隨著科技社會的成形，在社會安全與電腦科技密不可分的關係下，追蹤系統成為一種不可缺少的角色，除了以通訊方式為基礎，利用互動的方式，不斷的聯繫以追蹤的方式外，另一種則可被歸類於單方面監視系統的追蹤。單方面的追蹤方式必須使用監視的錄影設備與圖形識別的追蹤技術互相的配合，然而以錄影取像的方式所得到的資訊有限，因此後端圖形識別的追蹤方式也就顯的格外的重要。
本論文主要的目的在於提出一個智慧型交通即時監控系統中多車道的車輛追蹤系統，並使用此系統觀察此路段的交通狀況。在此系統中，除了在影像前處理上將運用各種動態影像技術來建立可靠的背景影像與陰影去除外，並提出以動態多邊型(active contour)的機制來描述車體外形，以及利用線性預測(linear prediction)動態物體的方式做為系統的追蹤模式，並以此為基礎做為主要的系統架構，以期能達到即時且正確的效果。
在實驗部份將會截取高速公路車流量影像，利用所提出的方法加以驗證該系統是可靠且有效的。

With the advancement of modernized society, the relationship between social security and computer technologies is getting closer and closer. Computer technologies can provide more comfortable and secure environment and improve the living standard of human beings. Tracking and monitoring systems gradually become an indispensable part in current society, which can be realized by utilizing image processing and pattern recognition techniques. They constitute the essential part of a video surveillance system.
In this thesis, an intelligent traffic monitoring system which can track vehicles in multi-lanes highway. The proposed system can also extract many important traffic parameters to reflect the real time traffic situation in highways. In the proposed system, the task of image preprocessing is first performed to construct reliable image background and eliminate shadows caused by the vehicles. Then, the mechanism of active contour is devised to describe the shape of vehicles. Last, the vehicle tracking model is built by utilizing the linear prediction model of dynamic objects.
Experiments were conducted on several image sequences captured in highways. Experimental results verify the validity of the proposed approach in successfully tracking vehicles.

[1] K. Toyama, J. Krumm,B. Brumitt, and B. Meyers, “Wallflower : Principles and Practice of Background Maintenance,” Internal Conference on Computer Vision, September 1999, Corfu, Greece
[2] S. Kamijo, Y. Matsushita, and K. Ikeuchi, “Traffic Monitoring and Accident Detection at Intersections,” IEEE Transactions on Intelligent Transportation System, Vol. 1, No. 2, JUNE 2000
[3] D. Gutchess, M. Trajkovic, E. Cohen-Solal, D. Lyons, and A. K. Jain, “A Background Model Initialization Algorithm for Video Survillance,” IEEE 2001
[4] S. Pumrin, A Framework for Dynamically Measuring Mean Vehicle Speed Using Un-Calibrated Cameras, General Examination Report, Intelligent Transportation Systems Laboratory Department of Electrical Engineering University of Washington, December 12, 2001
[5] B.K.P. Horn and B.G. Schunck., Determining optical flow, AI Memo 572. Massachusetts Institue of Technology, 1980
[6] Y.K. Jung and Y.S. Ho, “Traffic Parameter Extraction using Video-based Vehicle Tracking,” IEEE 1999
[7] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active contour models." International Journal of Computer Vision. Vol. 1, No. 4, pp. 321-331, 1987
[8] C. Vieren, F. Cabestaing, and J.G. Postaire, “Catching moving objects with snakes for motion tracking,” Pattern Recognition Letter 16, 1995
[9] W. Kim and J.J. Lee, “Visual Tracking using Snake for Object''s Discrete Motion,” IEEE International Conference on Robotics & Automation, 2001
[10] B. Coifman, D. Beymer, et. al., "A real-time computer vision system for vehicle tracking and traffic surveillance," Transportation Research Part C: Emerging Technologies, Vol. 6, No. 4, August, 1998, pp. 271-288.
[11] N. D. Matthews, P. E. An, D. Charnley, C. J. Harris, Vehicle detection and recognition in grayscale imagery, Control Eng. Practice, Vol. 4, No. 4, pp. 473-479, 1996.
[12] M. Fathy, M. Y. Siyal, "A window-based image processing technique for quantitative and qualitative analysis of road traffic parameters," IEEE Transactions on Vehicular Technology, Vol. 47, No. 4 , Nov. 1998, pp. 1342 –1349.
[13] M. Haag, T. Frank, H. Kollnig, and H.H. Nagel, “Influence of an Explicitly Modelled 3D Scene on the Tracking of Partially Occluded Vehicles,”Computer Vision and Image Understanding, Vol. 65, No. 2, February, pp. 206-225, 1997
[14] M. Haag and H.H. Nagel,“Combination of Edge Element and Optical Flow Estimates for 3D-Model-Based Vehicle Tracking in Traffic Image Sequences,” International Journal of Computer Vision 35(3), pp.295-319, 1999
[15] J.E.L. Hollis, J. David Brown, “Feature Vectors for Road Vehicle Scene Classification,” Neural Networks, Vol. 9, No, 2, pp. 337-344, 1996
[16] D.J. Dailey, F.W. Cathey, and S. Pumrin, An Algorithm to Estimate Mean Traffic Speed using Un-Calibrated Cameras, Elect. Eng. Dept., University of Washington, WA 98195
[17] N.J. Ferrier, S.M.Rowe, and A.Blake, “Real-Time Traffic Monitoring,” IEEE, 1994
[18] C. Stauffer, W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," Proceedings of CVPR 1999, June 1999, pp. 246-252.
[19] J. C. Rojas, J. D. Crisman, "Vehicle detection in color images," Proceedings of IEEE Int. Conf. on Intelligent Transportation System, 1997.
[20] A. H. S. Lai, N. H. C. Yung, "A video-based system methodology for detecting red light runners," Proceedings of IAPR Workshop on MVA ''98, pp. 23-26.
[21] L. Ji, H. Yan, “Attractable snakes based on the greedy algorithm for contour extraction,” Pattern Recognition 35, pp. 791-806, 2002