基于视频检测的行人交通参数提取技术研究
|
摘要
摘要：目前交通监控的主要方式是两种：人工观察；摄像机记录,人工统计这两种方式都需要投入大量的人力和物力资源,并且人工统计的准确性有限,可能会出现疏漏,对异常情况不能及时做出反应。为此需要建立一种不需人工干预、或者只需要很少人工操作的智能交通管理系统,通过安装在固定位置的摄像机拍摄视频,实现对目标的定位、识别和跟踪及交通参数的提取和分析,并在此基础上进一步实现目标(例如行人、车辆等)行为的分析与判断。
目前,针对车辆的目标检测、跟踪、识别研究已经比较成熟,但针对行人的目标检测、跟踪、识别研究则相对滞后,而且具体情况异常复杂,例如行人为非刚体,在视频中的面积小,行动较为随机,速度并不连贯,而且行人之间的间距有可能较小,这些都给相关技术造成了很大的挑战。本文对上述难点进行了研究,通过提取交叉口的行人流量、速度、步行方向等参数,给行人的交通管理与控制以及仿真系统模拟现实提供基础数据。
本文的主要研究内容包括：
(1)分析了智能交通监控视频中的降质因素,并研究了各种噪声的数学模型,针对交通视频中最常见的椒盐噪声和高斯噪声实现了经典滤波算法的去噪,并设计了一种改进算法,将加入图像像素点是否为噪声的判决预处理,只针对可能为噪声点的区域进行去噪,而对于非噪声点不进行去噪,更好地保持了图像的细节信息。
(2)对于行人检测和识别问题,针对各种具体难点设计了具体的解决方案和步骤。比较了常用目标检测算法,并根据交叉口智能交通监控视频的特点选用了合适的行人检测算法。由于检测算法可能造成区域的不完整和空洞,采用形态学操作对行人目标区域的断裂区域实现连接,并对目标区域内的空洞进行填充。对可能存在噪声的区域采用区域面积统计的方法计算面积,并去除小面积的噪声斑块。对阴影采用几何形状的方法予以去除。对交叉路口复杂环境中的各种运动目标进行建模,并总结了行人目标的特点,实现了基于视频检测的行人目标识别。
(3)实现了交通视频中交叉口行人目标的跟踪。通过对摄像机视场的标定,完成了摄像机空间拍摄的视频数字图像中的坐标到实际物理世界空间坐标系的映射换算,提取了包括行人目标的质心、位移、速度、加速度和流量等交通参数,为仿真系统模拟现实提供实际状况提供了翔实的基础数据。
综上所述,本文的研究成果能够为仿真系统模拟现实提供实际状况,并分析所在路口的交通状况,为交通管理与控制提供依据。
ABSTRACT:Currently, most monitoring of traffic scene is mainly achieved through manual supervisory control or artificial observation of video after the event. These methods need a lot of manpower, material resources; furthermore, omissions may occur abnormal situations can't be responded due to the limitation of human's energy and attention. Thus there is need to establish intelligent traffic management system that is without human intervention or requires very little manual operation. In the system, installing cameras are fixed to capture video to achieve targets location, identification and tracking. Behavior of goals (such as pedestrians, vehicles, etc.) are analyzed and judged based on the traffic parameters that are analyzed and extracted.
The methods of vehicle detection, tracking and recognition have been proposed and achieved some fruits and contributions, however, pedestrian detection, tracking and recognition is relatively lagging behind. Besides, the specific situation of pedestrian is much more complex. The pedestrian area in the video is small; the action of pedestrian is random; the speed of pedestrian is not consistent; and the spacing between the pedestrians may be very small. The above problems pose a great threat on technological realization. Therefore, it is required to search and solve the difficulties of parameters extracting, including the amount of pedestrian on intersection of traffic, speed, direction and other parameters important traffic data which are important to the simulation system that can simulate the actual state of reality.
The main contents of this paper include:
(1) The lower quality factors of the intelligent traffic surveillance video were analyzed and various noise models are summarizes. The most common noise in intelligent traffic video, salt & pepper noise and Gaussian noise, were reduced by classical filtering algorithms. An improved algorithm was proposed in which the image pixels will be pre-judged as noise or non-noise. Only possible pixels in the region of noise were filtered while non-noise pixels were not filtered, thus the image details were remained better.
