臺灣博碩士論文加值系統

隨著科技進步，現今社會上的每戶家庭都擁有一台以上的車輛，也造成了車輛擁擠的時代，所以當車禍發生或是各式犯罪的可疑車輛追緝也成為一大難題，一旦發生事故及案件，警方往往必須要消耗大量人力與物力追查可疑車輛才能找出破案線索。
本論文以電腦視覺技術為基礎，開發多攝影機環境車輛路徑追蹤系統，系統偵測到的車輛資訊會傳送到網路資料庫內，再藉由網際網路讓相關人員利用瀏覽器查詢記錄結果，讓使用者能快速找到想要搜尋的車輛，此外本系統能追蹤各種大小、顏色之車輛，並鎖定車輛的可能行經路線，將追蹤結果提供給相關人員或是單位使用。
本系統的設計相較於其他系統，有處理速度快、簡單、可同時追蹤多種車輛、多路口偵測、辨識車輛顏色、用於即時偵測更具效率等優點。經過多種道路影片測試過後，皆有不錯的成果，相信本研究對車輛追蹤會有很大的助益。

With advance of technology, almost every household in our society today owns more than one car, and that is the reason that brings about our traffic jam. Therefore, when there is accident or one is to investigate suspicious cars in various crimes, it has become very difficult. As a result, when there is any accident or event, the police always have to spend a great amount of manpower and resources to find out the suspicious cars before clues to resolve the case can be obtained.
This paper used computer vision technology to develop an integrated multi-camera vehicle tracking system. And vehicle information detected on the system will be transmitted to the network database. Then, relevant personnel can use the web browser to inquire the record results so that users can quickly discover the car they are after. The proposed system can follow cars of different size, and colors. In addition, the system can also lock on the possible route of transportation on the car, and provide information of tracking-down to relevant personnel or authorities for employment.
The design of the proposed system, in comparison to other systems, is given with advantages of fast speed, simplicity, tracking-down on several cars concurrently, detection at several road junctions, detection of vehicle color, and significant efficiency in real-time detection. With tests of several road films, the system has proven with favorable results, and it is believed the system can be most helpful to track down on vehicles.

第一章 緒論 1
1.1研究背景 1
1.2研究動機 4
1.3研究目的 4
1.4研究方法 5
1.5研究架構 6
第二章 相關研究 7
2.1電腦視覺技術相關研究 7
2.2車流量統計相關研究 8
2.3車輛監控系統相關研究 9
第三章 研究架構 12
3.1系統架構 12
3.2系統環境 12
3.3系統流程 14
3.4即時影像擷取 16
3.5背景更新 16
3.6背景相減 18
3.7灰階……………..…………………………………………………….. 21
3.8二值化 22
3.9形態學影像處理 25
3.9.1擴張(Dilation)與侵蝕(Erosion) 25
3.9.2斷開(Opening)與閉合(Closing) 26
3.10編號演算法(Connected Component Labeling) 28
3.11前景偵測與雜訊濾除 31
3.12感興趣區域偵測(ROI) 34
3.13車種識別 35
3.14物件追蹤 36
3.15網路資料庫系統 39
第四章 實驗與結果 41
4.1實驗環境 41
4.2車輛偵測和統計數量 41
4.3車輛路徑追蹤系統資料庫 45
第五章 結論與未來研究方向 49
5.1結論 49
5.2未來研究方向 49
參考文獻 50

