面向行人群信息提取的视频图像目标跟踪算法研究
|
摘要
交通作为城市社会经济发展中的纽带和动脉,具有举足轻重的地位。随着我国城镇化建设的不断推进,城市结构变化、规模扩大、人口增长,城市交通越来越复杂,交通拥挤、交通污染和交通安全等问题日益突出,城市交通问题已成为制约社会经济生产,影响民生的重要问题。行人作为交通系统的主要参与者,其活动、特征是影响交通系统设计、运行的重要因素。行人与机动车干扰、行人拥挤、行人交通安全等问题已经成为城市交通中严重的现实问题。《国家中长期科技发展规划纲要(2006-2020)》明确提出优先发展智能交通系统的战略决策,采用高新技术改造现有城市交通系统,提高其运行效率及服务质量,成为缓解交通问题的有力手段之一。
将计算机视觉技术应用于交通数据采集领域一直是智能交通系统的一个重要研究方向。基于视频图像处理和模式识别技术采集交通数据,与传统的检测方法相比,安装灵活,维护成本低,可提供丰富的交通数据。发达国家在交通视频检测方面进行了大量的理论研究与工程实践,大多以车辆为检测对象,较少考虑行人交通,因此,现有的方法不能有效获取实时行人交通数据,且不适合我国城市混合交通环境。分析和判断行人交通的运行规律、行人对机动车的干扰机理以及行人对信号交叉口通行能力的影响等,能够有效地管理和控制城市道路交通,科学规划设计公共交通设施,合理分配交通资源,解决我国城市特有的交通问题。在此背景下,我国在行人检测领域的研究逐步展开,具有良好的应用前景。
本论文以行人的交通特征为理论依据,以计算机视觉和模式识别为主要技术手段,以行人为检测对象,提出视频检测的理论与方法,并通过实际交通视频进行验证,分析系统运行结果的可靠性,为实际应用奠定基础。
本论文主要创新成果如下：
①对于摄像机标定,通过分析实际交通视频中场景特点划分场景类型,针对不同类型场景提出相应摄像机标定算法。根据道路边缘及路面上行人包含的几何约束关系,提出通常道路拍摄场景下摄像机标定方法；对允许行人过街道路交叉口拍摄场景,利用人行横道线包含的几何约束关系提出摄像机标定方法。通过充分利用实际交通视频场景中的几何约束条件,无需摆放特定的标定物体,可标定摄像机参数。
②在运动对象检测部分,提出自适应块均值的改进密码本模型。考虑像素之间的时间、空间联系,提出改进密码本框架。在此基础上,与HSV色彩空间结合,定义码本间相似度并据此精细化码本,并根据背景变化自适应调整图像块尺寸,提出自适应块均值的改进密码本模型。改进后模型可以处理动态多峰背景,得到较完整的检测对象区域,检测噪声容易处理,同时提高运算速度。
③对于目标跟踪,提出核窗口尺寸和目标模型自适应的改进均值漂移跟踪算法,并针对跟踪中可能产生的遮挡,提出多行人目标间遮挡处理方法。基于目标尺度方向估计,调整算法核窗口尺寸及核权重分布,以克服跟踪中背景干扰。基于目标变化剧烈程度定义及度量,构建目标模型更新机制,使目标模型能够自适应目标变化,提高跟踪精度。提出多信息融合算法融合目标颜色和运动信息,以克服多信息间误差叠加问题。定义遮挡因子描述多目标间遮挡状态,给出相应遮挡处理方法,以有效处理两目标间及更多目标参与的遮挡问题。
④在行人识别及数量统计方面,提出基于行人特征识别行人目标,并依据形状模型给出面向人群的行人计数方法。结合摄像机标定和目标跟踪算法,提取运动目标速度及目标图像面积信息,并据此建立行人目标分类准则。构建三维形状模型描述行人人群形状。给出形状模型对行人人群形状的最优估计及模型初始解求取方法,据此基于摄像机参数标定结果,提取行人人群占地面积,以计算当前帧行人目标数量。当行人目标团间发生合并与分离时,给出行人计数处理方法。
Transportation plays a decisive role in the bond and arteries of urban socio-economic development. With the changes of city structure, economic development, scale expansion, population growth, transportation is increasingly complex. Meanwhile, traffic congestion, traffic safety and other issues have become more and more prominent, and urban transport problems have become significant issues that constraint the social and economical production, and influence the livelihood of the people. Pedestrian as the main participants of the transportation system, its activities and characteristics are important factors for the design and operation of the transportation system. The interference between pedestrians and motor vehicles, pedestrian crowded, pedestrian safety and other issues have become serious practical problems in urban traffic. In "Medium-and-long-term Science and Technology Development Plan (2006-2020)", it has stated clearly the strategic decision of giving priority to the development of intelligent transportation systems. Using high technology to change the urban transport system, and improving its operating efficiency and service quality have become the key to solve the traffic problems.
The application of computer vision technology in the field of traffic data collection has been an important research direction of intelligent transportation systems. Comparing with the traditional method of detection, traffic data collection based on the technology of image processing and pattern recognition has flexible installation, maintenance costs, and can provide rich data. Developed countries did a lot of theoretical research and engineering practice in traffic video detection. However, most of those researches seemed the vehicles as detect objects and less considered pedestrian traffic. For this reason, existing methods cannot effectively obtain real-time pedestrian traffic data, and be suited to China's urban mixed traffic environment. Analysis and judgment the operation discipline of pedestrian traffic, interference mechanism of to automotive vehicles as well as the influence of pedestrian to signalized intersection capacity, etc., can productively manage and control urban road traffic, scientifically plan and design public transport facilities, rationally allocate transportation resources and solve the unique traffic problems in our city at last. In this context, the research within the field of pedestrian detection is carrying out step by step and has a good application prospect in China.
Based on the pedestrian traffic characteristics, with computer vision and pattern recognition as the main technical means and pedestrians as detection objects, a number of video detection theories and methods are proposed in the dissertation for laying the foundation for the practical applications. The presented methods are verified by actual traffic video, and their reliabilities are analyzed.
The innovations of the dissertation are as follows:
①For camera calibration, the scenes are classified after the analysis of characteristics of actual traffic video scene and formulate a camera calibration algorithm for different types of scenes. For the general road scene, a camera calibration method is proposed according to the geometrical constraints between road edges and pedestrians. For the crossing street intersection scene, the geometrical constraints in crosswalk lines can be used to calibrate a camera. By making full use of the geometric constraints of the real traffic video scenes, without placing specific objects, camera parameters can be calibrated.
②Towards motion object detection, an adaptive block mean codebook model is proposed. Considering the temporal and spatial relationship between the pixels, the improved codebook framework is proposed. On this basis, the similarities between codebooks are defined and codebooks can be refined accordingly. Then improved codebook model is proposed in combination with HSV color space and can adjust image block size. The improved model can handle dynamic multimodal background, gain more integrated regions of the detection subjects, product detection noise easily eliminated, and improve the operation speed, compared to the original model.
③With regard to object trakcing, an improved mean shift tracking algorithm with adaptive kernel window size and target model is proposed. Meanwhile, a multi-pedestrian occlusion handling method is proposed considering the occlusion during tracking. Based on the estimations of target scale and direction, kernel window size and weight distribution of the algorithm are adjusted, in order to overcome the background distraction in tracking. Based on the definition and measurement of the change intensity of target, the target model updating mechanism is built, so that the target model can adapt target changes and improve tracking accuracy. The proposed multi-information fusion algorithm can fuse target color and motion information to overcome error superimposed problem in multi-information. The defined block factors describe the blocked situations of multi-objective, and the occlusion handling method is given to deal with the occlusion problems involving two or more objects in effectively.
④As for pedestrian objects recognition and counting, pedestrian targets are classified based on their features, and in accordance with the shape model, the number of pedestrians in group can be calculated. The criterion of classification which is built according to the speed and image area of the moving target, can classify pedestrian target. A three-dimensional shape model is built to describe the pedestrians individual and group shape. The initial solution and the optimal estimation of the method for individual and group shape of the pedestrian are given to extract the occupied areas of pedestrians, and then the number of pedestrian objects in the current frame can be calculated. The method for counting pedestrians is presented when mergence and separation occur between target blobs.