(2) For pedestrian detection and identification, specific solutions and specific steps were developed to solve the difficulties. The commonly algorithms used for target detection were compared and suitable pedestrian detection algorithm was selected according to the characteristics intelligent traffic intersection surveillance video. The detected region of pedestrians is often incomplete and has empty regions, morphological operations were employed on the pedestrian region to connect the fracture of the target area and fill the holes in the target region. Small noise patches that may exist in region of pedestrians were removed by area calculation. The shadow of pedestrian was removed by geometric-based method. Various moving object models in the complex environment of intersection were established and the characteristics of pedestrian goals were summarized to achieve video-based pedestrian detection and recognition.
(3) Pedestrian tracking algorithm in intelligent traffic video intersections was realized. Through calibration of the camera field, the camera space of digital image coordinates in video was mapped to the actual physical world space coordinate. A lot of important traffic parameters were extracted, including center of pedestrian target, displacement, walking speed, walking acceleration, flow rate of pedestrian traffic and so on. The valuable traffic information and data are important for the simulation system to provide realistic simulation of the actual situation.
In conclusion, the results and conclusions of this research project can provide practical simulation system with the real traffic situation which analyzes the traffic situation in the junction of the transportation system. Besides, it provides the basis for comprehensive management and maintenance. Thus, this paper is not only of great theoretical significance, but also has extensive application value.
目前,针对车辆的目标检测、跟踪、识别研究已经比较成熟,但针对行人的目标检测、跟踪、识别研究则相对滞后,而且具体情况异常复杂,例如行人为非刚体,在视频中的面积小,行动较为随机,速度并不连贯,而且行人之间的间距有可能较小,这些都给相关技术造成了很大的挑战。本文对上述难点进行了研究,通过提取交叉口的行人流量、速度、步行方向等参数,给行人的交通管理与控制以及仿真系统模拟现实提供基础数据。
本文的主要研究内容包括：
(1)分析了智能交通监控视频中的降质因素,并研究了各种噪声的数学模型,针对交通视频中最常见的椒盐噪声和高斯噪声实现了经典滤波算法的去噪,并设计了一种改进算法,将加入图像像素点是否为噪声的判决预处理,只针对可能为噪声点的区域进行去噪,而对于非噪声点不进行去噪,更好地保持了图像的细节信息。
(2)对于行人检测和识别问题,针对各种具体难点设计了具体的解决方案和步骤。比较了常用目标检测算法,并根据交叉口智能交通监控视频的特点选用了合适的行人检测算法。由于检测算法可能造成区域的不完整和空洞,采用形态学操作对行人目标区域的断裂区域实现连接,并对目标区域内的空洞进行填充。对可能存在噪声的区域采用区域面积统计的方法计算面积,并去除小面积的噪声斑块。对阴影采用几何形状的方法予以去除。对交叉路口复杂环境中的各种运动目标进行建模,并总结了行人目标的特点,实现了基于视频检测的行人目标识别。
(3)实现了交通视频中交叉口行人目标的跟踪。通过对摄像机视场的标定,完成了摄像机空间拍摄的视频数字图像中的坐标到实际物理世界空间坐标系的映射换算,提取了包括行人目标的质心、位移、速度、加速度和流量等交通参数,为仿真系统模拟现实提供实际状况提供了翔实的基础数据。
综上所述,本文的研究成果能够为仿真系统模拟现实提供实际状况,并分析所在路口的交通状况,为交通管理与控制提供依据。
ABSTRACT:Currently, most monitoring of traffic scene is mainly achieved through manual supervisory control or artificial observation of video after the event. These methods need a lot of manpower, material resources; furthermore, omissions may occur abnormal situations can't be responded due to the limitation of human's energy and attention. Thus there is need to establish intelligent traffic management system that is without human intervention or requires very little manual operation. In the system, installing cameras are fixed to capture video to achieve targets location, identification and tracking. Behavior of goals (such as pedestrians, vehicles, etc.) are analyzed and judged based on the traffic parameters that are analyzed and extracted.
The methods of vehicle detection, tracking and recognition have been proposed and achieved some fruits and contributions, however, pedestrian detection, tracking and recognition is relatively lagging behind. Besides, the specific situation of pedestrian is much more complex. The pedestrian area in the video is small; the action of pedestrian is random; the speed of pedestrian is not consistent; and the spacing between the pedestrians may be very small. The above problems pose a great threat on technological realization. Therefore, it is required to search and solve the difficulties of parameters extracting, including the amount of pedestrian on intersection of traffic, speed, direction and other parameters important traffic data which are important to the simulation system that can simulate the actual state of reality.
