由於現代社會的交通日趨繁忙，智慧型運輸系統(ITS, Intelligent Transportation System)的建置已經變成一個相當重要的課題。如何能夠自動偵測出道路上的行人與車輛，並且進一步加以分類或追蹤，更是智慧型運輸系統中相當重要的一環。本論文即在提出一套能夠自動偵測、追蹤、並分類路口行人與車輛的交通監控系統。
　　本論文提出的方法內容簡述如下。在影像前置處理部份，本研究提出一種自動物體外型擷取演算法。首先架設攝影機以擷取路面交通影像，並使用所提之建立淨空背景方法作為分析移動物體之用。再將攝影機所拍攝的影像以影像相減為基礎，搭配多種影像處理的技術，把畫面中移動的物體外型輪廓從背景之中抽離出來。下一步是物體追蹤部份，利用主動輪廓模型(Active Contour Model)可以不斷包圍非剛性物體的特性，對各個移動的物體進行持續的追蹤。接著是物體辨識部份，經由預先設定的特徵分類法則，對畫面中各個移動的物體進行特徵的比對，分辨其為行人或者車輛。最後由實驗結果驗證本論文所提出之方法是可行的。

This study proposes a traffic surveillance system which can automatically detect, track, and classify pedestrians and cars at crossing.
Following is a simple description of the proposed method. An automatic moving object segmentation algorithm is proposed in image pre-process step. At this step, a camera is used to capture the video at crossing, and a clear background is built by the proposed method for moving objects detection. The shape and contour of moving objects in the image are extracted by background subtraction and multiple image process techniques. Next is the object tracking step. Considering its deformable characteristic, the active contour model is applied to continuously track each moving object, even it is non-rigid. Following is the object classification step; multiple features are used to determine whether a moving object is a pedestrian or car. Finally, the proposed method is verified through experiments to be practicable.

書名頁 i
論文口試委員審定書 ii
授權書 iii
摘要 v
Abstract vi
誌謝 vii
目錄 viii
圖目錄 x
表目錄 xii
第一章 序論 1
1.1 研究背景與動機 1
1.2 問題描述 2
1.3 相關研究 3
1.4 論文架構 4
第二章 移動物體偵測與擷取 6
2.1 背景影像的建立 6
2.2 移動物體之偵測 9
2.3 型態學 10
2.4 連結元件標示 11
2.5 移動物體偵測與擷取流程 14
第三章 使用主動輪廓模型進行移動物體追蹤 17
3.1 主動輪廓模型 17
3.2 初始輪廓之設定 21
3.3 追蹤移動物體 21
第四章 物體分類法則 25
4.1 各種物體之特徵與相異處 25
4.2 特徵擷取 25
4.3 分類決策法則 27
第五章 實驗與測試結果 30
5.1 實驗環境與設備 30
5.2 實驗影像 30
5.3 物體追蹤實驗結果 32
5.4 物體分類實驗結果 32
第六章 結論與未來研究方向 34
參考文獻 35

[1] 鄭伯順，吳坤榮，林建廷，「影像處理暨圖形識別技術應用於車輛通行管理之研究」，圖形與識別2002，Vol. 8，No. 4，pp. 49-56，2002。
[2] P. Comelli, P. Ferragina, M.N. Granieri, F. Stabil, “Optical Recognition of Motor Vehicle License Plates”, IEEE Transaction on Vehicular Technology, Vol. 44, No. 4, pp. 790-799, Nov. 1995.
[3] Nelson H.C. Yung, Andrew H.S. Lai, “An Effective Video Analysis Method for Detecting Red Light Runners”, IEEE Transactions on Vehicular Technology, Vol. 50, No. 4, pp. 1074-1084, July 2001.
[4] 許世宏，施皇嘉，黃仲陵，「使用比對搜尋方法的路標偵測辨識系統」，影像與識別2002，Vol. 8，No. 4，pp. 31-48，2002。
[5] O. Masoud, Nikolaos P. Papanikolopoulos, “A Novel Method for Tracking and Counting Pedestrians in Real-Time Using a Single Camera”, IEEE Transactions on Vehicular Technology, Vol. 50, No. 5, pp. 1267-1278, Sep. 2001.
[6] 白家榮，陳世旺，「十字路口行人的偵測及追蹤」，國立台灣師範大學資訊教育研究所，碩士論文，中華民國九十一年六月。
[7] Yuan-Kai Wang, Yu-Sheng Lin, “A Real-Time Approach for Classification and Tracking of Multiple Moving Objects”, 16th IPPR Conference on CVGIP, Aug. 2003.
[8] M. Sonka, V. Hlavac, R. Boyle, “Image Processing, Analysis, and Machine Vision”, 2nd. Ed., PWS Publishing, pp. 559-599, 1998.
[9] M. Kass, A. Within, D. Terzopoulos, “Snakes: Active Contour Models”, International Journal of Computer Vision, Vol. 1, pp. 321-331, 1988.
[10] M. Sonka, V. Hlavac, R. Boyle, “Image Processing, Analysis, and Machine Vision”, 2nd. Ed., PWS Publishing, pp. 142-143, 1998.
[11] N. Peterfreund, “Robust Tracking of Position and Velocity With Kalman Snakes”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, No. 6, pp. 564-569, Jun. 1999.
[12] N. Paragios, R. Deriche, “Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 3, pp. 266-280, Mar. 2000.
[13] W.-P. Choi, K.-M. Lam, W.-C. Siu, “An Adaptive Active Contour Model for Highly Irregular Boundaries”, Pattern Recognition 34 (2001), Vol. 34, pp. 323-331, 2001.
[14] C. Han, T. S. Hatsukami, J.-N. Hwang, C. Yuan, “A Fast Minimal Path Active Contour Model”, IEEE Transactions on Image Processing, Vol. 10, No. 6, pp. 865-873, Mar. 2001.
[15] R. Goldenberg, R. Kimmel, E. Rivlin, M. Rudzsky, “Fast Geodesic Active Contours”, IEEE Transactions on Image Processing, Vol. 10, No. 10, pp. 1467-1475, Oct. 2001.
[16] S. Sun, D. R. Haynor, Y. Kim, “Semiautomatic Video Object Segmentation Using VSnakes”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, No. 1, pp. 75-82, Jan. 2003.
[17] C. Han, W. S. Kerwin, T. S. Hatsukami, J.-N. Hwang , C. Yuan, “Detecting Objects in Image Sequences Using Rule-Based Control in an Active Contour Model”, IEEE Transactions on Biomedical Engineering, Vol. 50, No. 6, pp. 705-710, Jun. 2003.
[18] D. Freedman, T. Zhang, “Active Contours for Tracking Distributions”, IEEE Transactions on Image Processing, Vol. 13, No. 4, pp. 518-526, Apr. 2004.
[19] L. Ji, H. Yan, “Attractable Snakes Based on the Greedy Algorithm for Contour Extraction”, Pattern Recognition 35 (2002), Vol. 35, pp. 791-806, 2002.
[20] 陳炳富，范國清，「智慧型交通監控系統中多車道車輛之偵測與追蹤」，國立中央大學資訊工程研究所，碩士論文，中華民國九十二年六月。
[21] 邵得晉，孫永年，「電腦視覺技術於細胞影像序列運動分析之研究」，國立成功大學資訊工程研究所，碩士論文，中華民國九十二年六月。