臺灣博碩士論文加值系統

隨著車子的增加，我們需要更有效率的管理交通系統，而其中一個重要的課題，即是降低意外的發生。在某些路段，交通法規上並不允許車輛作變換車道的動作，因為在這些路段變換車道極易引起危險而造成意外。因此本篇論文提出了一個利用影像處理技巧來偵測車輛變換車道的方法。本篇論文採用的方法，是從巨觀的方式，也就是不先偵測出一輛輛的車子，個別追蹤，再判斷是否有變換車道的動作，而是利用觀察線，將觀察線上求得的移動向量(motion vector)轉換到時空圖，再從時空圖上判斷車輛變換車道的情形。經實驗結果，本系統可以有效偵測車輛變換車道並紀錄下來。本方法的優點是不需對個別的車輛作追蹤，亦不需要事先對相機作矯正的動作。

As the number of vehicles increased rapidly, we need to manage the traffic system more efficiently. One of the important issues is to reduce the occurring rate of accidents. In some road sections it is illegal to do lane change according to traffic regulations. The reason is that doing lane change in these road sections has potential danger to cause accidents. Therefore we proposed a method to detect vehicles that violate the rule based on image processing technique. In this paper the behavior of lane change will be detected from a macroscopic point of view. It means that we don’t detect an individual vehicle and track it to see if it is doing lane change. Instead we analyze the setting region and transform the information obtained from images to a 2D spatial-temporal diagram. We then extract lane change events from the spatial-temporal diagram. Via experiments the system is proven to be able to detect lane change event efficiently.

第一章緒論1
1.1研究動機1
1.2重要性4
第二章先前相關研究6
2.1車子的偵測6
2.1.1以模型為基礎(Model-based)方法6
2.1.2以區域為基礎(Region-based)方法8
2.1.3以輪廓為(Contour-based)方法11
2.1.4以特徵為基礎(Feature-based)方法12
2.1.5其他方法13
2.2時空圖 (Spatial-Temporal Diagram)15
第三章我們的方法18
3.1系統概觀18
3.2系統流程19
3.3詳細的偵測步驟22
3.3.1設定觀察線22
3.3.2判斷線上每一點並計算其移動向量23
3.3.3去除可能誤判的狀況25
3.3.4轉換移動向量至時空圖27
3.3.5分類(Grouping)28
3.3.6推估在不同影像中組成元件的對應情形30
3.3.7偵測車輛變換車道32
第四章實驗結果33
4.1實驗環境及裝置33
4.2偵測車輛變換車道34
4.2.1人工繪製的影像測試34
4.2.2實際道路影像測試34
4.3各種狀況分析35
第五章結論44
參考文獻47

