基于交通视频的交通拥堵状态自动识别方法

doi:10.3969/j.issn.1002-0268.2014.01.020

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1325 KB) HTML ()
输出: BibTeX | EndNote (RIS)

摘要 With the increasing demand for traffic information services as well as the extensive deployment of traffic video surveillance, there is a critical need for realizing automatic identification of congestion state with traffic video. To this end, this study proposes a traffic congestion evaluation model with adaptive learning ability. The qualitative process of the proposed model has been previously analyzed. In this method, the video image feature sets are extracted initially, followed by the state classification model training and learning via support vector machine. Subsequently, genetic algorithm is used to realize the online adaptive optimization. The field experimental results indicate that this method has high recognition accuracy, fast processing speed, and strong adaptive ability, and it can provide an appropriate solution for solving the problem of all-day traffic congestion states recognition based on the traffic video information.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ： traffic engineering, congestion states recognition, traffic video analysis, support vector machine (SVM), genetic algorithm (GA), machine learning (ML)

Abstract：With the increasing demand for traffic information services as well as the extensive deployment of traffic video surveillance, there is a critical need for realizing automatic identification of congestion state with traffic video. To this end, this study proposes a traffic congestion evaluation model with adaptive learning ability. The qualitative process of the proposed model has been previously analyzed. In this method, the video image feature sets are extracted initially, followed by the state classification model training and learning via support vector machine. Subsequently, genetic algorithm is used to realize the online adaptive optimization. The field experimental results indicate that this method has high recognition accuracy, fast processing speed, and strong adaptive ability, and it can provide an appropriate solution for solving the problem of all-day traffic congestion states recognition based on the traffic video information.

Key words： traffic engineering congestion states recognition traffic video analysis support vector machine (SVM) genetic algorithm (GA) machine learning (ML)

收稿日期: 2013-12-29

基金资助:Supported by the National Natural Science Foundation of China(No.61304199);the Major Projects of Science and Technology of Fujian Province of China(No.2011HZ0002-1);the Traffic Scientific Research Planning Project of Fujian Province (No.201122);and the Natural Science Foundation of Fujian Province of China (No.2012J06015, No.2013J01214)

通讯作者: ZOU Fu-min, fmzou@fjut.edu.cn E-mail: fmzou@fjut.edu.cn

引用本文:

邹复民, 廖律超, 蒋新华, 赖宏图. 基于交通视频的交通拥堵状态自动识别方法[J]. Journal of Highway and Transportation Research and Development, 2014, 8(2): 72-80.
ZOU Fu-min, LIAO Lü-chao, JIANG Xin-hua, LAI Hong-tu. An Automatic Recognition Approach for Traffic Congestion States Based on Traffic Video. Journal of Highway and Transportation Research and Development, 2014, 8(2): 72-80.

链接本文:

http://manu27.magtech.com.cn/Jwk_gljtkj_en/CN/10.3969/j.issn.1002-0268.2014.01.020 或 http://manu27.magtech.com.cn/Jwk_gljtkj_en/CN/Y2014/V8/I2/72

[1] KAMIJO S, MATSUSHITA Y, IKEUCHI K, et al. Traffic Monitoring and Accident Detection at Intersections[J]. IEEE Transactions on Intelligent Transportation Systems,2000, 1(2):108-118.
[2] REINARTZ P, LACHAISE M, SCHMEER E, et al. Traffic Monitoring with Serial Images from Airborne Cameras[J]. ISPRS Journal of Photogrammetry & Remote Sensing,2006, 61(3/4):149-158.
[3] PALUBINSKAS G, RUNGE H. Detection of Traffic Congestion in Airborne SAR Imagery[C]//Proceedings of 7th European Conference on Synthetic Aperture Radar (EUSAR). Friedrichshafen, Germany:VDE Conference Publications,2008:1-4.
[4] TOTH C K, GREJNER-BRZEZINSKA D. Extracting Dynamic Spatial Data from Airborne Imaging Sensors to Support Traffic Flow Estimation[J]. ISPRS Journal of Photogrammetry & Remote Sensing,2006,61(3/4):137-148.
[5] OKELLY M, MATISZIW T, LI R, et al. Identifying Truck Correspondence in Multi-frame Imagery[J]. Transportation Research Part C:Emerging Technologies, 2005, 13(1):1-17.
[6] SANTINI S. Analysis of Traffic Flow in Urban Areas Using Web Cameras[C]//Proceedings of 5th IEEE Workshop on Applications of Computer Vision. Palm Springs, CA:IEEE, 2000:140-145.
[7] LI Lin, HU Jian-ming, HUANG Qiao, et al. A Fuzzy Hidden Markov Model for Traffic Status Classification Based on Video Features[C]//IMACS Multiconference on Computational Engineering in Systems Applications (CESA). Beijing:IEEE, 2006:2050-2055.
[8] LOZANO A, MANFREDI G, NIEDDU L. An Algorithm for the Recognition of Levels of Congestion in Road Traffic Problems[J]. Mathematics and Computers in Simulation,2009, 79(6):1926-1934.
[9] LLORCA D F, SOTELO M A, SáNCHEZ S, et al. Traffic Data Collection for Floating Car Data Enhancement in V2I Networks[J]. EURASIP Journal on Advances in Signal Processing, 2010, 2010:1-13.
[10] BI Song, HAN Li-qun, ZHOND Yi-xin, et al. All-day Traffic States Recognition System without Vehicle Segmentation[J]. The Journal of China Universities of Posts and Telecommunications, 2011, 18(2):1-11.
[11] FU Yan, WANG Yao-wei, WANG Wei-qiang, et al. Content-based Natural Image Classification and Retrieval Using SVM[J]. Chinese Journal of Computers, 2003, 26(10):1261-1265. (in Chinese)
[12] GUAN Wei. Qualitative Modeling Method for Macro-traffic Flow[J]. China Civil Engineering Journal, 2003, 36(7):66-71. (in Chinese)
[13] CHEN Xiao-hong, QIAN Da-lin. Forecast of Traffic Jam at Intersections on Urban Road[J]. Journal of South China University of Technology:Natural Science Edition, 2010, 38(7):72-77. (in Chinese)
[14] HERMAN R, PRIGOGINE I. A Two-fluid Approach to Town Traffic[J]. Science, 1979, 204(4389):148-151.
[15] HERMAN R, ARDEKANI S. Characterizing Traffic Conditions in Urban Areas[J]. Transportation Science,1984, 18(2):101-140.
[16] WANG Dian-hai, CHEN Song, WEI Qiang, et al. Discrimination Model for Macroscopic Traffic Conditions of Urban Networks Using Two-fluid Theory[J]. Journal of Southeast University:Natural Science Edition,2011, 41(5):1091-1103. (in Chinese)
[17] YIN Hong-tao,FU Ping,SHA Xue-jun. Face Recognition Based on DCT and LDA[J]. Acta Electronica Sinica, 2009, 37(10):2212-2214. (in Chinese)