将计算机视觉技术应用于交通数据采集领域一直是智能交通系统的一个重要研究方向。基于视频图像处理和模式识别技术采集交通数据,与传统的检测方法相比,安装灵活,维护成本低,可提供丰富的交通数据。发达国家在交通视频检测方面进行了大量的理论研究与工程实践,大多以车辆为检测对象,较少考虑行人交通,因此,现有的方法不能有效获取实时行人交通数据,且不适合我国城市混合交通环境。分析和判断行人交通的运行规律、行人对机动车的干扰机理以及行人对信号交叉口通行能力的影响等,能够有效地管理和控制城市道路交通,科学规划设计公共交通设施,合理分配交通资源,解决我国城市特有的交通问题。在此背景下,我国在行人检测领域的研究逐步展开,具有良好的应用前景。
本论文以行人的交通特征为理论依据,以计算机视觉和模式识别为主要技术手段,以行人为检测对象,提出视频检测的理论与方法,并通过实际交通视频进行验证,分析系统运行结果的可靠性,为实际应用奠定基础。
本论文主要创新成果如下：
①对于摄像机标定,通过分析实际交通视频中场景特点划分场景类型,针对不同类型场景提出相应摄像机标定算法。根据道路边缘及路面上行人包含的几何约束关系,提出通常道路拍摄场景下摄像机标定方法；对允许行人过街道路交叉口拍摄场景,利用人行横道线包含的几何约束关系提出摄像机标定方法。通过充分利用实际交通视频场景中的几何约束条件,无需摆放特定的标定物体,可标定摄像机参数。
②在运动对象检测部分,提出自适应块均值的改进密码本模型。考虑像素之间的时间、空间联系,提出改进密码本框架。在此基础上,与HSV色彩空间结合,定义码本间相似度并据此精细化码本,并根据背景变化自适应调整图像块尺寸,提出自适应块均值的改进密码本模型。改进后模型可以处理动态多峰背景,得到较完整的检测对象区域,检测噪声容易处理,同时提高运算速度。
③对于目标跟踪,提出核窗口尺寸和目标模型自适应的改进均值漂移跟踪算法,并针对跟踪中可能产生的遮挡,提出多行人目标间遮挡处理方法。基于目标尺度方向估计,调整算法核窗口尺寸及核权重分布,以克服跟踪中背景干扰。基于目标变化剧烈程度定义及度量,构建目标模型更新机制,使目标模型能够自适应目标变化,提高跟踪精度。提出多信息融合算法融合目标颜色和运动信息,以克服多信息间误差叠加问题。定义遮挡因子描述多目标间遮挡状态,给出相应遮挡处理方法,以有效处理两目标间及更多目标参与的遮挡问题。
④在行人识别及数量统计方面,提出基于行人特征识别行人目标,并依据形状模型给出面向人群的行人计数方法。结合摄像机标定和目标跟踪算法,提取运动目标速度及目标图像面积信息,并据此建立行人目标分类准则。构建三维形状模型描述行人人群形状。给出形状模型对行人人群形状的最优估计及模型初始解求取方法,据此基于摄像机参数标定结果,提取行人人群占地面积,以计算当前帧行人目标数量。当行人目标团间发生合并与分离时,给出行人计数处理方法。
Transportation plays a decisive role in the bond and arteries of urban socio-economic development. With the changes of city structure, economic development, scale expansion, population growth, transportation is increasingly complex. Meanwhile, traffic congestion, traffic safety and other issues have become more and more prominent, and urban transport problems have become significant issues that constraint the social and economical production, and influence the livelihood of the people. Pedestrian as the main participants of the transportation system, its activities and characteristics are important factors for the design and operation of the transportation system. The interference between pedestrians and motor vehicles, pedestrian crowded, pedestrian safety and other issues have become serious practical problems in urban traffic. In "Medium-and-long-term Science and Technology Development Plan (2006-2020)", it has stated clearly the strategic decision of giving priority to the development of intelligent transportation systems. Using high technology to change the urban transport system, and improving its operating efficiency and service quality have become the key to solve the traffic problems.
The application of computer vision technology in the field of traffic data collection has been an important research direction of intelligent transportation systems. Comparing with the traditional method of detection, traffic data collection based on the technology of image processing and pattern recognition has flexible installation, maintenance costs, and can provide rich data. Developed countries did a lot of theoretical research and engineering practice in traffic video detection. However, most of those researches seemed the vehicles as detect objects and less considered pedestrian traffic. For this reason, existing methods cannot effectively obtain real-time pedestrian traffic data, and be suited to China's urban mixed traffic environment. Analysis and judgment the operation discipline of pedestrian traffic, interference mechanism of to automotive vehicles as well as the influence of pedestrian to signalized intersection capacity, etc., can productively manage and control urban road traffic, scientifically plan and design public transport facilities, rationally allocate transportation resources and solve the unique traffic problems in our city at last. In this context, the research within the field of pedestrian detection is carrying out step by step and has a good application prospect in China.
Based on the pedestrian traffic characteristics, with computer vision and pattern recognition as the main technical means and pedestrians as detection objects, a number of video detection theories and methods are proposed in the dissertation for laying the foundation for the practical applications. The presented methods are verified by actual traffic video, and their reliabilities are analyzed.
The innovations of the dissertation are as follows:
①For camera calibration, the scenes are classified after the analysis of characteristics of actual traffic video scene and formulate a camera calibration algorithm for different types of scenes. For the general road scene, a camera calibration method is proposed according to the geometrical constraints between road edges and pedestrians. For the crossing street intersection scene, the geometrical constraints in crosswalk lines can be used to calibrate a camera. By making full use of the geometric constraints of the real traffic video scenes, without placing specific objects, camera parameters can be calibrated.
②Towards motion object detection, an adaptive block mean codebook model is proposed. Considering the temporal and spatial relationship between the pixels, the improved codebook framework is proposed. On this basis, the similarities between codebooks are defined and codebooks can be refined accordingly. Then improved codebook model is proposed in combination with HSV color space and can adjust image block size. The improved model can handle dynamic multimodal background, gain more integrated regions of the detection subjects, product detection noise easily eliminated, and improve the operation speed, compared to the original model.
③With regard to object trakcing, an improved mean shift tracking algorithm with adaptive kernel window size and target model is proposed. Meanwhile, a multi-pedestrian occlusion handling method is proposed considering the occlusion during tracking. Based on the estimations of target scale and direction, kernel window size and weight distribution of the algorithm are adjusted, in order to overcome the background distraction in tracking. Based on the definition and measurement of the change intensity of target, the target model updating mechanism is built, so that the target model can adapt target changes and improve tracking accuracy. The proposed multi-information fusion algorithm can fuse target color and motion information to overcome error superimposed problem in multi-information. The defined block factors describe the blocked situations of multi-objective, and the occlusion handling method is given to deal with the occlusion problems involving two or more objects in effectively.
④As for pedestrian objects recognition and counting, pedestrian targets are classified based on their features, and in accordance with the shape model, the number of pedestrians in group can be calculated. The criterion of classification which is built according to the speed and image area of the moving target, can classify pedestrian target. A three-dimensional shape model is built to describe the pedestrians individual and group shape. The initial solution and the optimal estimation of the method for individual and group shape of the pedestrian are given to extract the occupied areas of pedestrians, and then the number of pedestrian objects in the current frame can be calculated. The method for counting pedestrians is presented when mergence and separation occur between target blobs.
引文
[1]王迎华,李凤超.步行交通设施及交通特性分析[J].交通标准化.2007,(10)：49-53.
[2]殷凤军.大城市行人交通设施系统规划方法研究[D].南京：东南大学,2010.
[3]LI J, SHAO C F, XU W T, LI J. A real-time system for tracking and classification of pedestrian and bicycles [J]. Transportation Research Record,2010,2198:83-92.
[4]郭磷.基于信息融合的交通信息采集研究[D].合肥：中国科学技术大学,2007.
[5]王笑京,齐彤岩,蔡华.智能交通系统体系框架原理与应用[M].北京：中国铁道出版社,2004.
[6]杨兆升.智能运输系统概论[M].北京：人民交通出版社,2003.
[7]贺国光.ITS系统工程导论[M].北京：中国铁道出版社,2004.
[8]陆化普,李瑞敏,朱茵.智能交通系统概论[M].北京：人民交通出版社,2004.
[9]陈旭梅.智能运输系统[M].北京：中国铁道出版社,2007.
[10]朱茵,王军利.智能交通系统导论[M].北京：中国人民公安大学出版社,2007.
