基于视频处理的城市道路交通拥堵判别技术研究
|
摘要
交通拥堵判别技术是及时掌握城市道路交通拥堵状况的重要方式之一。视频检测技术由于具有处理信息量大、无需破坏地面、安装维护方便等优点,因此,在道路交通拥堵判别方面具有较好的应用前景。现有交通视频检测技术一般侧重于道路交通事件检测或交通参数提取,已取得了良好的进展,但尚未用于城市道路交通拥堵的实时判别。因此,充分发挥视频检测技术的优势,研究从整体上实时地判别城市道路交通拥堵状况的方法,对于提高交通视频检测技术的实用性具有重要意义。
论文在深入分析基于视频处理的城市道路交通拥堵判别的问题和难点后,重点研究基于视频的交通特征参数获取和交通拥堵判别算法两部分内容。
在基于视频的交通特征参数获取方面,针对城市道路的复杂情况,选取了基于非参数核密度的背景建模方法并提出了基于概率比较的目标去噪方法实现车辆目标的提取,然后通过卡尔曼滤波跟踪与虚拟检测线法获取交通特征参数。与传统的背景建模方法相比,基于非参数核密度的背景建模方法具有更好的建模效果,更适应复杂场景的建模。提出的基于概率比较的目标去噪方法能有效去除路边抖动树叶造成的干扰,较好地实现了车辆目标的检测提取,进而提高了车辆识别的精度。
在交通拥堵判别算法方面,改进了传统的基于模糊综合判别的交通拥堵判别模型。本文在分析交通特征参数变化特征的基础上,提出先根据速度进行道路交通拥堵预判别,建立不同预判别等级下的参数权重值集合,然后结合预判别结果、实际判别结果和历史数据获得最终的交通拥堵判别结果。由于本文考虑了交通特征参数在不同的交通状态下具有不同的重要性,因此,本文方法能更好地拟合城市道路交通拥堵判别情况。
最后,结合提出的基于视频的交通特征参数提取和交通拥堵判别算法,建立了基于视频处理的城市道路交通拥堵判别实验系统,并利用重庆市的城市道路视频监控数据,在VC环境下进行了验证实验。结果表明,给出的方法能较准确地提取交通特征参数,改进的拥堵判别模型比直接用模糊综合判别算法二级跳变率更低,能实时、高效地实现城市道路交通拥堵判别,具有较好的准确性及可行性。
Traffic congestion identification technology is one of the important ways to grasp the status of city road congestion. Video processing technology can process large amount of information, and easy to install without destruction of the ground. Because of these advantages, video processing technology has good application prospects in the field of traffic congestion identification of city road. Now, existed video processing technology which generally focused on road traffic incident detection or traffic parameter extraction has acquired some good results, but it hasn’t been used in the part of traffic congestion identification. Therefore, study on video-based traffic congestion identification technology of city road, from the aspect of efficiency and real-time, has important practical significance.
This paper studied on the way of traffic congestion identification technology of city road based on video, including two aspects: One is the method of getting the traffic parameters by image processing, the other is the algorithm of traffic congestion identification technology.
In the part of getting traffic parameters by image processing, the way of background modeling based on non-parametric kernel density algorithm was selected and the way of denoising by comparing probability was proposed. Then, Kalman filtering algorithm and the virtual test line were used to get the traffic parameters. The way of background modeling based on non-parametric kernel density algorithm has better results than other algorithm, and could model background for slow movement. The way of denoising by comparing probability can denoise caused by leaves jittering. The presented algorithm above can detect vehicle targets perfectly, and improve vehicle identification accuracy.
In the part of traffic congestion identification technology, we improved the traditional fuzzy clustering algorithm. Firstly, the city road traffic congestion was made pre-identification by speed, Secondly, on the results of pre-identification, the traffic parameters weight sets were built at different traffic states. Finally, the result was getted by combining with pre-identification results, the actual identification results and historical identification results. The presented algorithm had better result and described the real traffic better, in which the traffic parameters in different traffic states have different importance and stability.
