臺灣博碩士論文加值系統

路口交通參數對於交通控制是非常重要的，它不僅可以做為道路設計的基礎，亦可做為號誌時制設定的指標，以往路口交通參數收集往往是以人工調查，近年來越來越多領域研究如何以影像偵測系統來收集交通參數，由於影像有大量資訊，故可利用影像處理(Image processing)及電腦視覺(Computer vison)技術將影像中的相關訊息擷取出來，有許多研究以固定式攝影機影像（CCTV），擷取交通影像並透過後端影像處理程式分析影像資料，已有相當的成果，然一般的研究多著重於高速公路及高架道路的偵測，對於市區路段及路口的交通參數偵測之研究則較少，推究其原因乃是由於高速公路及高架道路，沒有機車及行人的干擾因素，環境相對單純，偵測不易有誤差；反之，市區路口交通環境複雜，不僅存在大型車，小客車，機車，甚至存在著許多動向不定的行人，交通參數收集的難度因此大為提高。

本研究之研究核心主要包括了:(1)影像前處理、(2)前景分割、(3)陰影移除、(4)車輛追蹤、及(5)交通參數擷取，等五大項。本研究所開發之系統可由影像前處理獲得路段和路口之幾何型態，以及攝影機之初始設定參數。經影像前處理後，即可進行輸入影像之移動車輛擷取及陰影移除。目前本研究所開發之系統程式可進行一般市區路段、十字路口及五岔路口的交通參數擷取，透過參數擷取可計算各路口大車、小車、及機車之車流量參數，並可繪出各移動車輛之軌跡線，透過統計分析其結果，所擷取參數之準確率可達80%以上。

The traffic parameter at intersection is very important issue to traffic control. It is not only a basis of the road design, but a setting standard of the traffic signal. In recent years, more and more people research about how to develop an image detector system to collect traffic parameters. Since there is much information in the image, we can extract traffic parameter by image processing and computer vision technology.

The study of image detector on highway had been developed mature enough that it could extract traffic parameter with highly accurate rate. However, the researches about data collection at intersection are rare. The possible reason may be that intersections are more complex than highways; vehicles are difficult to be tracked well at intersections. In Taiwan, there are many motorcycles and pedestrians at intersection. Because of some characteristics of it, motorcycles are difficult detect at intersections. It becomes a challenge for image detector system to have reliable ability of vehicle detection.

This study is mainly composed of five stages: (1)pre-processing, (2)foreground segmentation,(3)shadow removal, (4)vehicle tracking and (5)traffic parameters extraction. The pre-processing is developed to obtain the information of road geometry and calibrate the camera. After the preprocessing is done, the foreground segmentation and shadow removal continue to segment the moving vehicles from the input images.

According to the results, the average success rates of different vehicles counting are higher than 80%. Moreover, it shows that this system is capable of successfully extracting the traffic parameters, including trajectory of the moving vehicle at road and various intersections.