[11]X. M. Chen, L. Yu, J. F. Guo, Y. S. Quan, Y. B. Geng, Y. Gao. Development of Beijing regional intelligent transportation system architecture [C]. Proceedings of the 6th IEEE International Conference on Intelligent Transportation Systems,2003:560-565.
[12]R. L. Courtney. A broad view of ITS standards in the US [C]. Proeeedings of Intelligent Transportation Systems,1997:529-536.
[13]R. Meier, A. Harrington, V. Cahill. A framework for integrating existing and novel intelligent transportation systems[C]. Proeeedings of Intelligent Transportation Systerms,2005:154-159.
[14]汤义.智能交通系统中基于视频的行人检测与跟踪方法的研究[D].广州：华南理工大学,2010.
[15]B. Coifman, D. Beymer, P. McLauchlan, J. Malik. A Real-time Computer Vision System for Vehicle Tracking and Traffic Surveillance [J]. Transportation Research Part C:Emerging Technologies,1998,6(4):271-288.
[16]Image Sensing Systems, Inc. Applications of Autoscope [EB/OL]. [2011-07-06]. http://autoscope.com/applications/.
[17]李娜.基于视频的交通信息采集系统的研究[D].广州：中南大学,2010.
[18]Y. Malinovskiy, J. Zheng, Y. Wang. Simple and model-free algorithm for real-Time pedestrian detection and tracking [C]. The 86th Annual Meeting of the Transportation Research Board (CD-ROM), Washington, D.C.,2007.
[19]M. Meuter, U. Iurgel, S. B. Park, A. Kummert. The unscented kalman filter for pedestrian tracking from a moving host [C]. IEEE Intelligent Vehicles Symposium, Eindhoven, Holland, 2008:37-42.
[20]H. Liu, Z. Yu, H. B. Zha, Y. X. Zou, L. Zhang. Robust human tracking based on multi-cue integration and mean-shift [J]. Pattern Recognition Letters,2009,30(9):827-837.
[21]T. Zhao, R. Nevatia. Tracking multiple humans in complexsituations [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1208-1221.
[22]李得伟,韩宝明.行人交通[M].北京：人民交通出版社,2011.
[23]杨进峰.城市交通流诱导系统及关键技术研究[D].武汉：武汉理工大学,2004.
[24]秦玲,朱玥季,王春燕.动态交通信息采集与处理系统设备开发及关键技术研究[J].公路交通科技,2006,(11):41-43.
[25]赵熠.基于图像处理的混合交通流中行人和非机动车数据采集理论与方法[D].北京：北京交通大学,2008.
[26]郑建湖,王明.动态交通信息采集技术比较分析[J].交通标准化,2009,194(4)：42-47.
[27]肖尧.智能交通信息采集与融合技术的应用研究[D].南昌：华东交通大学,2008
[28]姜桂艳.道路交通状态判别技术与应用[M].北京：人民交通出版社,2004,65-69.
[29]A. K. Lawrence. Sensor Technologies and Data Requirements for ITS [M]. Arrech House Boston&London,2001.
[30]付增辉.高速公路监控系统外场设备数据传输方式及应用[J].交通世界,2005,34(5)：92-95.
[31]张秀媛,达庆东,张国伍.公路自动事件检测技术[J].系统工程理论与实践,2001,(6)：118-124.
[32]高星文.交通检测器在高速公路中的应用及评价[J].山西建筑,2002,28(11)：125-126.
[33]陈青.基于GPS浮动车的城市道路交通状态判别技术研究[D].西安：长安大学,2009.
[34]徐勇军,高梅国,毛二可.智能运输系统中的雷达车辆检测器[J].北京理工大学学报,2001,21(2)：256-259.
[35]张晓峰,王大海,刘艳霞.多探头超声波车流检测系统的设计[J].计算机自动测量与控制,2000,8(5)：28-30.
[36]彭春华,刘建业,刘岳峰,等.车辆检测传感器综述[J].传感器与微系统,2007,26(6)：4-11.
[37]赵亚妮,高辉.基于超声波的车辆检测器设计[J].计算机测量与控制,2011,19(10)：2542-2548.
[38]徐义广,刘波,李艳红,张存林.被动式与主动式红外热成像技术研究[J].应用光学,2008,29(增刊)：44-47.
[39]陈强.高速公路交通流特征参数被动声学检测技术研究[D].吉林：吉林大学,2005.
[40]顾晓辉,王晓鸣.多传感器声目标识别的研究[J].探测与控制学报,2002,24(3)：39-43.
[41]K. O. Arras, O. M. Mozos, W. Burgard. Using boosted features for detection of people in 2D range scans[C]. IEEE Intrenational Conference on Robotics and Automation,2007.
[42]胡顺玺.基于三维激光扫描仪的车辆前方行人检测研究[D].吉林：吉林大学,2011.
[43]孙智勇,葛书芳,荣建,李美玲.行人交通的数据采集方法研究[J].北京工业大学学报,2006,32(6)：530-533.
[44]姜桂艳,常安德,吴超腾.基于GPS浮动车的交通信息采集方法[J].吉林大学学报：工学版.2010,40(4)：971-975.
[45]张晓东.动态交通流信息采集系统若干问题研究[D].吉林：吉林大学,2004.
[46]S. L. Chang, L. S. Chen, Y. C. Chung, S. W. Chen. Automatic license plate recognition [J]. IEEE Transactions on Intelligent Transportation Systems,2004,5(1):42-53.
[47]杨飞,裘炜毅.基于手机定位的实时交通数据采集技术[J].城市交通.2005,3(4)：63-68.
[48]Y. L. Zhao. Mobile phone location determination and its impact on intelligent transportation systems [J]. IEEE Transactions on Intelligent Transportation Systems,2000, 1(1):55-64.
[49]M. D. Fontaine, B. L. Smith. Improving the effectiveness of the traffic monitoring based on wireless location technology [R].Virginia Transportation Research Council VA:Charlottesville, 2005.
[50]王广宇.车辆牌照识别系统综述[J].郑州轻工业学院学报：自然科学版,2001,16(2)：47-50.
[51]黄有金.汽车牌照自动识别技术的研究与实现[D].南京：东南大学,2005.
[52]王俊龙,曲兴华,赵阳.多目视觉检测技术中的照明系统设计[J].光电技术应用,2009,24(4)：1-6.
[53]赵阳,曲兴华.平行照明多目视觉检测技术[J].红外与激光工程,2010,39(4)：339-345.
[54]赵敏.单目视觉多行人目标检测与跟踪技术研究[D].重庆：重庆大学,2010.
[55]L. Wang, H. Z. Ning, W. M. Hu, T. N. Tan. Gait recognition based on procrustes shape analysis [C]. Proceedings of IEEE International Conference on Image Processing,2002:433-436.
[56]I. Haritaoglu, D. Harwood, L. Davis. W4:Real-time surveillance of people and their activities [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[57]A. Ali, E.Dagless. Vehicle and pedestrian detection and tracking [C]. Proceeding of IEEE Colloquium on Iamge Analysis for Transport Apllications, London:1990:12-19.
[58]E. Nakamura, N.Kehtarnavaz, T. Urbanik. Quantification of pedestrian flow parameters along crosswalks [C]. Proceedings of the Intelligent Transportation Systems Meeting, Houston, TX: 1996.
[59]N. Kehtarnavaz, F. Rajkotwala. Real-time vision-based detection of waiting pedestrian [J].Real-Time Imaging,1997,3:433-440.
[60]S. P. Hoogendoorn. Walker behavior modeling by differential games [R]. Delft University of Technology,2002.
[61]S. P. Hoogendoorn. Pedetrian travel behavior in walking areas by subjective utility optimization [C]. Proceedings of the 81th Annual Meeting of the Transportation Research Board (CD-ROM), Washington D.C.,2002.
[62]S. P. Hoogendoorn, P. H. L. Bovy. Nomative pedestrian behavior theory and modeling [C]. Proceedings of the 15th International Symposium on Transportation and Traffic Theory,2002.
[63]T. Kardi, Y. Takeyama, H. Inamura. Tracking system to automate data collection of microscopic pedestrian traffic flow [C]. Proceeding of the 4th Eastern Asia Society for Transportation studies, Hanoi, Vietnam,2001,3(1):11-25.
