基于视频图像处理的车辆检测与跟踪方法研究
|
摘要
视频检测技术是机器视觉研究领域中一个十分活跃的分支，而基于视频的运动目标检测与跟踪技术在国民经济和军事领域的许多方面有着广泛的应用，因此这方面的研究普遍受到各国科学家的关注。同时，随着基于计算机视觉技术的智能交通系统的重要性日益显著，在静止相机拍摄的图像序列中进行运动车辆检测与跟踪成为研究的重要领域，起到承上启下的关键作用。本文基于图像处理领域的相关理论和方法，针对运动目标检测、跟踪和识别中存在的关键问题，如运动目标分割、阴影去除、跟踪和遮挡进行了相关的研究，并将研究结果应用到实际的智能交通系统中，文章主要研究工作包括以下几个方面：
1阴影去除方法
传统方法往往在运动识别的时候再去掉运动阴影，然而在城市复杂交通环境下存在高大建筑物的投射阴影和路旁灯光的影响以及天气变化，这些场景中光照的变化都会影响运动检测算法的性能。而通过固有图像去除光照变化的影响后再进行运动检测，将有助于实现鲁棒的视频监控。因此，本文基于固有图像提取的思路，提出将阴影的消除放在预处理阶段的方法。该方法利用色度比作为衡量彩色不变性的特征，首先在每个颜色通道进行高斯平滑去除噪声，然后将几何平均色度映射到对数色度比空间，在特征空间中进行投影得出一系列灰度图像，再通过计算投影数据的熵确定出光照无关角，进而得出去除阴影的固有图像，该图像只反映物理材料反射率的变化而与光照变化无关。最后通过非线性动态范围调整增强亮度和对比度，使结果更符合人类视觉，有利于进一步的检测和跟踪。仿真实验表明，本文提出的方法在城市交通环境下，能够有效的去除车辆自身运动阴影和周围建筑投射的阴影。
2前景提取方法
运动目标检测是智能交通监控中的重要环节。本文首先从稀疏背景建模的思想出发，对基于边缘检测的运动前景提取方法进行仿真实验。采用边缘作为图像的特征进行前景提取的方法具有高效、性能稳健的优点，这是因为边缘信息在昏暗的环境下仍然能够检测到，即使在夜间也可以使用，并且图像边缘不容易受光线变化的影响。然后我们将对数色度比空间投影获得的固有灰度图像进行提取前景的实验，发现传统的方法并不适用，因此提出了频域前景提取方法，通过三级平稳小波变换将图像中低频的车辆区域提取出来，然后进行形态学后处理。仿真实验结果表明，该方法能够有效提取图像中静止和运动的车辆和行人，为进一步的跟踪和分类识别提供有用的数据。
3运动跟踪与遮挡处理
计算机视觉中，三维空间向二维平面的投影成像不可避免的会带来遮挡问题，在平面上由于丢失了深度信息，使得遮挡问题的解决成为非适定问题，存在着歧义，而视知觉组合(Perceptual grouping)理论基于大量的心理学实验提供了划分遮挡区域的判别规则。本文首先根据车辆的刚体运动特性，利用运动区域的几何特征建立自动的跟踪。相对于点来说，区域携带了形状和尺寸等更多的信息，更能提供运动跟踪的一致性。在运动区域匹配失败时判断是否发生了遮挡，进一步的遮挡处理提取了车辆的颜色和轮廓特征，为了将相似性和闭合性规则进行数学上的描述，用像素点在CIE-Lab颜色空间的色差的欧式距离定义了颜色相似程度矩阵，然后用空间位置和轮廓信息共同衡量像素点之间的差异，在标准化切割(Normalized Cut)准则下将发生遮挡的区域分割开。
The video detection technology is a very active branch in the research field ofmachine vision. The moving target detection and tracking has a wide range ofapplications in many aspects of national economic and military fields, and scientistsfrom various countries are of great concern to the research in this area.Meanwhile,with the importance of intelligent transportation systems based oncomputer vision technology increasingly significant, the moving vehicle detectionand tracking in the stationary camera image sequence has become an importantresearch area, and played a key connecting role. This paper studys on some key issuesin the moving target detection, tracking and recognition such as moving targetsegmentation, shadow removal, tracking and occlusion based on the theories andmethods of image processing, and applys the research results into practice intelligenttransportation systems. The main research work including the following aspects:
1. Shadow elimination method
Traditional methods tend to remove the moving shadows in motion recognition,however, the cast shadows of tall buildings and on-street light as well as changes inthe weather exist in the complex urban traffic environment and the light conditionchange in these scenes will affect the motion detection algorithm properties.Removing illumination changes with the intrinsic image before the motion detectionwill help to achieve robust video surveillance. Therefore, we proposed the shadowelimination method in the pre-processing stage based on the idea of extractingintrinsic image. The method uses the chromaticity characteristics as a measure ofcolor invariance. Firstly, in each color channel, the Gaussian smoothing is used toremove noise, then the geometric mean chromaticity mapping to the logarithmchromaticity ratio space,and we