Finally, the system of traffic congestion identification technology based on video was established using the video surveillance data in ChongQing. The experimental results show that this algorithm can get the traffic parameters more accurate, and the algorithm of traffic congestion identification has better sensitivity and lower percentage of two or more congestion level jumps. This system can realize the traffic congestion identification efficiently,and therefore improve the accuracy and feasibility.
论文在深入分析基于视频处理的城市道路交通拥堵判别的问题和难点后,重点研究基于视频的交通特征参数获取和交通拥堵判别算法两部分内容。
在基于视频的交通特征参数获取方面,针对城市道路的复杂情况,选取了基于非参数核密度的背景建模方法并提出了基于概率比较的目标去噪方法实现车辆目标的提取,然后通过卡尔曼滤波跟踪与虚拟检测线法获取交通特征参数。与传统的背景建模方法相比,基于非参数核密度的背景建模方法具有更好的建模效果,更适应复杂场景的建模。提出的基于概率比较的目标去噪方法能有效去除路边抖动树叶造成的干扰,较好地实现了车辆目标的检测提取,进而提高了车辆识别的精度。
在交通拥堵判别算法方面,改进了传统的基于模糊综合判别的交通拥堵判别模型。本文在分析交通特征参数变化特征的基础上,提出先根据速度进行道路交通拥堵预判别,建立不同预判别等级下的参数权重值集合,然后结合预判别结果、实际判别结果和历史数据获得最终的交通拥堵判别结果。由于本文考虑了交通特征参数在不同的交通状态下具有不同的重要性,因此,本文方法能更好地拟合城市道路交通拥堵判别情况。
最后,结合提出的基于视频的交通特征参数提取和交通拥堵判别算法,建立了基于视频处理的城市道路交通拥堵判别实验系统,并利用重庆市的城市道路视频监控数据,在VC环境下进行了验证实验。结果表明,给出的方法能较准确地提取交通特征参数,改进的拥堵判别模型比直接用模糊综合判别算法二级跳变率更低,能实时、高效地实现城市道路交通拥堵判别,具有较好的准确性及可行性。
Traffic congestion identification technology is one of the important ways to grasp the status of city road congestion. Video processing technology can process large amount of information, and easy to install without destruction of the ground. Because of these advantages, video processing technology has good application prospects in the field of traffic congestion identification of city road. Now, existed video processing technology which generally focused on road traffic incident detection or traffic parameter extraction has acquired some good results, but it hasn’t been used in the part of traffic congestion identification. Therefore, study on video-based traffic congestion identification technology of city road, from the aspect of efficiency and real-time, has important practical significance.
This paper studied on the way of traffic congestion identification technology of city road based on video, including two aspects: One is the method of getting the traffic parameters by image processing, the other is the algorithm of traffic congestion identification technology.
In the part of getting traffic parameters by image processing, the way of background modeling based on non-parametric kernel density algorithm was selected and the way of denoising by comparing probability was proposed. Then, Kalman filtering algorithm and the virtual test line were used to get the traffic parameters. The way of background modeling based on non-parametric kernel density algorithm has better results than other algorithm, and could model background for slow movement. The way of denoising by comparing probability can denoise caused by leaves jittering. The presented algorithm above can detect vehicle targets perfectly, and improve vehicle identification accuracy.
In the part of traffic congestion identification technology, we improved the traditional fuzzy clustering algorithm. Firstly, the city road traffic congestion was made pre-identification by speed, Secondly, on the results of pre-identification, the traffic parameters weight sets were built at different traffic states. Finally, the result was getted by combining with pre-identification results, the actual identification results and historical identification results. The presented algorithm had better result and described the real traffic better, in which the traffic parameters in different traffic states have different importance and stability.