The main contents of this paper include:
(1) The lower quality factors of the intelligent traffic surveillance video were analyzed and various noise models are summarizes. The most common noise in intelligent traffic video, salt & pepper noise and Gaussian noise, were reduced by classical filtering algorithms. An improved algorithm was proposed in which the image pixels will be pre-judged as noise or non-noise. Only possible pixels in the region of noise were filtered while non-noise pixels were not filtered, thus the image details were remained better.
(2) For pedestrian detection and identification, specific solutions and specific steps were developed to solve the difficulties. The commonly algorithms used for target detection were compared and suitable pedestrian detection algorithm was selected according to the characteristics intelligent traffic intersection surveillance video. The detected region of pedestrians is often incomplete and has empty regions, morphological operations were employed on the pedestrian region to connect the fracture of the target area and fill the holes in the target region. Small noise patches that may exist in region of pedestrians were removed by area calculation. The shadow of pedestrian was removed by geometric-based method. Various moving object models in the complex environment of intersection were established and the characteristics of pedestrian goals were summarized to achieve video-based pedestrian detection and recognition.
(3) Pedestrian tracking algorithm in intelligent traffic video intersections was realized. Through calibration of the camera field, the camera space of digital image coordinates in video was mapped to the actual physical world space coordinate. A lot of important traffic parameters were extracted, including center of pedestrian target, displacement, walking speed, walking acceleration, flow rate of pedestrian traffic and so on. The valuable traffic information and data are important for the simulation system to provide realistic simulation of the actual situation.
In conclusion, the results and conclusions of this research project can provide practical simulation system with the real traffic situation which analyzes the traffic situation in the junction of the transportation system. Besides, it provides the basis for comprehensive management and maintenance. Thus, this paper is not only of great theoretical significance, but also has extensive application value.
引文
[1]AHuW., TanT.,Wang L. and Maybank S. A survey on visual surveillance of object motion and behaviors[J]. IEEE Transactions on Systems, Man, and Cybernetics-PART C:Applications and Reviews.2004,34(3):334-351.
[2]Collins R.T, LiptonA.J., etal. A system for video surveillance and monitoring[R], Technology Report, The Robotics Institute,Pittsburgh,USA,2000.
[3]Haritaoglul., Harwood D. And DavisL.S.W4:real-time surveillance of people and their activities s[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(8):809-830.
[4]Christopher Richard Wren, Ali Azarbayejani, Trevor Darrell, Alex Paul Pentland. Pfinder:real-time tracking of the human bodys[J], IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(7):780-785.
[5]于万波.基于MATLAB的图像处理[M].北京：清华大学出版社,2008,3.
[6]R. C. Gonzalez, R E. Woods, S. L. Eddins. Digital image processing using MATLAB [M].Beijing:Pub. House of Electronics Industry:Pearson Education (Asia) Co.,2004:231-234.
[7]章毓晋.图像处理和分析技术(第二版)[M].北京：高等教育出版社,2008：71-72.
[8]唐彩虹,蔡利栋.一种基于直方图的加权均值滤波方法[J].微计算机信息,2006,22(22)：202-204.
[9]陈初伙,丁勇,刘栎莉.去除椒盐噪声的自适应开关加权均值滤波[J].计算机工程,2010,36(4)：210-212.
[10]张媛,蔡利栋.一种去除文本图像椒盐噪声的方法[J].长春理工大学学报(自然科学版),2010,33(2)：129-132.
[11]周志宇,汀亚明,黄文清,计算机视觉在交通监控中的应用.实用案例,2003,(1)：51-53.
[12]张泽旭,李金宗,李宁宁.基于光流场分荆和Canny边缘提取融合算法的运动目标检测.电子学报,2003,31(9)：1299-1302.
[13]屈有山,田维坚,李英才.基于并行隔帧差分光流场与灰度分析综合算法的运动目标检测[J].光子学报,2003,32(2)：182-186.
[14]Sasa G,Loncaric S. Spatio-temporal image segmentation using optical flow and clustering algorithm[C]. First Int'1 Workshop on Image and Signal Processing and Analysis.Pula, Croatia, 2000:63-68.
[15]Smith SM, Brady JM.ASSET-2:Real-time motion segmentation and shape trackingfJ]. IEEE Trans,1995,8(17):814-820.