[64]C. Wren, A. Azarbaycjfani, T. Darrell, et al. Real-time tracking of the human body[J]. Proceeding of the SPIE Conference on Intergration Issuse in Large Commercial Media Delivery Systems,1995.
[65]A. Broggi, M. Bertozzi, A. Fascioli, M. Sechi. Shape-based pedestrian detection[C]. Proceedings of IEEE Intelligent Vehicles Symposium. Dearborn, USA.2000:215-220.
[66]D. M. Gavrila, J. Giebel, S. Munder. Vision-based pedestrian detection:the protector system[C]. Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy.2004:13-18.
[67]M. Tons, R. Doerfler, M. M. Meinecke, M. A. Obojski. Radar sensors and sensor platform used for pedestrian protection in the EC-funded project SAVE-U[C]. Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy. IEEE,2004:813-818.
[68]许言午.面向行人检测的组合分类计算机模型与应用研究[D].安徽：中国科技大学,2009.
[69]F. L. Xu, X. Liu, K. Fujimura. Pedetrain detection and tracking eith night vision [J]. IEEE Transactions onIntelligent Transportation Systems,2005,6(1):63-71.
[70]王亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报,2002,25(3)：225-237.
[71]L. Wang, H. Ning, T. Tan, and W. Hu. Fusion of static and dynamic body biometrics for gait recognition [J]. IEEE Transactions on Circuits and Systems for Video Technology,2004, 14(2):149-158.
[72]A. Yilmaz, O. Javed, M. Shah. Object tracking:A Survey [J].ACM Computing Surveys,2006, 38(4):11-45.
[73]王亮.步态分析与识别[D].北京：中国科学院,2004.
[74]赵明.三维视觉对象分割[D].杭州：浙江大学,2004.
[75]M. Zhao, S.Z. Li, J. J. Bu. Shape evaluation for weighted active shape mocels[C].Proceedings of the Asian Conference on Computer Vision,2004(2):1074-1079.
[76]潘锦辉,廖庆敏,林行刚.视频序列中运动目标的自动提取[J].清华大学学报：自然科学版,2001,41(4/5)：190-193.
[77]胡斌,王生进,丁晓青.基于部位检测和子结构组合的行人检测方法[J].计算机科学,2009,36(11)：242-246.
[78]李同治,丁晓青,王生进.利用级联SVM的人体检测方法[J].中国图形图像学报,2008,13(3)：566-570.
[79]程如中,赵勇,王执中,徐家尧,王新安.实时行人检测预警系统[J].交通运输工程学报,2012,12(5).
[80]赵春晖,张洪才,陆朝霞.一种基于三角特征的行人检测算法[J].计算机工程与应用,2008,44(7)：202-205.
[81]李伟,何鹏举,杨恒,陈明.基于双阈值运动区域分割的Adaboost行人检测算法[J].计算机应用研究,2012,29(9)：3571-3574,3596.
[82]杨涛,李静,潘泉,张艳宁.基于场景模型与统计学习的鲁棒行人检测算法[J].自动化学报,2010(4)：499-508.
[83]汤义,刘伟铭,温金辉.基于MPEG-7标准的行人模型描述与实现[J].科学技术与工程,2010,10(4)：933-937.
[84]勒晶,万卫兵,方涛.使用单目摄像头的实时行人计数算法[J].计算机工程,2009,35(23)：204-206.
[85]勒晶,基于图像处理技术的单目客流检测系统研究[D].上海：上海交通大学,2009.
[86]C.F. Shao, Y. Zhao, H. Yue, X. Zhang. Study on a vision based system for real-time collection of mixed traffic data[C]. Proceedings of International Conference on Traffic and Transportation Studies,2006:606-614.
[87]Y. Zhao, C. F. Shao, X. M. Chen. Study on the vision-based detection and tracking of cyclists and pedestrian [C]. Proceedings of the 14th world Congress on Intelligent Transport Systems, 2007(CD-ROM).
[88]赵熠,邵春福,岳昊等.基于视频图像处理的行人和非机动车数据采集技术研究[J].北京交通大学学报,2007,31(6)：10-14.
[89]赵熠,基于图像处理的混合交通流中行人和非机动车数据采集理论与方法[D].北京：北京交通大学,2008.
[90]岳昊,邵春福,赵熠,陈晓明.基于视频序列的行人多目标跟踪方法研究[J].交通运输系统工程与信息,2007,7(4)：47-51.
[91]李娟.城市交通系统中行人视频检测理论与方法[D].北京：北京交通大学,2010.
[92]J. Li, C. F. Shao, W. T. Xu, C. J. Dong. Real-time pedestrian detection based on improved Gaussian mixture model[C].Proceeding of IEEE International Conference on Measuring Technology and Mechatronics Automation,2009:269-272.
[93]李娟,邵春福,杨励雅.基于混合高斯模型的行人检测方法[J].吉林大学：工学版,2011,41(1)：41-45.
[94]A. N. Marana, S. A. Velastin, L. F. Costa, et al. Automatic estimation of crowd density using texture [J]. Safety Science,1998,28(3):165-175.
[95]X. Zhang, M. R. B. Forshaw. A parallel algorithm to extract information about the motion of road traffic using image analysis [J]. Transportation Research:Part C,1997,5(2):141-152.
[96]王建华,冯帆,梁伟,王惠萍.非线性模型下的摄像机标定[J].光电子技术.2012,32(1)：33-38.
[97]马颂德,张正友.计算机视觉：计算机理论与算法基础[M].北京：科学出版社,1998.
[98]徐静.基于非线性模型的摄像机标定技术研究[J].现代电子技术.2008,(12)：153-157.
[99]张玲,陈丽敏,何伟,郭磊民.基于视频的改进帧差法在车流量检测中的应用[J].重庆大学学报,2004,27(5)：31-34.
[100]W.B. Thomspon, K.M. Mutch, V.A. Berzins. Dynamic occlusion analysis in optical flow fields. IEEE Transactions on Pattern Analysis and Machine Intelligence,1985,7(4):374-383.
[101]裴巧娜.基于光流法的运动目标检测与跟踪技术[D].北京：北方工业大学,2009.
[102]R. Cucchiara, C. Grana, M. Piccardi, A. Prati. Detecting moving objects, ghosts, and shadows in video streams [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003, 25:1337-1342.
[103]C. Stauffer, W.E.L Grimson. Adaptive background mixture models for real-time tracking[C]. Proc IEEE Conference on Computer Vision and Pattern Recognition,1999:246-252.
[104]K. Kim, T. H. Chalidabhongse, D. Harwood, and L. Davis. Real-time foreground-background segmentation using codebook model [J]. Real- Time Imaging,2005,11:172-185.
[105]P. Viola, M. J. Jones, D. Snow. Detecting pedestrians using pattern of motion and apparence [J]. Proceedings of International Conference on Computer Vision,2005,63(2):153-161.
[106]N. Dalal, B. Triggs. Histograms of oriented gradients for human detection [C]. Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition,2005,1:886-893.
[107]A. Mohan, C. Papageorgiou, et al. Example-based object detection in images by components [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2001,23(4):349-361.
[108]龙开文.基于模板匹配的人脸检测[D].四川：四川大学,2005.
[109]林月贡,何小海,张生军.基于区域模板匹配的多目标实时跟踪[J].计算机仿真.2011,28(1)：277-284.
[110]D. Comaniciu, V. Ramesh, P. Meer. Kernel-based object tracking [J]. IEEE Transactions on PatternAnalysis and Machine Intelligence.2003,25(5):564-575.
[111]K. Okuma, A. Taleghani, N. Freitas, et al. A boosted particle filter:multi-taxget detection and tracking[C]. In Porceedings of European Conference on Computer Vision, Prague, Czech Republic,2004,1:28-39.
[112]汪颖进,张桂林.新的基于Kalman滤波的跟踪方法[J].红外与激光工程,2004,33(5)：505-508.
[113]A. Bobick, J. Davis, S. Intille, et al. Action recognition in an interactive story environment, PerCom TR 398[R]. MIT Media Lab,1996.
[114]M. Fukumoto, T. Ogata, J. K. Tan. Human motions representation and recognition by directional motion history images [J]. Artif Life Robotics,2008,13:326-330.
[115]H. Meng, M. Freeman. Real-time human action recognition on embedded reconfigurable video processing architecture [J]. Real-Time Image Proc,2008,3:163-176.
[116]J. Davis, G Bradski. Real-time motion template gradients using intel CVLib[C]. IEEE International Conference on Computer Vision, Kerhyra,1999,3:251-263.