Finally, the system of traffic congestion identification technology based on video was established using the video surveillance data in ChongQing. The experimental results show that this algorithm can get the traffic parameters more accurate, and the algorithm of traffic congestion identification has better sensitivity and lower percentage of two or more congestion level jumps. This system can realize the traffic congestion identification efficiently,and therefore improve the accuracy and feasibility.
引文
[1]何最红.基于视频流的交通流参数检测方法研究[D].广东工业大学硕士学位论文, 2006.6.
[2] SHANGA P, LUBY, KAMA S. The application of Holder exponent to traffic congestion warming[J]. Physical, 2006, 3(10):769-776.
[3]刘清.城市道路交通状况的F-评价及其实例研究[J].武汉交通科技大学学报, 2000, 24(5):473-475.
[4]谈蔚欣.基于分类器组合的交通拥堵预测[D].福州大学硕士学位论文, 2005.6.
[5]王东.城市交通拥堵状态自动判别方法研究[D].贵州大学硕士学位论文, 2008.9.
[6] Meyer, Michael. Alternative Methods for Measuring Congestion Levels[J]. Transportation Research Board, 1993, 8:78-80.
[7] Byrne, G. E and S M Mulhall. Congestion Management Data requirements and Comparisons[J]. Transportation Research Record, 1980, 5:65-68.
[8] Antony Stathopoulos, Matthew G. Karlaftis. Modeling the Duration of Urban Traffic Congestion[C]. Transportation Research Board Annual Meeting, 2002, 9:24-26.
[9] Congestion Management System for the Albuquerque Urban Area Final Report[C], 1995.10.
[10] Young-kee Jung, Kyu-Won Lee, and Yo-Sung Ho. Content-Based Event Retrieval Using Semantic Scene Interpretation for Automated Traffic Surveillance[J]. IEEE Transactions on Intelligent Transportation Systems, 2001, 13(2):151-163.
[11] Gerard Medioni, Isaac Cohen, Francois Bremond, Somboon Honggeng and Ramakant Nevada. Event Detection and Analysis from Video Streams[J]. IEEE Transactions on Pattern Analyse is and Machine Intelligence, 2001, 23(8):873-889.
[12] Rita Cucchiara, Massimo Piccardi, and Paola Mello. Image Analysis and Rule-Based Reasoning for a Traffic Monitoring System[J]. IEEE Transactions on Intelligent Transportation Systems, 2000, 12(1):119-130.
[13] Bejamin Maurin, Osama Masoud, Nikolaos Papanikolopoulos. Monitoring Crowded Traffic Scenes[C]. IEEE International Conference on Intelligent Transportation Systems (ITSC02), 2002, 9:19-24.
[14]彭雅芳.交通事件视频检测系统中图像处理算法的研究[D].武汉理工大学硕士学位论文, 2009.4.
[15] Video Imaging Vehicle Detection System[C]. Autoscope Incorporated, 1997.
[16]郭恒明,张鹏飞.基于环形线圈的城市道路段交通异常自动检测方法研究[J].上海公路,2001, 12(4):31-33.
[17]庄斌,杨晓光,李克平.道路交通拥挤事件判别准则与检测算法[J].中国公路学报, 2006, 19(3):82-86.
[18]杨兆升,杨庆芳,冯金巧.基于模糊综合推理的道路交通事件识别算法[J].公路交通科技, 2003, 20(4):92-94.
[19]姜紫峰,刘小坤.基于神经网络的交通事件检测算法[J].西安公路交通大学学报, 2000, 13(3):67-69.
[20]师海. Citilog视频系统在城市文通事件检测中的应用研究[D].复旦大学硕士学位论文, 2008.2.
[21]伍友龙.基于图像分析的高速公路交通事件检测算法研究[J].计算机应用技术, 2005, 9(4):32-35.
[22]邵祖峰.城市道路交通堵塞治理研究[J].城市交通, 2005, 1(3):71-73.
