Traffic Flow Investigation at Intersections by Applying Image Analysis Techniques 吳詮振、曾逸鴻
E-mail: [email protected]
ABSTRACT
Automatic traffic monitoring has always been the goal of intelligent transportation systems. However, the traditional monitoring work of traffic intersections most still rely on manual count methods to survey traffic volumes by visual observation now, that wastes much human resources and time costs , while manual count methods are not precise and accuracy. In this paper, at the original region and the goal region we use multi-camera to detect foreground objects and extract and transform the features, and then store the features into the temporary database. According to the time difference mechanism, we extract the goal region of vehicle features to match the original region of vehicles features. If the two objects’ features are be transformed and matched by extracting objects
’ features(position, shape, color) are similar, the two objects will be the same vehicle. In addition, in this paper it can be used to automatically determine the region of interest(ROI) by the traffic flow of continuous images. It detects all vehicles in ROI to reduce processing time of the frame. The results of our research can save human resource, and does not use manual count method to survey; on the other hand, it also can automatically survey turning traffic flow. In order to provide traffic information to Traffic Control Center(TCC), our systems can be more effective controlled by automatically surveying turning traffic flow at the
intersection, so that each traffic area can be achieved the most efficient use by controlling the traffic signals, easing traffic flow, and reducing the opportunity of idle lanes.
Keywords : multiple camera、video surveillance systems、feature extraction、image analysis Table of Contents
中文摘要 ．．．．．．．．．．．．．．．．．．．．．．iii 英文摘要 ．．．．．．．．．．．．．．．．．．．．
．．iv 誌謝詞 ．．．．．．．．．．．．．．．．．．．．．．v 內容目錄 ．．．．．．．．．．．．．．．．．
．．．．．vi 表目錄 ．．．．．．．．．．．．．．．．．．．．．．viii 圖目錄 ．．．．．．．．．．．．．
．．．．．．．．．ix 第一章 緒論 ．．．．．．．．．．．．．．．．．．．1 第一節 研究背景與動機 ．．
．．．．．．．．．．1 第二節 研究目的 ．．．．．．．．．．．．．．．4 第三節 系統流程 ．．．．
．．．．．．．．．．．5 第四節 研究範圍與限制 ．．．．．．．．．．．．7 第五節 論文架構 ．．．
．．．．．．．．．．．．7 第二章 文獻探討 ．．．．．．．．．．．．．．．．．8 第一節 前景物體偵測
．．．．．．．．．．．．．8 第二節 移動物體追蹤 ．．．．．．．．．．．．．10 第三節 車道偵測與 車流量統計 ．．．．．．．．．11 第三章 移動車輛之偵測與比對 ．．．．．．．．．．．15 第一節 移動車 輛偵測 ．．．．．．．．．．．．．15 第二節 車輛特徵抽取、轉換與比對 ．．．．．．．21 第四章 交叉路 口車流統計與判定 ．．．．．．．．．．37 第一節 關注區域(ROI)自動判定 ．．．．．．．．．37 第二節 關注區域(ROI)車輛之比對與統計 ．．．．46 第五章 實驗結果與分析 ．．．．．．．．．．．．．．49 第 一節 實驗結果 ．．．．．．．．．．．．．．．49 第二節 錯誤分析 ．．．．．．．．．．．．．．．52 第 六章 結論．．．．．．．．．．．．．．．．．．．．57 參考文獻 ．．．．．．．．．．．．．．．．．．．．．
．59
REFERENCES
一、中文部份 [1]交通部統計處(2009)，機動車輛登記數[線上資料]，來源: http://www.motc.gov.tw/motchypage/monthly_report/23050.pdf [2010, June 30]。
[2]交通部統計處(2009)，臺灣地區道路概況[線上資料]，來源:
http://www.motc.gov.tw/mocwebGIP/wSite/public/Attachment/f1273645527177.doc [2010, June 30]。
[3]顏應明(2002)，道路交通特性調查與統計分析[線上資料]，來源: http://safety2.iot.gov.tw/technology/files/91/二-3_顏應明_道路交通特 性調查與統計分析.pdf [2010, June 30]。 二、英文部分 [4]Boltz, S., Debreuve, E., & Barlaud, M. (2009). High-dimensional statistical measure for region-of-interest tracking. IEEE Transactions on Image Processing, 18(6), 1266-1283.
[5]Bugeau, A., & Perez, P. (2009). Detection and segmentation of moving objects in complex scenes. Computer Vision and Image Understanding, 113(4), 459-476.
[6]Carmona, E. J., Mart?nez-Cantos, J., & Mira, J. (2008). A new video segmentation method of moving objects based on blob-level knowledge.
Pattern Recognition Letters, 29(3), 272-285.