have a series of grayscale images in the feature space by projection. By computing the entropy of the projection data to determine theillumination invariant angle, then come to the natural images with shadow removed,and the images only reflect the physical material changes in the reflectivity and havenothing to do with illumination changes. The final adjustment by the non-lineardynamic range is to enhance the brightness and contrast to make the results morecomfortable with human vision, and conducive to the further detecting andtracking.Simulation results show that the proposed method can effectively remove thevehicle moving shadow and cast shadows by the surrounding buildings in urbantraffic environment.
2. Foreground extraction method
Moving object detection is an important part of the Intelligent Traffic MonitoringSystem,and there has been a lot of research in this regard. We first start from thethinking of the sparse background modeling to reduce storage space and computingtime of the background modeling, and make simulation of the moving foregroundextraction method based on edge detection. Using the edge as the characteristics ofthe image foreground extraction method has advantages in efficient, robustperformance. This is because the edge information is still able to be detected in a darkenvironment, even at night it can also be used, and the image edge is less susceptibleto changes in light impact.Then we found that traditional methods can not be appliedto the intrinsic image obtained from the logarithm chromaticity ratio feature space, sowe propose a frequency domain extraction method using three stationary wavelettransform image to extract vehicle area which is in the low-frequency, and thenmorphological post-processing is applied. The simulation results show that thismethod can effectively extract the stationary and moving vehicles and pedestrians,and provide useful data for further tracking and classification.
3. Motion tracking with occlusion handling
In the computer vision when three-dimensional space projection totwo-dimensional imaging will inevitably bring occlusion, and due to the loss of depthinformation making the solve of occlusion on a flat surface to an incorrectly posedambiguity problem. The perceptual grouping theory provide us discriminant rules todivide block regions based on a large number of psychology experiments.Firstly,according to the rigid body motion characteristics of the vehicle, we set up automatictracking with the geometric characteristics of the movement region.The region feature,relative to the point feature, carrys more information such as the shape and size, etc.and provides the consistency of motion tracking. When the motion region fails tomatch block because of occlusion, we extract the color and contour of the vehiclecharacteristics, and in order to make the mathematical description of similarity andclosed rules we use Euclidean distance of pixels in CIE-Lab color space to define thedegree of color similarity matrix, and then measure the difference between the pixelswith spatial position and profile information. Finally, the block area is separated in theguidelines of the Normalized Cut.