[23]孙莉芬.城市交通拥挤疏导决策支持系统的研究[D].华中科技大学硕士学位论文, 2005.6.
[24]姜桂艳.道路交通状态判别技术与应用[M].人民交通出版社, 2004.
[25]王玮,陈恩红,王煦法.基于贝叶斯方法的知识发现[J].小型微型计算机系统, 2000, 21(7):703-705.
[26]刘怀强.基于视频的车辆检测与跟踪技术研究[D].中国海洋大学硕士学位论文, 2006.6.
[27] Lipton A, Fujiyoshi H, Patil R. Moving target classification and tracking from real-time video[C] DARPA Image Understanding Workshop. Princeton, New Jersey, Proc of WACV, 1998, 12(6):8-14.
[28]郑江滨.智能视频监视研究[D].西安工业大学博士学位论文, 2002.6.
[29] Wang L, Hu W, Tan T. Recent. Developments in human motion analysis[J]. Pattern Recognition, 2003, 6(3): 585-601.
[30] Chris Stauffer, W.E.L Grimson. Adaptive background mixture models for real-time tracking[J]. IEEE Computer society Conference on Computer Vision and Pattern Recognition, 1999, 11(2):246-252.
[31] B.W.Silverman. Density estimation of statistics and data analysis[J]. Chapman and Hall, 1986
[32] Yaser Sheikh, Mubarak Shah. Bayesian Modeling of Dynamic Scenes for Object Detection[J]. IEEE Transactions on pattern analysis and machine intelligence, 2005, 27(11):1778-1792.
[33] Smith, E.A. and D.R. Phillips. Automated cloud tracking using precisely aligned digital picture[J]. IEEE Trans. Computers, 1972, 21(7):715-729.
[34] Isard, M. and A. Blake. Condensation-conditional density propagation for visual tracking[J]. International Journal on Computer Vision, 1998, 2(1):5-28.
[35] Lu, S., et al. Using multiple cues for hand tracking and model refinement[C]. In Computer Vision and Pattern Recognition, 2003 Proceedings. 2003 IEEE Computer Society Conference 2003.
[36] Zhujie and Y.L. Yu. Face recognition with eigenfaces. In Industrial Technology[C]. 1994. Proceedings of the IEEE International Conference 1994.
[37]景晓军,蔡安妮,孙景鳌.一种基于二维最大类间方差的图像分割算法[J].通信学报, 2001, 22(4):122-125.
[38]邓聚龙.灰色系统基本方法[M].华中科技大学出版社, 2004.
[39]高克林,刘淼.闸北区道路服务水平的灰色局势评价[J].交通与运输, 2008.5(5):43-47.
[40]白竹.城市主干路交通异常状态自动差别方法研究[D].吉林大学硕士学位论文, 2006.6.
[41]刘秉瀚,王伟智,方秀端.协同模式识别方法综述[J].系统工程与电子技术, 2003, 25(6):758-762.
[42]成卫,李江.模糊聚类法在基于交通冲突技术的交叉口安全评价中的应用[J].交通运输系统工程与信息, 2004, 4(2): 48-55.
[43]姜桂艳,江龙晖,王江锋.城市快速路交通拥挤识别方法[J].交通运输工程学报, 2006, 6(3):87-91.
[44]王殿海.交通流理论[M].人民交通出版社, 2002.
[45]马世勇,郑应文,柯栋忠.城市交通拥堵自动判别方法研究[J].福建电脑, 2007.1(1):7-8.
[46]杨祖元,黄席越,杜长海,唐明霞.基于FFCM聚类的城市交通拥堵判别研究[J].计算机应用研究, 2008, 25(9):2768-2770.
[47]李梅红.基于GPS浮动车的道路交通服务水平实时评估研究[D].重庆大学硕士学位论文, 2007.4.
[48]张继平,刘直芳.背景估计与运动目标检测跟踪[J].计算机技术与自动化, 2004, 23(4):51-54.