[16]Thompson W B, Pong T C. Detecting moving object[J]. International Journal Computer and Vision.1990,4:39-57.
[17]Jong Bae Kim, Hang Joon Kim. Efficient region-based motion segmentation for a video monitoring system[J]. Pattern Recognition Letters 2003,24(1-3):113-128.
[18]Needham C J, Boyle R D. Tracking multiple sports players through occlusion, congestion and scale[J]. British Machine Vision Conference,2001,1:93-102.
[19]Elgammal A, Harwood D, Davis L. Non-parametric model for background subtraction[C]. European Conference on Computer Vision.Dublin, Ireland,2000.751-767.
[20]Haritaoglu I, Harwood D, Davis L, W4:Real-time surveillance of people and their activities[J]. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[21]McKenna Setal, Tracking groups of people[J]. Computer Vision and Image Understanding, 2000,80(1):42-56.
[22]Karmann K, Brandt A. Moving object recognition using an adaptive background memory[J]. In: Cappellini V ed. Time-varying Image Processing and Moving Object Recognition.2.Elsevier, Amsterdam, The Netherlands,1990.
[23]Kilger M.A shadow handler in a video-based real-time traffic monitoring system[C]. In:Proc IEEE Workshop on Application of Computer Vision, Palm Springs, CA,1992.1060-1066.
[24]Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking[C]. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, 1999,2:246-252.
[25]郑江滨,张艳宁,冯大淦等.视频监视中运动目标的检测与跟踪算法[J].系统工程与电子技术,2002,10：34-37.
[26]Xiaobo Li,Zhi-Qiang Liu,Ka-Ming Leung.Detection of vehicles from traffic scenes using fuzzy integrals[J]. Pattern Recognition 2002,35(4):967-980.
[27]Vieren C,Cabestaing F,Postaire J.Catching moving objects with snakes for motion tracking[J]. Pattern Recognition Letters,1995,16(7):679-685.
[28]乐应英.智能视频监控系统中目标检测与跟踪关键技术研究[D].云南大学硕十论文,2010：21-22.
[29]欧珊瑚,王倩丽,朱哲瑜.Visual C++.NET数字图像处理技术与应用[M],北京：清华大学出版社,2003.
[30]唐常青,吕宏伯,黄铮.数学形态学方法及其应用[M],北京：科学出版社,1986.
[31]J. Serra. Image Analysis and Mathematical Morphology[M].Academic Press, London,1982.
[32]仲亮亮.视频对象分割与跟踪方法研究[D].中国石油大学硕十论文,2010：19-21.
[33]R. Cucchiara, C. Grana, M. Piccardi, A. Prati, S. Sirotti. Improving Shadow Suppression in Moving Object Detection with HSV Color Information[C], Proceedings of IEEE Intelligent Transportation Systems Conference. Oakland, CA,2001:334-339.
[34]李娟.城市交通系统中行人交通视频检测的理论与方法[D].北京交通大学博十论文,2010：44-45.
[35]D.Xu,X.Li,Z.Liu,Y.Yuan.Cast shadow detection in video seginentation[J].Pattern Recognition Letter,2005,26:91-99.
[36]A.Leone,C.Distante, F.Buccolieri.A shadow elimination approach invideo-surveillance context[J].Pattern Recognition Letter,2006,27(5):345-355.
[37]W.Zhang,X.Z.Fang, Y.Xu.Detection of moving cast shadows using imageorthogonal transform[A].In Proc.IEEE Int.Conf.Pattem Recognition[C],2006,1:626-629.
[38]D.Toth,I.Stuke,A.Wagner, T.Aach.Detection of moving shadows using mean shiftclustering and a significance test.In Proc.Int.Conf.Pattern Recognition[C],2004,4:260-263.
[39]Y.Wang,T.Tan, K.F.Loe.A probabilistic method for foreground and shadowsegmentation.In Proc.Int.Conf.Image Processing[C],2003,3:937-940.
[40]N.Martel-Brisson, A.Zaccarin.Moving cast shadow detection from a Gaussianmixture shadow model.In Proc.IEEE Computer Soc.Conf.Computer Vision andPattern Recognition[C], 2005,2:643-648.
[41]J.W.Hsieh,S.H.Yu,Y.S.Chen, W.F.Hu.Automatic traffic surveillance systemfor vehicle tracking and classification [J].IEEE Transactions on Intelligence Transportation System, 2006,7(2):175-187.