[7]Cheng, H. Y., Jeng, B. S., Tseng, P. T., & Fan, K. C. (2006). Lane detection with moving vehicles in the traffic scenes. IEEE Transactions on Intelligent Transportation Systems, 7(4), 571-582.
[8]Cheng, W. H., Chu, W. T., Kuo, J. H., & Wu, J. L. (2005). Automatic video region-of-interest determination based on user attention model. In Proceedings of IEEE International Symposium on Circuits and Systems, 4, 3219-3222.
[9]Davis, J. W., & Sharma, V. (2007). Background-subtraction using contour-based fusion of thermal and visible imagery. Computer Vision and Image Understanding, 106(2-3), 162-182.
[10]Duda, R. O., & Hart, P. E. (1972). Use of the hough transformation to detect lines and curves in pictures. Comm. ACM, 15(1), 11-15.
[11]Gao, X., Yang, Y., Tao, D., & Li, X. (2009). Discriminative optical flow tensor for video semantic analysis. Computer Vision and Image Understanding, 113(3), 372-383.
[12]Garber, N. J. , & Hoel, L. A. (2008). Traffic and highway engineering (4th ed.). California:Cengage Learning.
[13]Ge, J., Luo, Y., & Tei, G. (2009). Real-time pedestrian detection and tracking at nighttime for driver-assistance systems. IEEE Transactions on Intelligent Transportation Systems, 10(2), 283-298.
[14]Gonzalez, R. C., & Woods, R. E. (2007). Digital image processing(3nd ed.). New Jersey:Prentice Hall.
[15]Guo, Y., Hsu, S., Sawhney, H. S., Kumar, R., & Shan, Y. (2007). Robust object matching for persistent tracking with heterogeneous features.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(5), 824-839.
[16]Jung, C. R. (2009). Efficient background subtraction and shadow removal for monochromatic video sequences. IEEE Transactions on Multimedia, 11(3), 571-577.
[17]Kanhere, N. K., & Birchfield, S. T. (2008). Real-time incremental segmentation and tracking of vehicles at low camera angles using stable features. IEEE Transactions on Intelligent Transportation Systems, 9(1), 148-160.
[18]Kanungo, T., Mount, D. M., Netanyahu, N. S., Piatko, C. D., Silverman, R., & Wu, A. Y. (2002). An efficient k-means clustering algorithm:
Analysis and implementation. IEEE Transaction on Pattern Analysis and Machine Intelligence, 24(7), 881-892.
[19]Lee, T. S., Lee, E. M., Park, H. T., Kwag, Y. K., Lim, S. S., Baek, J. H., & Hwang, B. W. (2003). Implementation of traffic flow measuring algorithm using real-time dynamic image processing. In J. L. Crowley et al. (Eds.), International Conference on Computer Vision Systems, 2626, 78-87.
[20]Nagatani, T. (2005). Chaos and dynamical transition of a single vehicle induced by traffic light and speedup. Physica A, 348(15), 561-571.
[21]Shen, S., Tong, M., Deng, H., Liu, Y., Wu, X., Wakabayashi, K., & Koike, H. (2008). Model based human motion tracking using probability evolutionary algorithm. Pattern Recognition Letters, 29(13), 1877-1886.
[22]Smith, D., McIntyre, J., Anderson-Wilk, M., & Moreau, S. (2002). Handbook of Simplified Practice for Traffic Studies. Iowa: University of Iowa.
[23]Sundaramoorthi, G., Yezzi, A., & Mennucci, A. C. (2008). Coarse-to-Fine segmentation and tracking using sobolev active contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(5), 851-864.
[24]Tseng, Y. H., & Xiao, H. Z. (2005). Background model construction and maintenance in a video surveillance system. In Proceedings of the 18th Conference on Computer Vision, Graphics and Image Processing, 303-309.
[25]Wang, F. Y. (2006). Driving into the future with ITS. IEEE Intelligent Systems, 21(3), 94-95.
[26]Wang, J., & Yagi, Y. (2008). Integrating color and shape-texture features for adaptive real-time object tracking. IEEE Transactions on Image Processing, 17(2), 235-240.
[27]Yim, Y. U., & Oh, S. Y. (2003). Three-feature based automatic lane detection algorithm(TFALDA) for autonomous driving. IEEE Transactions on Intelligent Transportation Systems, 4(4), 219-225.
[28]Yu, X., & Leong, H. W. (2004). A robust hough-based algorithm for partial ellipse detection in broadcast soccer video. Proc. Of IEEE Intl.
Conf. on Computer Vision, 3, 27-30.
[29]Zhang, J., & Gong, S. (2009). People detection in low-resolution video with non-stationary background. Image and Vision Computing, 27(4), 437-443.
[30]Zhang, R., Zhang, S., & Yu, S. (2007). Moving objects detection method based on brightness distortion and chromaticity distortion. IEEE Transactions on Consumer Electronics, 53(3), 1177-1185.