[117]T. Ojala, M. Pietikainen, T. Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[118]郑永斌,黄新生,丰松江.SIFT和旋转不变LBP相结合的图像匹配算法[J].计算机辅助设计与图像学学报,2010,2：286-292.
[119]D. G Lowe. Distinctive image features form scale-invariant keypoint [J]. International Journal of Computer Vision,2004,60(2):91-110.
[120]孙宁,冀贞海,邹采荣,等.基于局部二元模式算子的人脸性别分类方法[J].华中科技大学学报(自然科学版),2007,35(增刊)：177-181.
[121]杨淑荣.图像模式识别vc++技术实现[M].北京：清华大学出版社,2005.
[122]卜建军,严宝杰.交通调查与分析[M].北京：人民交通出版社,2004.
[123]飞思科技产品研发中心.神经网络理论与Matlab7实现[M],北京：电子工业出版社,2005.
[124]王凌.料能优化算法及其应用[M].北京：清华大学出版社,2003.
[125]朱健英.智能系统非经典数学方法[M].武汉：华中科技大学出版社,2001.
[126]O. Masoud, N. P. Papanikolopoulos. Using geometric primitives to calibrate traffic scenes [J]. Transportation Research Part C,2007,15(6):361-379.
[127]A. Bartoli, P. Sturm. Constrained structure and motion from multiple uncalibrated views of a piecewise planar scene [J]. Computer Vision,2003,52 (1):45-64.
[128]A. Criminisi, I. Reid, A. Zisserman. Single view metrology [J]. Computer Vision,2001,40 (2):123-148.
[129]M. Wilczkowiak, G. Trombettoni, C. Jermann, P. Sturm, E. Boyer. Scene modeling based on constraint system decomposition techniques [C]. Proceedings of International Conference on Computer Vision (ICCV),2003:1004-1010.
[130]K. T. Song, J. C. Tai. Dynamic calibration of pan-tilt-zoom cameras for traffic monitoring [J]. IEEE Trans. on Systems, Man and Cybernetics, Part B,2006,36(5):1091-1103.
[131]C. Zhaoxue, S. Pengfei. Efficient method for camera calibration in traffic scenes [C]. IEEE Electron. Lett,2004,40(6):368-369.
[132]A. H. S. Lai, N. H. C. Yung. Lane detection by orientation and length discrimination [J]. IEEE Trans. Syst., Man, Cybem. Part B,2000,30(4):539-548.
[133]O. Masoud, N. P. Papanikolopoulos. Using geometric primitives to calibrate traffic scenes [C].Intelligent Robots and Systems,2004,2:1878-1883.
[134]L. Fengjun, T. Zhao, N. Ramakant. Camera calibration from video of a walking human [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(9):1513-1518.
[135]T. N. Schoepflin, D. J. Dailey. Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation [J]. IEEE Trans. Intell. Transp. Syst,2003,4(2):90-98.
[136]卞晓东.基于机器视觉的车辆几何尺寸测量系统研究[D].南京：东南大学,2005.
[137]P. Kilambi, E. Ribnick, A. J. Joshi, O. Masoud, N. Papanikolopoulos. Estimating pedestrian counts in groups [J].Computer Vision and Image Understanding,2008,110(1):43-59.
[138]M. Pollefeys, R. Koch, L. V. Goll. Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters[C]. Proceedings of International Conference on Computer Vision (ICCV),1998:90-95.
[139]杨久龄,刘学会.GB5768-1999道路交通标志和标线[S].北京：中国标准出版社,1999.
[140]李琦,邵春福,岳吴,赵丹,孙轶轩.基于改进密码本模型的视频对象检测[J].交通信息与安全,2011,29(5)：140-144.
[141]Q. Li, C.F. Shao, H. Yue, J. Li. Real-time foreground-background segmentation Based on improved Codebook Model[C]. International Conference on BioMedical Engineering and Informatics,2010,1:269-273.
[142]K.Toyama, J. Krumm, B. Brumitt, B. Meyers. WallFlower:Principles and Practice of background maintenance[C]. IEEE International Conferenceon Computer Vision,1999: 255-261.
[143]A. Elgammal, R. Duraiswami, L. S. Davis. Efficient kernel density estimation using the fast Gauss transform with applications to color modeling and tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(11):1499-1504.
[144]邵春福,赵熠,吴戈.道路交通数据采集技术研究展望[J].现代交通技术,2006,3(6)：66-70.
[145]D. M. Ha, J. M. Lee, and Y. D. Kim. Neural-edge-based vehicle detection and traffic parameter extraction [J]. Image and Vision Computing,2004,22(11):899-907.
[146]Y. Chen, C. Chen, C. Huang, Y. Hung. Efficient hierarchical method for background subtraction [J]. Pattern Recognition,2007(40):2706-2715.
[147]D.S. Lee. Effective gaussian mixture learning for video background subtraction [C].Proc IEEE Pattern Analysis and Machine Intelligence,2005,27(5):827-832.
[148]阮秋琦,阮宇智译.数字图像处理(第二版)[M].北京：电子工业出版社,2007.
[149]M. Isard, A. Blake. Contour tracking by stochastic propagation of conditional density[C].Computer Vision,1996:343-356.
[150]Z. W. Wang, X. K. Yang, X. Yi, S, and Y. Yu. CamShift guided particle filter for visual tracking [J]. Pattern Recognition Letters,2009,30:407-413.
[151]D. Comaniciu, V. Ramesh, P. Meer. Real-Time tracking of non-rigid objects using mean shift [J].IEEE Computer Vision and Pattern Recognition,2000,2:142-149.
[152]W. Hao, A. C. Sankaranarayanan, R. Chellappa. Online empirical evaluation of tracking algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(8): 1443-1458.
[153]B.Y. Liu, J. Z. Huang, Y. Lin, C. Kulikowsk. Robust tracking using local sparse appearance model and K-selection [C].IEEE Conference on Computer Vision and Pattern Recognition,2011:1313-1320.
[154]张玲.视频目标跟踪方法研究[D].安徽：中国科学技术大学,2009.
[155]J. Canny. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003 (8)6:679-698.
[156]吴上生,方飞村,段富海,苟国华.B样条二进小波在齿轮轮廓图像处理中的应用[J].华南理工大学学报：自然科学版,2007,35(8)：55-58.
[157]闫蓓,王斌,李媛.基于最小二乘法的椭圆拟合改进算法[J].北京航空航天大学学报,2008,34(3)：295-298.
[158]R. T. Collins. Mean-shift blob tracking through scale space[C]. IEEE Computer Society Conference on Computer Visionand Pattern Recognition, Pittsburgh, USA,2003,2:234-240.
[159]J. Owens, A. Hunter, E. Fletcher. A fast model-free morphology-based object tracking algorithm[C]. British MachineVision Conference, Cardiff, UK,2002:767-776.
[160]C. G. Broyden. The convergence of a class of double rank minimization algorithms:the new algorithm [J]. Journal of the Institute of Mathematics and its Applications,1970,6:222-231.
[161]R. Fletcher. A new approach to variable metric algorithms [J]. Computer Journal,1970,13: 317-322.
[162]D. Goldfarb. A family of variable metric methods derived by variational means [J]. Mathematics of Computation,1970,24:23-26.
[163]D. F. Shanno. Conditioning of quasi-Newton methods for function minimization [J]. Mathematics of Computation,1970,24:647-650.
[164]袁亚湘,孙文瑜.最优化理论与方法[M].北京：科学出版社,1997.
[165]美国交通研究委员会编.美国道路通行能力手册(2000年版)[M].任福田等译.北京：中国建筑出版社,2000.
[166]K. Prahlad, R. Evan, J. J. Ajay, M. Osama, P. Nikolaos. Estimating pedestrian counts in groups [J]. Computer Vision and Image Understanding,2008,110:43-59.
[2]殷凤军.大城市行人交通设施系统规划方法研究[D].南京：东南大学,2010.
[3]LI J, SHAO C F, XU W T, LI J. A real-time system for tracking and classification of pedestrian and bicycles [J]. Transportation Research Record,2010,2198:83-92.
[4]郭磷.基于信息融合的交通信息采集研究[D].合肥：中国科学技术大学,2007.
[5]王笑京,齐彤岩,蔡华.智能交通系统体系框架原理与应用[M].北京：中国铁道出版社,2004.