[1] 中華電信公司數據通信分公司，「臺閩地區機動車輛登記數」，http://tpe.land.hinet.net/（2008/3/5 瀏覽）。
[2] 公路總局，「臺灣地區道路概況」，http://www.thb.gov.tw/index.aspx（2008/3/5 瀏覽）。
[3] 內政部警政署，「臺閩地區道路交通事故及違規概況」，http://www.npa.gov.tw/NPAGip/wSite/mp?mp=1（2008/3/5 瀏覽）。
[4] M. Oren, C. Papageorgiou, P. Sinha, E. Osuna, and T. Poggio, “Pedestrian detection using wavelet templates,” in Proceedings of IEEE Conference Computer Vision and Pattern Recognition, June 1997, pp. 193-199.
[5] W. H. Wu, and R. C. Lo, “A stucy on the lending support of blocks detecting based on image processing applied to the highway crossing system,” IPPR Conference on Computer Vision, Graphics and Image Processing (CVGIP), July 2006.
[6] M. H. Tsai, and S. J. Wang, “A new region tracking model for visual surveillance systems,” IPPR Conference on Computer Vision, Graphics and Image Processing (CVGIP), July 2006.
[7] 張家榮，使用等高集合法對多目標移動物追蹤之研究，大同大學電機工程研究所碩士論文，民國90年。
[8] Q. Zhou and J. K. Aggarwal, “Tracking and Classifying Moving Objects from Video,” in Proc. of IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Hawaii USA, Dec. 2001, pp. 52-59.
[9] 林文祥，以DSP實現移動物體影像的即時偵測與追蹤系統，國立台灣科技大學電機工程研究所碩士論文，民國95年。
[10] 陳彥佑，應用有限偵測器推估公路車流量之研究，國立交通大學運輸科技與管理學系研究所碩士論文，民國93年。
[11] 張子健，關於高速公路車流量問題之分析，國立臺灣大學物理學研究所碩士論文，民國92年。
[12] 莊忠儒，為提供先進旅行者資訊下之偵測器最佳佈設位置研究，國立交通大學運輸科技與管理學系碩士論文，民國93年。
[13] 洪順煌，即時影像之交通資訊偵測系統研究，國防大學中正理工學院電子工程研究所碩士論文，民國95年。
[14] 莊建宏，自動化交通監控系統，國立臺灣師範大學資訊教育研究所碩士論文，民國89年。
[15] 鄭世杰，應用於交通監視系統上之行人與車輛分類演算法，國立成功大學電腦與通信工程研究所論文，民國94年。
[16] 蔡洛緯，以正規化色彩與邊緣資訊作車輛偵測，國立中央大學資訊工程研究所論文，民國93年。
[17] J. Wang, G. Bebis and R. Miller, "Overtaking Vehicle Detection Using Dynamic and Quasi-Static Background Modeling," in Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun 2005, p. 64.
[18] M. Bertozzi, A. Broggi, A. Fascioli and S. Nichele, "Stereo vision-based vehicle detection," in Proceedings of the IEEE Intelligent Vehicles Symposium, 2000, pp. 39-44.
[19] M. Betke, E. Haritaoglu and L.S. Davis, "Multiple Vehicle Detection and Tracking in Hard Real-Time," in Proceedings of the 1996 IEEE Intelligent Vehicles Symposium, Sep. 1996, pp. 351-356.
[20] J. Marchant, C. Onyango and, M. Street, “Computer vision for potato inspection without singulation,” Computers and Electronics in Agriculture, vol. 4, no. 3, pp. 235-244, 1990.
[21] C. Anderson, Peter Burt and G. van der Wal, “Change detection and tracking using pyramid transformation techniques,” in Proceedings of SPIE - Intelligent Robots and Computer Vision, Vol. 579, pp. 72-78, 1985.
[22] 鍾國亮編著，影像處理與電腦視覺，第二版，東華書局，台北，2004。
[23] M. J. Swain and D. H. Ballard, “Colour indexing,” International Journal of Computer Vision, Vol. 7, pp. 11-32, 1999.
[24] 陳又慈，應用於監控系統上之即時人物追蹤、區分與異常行為偵測演算法，國立成功大學電腦與通信工程研究所碩士論文，民國93年。
[25] A. C. Sanderson, and L. E. Weiss, “Image-base visual servo control using relational graph error signals,” in Proceedings of IEEE International Conference on Cybernetics and Soceity, pp. 1074-1077, 1980.
[26] 鄒華龍，即時的人物偵測與追蹤，大同大學電機工程研究所碩士論文，民國91年。
[27] J. Serra, “Image analysis and mathematical morphology,” London:Academic, 1982.
[28] P. Soille, “Morphological image analysis-principles and application,” Springer, 2003.
[29] 游世豪，交通自動監控系統之研究，元智大學電機工程研究所碩士論文，民國91年。
[30] L. D. Stefano and A. Bulgarelli, “A simple and efficient connected components labeling algorithm,” in Proceedings of 10th International Conference on Image Analysis, pp. 322-327, 1999.
[31] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis and Machine vision, Brooks/Cole Publishing Company, 1999.