[42]J. Segen, S. Pingali. A camera-based system for tracking people in real time[C]. Proceedings of International Conference on Pattern Recognition, Vienna,1996:63-67.
[43]Haag M,Nagel H-H. Incremental recognition of traffic situations from video image sequences[J].Image and Vision Computing.2000,(18)137-153.
[44]Rogerio Richa, Antonio P.L. Bo, Philippe Poignet. Towards robust 3D visual tracking for motion compensation in beating heart surgery[J]. Medical Image Analysis,2011,15(3):302-315.
[45]Wren C R, Azarbyejani A,Darrell T.P finder:Real-time Tracking of the Human Body. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):780-785.
[46]I-Cheng Chang, Shih-Yao Lin.3D human motion tracking based on a progressive particle filter[J].3D human motion tracking based on a progressive particle filter[J]Pattern Recognition, 2010,43(10):3621-3635.
[47]S. Lefevre, C. Fluck, B. Maillard. A fast snake-based method to track football players[C]. Proceedings of IAPR International Workshop on Machine Vision Applications, Tokyo, Japan, 2000:501-504.
[48]Jorge Badenas, Bober M, and Pla F.Motion and intensity based segmentation and its application to traffic monitoring[C].In Proceeding, International Conference on Image and Processings ICIAP'97, Florence, Italy.1997,502-509.
[49]Jorge Badenas and Pla F.Segmentation based on region tracking in image sequences for traffic monitoring[C].In 14th International Conference on PatternR.ecognition.1998,999-1001.
[50]Jorge Badenas,Jose Miguel,Sanchiz,Filiberto Pla. Motion-based segmentation and region tracking in image sequences[J].Pattern Recognition,2001,(34):661-670.
[51]Fukunaga K, Hostetler L D. The estimation of thegradient of a density function with applications inpattern recognition [J]. IEEE Trans on InformationTheory,1975,21(1):32-40.
[52]Cheng Y Z. Mean shift, mode seeking, and clustering[J]. IEEE Trans on Pattern Analysis and MachineIntelligence,1995,17(8):790-799.
[53]Comaniciu D, Meer P. Mean shift analysis andapplications[C]. Proc of the IEEE Int ConfonComputer Vision. Kerkyra,1999:1197-1203.
[54]Comaniciu D, Meer P. Distribution free decompositionof multivariate data [J]. Pattern Analysis andApplications,1999,2(1):22-30.
[55]Comaniciu D, Ramesh V, Meer P. Real-time tracking ofnon-rigid objects using mean shift[C]. Proc of the IEEEConf on Computer Vision and Pattern Recognition.Hilton Head Island,2000: 142-149.
[56]Ido Leichter, Michael Lindenbaum, Ehud Rivli. Mean Shift tracking with multiple reference color histograms [J]. Computer Vision and Image Understanding,2010,114(3):400-408.
[57]Fanglin Wang, Shengyang Yu, Jie Yang.Robust and efficient fragments-based tracking using mean shift[J].EU-International Journal of Electronics and Communications, 2010,64(7):614-623.
[58]Shu-Xiao Li, Hong-Xing Chang, Cheng-Fei Zhu.Adaptive pyramid mean shift for global real-time visual tracking[J].Image and Vision Computing,2010,28(3):424-4.
[2]Collins R.T, LiptonA.J., etal. A system for video surveillance and monitoring[R], Technology Report, The Robotics Institute,Pittsburgh,USA,2000.
[3]Haritaoglul., Harwood D. And DavisL.S.W4:real-time surveillance of people and their activities s[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(8):809-830.
[4]Christopher Richard Wren, Ali Azarbayejani, Trevor Darrell, Alex Paul Pentland. Pfinder:real-time tracking of the human bodys[J], IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(7):780-785.
[5]于万波.基于MATLAB的图像处理[M].北京：清华大学出版社,2008,3.
[6]R. C. Gonzalez, R E. Woods, S. L. Eddins. Digital image processing using MATLAB [M].Beijing:Pub. House of Electronics Industry:Pearson Education (Asia) Co.,2004:231-234.
[7]章毓晋.图像处理和分析技术(第二版)[M].北京：高等教育出版社,2008：71-72.
[8]唐彩虹,蔡利栋.一种基于直方图的加权均值滤波方法[J].微计算机信息,2006,22(22)：202-204.