[6]杨兆升.智能运输系统概论[M].北京：人民交通出版社,2003.
[7]贺国光.ITS系统工程导论[M].北京：中国铁道出版社,2004.
[8]陆化普,李瑞敏,朱茵.智能交通系统概论[M].北京：人民交通出版社,2004.
[9]陈旭梅.智能运输系统[M].北京：中国铁道出版社,2007.
[10]朱茵,王军利.智能交通系统导论[M].北京：中国人民公安大学出版社,2007.
[11]X. M. Chen, L. Yu, J. F. Guo, Y. S. Quan, Y. B. Geng, Y. Gao. Development of Beijing regional intelligent transportation system architecture [C]. Proceedings of the 6th IEEE International Conference on Intelligent Transportation Systems,2003:560-565.
[12]R. L. Courtney. A broad view of ITS standards in the US [C]. Proeeedings of Intelligent Transportation Systems,1997:529-536.
[13]R. Meier, A. Harrington, V. Cahill. A framework for integrating existing and novel intelligent transportation systems[C]. Proeeedings of Intelligent Transportation Systerms,2005:154-159.
[14]汤义.智能交通系统中基于视频的行人检测与跟踪方法的研究[D].广州：华南理工大学,2010.
[15]B. Coifman, D. Beymer, P. McLauchlan, J. Malik. A Real-time Computer Vision System for Vehicle Tracking and Traffic Surveillance [J]. Transportation Research Part C:Emerging Technologies,1998,6(4):271-288.
[16]Image Sensing Systems, Inc. Applications of Autoscope [EB/OL]. [2011-07-06]. http://autoscope.com/applications/.
[17]李娜.基于视频的交通信息采集系统的研究[D].广州：中南大学,2010.
[18]Y. Malinovskiy, J. Zheng, Y. Wang. Simple and model-free algorithm for real-Time pedestrian detection and tracking [C]. The 86th Annual Meeting of the Transportation Research Board (CD-ROM), Washington, D.C.,2007.
[19]M. Meuter, U. Iurgel, S. B. Park, A. Kummert. The unscented kalman filter for pedestrian tracking from a moving host [C]. IEEE Intelligent Vehicles Symposium, Eindhoven, Holland, 2008:37-42.
[20]H. Liu, Z. Yu, H. B. Zha, Y. X. Zou, L. Zhang. Robust human tracking based on multi-cue integration and mean-shift [J]. Pattern Recognition Letters,2009,30(9):827-837.
[21]T. Zhao, R. Nevatia. Tracking multiple humans in complexsituations [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1208-1221.
[22]李得伟,韩宝明.行人交通[M].北京：人民交通出版社,2011.
[23]杨进峰.城市交通流诱导系统及关键技术研究[D].武汉：武汉理工大学,2004.
[24]秦玲,朱玥季,王春燕.动态交通信息采集与处理系统设备开发及关键技术研究[J].公路交通科技,2006,(11):41-43.
[25]赵熠.基于图像处理的混合交通流中行人和非机动车数据采集理论与方法[D].北京：北京交通大学,2008.
[26]郑建湖,王明.动态交通信息采集技术比较分析[J].交通标准化,2009,194(4)：42-47.
[27]肖尧.智能交通信息采集与融合技术的应用研究[D].南昌：华东交通大学,2008
[28]姜桂艳.道路交通状态判别技术与应用[M].北京：人民交通出版社,2004,65-69.
[29]A. K. Lawrence. Sensor Technologies and Data Requirements for ITS [M]. Arrech House Boston&London,2001.
[30]付增辉.高速公路监控系统外场设备数据传输方式及应用[J].交通世界,2005,34(5)：92-95.
[31]张秀媛,达庆东,张国伍.公路自动事件检测技术[J].系统工程理论与实践,2001,(6)：118-124.
[32]高星文.交通检测器在高速公路中的应用及评价[J].山西建筑,2002,28(11)：125-126.
[33]陈青.基于GPS浮动车的城市道路交通状态判别技术研究[D].西安：长安大学,2009.
[34]徐勇军,高梅国,毛二可.智能运输系统中的雷达车辆检测器[J].北京理工大学学报,2001,21(2)：256-259.
[35]张晓峰,王大海,刘艳霞.多探头超声波车流检测系统的设计[J].计算机自动测量与控制,2000,8(5)：28-30.
[36]彭春华,刘建业,刘岳峰,等.车辆检测传感器综述[J].传感器与微系统,2007,26(6)：4-11.
[37]赵亚妮,高辉.基于超声波的车辆检测器设计[J].计算机测量与控制,2011,19(10)：2542-2548.
[38]徐义广,刘波,李艳红,张存林.被动式与主动式红外热成像技术研究[J].应用光学,2008,29(增刊)：44-47.
[39]陈强.高速公路交通流特征参数被动声学检测技术研究[D].吉林：吉林大学,2005.
[40]顾晓辉,王晓鸣.多传感器声目标识别的研究[J].探测与控制学报,2002,24(3)：39-43.
[41]K. O. Arras, O. M. Mozos, W. Burgard. Using boosted features for detection of people in 2D range scans[C]. IEEE Intrenational Conference on Robotics and Automation,2007.
[42]胡顺玺.基于三维激光扫描仪的车辆前方行人检测研究[D].吉林：吉林大学,2011.
[43]孙智勇,葛书芳,荣建,李美玲.行人交通的数据采集方法研究[J].北京工业大学学报,2006,32(6)：530-533.
[44]姜桂艳,常安德,吴超腾.基于GPS浮动车的交通信息采集方法[J].吉林大学学报：工学版.2010,40(4)：971-975.
[45]张晓东.动态交通流信息采集系统若干问题研究[D].吉林：吉林大学,2004.
[46]S. L. Chang, L. S. Chen, Y. C. Chung, S. W. Chen. Automatic license plate recognition [J]. IEEE Transactions on Intelligent Transportation Systems,2004,5(1):42-53.
[47]杨飞,裘炜毅.基于手机定位的实时交通数据采集技术[J].城市交通.2005,3(4)：63-68.
[48]Y. L. Zhao. Mobile phone location determination and its impact on intelligent transportation systems [J]. IEEE Transactions on Intelligent Transportation Systems,2000, 1(1):55-64.
[49]M. D. Fontaine, B. L. Smith. Improving the effectiveness of the traffic monitoring based on wireless location technology [R].Virginia Transportation Research Council VA:Charlottesville, 2005.
[50]王广宇.车辆牌照识别系统综述[J].郑州轻工业学院学报：自然科学版,2001,16(2)：47-50.
[51]黄有金.汽车牌照自动识别技术的研究与实现[D].南京：东南大学,2005.
[52]王俊龙,曲兴华,赵阳.多目视觉检测技术中的照明系统设计[J].光电技术应用,2009,24(4)：1-6.
[53]赵阳,曲兴华.平行照明多目视觉检测技术[J].红外与激光工程,2010,39(4)：339-345.
[54]赵敏.单目视觉多行人目标检测与跟踪技术研究[D].重庆：重庆大学,2010.
[55]L. Wang, H. Z. Ning, W. M. Hu, T. N. Tan. Gait recognition based on procrustes shape analysis [C]. Proceedings of IEEE International Conference on Image Processing,2002:433-436.
[56]I. Haritaoglu, D. Harwood, L. Davis. W4:Real-time surveillance of people and their activities [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[57]A. Ali, E.Dagless. Vehicle and pedestrian detection and tracking [C]. Proceeding of IEEE Colloquium on Iamge Analysis for Transport Apllications, London:1990:12-19.
[58]E. Nakamura, N.Kehtarnavaz, T. Urbanik. Quantification of pedestrian flow parameters along crosswalks [C]. Proceedings of the Intelligent Transportation Systems Meeting, Houston, TX: 1996.
[59]N. Kehtarnavaz, F. Rajkotwala. Real-time vision-based detection of waiting pedestrian [J].Real-Time Imaging,1997,3:433-440.
[60]S. P. Hoogendoorn. Walker behavior modeling by differential games [R]. Delft University of Technology,2002.
[61]S. P. Hoogendoorn. Pedetrian travel behavior in walking areas by subjective utility optimization [C]. Proceedings of the 81th Annual Meeting of the Transportation Research Board (CD-ROM), Washington D.C.,2002.