[1]運輸研究所智慧型運輸系統網站, http://www.iot.gov.tw/its/.
[2]ITS America, http://www.itsa.org/.
[3]VERTIS, http://www.vertis.or.jp/.
[4]ITS Korea, http://www.itskorea.or.kr/.
[5]ITS Australia, http://www.its-australia.com.au/.
[6]ITS Europe, http://www.ertico.com/.
[7]ITS Taiwan, http://www.its-taiwan.org.tw/.
[8]S. Chen, Z.P. Sun, B. Bridge, “Automatic Traffic Monitoring by Intelligent Sound Detection”, Proceedings of IEEE Conference on Intelligent Transportation System, 1997, pp: 171-176.
[9]T. Matsuo, Y. Kaneko, M. Matano, “Introduction of Intelligent Vehicle Detection Sensors”, Proceedings of IEEE Conference on Intelligent Transportation System, 1999, pp: 709-713.
[10]Andrew H.S. Lai, Nelson H.C. Yung, “Vehicle-Type Identification Through Automated Virtual Loop Assignment and Block-Based Direction-Biased Motion Estimation”, IEEE Transactions on Intelligent Transportation Systems, Volume: 1, Issue: 2, June, 2000, pp: 86-97.
[11]K.D. Baker, G.D. Sullivan, “Performance Assessment of Model-Based Tracking”, Proceedings of IEEE Workshop on Applications of Computer Vision, 1992, pp: 28-35.
[12]D. Koller, K. Daniilidis, H. Nagel, “Model-Based Object Tracking in Monocular Image Sequence of Road Traffic Scenes”, International Journal of Computer Vision, 1993, pp: 257-281.
[13]Nelson H.C. Yung, Andrew H.S. Lai, “Detection of Vehicle Occlusion Using a Generalized Deformable Model”, IEEE ISCAS’98, vol. 4, 1998, pp: 154-157.
[14]M.D. Jolly, S. Lakshmanan, A.K. Jain, “Vehicle Segmentation and Classification Using Deformable Templates”, IEEE Transaction on Pattern Analysis and Machine Intelligence, Volume: 18, Issue: 3, March, 1996, pp: 293-308.
[15]M. Kilger, “A Shadow Handler in a Video-Based Real-Time Traffic Monitoring System”, Proceedings of IEEE Workshop on Applications of Computer Vision, 1992, pp: 11-18.
[16]K.P. Karmann, A. Brandt, “Moving Object Recognition Using an Adaptive Background Memory”, Time-Varying Image Processing and Moving Object Recognition II, V. Cappellini, editor, Elsevier Science Publishers, 1990, pp: 289-296.
[17]O. Masoud, N.P. Papanikolopoulos, “The Use of Computer Vision in Monitoring Weaving Sections”, IEEE Trans. on Intelligent Transportation System, Volume: 2, Issue: 1, March, 2001, pp: 18-25.
[18]Y.K. Jung, Y.S. Ho, “Traffic Parameter Extraction Using Video-Based Vehicle Tracking”, Proceedings of IEEE Conference on Intelligent Transportation System, 1999, pp: 764, 769.
[19]D. Koller, J. Weber, J. Malik, “Robust Multiple Car Tracking with Occlusion Reasoning”, ECCV, LNCS 800, Springer-Verlag, 1994, pp: 189-196.
[20]D. Koller, J. Weber, T. Huang, J. Malik, G. Ogasawara, B. Rao, S. Russell, “Towards Robust Automatic Traffic Scene Analysis in Real-Time”, Proceedings of the 12th IAPR International Conference on Pattern Recognition, vol. 1, 1994, pp: 126-193.
[21]B. Coifman, D. Beymer, P. McLauchlan, J. Malik, “A Real-Time Computer Vision System for Vehicle Tracking and Traffic Surveillance”, Transportation Research Part C, vol. 6, no. 4, 1998, pp: 271-288.
[22]M. Fathy, M.Y. Siyal, “A Window-Based Image Processing Technique for Quantitative and Qualitative Analysis of Road Traffic Parameters”, IEEE Trans. on Vehicular Technology, Volume: 47, Issue: 4, Nov, 1998, pp: 1342-1349.
[23]R. DeFauw, S. Lakshmanan, K.V. Prasad, “A System for Small Target Detection, Tracking, and Classification”, Proceedings of IEEE Conference on Intelligent Transportation System, 1999, pp: 639-644.
[24]Y. Iwasaki, “A Measurement Method of Pedestrian Traffic Flows by Use of Image Processing and Its Application to a Pedestrian Traffic Signal Control”, Proceedings of IEEE Conference on Intelligent Transportation System, 1999, pp: 310-313.
[25]H. Taniguchi, T. Nakamura, H. Furusawa, “Methods of Traffic Flow Measurement Using Spatio-Temporal Image”, Interational Conference on Image Processing, vol. 4, 1999, pp: 16-20.
[26]C. Li, K. Ikeuchi, M. Sakauchi, “Acquisition of Traffic Information Using a Video Camera with 2D Spatio-Temporal Image Transformation Technique”, Proceedings of IEEE Conference on Intelligent Transportation System, 1999, pp: 634-638.
[27]Z. Zhu, G. Xu, B. Yang, D. Shi, X. Lin, “VISATRAM: A Real-Time Vision System for Automatic Traffic Monitoring”, Image and Vision Computing, Volume: 18, Issue: 10, 2000, pp: 781-794.