誌謝 I
摘要 III
Abstract V
目錄 VII
圖目錄 XI
表目錄 XV
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 2
1.3 研究範圍 3
1.4 研究流程 3
第二章 文獻回顧 5
2.1 影像處理概論 5
2.2基本影像處理方法 7
2.2.1 影像插補 8
2.2.1.1 Bilinear Interpolation 8
2.2.2 影像濾波器 9
2.2.2.1 平滑線性濾波器 10
2.2.2.2 高斯濾波器(Gaussian filter) 11
2.2.3 邊緣偵測 12
2.2.4 影像分割 13
2.2.4.1門檻值之定義 14
2.2.4.2臨界值法 14
2.2.5 型態學影像處理 17
2.2.6 區塊標記 19
第三章 影像式路口偵測系統介紹與開發 21
3.1 系統概述 21
3.1.1 本研究所使用之軟硬體 21
3.1.1.1 硬體 21
3.1.1.2 軟體 22
3.1.2本研究之影像環境 22
3.1.3本研究之影像特性 24
3.1.4 本研究系統處理流程 25
3.2 系統前置處理 27
3.2.1 背景影像建立 28
3.2.1.1 漸近式背景建立法 28
3.2.2 座標轉換模式 33
3.2.2.1消失點(vanishing point)之定義 35
3.3 車輛偵測 36
3.3.1 前景分割 37
3.3.1.1 動態門檻值之建立 38
3.3.1.2 型態學影像處理 38
3.3.1.3 區塊分析 39
3.3.1.4 影像缺陷修補 40
3.3.2陰影移除 41
3.3.2.1陰影之性質 42
3.3.2.2陰影移除方法 43
3.4 車輛追蹤 46
3.4.1車輛分割 47
3.4.2車輛追蹤模式 50
3.4.2.1 車輛初始化追蹤及終結追蹤 51
3.4.2.2 濾波器預測模式 52
3.4.2.3車輛特徵比對模式 55
3.4.2.4車輛資訊彌補模式 57
第四章 系統驗證分析 59
4.1 實驗介紹 59
4.2 系統使用者介面介紹 61
4.2.1 主使用者介面介紹 62
4.2.2 影像前處理介面介紹 63
4.2.2.1 座標轉換設定模式 64
4.2.2.2 虛擬偵測區設定模式 66
4.3 多型態路口偵測 68
4.3.1 路段偵測 69
4.3.2 十字路口偵測 70
4.3.3 五岔路口偵測 71
4.4 實驗結果統計分析 73
4.5小結 79
第五章 結論與建議 83
5.1 研究結論 83
5.2 研究建議 84
參考文獻 87
英文部分 87
中文部分 90

英文部分
[1] Badenas J and Pla , F , “Segmentation Based on Region -Tracking In Image Sequences for Traffic Monitoring , ” Pattern Recognition ,Proceedings of the 14th International Conference , Vol.2 , pp999 , 1998.

[2] Bas, E. K. and J.D.Crisman, “An Easy to Install Camera Calibration For Traffic Monitoring,”IEEE Conference on Intelligent Transportation System,pp.362-366,1997.

[3] Benjamin Coifman, David Beymer, Philip McLauchlan, Jitendra Malik, “A real-time computer vision system for vehicle tracking and traffic surveillance.”Transportation Research Part C 6,271-288, 1998.

[4] B. Gloyer, H. Aghajan, K. Siu, and T. Kailath, “Video-based Freeway Monitoring System using RecursiveVehicle Tracking,”, Proc. Of IS&T/SPIE Symposium on Electronic Imaging: Science& Technology –Image and Video Processing, 1995.

[5] D Roller, K Daniilidis, HH Nagel, “ Model-Based Object “Tracking in Monocular Image Sequences of Road Traffic Scenes.” International Journal of Computer Vision,10:3, 257-281, 1993.

[6] Ferryman, J M, Worrall, A D, Sullivan, G D and Baker, K D. “A generic deformable model for vehicle recognition. ” Proc. of British Machine Vision Conference 1995, University of Birmingham, September 1995 (127-36).

[7] G D Sullivan, K D Baker, A D Worrall, C I Attwood and P R Remagnino,“Model-basedvehicle detection and classification using orthographic approximations,”Image. and Vision Computing, Vol. 15, No. 8, pp.649-654,Aug. 1997.

[8] J. Lee et al., “Morphologic edge detection,” IEEE J. Robot. Automat., vol. RA-3 no. 2, Apr. 1987.

[9] K. W. Dickinson and C. I. Wan, “Road traffic monitoring using the TRIP II system,” in IEE 2nd Int.Conf. Road Traffic Monitoring, London, U.K.,1989.

[10] M. Fathy, M.Y. Siyal, “ An image detection technique based on morphological edge detection and background differencing for real-time traffic analysis.”Parrern Recognition Letters, Vol.16, 1321-1330, 1995.

[11] M. Y. Siyal, and M. Fathy, “Real-time measurement of traffic queue parameters by using image processing techniques,” Proc. 5th IEE Int. Conf. Image Processing Applicant. (IPA95), Edinburgh, U.K., July 1995.

[12] M. Fathy and M. Y. Siyal, “A window-based edge detection technique for measuring road traffic parameters in real-time,” Real-Time Imaging1, 1995,pp. 297–305.