[62]S. P. Hoogendoorn, P. H. L. Bovy. Nomative pedestrian behavior theory and modeling [C]. Proceedings of the 15th International Symposium on Transportation and Traffic Theory,2002.
[63]T. Kardi, Y. Takeyama, H. Inamura. Tracking system to automate data collection of microscopic pedestrian traffic flow [C]. Proceeding of the 4th Eastern Asia Society for Transportation studies, Hanoi, Vietnam,2001,3(1):11-25.
[64]C. Wren, A. Azarbaycjfani, T. Darrell, et al. Real-time tracking of the human body[J]. Proceeding of the SPIE Conference on Intergration Issuse in Large Commercial Media Delivery Systems,1995.
[65]A. Broggi, M. Bertozzi, A. Fascioli, M. Sechi. Shape-based pedestrian detection[C]. Proceedings of IEEE Intelligent Vehicles Symposium. Dearborn, USA.2000:215-220.
[66]D. M. Gavrila, J. Giebel, S. Munder. Vision-based pedestrian detection:the protector system[C]. Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy.2004:13-18.
[67]M. Tons, R. Doerfler, M. M. Meinecke, M. A. Obojski. Radar sensors and sensor platform used for pedestrian protection in the EC-funded project SAVE-U[C]. Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy. IEEE,2004:813-818.
[68]许言午.面向行人检测的组合分类计算机模型与应用研究[D].安徽：中国科技大学,2009.
[69]F. L. Xu, X. Liu, K. Fujimura. Pedetrain detection and tracking eith night vision [J]. IEEE Transactions onIntelligent Transportation Systems,2005,6(1):63-71.
[70]王亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报,2002,25(3)：225-237.
[71]L. Wang, H. Ning, T. Tan, and W. Hu. Fusion of static and dynamic body biometrics for gait recognition [J]. IEEE Transactions on Circuits and Systems for Video Technology,2004, 14(2):149-158.
[72]A. Yilmaz, O. Javed, M. Shah. Object tracking:A Survey [J].ACM Computing Surveys,2006, 38(4):11-45.
[73]王亮.步态分析与识别[D].北京：中国科学院,2004.
[74]赵明.三维视觉对象分割[D].杭州：浙江大学,2004.
[75]M. Zhao, S.Z. Li, J. J. Bu. Shape evaluation for weighted active shape mocels[C].Proceedings of the Asian Conference on Computer Vision,2004(2):1074-1079.
[76]潘锦辉,廖庆敏,林行刚.视频序列中运动目标的自动提取[J].清华大学学报：自然科学版,2001,41(4/5)：190-193.
[77]胡斌,王生进,丁晓青.基于部位检测和子结构组合的行人检测方法[J].计算机科学,2009,36(11)：242-246.
[78]李同治,丁晓青,王生进.利用级联SVM的人体检测方法[J].中国图形图像学报,2008,13(3)：566-570.
[79]程如中,赵勇,王执中,徐家尧,王新安.实时行人检测预警系统[J].交通运输工程学报,2012,12(5).
[80]赵春晖,张洪才,陆朝霞.一种基于三角特征的行人检测算法[J].计算机工程与应用,2008,44(7)：202-205.
[81]李伟,何鹏举,杨恒,陈明.基于双阈值运动区域分割的Adaboost行人检测算法[J].计算机应用研究,2012,29(9)：3571-3574,3596.
[82]杨涛,李静,潘泉,张艳宁.基于场景模型与统计学习的鲁棒行人检测算法[J].自动化学报,2010(4)：499-508.
[83]汤义,刘伟铭,温金辉.基于MPEG-7标准的行人模型描述与实现[J].科学技术与工程,2010,10(4)：933-937.
[84]勒晶,万卫兵,方涛.使用单目摄像头的实时行人计数算法[J].计算机工程,2009,35(23)：204-206.
[85]勒晶,基于图像处理技术的单目客流检测系统研究[D].上海：上海交通大学,2009.
[86]C.F. Shao, Y. Zhao, H. Yue, X. Zhang. Study on a vision based system for real-time collection of mixed traffic data[C]. Proceedings of International Conference on Traffic and Transportation Studies,2006:606-614.
[87]Y. Zhao, C. F. Shao, X. M. Chen. Study on the vision-based detection and tracking of cyclists and pedestrian [C]. Proceedings of the 14th world Congress on Intelligent Transport Systems, 2007(CD-ROM).
[88]赵熠,邵春福,岳昊等.基于视频图像处理的行人和非机动车数据采集技术研究[J].北京交通大学学报,2007,31(6)：10-14.
[89]赵熠,基于图像处理的混合交通流中行人和非机动车数据采集理论与方法[D].北京：北京交通大学,2008.
[90]岳昊,邵春福,赵熠,陈晓明.基于视频序列的行人多目标跟踪方法研究[J].交通运输系统工程与信息,2007,7(4)：47-51.
[91]李娟.城市交通系统中行人视频检测理论与方法[D].北京：北京交通大学,2010.
[92]J. Li, C. F. Shao, W. T. Xu, C. J. Dong. Real-time pedestrian detection based on improved Gaussian mixture model[C].Proceeding of IEEE International Conference on Measuring Technology and Mechatronics Automation,2009:269-272.
[93]李娟,邵春福,杨励雅.基于混合高斯模型的行人检测方法[J].吉林大学：工学版,2011,41(1)：41-45.
[94]A. N. Marana, S. A. Velastin, L. F. Costa, et al. Automatic estimation of crowd density using texture [J]. Safety Science,1998,28(3):165-175.
[95]X. Zhang, M. R. B. Forshaw. A parallel algorithm to extract information about the motion of road traffic using image analysis [J]. Transportation Research:Part C,1997,5(2):141-152.
[96]王建华,冯帆,梁伟,王惠萍.非线性模型下的摄像机标定[J].光电子技术.2012,32(1)：33-38.
[97]马颂德,张正友.计算机视觉：计算机理论与算法基础[M].北京：科学出版社,1998.
[98]徐静.基于非线性模型的摄像机标定技术研究[J].现代电子技术.2008,(12)：153-157.
[99]张玲,陈丽敏,何伟,郭磊民.基于视频的改进帧差法在车流量检测中的应用[J].重庆大学学报,2004,27(5)：31-34.
[100]W.B. Thomspon, K.M. Mutch, V.A. Berzins. Dynamic occlusion analysis in optical flow fields. IEEE Transactions on Pattern Analysis and Machine Intelligence,1985,7(4):374-383.
[101]裴巧娜.基于光流法的运动目标检测与跟踪技术[D].北京：北方工业大学,2009.
[102]R. Cucchiara, C. Grana, M. Piccardi, A. Prati. Detecting moving objects, ghosts, and shadows in video streams [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003, 25:1337-1342.
[103]C. Stauffer, W.E.L Grimson. Adaptive background mixture models for real-time tracking[C]. Proc IEEE Conference on Computer Vision and Pattern Recognition,1999:246-252.
[104]K. Kim, T. H. Chalidabhongse, D. Harwood, and L. Davis. Real-time foreground-background segmentation using codebook model [J]. Real- Time Imaging,2005,11:172-185.
[105]P. Viola, M. J. Jones, D. Snow. Detecting pedestrians using pattern of motion and apparence [J]. Proceedings of International Conference on Computer Vision,2005,63(2):153-161.
[106]N. Dalal, B. Triggs. Histograms of oriented gradients for human detection [C]. Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition,2005,1:886-893.
[107]A. Mohan, C. Papageorgiou, et al. Example-based object detection in images by components [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2001,23(4):349-361.
[108]龙开文.基于模板匹配的人脸检测[D].四川：四川大学,2005.
[109]林月贡,何小海,张生军.基于区域模板匹配的多目标实时跟踪[J].计算机仿真.2011,28(1)：277-284.
[110]D. Comaniciu, V. Ramesh, P. Meer. Kernel-based object tracking [J]. IEEE Transactions on PatternAnalysis and Machine Intelligence.2003,25(5):564-575.
[111]K. Okuma, A. Taleghani, N. Freitas, et al. A boosted particle filter:multi-taxget detection and tracking[C]. In Porceedings of European Conference on Computer Vision, Prague, Czech Republic,2004,1:28-39.
[112]汪颖进,张桂林.新的基于Kalman滤波的跟踪方法[J].红外与激光工程,2004,33(5)：505-508.
[113]A. Bobick, J. Davis, S. Intille, et al. Action recognition in an interactive story environment, PerCom TR 398[R]. MIT Media Lab,1996.