1阴影去除方法
传统方法往往在运动识别的时候再去掉运动阴影，然而在城市复杂交通环境下存在高大建筑物的投射阴影和路旁灯光的影响以及天气变化，这些场景中光照的变化都会影响运动检测算法的性能。而通过固有图像去除光照变化的影响后再进行运动检测，将有助于实现鲁棒的视频监控。因此，本文基于固有图像提取的思路，提出将阴影的消除放在预处理阶段的方法。该方法利用色度比作为衡量彩色不变性的特征，首先在每个颜色通道进行高斯平滑去除噪声，然后将几何平均色度映射到对数色度比空间，在特征空间中进行投影得出一系列灰度图像，再通过计算投影数据的熵确定出光照无关角，进而得出去除阴影的固有图像，该图像只反映物理材料反射率的变化而与光照变化无关。最后通过非线性动态范围调整增强亮度和对比度，使结果更符合人类视觉，有利于进一步的检测和跟踪。仿真实验表明，本文提出的方法在城市交通环境下，能够有效的去除车辆自身运动阴影和周围建筑投射的阴影。
2前景提取方法
运动目标检测是智能交通监控中的重要环节。本文首先从稀疏背景建模的思想出发，对基于边缘检测的运动前景提取方法进行仿真实验。采用边缘作为图像的特征进行前景提取的方法具有高效、性能稳健的优点，这是因为边缘信息在昏暗的环境下仍然能够检测到，即使在夜间也可以使用，并且图像边缘不容易受光线变化的影响。然后我们将对数色度比空间投影获得的固有灰度图像进行提取前景的实验，发现传统的方法并不适用，因此提出了频域前景提取方法，通过三级平稳小波变换将图像中低频的车辆区域提取出来，然后进行形态学后处理。仿真实验结果表明，该方法能够有效提取图像中静止和运动的车辆和行人，为进一步的跟踪和分类识别提供有用的数据。
3运动跟踪与遮挡处理
计算机视觉中，三维空间向二维平面的投影成像不可避免的会带来遮挡问题，在平面上由于丢失了深度信息，使得遮挡问题的解决成为非适定问题，存在着歧义，而视知觉组合(Perceptual grouping)理论基于大量的心理学实验提供了划分遮挡区域的判别规则。本文首先根据车辆的刚体运动特性，利用运动区域的几何特征建立自动的跟踪。相对于点来说，区域携带了形状和尺寸等更多的信息，更能提供运动跟踪的一致性。在运动区域匹配失败时判断是否发生了遮挡，进一步的遮挡处理提取了车辆的颜色和轮廓特征，为了将相似性和闭合性规则进行数学上的描述，用像素点在CIE-Lab颜色空间的色差的欧式距离定义了颜色相似程度矩阵，然后用空间位置和轮廓信息共同衡量像素点之间的差异，在标准化切割(Normalized Cut)准则下将发生遮挡的区域分割开。
The video detection technology is a very active branch in the research field ofmachine vision. The moving target detection and tracking has a wide range ofapplications in many aspects of national economic and military fields, and scientistsfrom various countries are of great concern to the research in this area.Meanwhile,with the importance of intelligent transportation systems based oncomputer vision technology increasingly significant, the moving vehicle detectionand tracking in the stationary camera image sequence has become an importantresearch area, and played a key connecting role. This paper studys on some key issuesin the moving target detection, tracking and recognition such as moving targetsegmentation, shadow removal, tracking and occlusion based on the theories andmethods of image processing, and applys the research results into practice intelligenttransportation systems. The main research work including the following aspects:
1. Shadow elimination method
Traditional methods tend to remove the moving shadows in motion recognition,however, the cast shadows of tall buildings and on-street light as well as changes inthe weather exist in the complex urban traffic environment and the light conditionchange in these scenes will affect the motion detection algorithm properties.Removing illumination changes with the intrinsic image before the motion detectionwill help to achieve robust video surveillance. Therefore, we proposed the shadowelimination method in the pre-processing stage based on the idea of extractingintrinsic image. The method uses the chromaticity characteristics as a measure ofcolor invariance. Firstly, in each color channel, the Gaussian smoothing is used toremove noise, then the geometric mean chromaticity mapping to the logarithmchromaticity ratio space,and we have a series of grayscale images in the feature space by projection. By computing the entropy of the projection data to determine theillumination invariant angle, then come to the natural images with shadow removed,and the images only reflect the physical material changes in the reflectivity and havenothing to do with illumination changes. The final adjustment by the non-lineardynamic range is to enhance the brightness and contrast to make the results morecomfortable with human vision, and conducive to the further detecting andtracking.Simulation results show that the proposed method can effectively remove thevehicle moving shadow and cast shadows by the surrounding buildings in urbantraffic environment.