[9]陈初伙,丁勇,刘栎莉.去除椒盐噪声的自适应开关加权均值滤波[J].计算机工程,2010,36(4)：210-212.
[10]张媛,蔡利栋.一种去除文本图像椒盐噪声的方法[J].长春理工大学学报(自然科学版),2010,33(2)：129-132.
[11]周志宇,汀亚明,黄文清,计算机视觉在交通监控中的应用.实用案例,2003,(1)：51-53.
[12]张泽旭,李金宗,李宁宁.基于光流场分荆和Canny边缘提取融合算法的运动目标检测.电子学报,2003,31(9)：1299-1302.
[13]屈有山,田维坚,李英才.基于并行隔帧差分光流场与灰度分析综合算法的运动目标检测[J].光子学报,2003,32(2)：182-186.
[14]Sasa G,Loncaric S. Spatio-temporal image segmentation using optical flow and clustering algorithm[C]. First Int'1 Workshop on Image and Signal Processing and Analysis.Pula, Croatia, 2000:63-68.
[15]Smith SM, Brady JM.ASSET-2:Real-time motion segmentation and shape trackingfJ]. IEEE Trans,1995,8(17):814-820.
[16]Thompson W B, Pong T C. Detecting moving object[J]. International Journal Computer and Vision.1990,4:39-57.
[17]Jong Bae Kim, Hang Joon Kim. Efficient region-based motion segmentation for a video monitoring system[J]. Pattern Recognition Letters 2003,24(1-3):113-128.
[18]Needham C J, Boyle R D. Tracking multiple sports players through occlusion, congestion and scale[J]. British Machine Vision Conference,2001,1:93-102.
[19]Elgammal A, Harwood D, Davis L. Non-parametric model for background subtraction[C]. European Conference on Computer Vision.Dublin, Ireland,2000.751-767.
[20]Haritaoglu I, Harwood D, Davis L, W4:Real-time surveillance of people and their activities[J]. IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[21]McKenna Setal, Tracking groups of people[J]. Computer Vision and Image Understanding, 2000,80(1):42-56.
[22]Karmann K, Brandt A. Moving object recognition using an adaptive background memory[J]. In: Cappellini V ed. Time-varying Image Processing and Moving Object Recognition.2.Elsevier, Amsterdam, The Netherlands,1990.
[23]Kilger M.A shadow handler in a video-based real-time traffic monitoring system[C]. In:Proc IEEE Workshop on Application of Computer Vision, Palm Springs, CA,1992.1060-1066.
[24]Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking[C]. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, 1999,2:246-252.
[25]郑江滨,张艳宁,冯大淦等.视频监视中运动目标的检测与跟踪算法[J].系统工程与电子技术,2002,10：34-37.
[26]Xiaobo Li,Zhi-Qiang Liu,Ka-Ming Leung.Detection of vehicles from traffic scenes using fuzzy integrals[J]. Pattern Recognition 2002,35(4):967-980.
[27]Vieren C,Cabestaing F,Postaire J.Catching moving objects with snakes for motion tracking[J]. Pattern Recognition Letters,1995,16(7):679-685.
[28]乐应英.智能视频监控系统中目标检测与跟踪关键技术研究[D].云南大学硕十论文,2010：21-22.
[29]欧珊瑚,王倩丽,朱哲瑜.Visual C++.NET数字图像处理技术与应用[M],北京：清华大学出版社,2003.
[30]唐常青,吕宏伯,黄铮.数学形态学方法及其应用[M],北京：科学出版社,1986.
[31]J. Serra. Image Analysis and Mathematical Morphology[M].Academic Press, London,1982.
[32]仲亮亮.视频对象分割与跟踪方法研究[D].中国石油大学硕十论文,2010：19-21.
[33]R. Cucchiara, C. Grana, M. Piccardi, A. Prati, S. Sirotti. Improving Shadow Suppression in Moving Object Detection with HSV Color Information[C], Proceedings of IEEE Intelligent Transportation Systems Conference. Oakland, CA,2001:334-339.
[34]李娟.城市交通系统中行人交通视频检测的理论与方法[D].北京交通大学博十论文,2010：44-45.
[35]D.Xu,X.Li,Z.Liu,Y.Yuan.Cast shadow detection in video seginentation[J].Pattern Recognition Letter,2005,26:91-99.
[36]A.Leone,C.Distante, F.Buccolieri.A shadow elimination approach invideo-surveillance context[J].Pattern Recognition Letter,2006,27(5):345-355.