[114]M. Fukumoto, T. Ogata, J. K. Tan. Human motions representation and recognition by directional motion history images [J]. Artif Life Robotics,2008,13:326-330.
[115]H. Meng, M. Freeman. Real-time human action recognition on embedded reconfigurable video processing architecture [J]. Real-Time Image Proc,2008,3:163-176.
[116]J. Davis, G Bradski. Real-time motion template gradients using intel CVLib[C]. IEEE International Conference on Computer Vision, Kerhyra,1999,3:251-263.
[117]T. Ojala, M. Pietikainen, T. Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[118]郑永斌,黄新生,丰松江.SIFT和旋转不变LBP相结合的图像匹配算法[J].计算机辅助设计与图像学学报,2010,2：286-292.
[119]D. G Lowe. Distinctive image features form scale-invariant keypoint [J]. International Journal of Computer Vision,2004,60(2):91-110.
[120]孙宁,冀贞海,邹采荣,等.基于局部二元模式算子的人脸性别分类方法[J].华中科技大学学报(自然科学版),2007,35(增刊)：177-181.
[121]杨淑荣.图像模式识别vc++技术实现[M].北京：清华大学出版社,2005.
[122]卜建军,严宝杰.交通调查与分析[M].北京：人民交通出版社,2004.
[123]飞思科技产品研发中心.神经网络理论与Matlab7实现[M],北京：电子工业出版社,2005.
[124]王凌.料能优化算法及其应用[M].北京：清华大学出版社,2003.
[125]朱健英.智能系统非经典数学方法[M].武汉：华中科技大学出版社,2001.
[126]O. Masoud, N. P. Papanikolopoulos. Using geometric primitives to calibrate traffic scenes [J]. Transportation Research Part C,2007,15(6):361-379.
[127]A. Bartoli, P. Sturm. Constrained structure and motion from multiple uncalibrated views of a piecewise planar scene [J]. Computer Vision,2003,52 (1):45-64.
[128]A. Criminisi, I. Reid, A. Zisserman. Single view metrology [J]. Computer Vision,2001,40 (2):123-148.
[129]M. Wilczkowiak, G. Trombettoni, C. Jermann, P. Sturm, E. Boyer. Scene modeling based on constraint system decomposition techniques [C]. Proceedings of International Conference on Computer Vision (ICCV),2003:1004-1010.
[130]K. T. Song, J. C. Tai. Dynamic calibration of pan-tilt-zoom cameras for traffic monitoring [J]. IEEE Trans. on Systems, Man and Cybernetics, Part B,2006,36(5):1091-1103.
[131]C. Zhaoxue, S. Pengfei. Efficient method for camera calibration in traffic scenes [C]. IEEE Electron. Lett,2004,40(6):368-369.
[132]A. H. S. Lai, N. H. C. Yung. Lane detection by orientation and length discrimination [J]. IEEE Trans. Syst., Man, Cybem. Part B,2000,30(4):539-548.
[133]O. Masoud, N. P. Papanikolopoulos. Using geometric primitives to calibrate traffic scenes [C].Intelligent Robots and Systems,2004,2:1878-1883.
[134]L. Fengjun, T. Zhao, N. Ramakant. Camera calibration from video of a walking human [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(9):1513-1518.
[135]T. N. Schoepflin, D. J. Dailey. Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation [J]. IEEE Trans. Intell. Transp. Syst,2003,4(2):90-98.
[136]卞晓东.基于机器视觉的车辆几何尺寸测量系统研究[D].南京：东南大学,2005.
[137]P. Kilambi, E. Ribnick, A. J. Joshi, O. Masoud, N. Papanikolopoulos. Estimating pedestrian counts in groups [J].Computer Vision and Image Understanding,2008,110(1):43-59.
[138]M. Pollefeys, R. Koch, L. V. Goll. Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters[C]. Proceedings of International Conference on Computer Vision (ICCV),1998:90-95.
[139]杨久龄,刘学会.GB5768-1999道路交通标志和标线[S].北京：中国标准出版社,1999.
[140]李琦,邵春福,岳吴,赵丹,孙轶轩.基于改进密码本模型的视频对象检测[J].交通信息与安全,2011,29(5)：140-144.
[141]Q. Li, C.F. Shao, H. Yue, J. Li. Real-time foreground-background segmentation Based on improved Codebook Model[C]. International Conference on BioMedical Engineering and Informatics,2010,1:269-273.
[142]K.Toyama, J. Krumm, B. Brumitt, B. Meyers. WallFlower:Principles and Practice of background maintenance[C]. IEEE International Conferenceon Computer Vision,1999: 255-261.
[143]A. Elgammal, R. Duraiswami, L. S. Davis. Efficient kernel density estimation using the fast Gauss transform with applications to color modeling and tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(11):1499-1504.
[144]邵春福,赵熠,吴戈.道路交通数据采集技术研究展望[J].现代交通技术,2006,3(6)：66-70.
[145]D. M. Ha, J. M. Lee, and Y. D. Kim. Neural-edge-based vehicle detection and traffic parameter extraction [J]. Image and Vision Computing,2004,22(11):899-907.
[146]Y. Chen, C. Chen, C. Huang, Y. Hung. Efficient hierarchical method for background subtraction [J]. Pattern Recognition,2007(40):2706-2715.
[147]D.S. Lee. Effective gaussian mixture learning for video background subtraction [C].Proc IEEE Pattern Analysis and Machine Intelligence,2005,27(5):827-832.
[148]阮秋琦,阮宇智译.数字图像处理(第二版)[M].北京：电子工业出版社,2007.
[149]M. Isard, A. Blake. Contour tracking by stochastic propagation of conditional density[C].Computer Vision,1996:343-356.
[150]Z. W. Wang, X. K. Yang, X. Yi, S, and Y. Yu. CamShift guided particle filter for visual tracking [J]. Pattern Recognition Letters,2009,30:407-413.
[151]D. Comaniciu, V. Ramesh, P. Meer. Real-Time tracking of non-rigid objects using mean shift [J].IEEE Computer Vision and Pattern Recognition,2000,2:142-149.
[152]W. Hao, A. C. Sankaranarayanan, R. Chellappa. Online empirical evaluation of tracking algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(8): 1443-1458.
[153]B.Y. Liu, J. Z. Huang, Y. Lin, C. Kulikowsk. Robust tracking using local sparse appearance model and K-selection [C].IEEE Conference on Computer Vision and Pattern Recognition,2011:1313-1320.
[154]张玲.视频目标跟踪方法研究[D].安徽：中国科学技术大学,2009.
[155]J. Canny. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003 (8)6:679-698.
[156]吴上生,方飞村,段富海,苟国华.B样条二进小波在齿轮轮廓图像处理中的应用[J].华南理工大学学报：自然科学版,2007,35(8)：55-58.
[157]闫蓓,王斌,李媛.基于最小二乘法的椭圆拟合改进算法[J].北京航空航天大学学报,2008,34(3)：295-298.
[158]R. T. Collins. Mean-shift blob tracking through scale space[C]. IEEE Computer Society Conference on Computer Visionand Pattern Recognition, Pittsburgh, USA,2003,2:234-240.
[159]J. Owens, A. Hunter, E. Fletcher. A fast model-free morphology-based object tracking algorithm[C]. British MachineVision Conference, Cardiff, UK,2002:767-776.
[160]C. G. Broyden. The convergence of a class of double rank minimization algorithms:the new algorithm [J]. Journal of the Institute of Mathematics and its Applications,1970,6:222-231.
[161]R. Fletcher. A new approach to variable metric algorithms [J]. Computer Journal,1970,13: 317-322.
[162]D. Goldfarb. A family of variable metric methods derived by variational means [J]. Mathematics of Computation,1970,24:23-26.
[163]D. F. Shanno. Conditioning of quasi-Newton methods for function minimization [J]. Mathematics of Computation,1970,24:647-650.
[164]袁亚湘,孙文瑜.最优化理论与方法[M].北京：科学出版社,1997.
[165]美国交通研究委员会编.美国道路通行能力手册(2000年版)[M].任福田等译.北京：中国建筑出版社,2000.
[166]K. Prahlad, R. Evan, J. J. Ajay, M. Osama, P. Nikolaos. Estimating pedestrian counts in groups [J]. Computer Vision and Image Understanding,2008,110:43-59.