[49] Huwer S, Nie mann H. Adaptive change detection for real time surveillance applications. Proceedings, 3rd IEEE International workshop on Visual Surveillance[C]. 2000. 37-46.
[50] Wern C R, Azarbaycjani A, Darrell T, et al. Pfinder: Real time tracking human body [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19:780-785.
[51]朱胜利. Meanshift及相关算法在视频跟踪中的应用[D].浙江大学博士学位论文, 2006.4.
[52]何恒攀.基于序列图像的行人流量检测技术研究[D].重庆大学硕士学位论文, 2007. 4.
[53] Hui-zhong Zhuang. A Novel Algorithm for Background Updating and Target Tracking[C]. 2008 International Symposium on Computer Science and Computational Technology, 2008, 6:505-508.
[54] Elgammal A, Duraiswami R, Harwood D, etc. Background and foreground modeling usingnonparametric kernel density estimation for visual surveillance [J]. Proc. of the IEEE, 2002, 7:1151-1163.
[55]刘英霞,贺长伟.基于贝叶斯模型的动态背景检测[J].系统仿真学报, 2007, 21(11): 5042-5045.
[56]杨群生,黄继武,康显桂等.直方图加权均值滤波器[J].电子学报, 2004, 7 (32):1108-1111.
[57]支高英,郭文成.智能车辆导航中道路图像的处理[J].微计算机信息, 2009, 25(5):297-299.
[58]徐棍贺,贺耀,王夏黎.基于背景模型的运动车辆检测算法研究[J].微计算机信息, 2007, 4(23):120-121.
[59]田大增,郝永旦,哈明虎旦.一种新的去除视觉文本图像椒盐噪声的算法[J].计算机工程与应用, 2007, 14(4):81-83.
[60]朱芬芳,李维来.基于自适应背景更新的运动车辆检测技术[J].武汉理工大学学报, 2007, 29(11):140-142.
[61]王海虎,许志祥.智能交通检测与违法处理[J].电视应用, 2001, 3:29-32.
[62]吴庆翔,周永生等.一种新型的汽车闯红灯抓拍系统[C].第八届全国光电技术与系统学术会议论文专集, 1999, 5:31-33.
[2] SHANGA P, LUBY, KAMA S. The application of Holder exponent to traffic congestion warming[J]. Physical, 2006, 3(10):769-776.
[3]刘清.城市道路交通状况的F-评价及其实例研究[J].武汉交通科技大学学报, 2000, 24(5):473-475.
[4]谈蔚欣.基于分类器组合的交通拥堵预测[D].福州大学硕士学位论文, 2005.6.
[5]王东.城市交通拥堵状态自动判别方法研究[D].贵州大学硕士学位论文, 2008.9.
[6] Meyer, Michael. Alternative Methods for Measuring Congestion Levels[J]. Transportation Research Board, 1993, 8:78-80.
[7] Byrne, G. E and S M Mulhall. Congestion Management Data requirements and Comparisons[J]. Transportation Research Record, 1980, 5:65-68.
[8] Antony Stathopoulos, Matthew G. Karlaftis. Modeling the Duration of Urban Traffic Congestion[C]. Transportation Research Board Annual Meeting, 2002, 9:24-26.
[9] Congestion Management System for the Albuquerque Urban Area Final Report[C], 1995.10.
[10] Young-kee Jung, Kyu-Won Lee, and Yo-Sung Ho. Content-Based Event Retrieval Using Semantic Scene Interpretation for Automated Traffic Surveillance[J]. IEEE Transactions on Intelligent Transportation Systems, 2001, 13(2):151-163.
[11] Gerard Medioni, Isaac Cohen, Francois Bremond, Somboon Honggeng and Ramakant Nevada. Event Detection and Analysis from Video Streams[J]. IEEE Transactions on Pattern Analyse is and Machine Intelligence, 2001, 23(8):873-889.