[37]W.Zhang,X.Z.Fang, Y.Xu.Detection of moving cast shadows using imageorthogonal transform[A].In Proc.IEEE Int.Conf.Pattem Recognition[C],2006,1:626-629.
[38]D.Toth,I.Stuke,A.Wagner, T.Aach.Detection of moving shadows using mean shiftclustering and a significance test.In Proc.Int.Conf.Pattern Recognition[C],2004,4:260-263.
[39]Y.Wang,T.Tan, K.F.Loe.A probabilistic method for foreground and shadowsegmentation.In Proc.Int.Conf.Image Processing[C],2003,3:937-940.
[40]N.Martel-Brisson, A.Zaccarin.Moving cast shadow detection from a Gaussianmixture shadow model.In Proc.IEEE Computer Soc.Conf.Computer Vision andPattern Recognition[C], 2005,2:643-648.
[41]J.W.Hsieh,S.H.Yu,Y.S.Chen, W.F.Hu.Automatic traffic surveillance systemfor vehicle tracking and classification [J].IEEE Transactions on Intelligence Transportation System, 2006,7(2):175-187.
[42]J. Segen, S. Pingali. A camera-based system for tracking people in real time[C]. Proceedings of International Conference on Pattern Recognition, Vienna,1996:63-67.
[43]Haag M,Nagel H-H. Incremental recognition of traffic situations from video image sequences[J].Image and Vision Computing.2000,(18)137-153.
[44]Rogerio Richa, Antonio P.L. Bo, Philippe Poignet. Towards robust 3D visual tracking for motion compensation in beating heart surgery[J]. Medical Image Analysis,2011,15(3):302-315.
[45]Wren C R, Azarbyejani A,Darrell T.P finder:Real-time Tracking of the Human Body. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):780-785.
[46]I-Cheng Chang, Shih-Yao Lin.3D human motion tracking based on a progressive particle filter[J].3D human motion tracking based on a progressive particle filter[J]Pattern Recognition, 2010,43(10):3621-3635.
[47]S. Lefevre, C. Fluck, B. Maillard. A fast snake-based method to track football players[C]. Proceedings of IAPR International Workshop on Machine Vision Applications, Tokyo, Japan, 2000:501-504.
[48]Jorge Badenas, Bober M, and Pla F.Motion and intensity based segmentation and its application to traffic monitoring[C].In Proceeding, International Conference on Image and Processings ICIAP'97, Florence, Italy.1997,502-509.
[49]Jorge Badenas and Pla F.Segmentation based on region tracking in image sequences for traffic monitoring[C].In 14th International Conference on PatternR.ecognition.1998,999-1001.
[50]Jorge Badenas,Jose Miguel,Sanchiz,Filiberto Pla. Motion-based segmentation and region tracking in image sequences[J].Pattern Recognition,2001,(34):661-670.
[51]Fukunaga K, Hostetler L D. The estimation of thegradient of a density function with applications inpattern recognition [J]. IEEE Trans on InformationTheory,1975,21(1):32-40.
[52]Cheng Y Z. Mean shift, mode seeking, and clustering[J]. IEEE Trans on Pattern Analysis and MachineIntelligence,1995,17(8):790-799.
[53]Comaniciu D, Meer P. Mean shift analysis andapplications[C]. Proc of the IEEE Int ConfonComputer Vision. Kerkyra,1999:1197-1203.
[54]Comaniciu D, Meer P. Distribution free decompositionof multivariate data [J]. Pattern Analysis andApplications,1999,2(1):22-30.
[55]Comaniciu D, Ramesh V, Meer P. Real-time tracking ofnon-rigid objects using mean shift[C]. Proc of the IEEEConf on Computer Vision and Pattern Recognition.Hilton Head Island,2000: 142-149.
[56]Ido Leichter, Michael Lindenbaum, Ehud Rivli. Mean Shift tracking with multiple reference color histograms [J]. Computer Vision and Image Understanding,2010,114(3):400-408.
[57]Fanglin Wang, Shengyang Yu, Jie Yang.Robust and efficient fragments-based tracking using mean shift[J].EU-International Journal of Electronics and Communications, 2010,64(7):614-623.
[58]Shu-Xiao Li, Hong-Xing Chang, Cheng-Fei Zhu.Adaptive pyramid mean shift for global real-time visual tracking[J].Image and Vision Computing,2010,28(3):424-4.