[13] M. Y. Siyal and M. Fathy, “Triple RISC image processor for real-time image Processing applications,” Inst. Electr. Eng. Electr. Lett., vol. 32,no. 24, pp.2224–2225, Nov. 1996.

[14] Malik, J.,S. Russell, J. Webber, T. Huang, “A machine Vision Based Surveilluance System for California Roads,”MOU-083 Final Report, November 1994.

[15] Rafael M. “Traffic Monitoring and Control Using Machine Vision: A Survey,”IEEE on Industrial Electronics, Vol. IE-32, No.3, 1985.

[16] Rafael M. “Application of Machine Vision to Traffic Monitoring and Control,”IEEE Transaction on vehicular technology, Vol.38, No.3, 1989.

[17] Rafael C.Gonzalez, Richard E. Woods “Digital Image Processing，2nd edition”, Prenice Hall, 2002.

[18] R. Cucchiara, M. Piccardi, A. Prati, N. Scarabottolo, Real-time detection of moving vehicles, Image Analysis and Proceeding, 1999. Proceedings.International Conference on, 1999, pp.618-623, 1999.

[19] Rita Cucchiara , Massimo Piccardi, Paola Mello., “Image analysis and rule-based reasoning for a traffic monitoring system”, IEEE Transaction on intelligent transportation system, vol. 1,No. 2 , Page(s):119-128, June 2000.

[20] Ramesh Jain. Rangachar Kasturi. Brian G.Schunck, “Machine Vision, ”McGraw-Hill International Editions, 1995.

[21] Se Hyun Park, Keechul Jung, Jun Koo Hea, and Hang Joon Kim, “Vision-based Traffic Surveillance System on the Internet” Dept. of Computer Engineering, Kyungpook National University, Republic of Korea.

[22] Schlutsmeyer, A. P., “Wide Area Detection System (WADS) ”, FHWA-RD-82-144, Federal Highway Administration, September 1982.

[23] S. Takaba et al., “ A traffic flow measuring system using a solid state sensor,” in Proc. IEE Conf. Road Traffic Data Collection, London, U.K.,1984.

[24] Song , KT and Tal , JC. , “Image-Based Traffic Monitoring with Shadow Suppression,” Proceedings of the IEEE , Vol95 , No.2 , pp.413-426. 2007.

[25] Veeraraghavan, H , Masoud , O., Papanikolopoulos, N.P. , “ Computer Vision Algorithms for Intersection Monitoring”, Transactions on Intelligent Transportation Systems, Vol.4 , No2 , pp 78 -79 , 2003.

[26] Xiaxi Huang and Nikolaos V. Boulgouris , “ Robust Object Segmentation using Adaptive Thresholding”, Department of Electronic Engineering King’s College London United Kingdom,2007.


中文部分

[1]林清波，基於即時影像追蹤之交通監控系統，國立交通大學電機與控制工程學系碩士論文，民國91年7月。

[2]許威烈，以熵為特徵之視覺化交通監視系統，國立中央大學資訊工程研究所博士論文，民國93年6月。

[3]吳耀然，電腦視覺為基礎之交通辨識技術應用於車載機駕駛技術輔助與交通監控系統研究，國立台灣大學土木工程學研究所碩士論文，民國93年6月。

[4]曾佩婷，在特定車道行駛之大型車偵測與追蹤，國立中央大學資訊工程研究所碩士論文，民國94年6月。

[5]黃婉婷，適用於物體追蹤一維時空域濾波器之設計與應用，國立台灣大學電信工程學研究所碩士論文，民國94年6月。

[6]鄭其政，影像監控系統交通參數擷取技術之研究，國立台灣大學土木工程學研究所碩士論文，民國95年6月。

[7]蔡濬帆，平行線段模型之車道偵測與具自動更新功能之車輛偵測，國立台灣大學資訊工程學研究所碩士論文，民國95年6月。

[8]林銘樂，夜間即時影像處理擷取交通參數之研究，國立台灣大學土木工程學研究所碩士論文，民國96年6月。

[9]陳彥政，影像式偵測器於路口交通參數之擷取研究，國立台灣大學土木工程學研究所碩士論文，民國97年6月。