[12] Rita Cucchiara, Massimo Piccardi, and Paola Mello. Image Analysis and Rule-Based Reasoning for a Traffic Monitoring System[J]. IEEE Transactions on Intelligent Transportation Systems, 2000, 12(1):119-130.
[13] Bejamin Maurin, Osama Masoud, Nikolaos Papanikolopoulos. Monitoring Crowded Traffic Scenes[C]. IEEE International Conference on Intelligent Transportation Systems (ITSC02), 2002, 9:19-24.
[14]彭雅芳.交通事件视频检测系统中图像处理算法的研究[D].武汉理工大学硕士学位论文, 2009.4.
[15] Video Imaging Vehicle Detection System[C]. Autoscope Incorporated, 1997.
[16]郭恒明,张鹏飞.基于环形线圈的城市道路段交通异常自动检测方法研究[J].上海公路,2001, 12(4):31-33.
[17]庄斌,杨晓光,李克平.道路交通拥挤事件判别准则与检测算法[J].中国公路学报, 2006, 19(3):82-86.
[18]杨兆升,杨庆芳,冯金巧.基于模糊综合推理的道路交通事件识别算法[J].公路交通科技, 2003, 20(4):92-94.
[19]姜紫峰,刘小坤.基于神经网络的交通事件检测算法[J].西安公路交通大学学报, 2000, 13(3):67-69.
[20]师海. Citilog视频系统在城市文通事件检测中的应用研究[D].复旦大学硕士学位论文, 2008.2.
[21]伍友龙.基于图像分析的高速公路交通事件检测算法研究[J].计算机应用技术, 2005, 9(4):32-35.
[22]邵祖峰.城市道路交通堵塞治理研究[J].城市交通, 2005, 1(3):71-73.
[23]孙莉芬.城市交通拥挤疏导决策支持系统的研究[D].华中科技大学硕士学位论文, 2005.6.
[24]姜桂艳.道路交通状态判别技术与应用[M].人民交通出版社, 2004.
[25]王玮,陈恩红,王煦法.基于贝叶斯方法的知识发现[J].小型微型计算机系统, 2000, 21(7):703-705.
[26]刘怀强.基于视频的车辆检测与跟踪技术研究[D].中国海洋大学硕士学位论文, 2006.6.
[27] Lipton A, Fujiyoshi H, Patil R. Moving target classification and tracking from real-time video[C] DARPA Image Understanding Workshop. Princeton, New Jersey, Proc of WACV, 1998, 12(6):8-14.
[28]郑江滨.智能视频监视研究[D].西安工业大学博士学位论文, 2002.6.
[29] Wang L, Hu W, Tan T. Recent. Developments in human motion analysis[J]. Pattern Recognition, 2003, 6(3): 585-601.
[30] Chris Stauffer, W.E.L Grimson. Adaptive background mixture models for real-time tracking[J]. IEEE Computer society Conference on Computer Vision and Pattern Recognition, 1999, 11(2):246-252.
[31] B.W.Silverman. Density estimation of statistics and data analysis[J]. Chapman and Hall, 1986
[32] Yaser Sheikh, Mubarak Shah. Bayesian Modeling of Dynamic Scenes for Object Detection[J]. IEEE Transactions on pattern analysis and machine intelligence, 2005, 27(11):1778-1792.
[33] Smith, E.A. and D.R. Phillips. Automated cloud tracking using precisely aligned digital picture[J]. IEEE Trans. Computers, 1972, 21(7):715-729.
[34] Isard, M. and A. Blake. Condensation-conditional density propagation for visual tracking[J]. International Journal on Computer Vision, 1998, 2(1):5-28.
[35] Lu, S., et al. Using multiple cues for hand tracking and model refinement[C]. In Computer Vision and Pattern Recognition, 2003 Proceedings. 2003 IEEE Computer Society Conference 2003.
[36] Zhujie and Y.L. Yu. Face recognition with eigenfaces. In Industrial Technology[C]. 1994. Proceedings of the IEEE International Conference 1994.
