由於交通工具的普及率提高，道路壅塞程度也節節攀升，造成用路人許多不方便。若能有效監控車流量，提供資訊給相關單位，則可使用路人避開尖峰路段並且縮短交通時間。許多研究提出相當複雜的數學計算式，用來解決黏合車輛之問題，其辨識度高達95%。然而，在計算過程中花費過多時間，以致於無法達到即時的效果。因此，本篇論文提出一個在黏合狀態下即時計算車流量的系統，應用於交通的數位監視技術上，此系統能即時追蹤出現在監控畫面中的所有車輛，當車輛發生黏合狀態時，亦會快速分割車輛的黏合畫面並正確追蹤每一台車輛。首先，經過前處理得到粗略的前景，再利用亮度和飽和度去除前景裡陰影的部分，可得到較為精確的前景。然後，根據車體的物理性質判斷每個前景區塊是否有黏合狀態，有黏合狀態的前景區塊，依照不同的黏合方式給予不同的方法分割。最後，利用前、後張影像的關係和區塊間中心點位置的關係，找出相對的前景區塊，進而得到正確的車量計數。本篇論文所提的方法可用在一般道路上，除了即時計算車流量且正確率仍然可達95%以上。

According to vehicles are prevailing and the degree of road congestion is increasing, it is inconvenient for most to utilize. If the system can monitor control the flow of vehicles and provide the information for related organization, the people who use roads are able to keep away from the traffic jam and shorten the time of traffic. Many researches propose complex equation to solve the problem of occluded vehicles at a high accuracy rate of 95%. However, it costs too much time to do this job in real time. In the thesis, an algorithm is proposed to count vehicles in multiple-vehicle occlusions in real time. It can not only track every vehicle in surveillance images, but also detect and segment the occluded vehicles correctly. First of all, the system gets rough foreground by pre-process. According to the difference of saturation and brightness between the foreground pixel and the corresponding background pixel, self-shadows in foreground are removed. If the occlusion is happened, the system will segment the foreground object immediately. Finally, the relation of successive frames and centric matching strategy is used to find out the correspondence of regions. Experimental results show that the system can not only get correct vehicle count even in vehicle occlusion but also in real time.

[1]B.P.L. Lo and S.A. Velastin, “Automatic Congestion Detection System for Underground Platforms,” Proc. Int’l Symp. Intelligent Multimedia, Video, and Speech Processing, pp. 158-161, 2000.
[2]Q. Zhou and J.K. Aggarwal, “Tracking and Classifying Moving Objects from Video,” Proceedings of IEEE Int. Workshop on PETS, 2001.
[3]C. Stauffer, W. E. L. Grimson “Adaptive background mixture models for real-time tracking,” 1999. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2, June 1999.
[4]I. Haritaoglu, David Harwood, and L. S. Davis, “W4:Real-time surveillance of people and their activities,” IEEE Trans. Pattern Analysis and Machine intelligence, 22(8):809–830, August 2000.
[5]Klaus-Peter Karmann, Achim von Brandt, “Moving Object Recognition Using an Adaptive Background Memory,” Time-Varying Image Processing and Moving Object Recognition, 2, Elservier, Amsterdam, The Netherlands,1990.
[6]D. Beymer and K. Konolige,”Real-time Tracking of Multiple People Using Stereo,” Proc. IEEE Frame Rate Workshop, 1999.
[7]M. Kilger, “A Shadow Handler in a Video-Based Real-time Traffic Monitoring System,” IEEE Workshop on Applications of Computer Vision, Palm Spring, CA, 1992
[8]Monnet A., Mittal A., et al, “Background modeling and subtraction of dynamic scenes,” Proceedings of Ninth IEEE International Conference on Computer Vision, 2003.
[9]Wang L., Tan T., “Silhouette analysis-based gait recognition for human identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003.
[10]Suchendra M., Bhandarkar and Xingzhi Luo, “Fast and Robust Background Updating for Real-time Traffic Surveillance and Monitoring,” Computer Society Conference on Computer Vision and Pattern Recognition, 2005.
