Hwang, Y. C. L. Adrian, C. Laugier, "Traffic monitoring using short-long term background memory," Intelligent Transportation Systems, 2002. Proceedings. The IEEE 5th International Conference on, vol., no., pp. 124- 129, 2002
[19] C. Wren, A. Azarbayejani, T. Darrell and A. Pentland, "Pfinder: real-time tracking of the human body," Automatic Face and Gesture Recognition, 1996., Proceedings of the Second International Conference on , vol., no., pp.51-56, 14-16 Oct 1996
[20] H. Fujiyoshi and A. J. Lipton, "Real-time human motion analysis by image skeletonization," Applications of Computer Vision, 1998. WACV '98. Proceedings., Fourth IEEE Workshop on , vol., no., pp.15-21, 19-21 Oct 1998
[21] W. E. L. Grimson, C. Stauffer, R. Romano and L. Lee, "Using adaptive tracking to classify and monitor activities in a site," Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on , vol., no., pp.22-29, 23-25 Jun 1998
[22] 林士山，"Integrating object data and SAD Method to design a motion detection and tracking system"，國立台灣科技大學電機工程系，2009
[23] R. Szeliski, "Video mosaics for virtual environments," Computer Graphics and Applications, IEEE , vol.16, no.2, pp.22-30, Mar 1996
[24] J. Yeh, M. Vetterli, M. Khansari, "Motion compensation of motion vectors," Image Processing, 1995. Proceedings., International Conference on , vol.1, no., pp.574-577 vol.1, 23-26 Oct 1995
[25] A. Barjatya, "Block matching algorithms for motion estimation", IEEE Signal Processing,Conference Proceedings, 2004
[26] N. Ling; R. Advani, "A high speed motion estimator using 2-D log search algorithm," Data Compression Conference, 1996. DCC '96. Proceedings , vol., no., pp.448, Mar/Apr 1996
[27] R. Li; B. Zeng and M. L. Liou, "A new three-step search algorithm for block motion estimation," Circuits and Systems for Video Technology, IEEE Transactions on , vol.4, no.4, pp.438-442, Aug 1994
[28] S. Zhu and K. K. Ma, "A new diamond search algorithm for fast block matching motion estimation," Information, Communications and Signal Processing, 1997. ICICS., Proceedings of 1997 International Conference on , vol.1, no., pp.292-296 vol.1, 9-12 Sep 1997
[29] L. M. Po and W. C. Ma; , "A novel four-step search algorithm for fast block motion estimation ," Circuits and Systems for Video Technology, IEEE Transactions on , vol.6, no.3, pp.313-317, Jun 1996
[30] Y. Nie and K. K. Ma, "Adaptive rood pattern search for fast block-matching motion estimation," Image Processing, IEEE Transactions on , vol.11, no.12, pp. 1442- 1449, Dec 2002
[31] 楊英魁、孫宗瀛，"Fuzzy控制：理論、實作與應用"，全華圖書，September 2005.
[32] H. J. Zimmermann, "Fuzzy set theory and its applications ",Kluwer Academic Pub.,New York, 1991.
[33] 陳彥汝、李翊瑄、謝正展，"利用模糊邏輯理論應用於倒車入庫控制"，致遠管理學院電腦與通訊學系，December 2008.
[34] 王文俊，"認識 Fuzzy"，全華圖書，第三版，2005.
[35] S. Yigang and P. C. Sen, "A new defuzzification method for fuzzy control of power converters ," Industry Applications Conference, 2000. Conference Record of the 2000 IEEE , vol.2, no., pp.1202-1209 vol.2, 2000
[36] D. Stanescu, M. Stratulat, V. Groza, I. Ghergulescu and D. Borca, "Steganography in YUV color space," Robotic and Sensors Environments, 2007. ROSE 2007. International Workshop on , vol., no., pp.1-4, 12-13 Oct. 2007
[37] X. J. Yuan, H. C. Feng, "An abrupt shot change detection algorithm based on the YUV space," Electrical and Control Engineering (ICECE), 2010 International Conference on , vol., no., pp.4630-4633, 25-27 June 2010
[38] A. Hore and D. Ziou, "Image quality metrics: PSNR vs. SSIM," Pattern Recognition (ICPR), 2010 20th International Conference on , vol., no., pp.2366-2369, 23-26 Aug. 2010
[39] A. Almohammad and G. Ghinea, "Stego image quality and the reliability of PSNR," Image Processing Theory Tools and Applications (IPTA), 2010 2nd International Conference on , vol., no., pp.215-220, 7-10 July 2010
[40] B. Geary and C. Grecos, "Image quality assessment using a rotated Gaussian discrimination function," Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on , vol., no., pp.47-52, 13-18 June 2010
[41] Z. Wang and A.C. Bovik,“A universal quality metric” IEEE Signal Processing Letters, Vol.9 no.3, pp.81-84, 2002.
[42] 鍾宜岑，"A real-time motion detection and tracking system in the dynamic background"，國立交通大學，October 2007.
[43] 何祈磊，"具有影像優化處理的環場鳥瞰監視停車輔助系統"，國立中央大學，July 2009.
[44] A.Jain, "Bit reduction based matching criterion for motion compensation in video coding," Multimedia, Signal Processing and Communication Technologies, 2009. IMPACT '09. International , vol., no., pp.36-39, 14-16 March 2009
[45] Y. K. Chen, T.Y. Cheng and S. T. Chiu, "Motion Detection with Entropy in Dynamic Background," Informatics in Control, Automation and Robotics, 2009. CAR '09. International Asia Conference on , vol., no., pp.263-266, 1-2 Feb. 2009