[37]景晓军,蔡安妮,孙景鳌.一种基于二维最大类间方差的图像分割算法[J].通信学报, 2001, 22(4):122-125.
[38]邓聚龙.灰色系统基本方法[M].华中科技大学出版社, 2004.
[39]高克林,刘淼.闸北区道路服务水平的灰色局势评价[J].交通与运输, 2008.5(5):43-47.
[40]白竹.城市主干路交通异常状态自动差别方法研究[D].吉林大学硕士学位论文, 2006.6.
[41]刘秉瀚,王伟智,方秀端.协同模式识别方法综述[J].系统工程与电子技术, 2003, 25(6):758-762.
[42]成卫,李江.模糊聚类法在基于交通冲突技术的交叉口安全评价中的应用[J].交通运输系统工程与信息, 2004, 4(2): 48-55.
[43]姜桂艳,江龙晖,王江锋.城市快速路交通拥挤识别方法[J].交通运输工程学报, 2006, 6(3):87-91.
[44]王殿海.交通流理论[M].人民交通出版社, 2002.
[45]马世勇,郑应文,柯栋忠.城市交通拥堵自动判别方法研究[J].福建电脑, 2007.1(1):7-8.
[46]杨祖元,黄席越,杜长海,唐明霞.基于FFCM聚类的城市交通拥堵判别研究[J].计算机应用研究, 2008, 25(9):2768-2770.
[47]李梅红.基于GPS浮动车的道路交通服务水平实时评估研究[D].重庆大学硕士学位论文, 2007.4.
[48]张继平,刘直芳.背景估计与运动目标检测跟踪[J].计算机技术与自动化, 2004, 23(4):51-54.
[49] Huwer S, Nie mann H. Adaptive change detection for real time surveillance applications. Proceedings, 3rd IEEE International workshop on Visual Surveillance[C]. 2000. 37-46.
[50] Wern C R, Azarbaycjani A, Darrell T, et al. Pfinder: Real time tracking human body [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19:780-785.
[51]朱胜利. Meanshift及相关算法在视频跟踪中的应用[D].浙江大学博士学位论文, 2006.4.
[52]何恒攀.基于序列图像的行人流量检测技术研究[D].重庆大学硕士学位论文, 2007. 4.
[53] Hui-zhong Zhuang. A Novel Algorithm for Background Updating and Target Tracking[C]. 2008 International Symposium on Computer Science and Computational Technology, 2008, 6:505-508.
[54] Elgammal A, Duraiswami R, Harwood D, etc. Background and foreground modeling usingnonparametric kernel density estimation for visual surveillance [J]. Proc. of the IEEE, 2002, 7:1151-1163.
[55]刘英霞,贺长伟.基于贝叶斯模型的动态背景检测[J].系统仿真学报, 2007, 21(11): 5042-5045.
[56]杨群生,黄继武,康显桂等.直方图加权均值滤波器[J].电子学报, 2004, 7 (32):1108-1111.
[57]支高英,郭文成.智能车辆导航中道路图像的处理[J].微计算机信息, 2009, 25(5):297-299.
[58]徐棍贺,贺耀,王夏黎.基于背景模型的运动车辆检测算法研究[J].微计算机信息, 2007, 4(23):120-121.
[59]田大增,郝永旦,哈明虎旦.一种新的去除视觉文本图像椒盐噪声的算法[J].计算机工程与应用, 2007, 14(4):81-83.
[60]朱芬芳,李维来.基于自适应背景更新的运动车辆检测技术[J].武汉理工大学学报, 2007, 29(11):140-142.
[61]王海虎,许志祥.智能交通检测与违法处理[J].电视应用, 2001, 3:29-32.
[62]吴庆翔,周永生等.一种新型的汽车闯红灯抓拍系统[C].第八届全国光电技术与系统学术会议论文专集, 1999, 5:31-33.