[11]Juan L, Mattthew M, Naveed S. Performance of passive ranging form image flow. IEEE, ICIP, 2003.
[12]Sasa G, Loncaric S. Spatio-temporal image segmentation using optical flow and clustering algorithm. Proceedings of the First International Workshop on Image and Signal Processing and Analysis, 2000.
[13]Baoxin Li, Rama Chellappa, “A generic approach to simultaneous tracking and verification in video,” IEEE Transactions on Image Processing, 2002.
[14]Hai Tao, Harpreet S. Sawhney, and Rakesh Kumar, “Object tracking with Bayesian estimation of dynamic layer representations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002.
[15]R. Mech and M. Wollborn, “A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera,” Signal Processing, vol. 66, pp. 203–217, Apr. 1998.
[16]S.J. McKenna, S. Jabri, Z. Duric, A. Rosenfeld, and H. Wechsler, “Tracking Groups of People,” Computer Vision and Image Understanding, vol. 80, no. 1, pp. 42-56, Oct. 2000.
[17]Y-L Tian and A. Hampapur, “Robust Salient Motion Detection with Complex Background for Real-time Video Surveillance,” IEEE Computer Society Workshop on Motion and Video Computing, Breckenridge, Colorado, January 5 and 6, 2005.
[18]A. C. Davies, J. H. Yin, and S. A. Velastin, “Crowd monitoring using image processing,” IEE Electron. Commun. Eng. J., vol. 7, no. 1, pp. 37–47, 1995.
[19]S. A. Velastin, A. C. Davies, J. H. Yin, M. A. Vicencio-Silva, R. E. Allsop, and A. Penn, “Analysis of crowd movements and densities in built-up environments using image processing,” in IEE Coll. Image Process. Transport Applicat., vol. 236, London, UK, 1993, pp. 8/1–8/6.
[20]S.A. Velastin, B.A. Boghossian, B.P.L. Lo, Jie Sun, and M.A. Vicencio-Silva, “PRISMATICA: toward ambient intelligence in public transport environments,” IEEE Transactions on Systems, Man and Cybernetics, Part A, Volume: 35, Issue: 1, pp. 164- 182, Jan. 2005.
[21]A. Neri, S. Colonnese, G. Russo, and P. Talone, “Automatic moving object and background separation,” Signal Processing, vol. 66, no. 2, pp. 219–232, 1998.
[22]C. Kim and J-N Hwang, “Fast and automatic video object segmentation and tracking for content-based applications,” IEEE transaction on circuits and systems for video technology, vol. 12, Feb. 2002.
[23]R. Mech and M. wollborn, “A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera,” Signal Processing, 1998.
[24]Harini Veerarahavan, Osama Masoud, and Nikolaos P. Papanikolopoulos, “Computer Vision Algorithm for Intersection Monitoring,” IEEE transaction on intelligent transportation systems, 2003.
[25]C.C.C. Pang, W.W.L. Lam, and N.H.C. Yung, “A Novel Method for Resolving Vehicle Occlusion in a Monocular Traffic-Image Sequence,” IEEE Trans. On Intelligent Transportation Systems, 2004.
[26]D. Beymer, P. McLauchlan, B. Coifman, and J. Malik, “A real-time computer vision system for measuring traffic parameters,” in Proc. of IEEE Conf. on computer Vision and Pattern Recognition, 1997.
[27]X. Song and R. Nevatia, “A Model-Based Vehicle Segmentation Method for Tracking,” Tenth IEEE International Conference on Computer Vision, 2005.
[28]Yu-Tzu Chen and Shen-Chuan Tai, A Real-Time People Tracking, Discrimination and Abnormal Behavior Detection Algorithm for Surveillance System, Master’s thesis, National Cheng Kung University, Tainan, Taiwan, R.O.C. Thesis for Master of Science Degree, 2005
[29]Hui-Chi Zeng and Shang-Hong Lai, “Adaptive Foreground Object Extraction for Real-time Video Surveillance with Lighting Variations,” IEEE international conference, 2007