2. Foreground extraction method
Moving object detection is an important part of the Intelligent Traffic MonitoringSystem,and there has been a lot of research in this regard. We first start from thethinking of the sparse background modeling to reduce storage space and computingtime of the background modeling, and make simulation of the moving foregroundextraction method based on edge detection. Using the edge as the characteristics ofthe image foreground extraction method has advantages in efficient, robustperformance. This is because the edge information is still able to be detected in a darkenvironment, even at night it can also be used, and the image edge is less susceptibleto changes in light impact.Then we found that traditional methods can not be appliedto the intrinsic image obtained from the logarithm chromaticity ratio feature space, sowe propose a frequency domain extraction method using three stationary wavelettransform image to extract vehicle area which is in the low-frequency, and thenmorphological post-processing is applied. The simulation results show that thismethod can effectively extract the stationary and moving vehicles and pedestrians,and provide useful data for further tracking and classification.
3. Motion tracking with occlusion handling
In the computer vision when three-dimensional space projection totwo-dimensional imaging will inevitably bring occlusion, and due to the loss of depthinformation making the solve of occlusion on a flat surface to an incorrectly posedambiguity problem. The perceptual grouping theory provide us discriminant rules todivide block regions based on a large number of psychology experiments.Firstly,according to the rigid body motion characteristics of the vehicle, we set up automatictracking with the geometric characteristics of the movement region.The region feature,relative to the point feature, carrys more information such as the shape and size, etc.and provides the consistency of motion tracking. When the motion region fails tomatch block because of occlusion, we extract the color and contour of the vehiclecharacteristics, and in order to make the mathematical description of similarity andclosed rules we use Euclidean distance of pixels in CIE-Lab color space to define thedegree of color similarity matrix, and then measure the difference between the pixelswith spatial position and profile information. Finally, the block area is separated in theguidelines of the Normalized Cut.
引文
[1] Massimo Bertozzi, Alberto Broggi, Alessandra Fascioli. Vision-based intelligent vehicles:state of the art and perspective. Robotics and Autonomous System,1998,17(5):56~63
[2] AUTOSCOPE-2020Video Vehicle Detection System, Econolite Control Products, Inc.
[3]朱志刚,徐光佑.VISATARAM:全天候自动交通检测视觉系统.北京智能交通系统发展趋势国际学术研讨会论文集,1997,97~101
[4] P. Shi, E. G. Jones, and Q. Zhu. Median model for background subtraction in intelligenttransportation system. Imaging Processing: Algorithms and Systems III,2004,vol.5298:168~176
[5] D. Farin, P. H. N. de With, and W. Effelsberg. Robust background estimation for complexvideo sequences.IEEE International Conference on Image Processing,2003,vol.1,145~148
[6] S. S. Cheung and C. Kamath.Robust techniques for background subtraction in urban trafficvideo. Visual Communications and Image Processing,2004,vol.5308, no.2,881~892
[7] Y. Sun and B. Yuan.Hierarchical GMM to handle sharp changes in moving object detection.Electronics Letters,2004,vol.40,801~802
[8] Reilly Vladimir,Idrees Haroon,Shah Mubarak. Detection and tracking of large number oftargets in wide area surveillance.11th European Conference on Computer Vision,2010,3:186~199
[9]张辉,王强,徐光祐,朱志刚.运动目标的快速检测、跟踪和判别.清华大学学报(自然科学版),2002,42(10):1401~1404
[10] L W. Tsai, J W. Hsieh, and K C. Fan.Vehicle detection using normalized color and edgemap. International Conference on Image Processing,2005,vol.2,598~601
[11] O. Javed, S. Ali, and M. Shah.Online detection and classification of moving objects usingprogressively improving detectors. IEEE Conference on Computer Vision and Pattern Recognition,2005,vol.1,696~701
[12] A. Yoneyama, C. H. Yeh, and C. C. J. Kuo.Robust vehicle detection for highwaysurveillance via rear-view monitoring. Applications of Digital Image Processing XXVI,2003,vol.5203,21~32
[13] F. E. Alsaqre and B. Z. Yuan.Moving object segmentation for video surveillance andconferencing applications. International Conference on Communication Technology,2003, vol.2,1856~1859
[14] S. Barotti, L. Lombardi, and P. Lombardi.Multi-module switching and fusion for robustvideo surveillance. International Conference on Image Analysis and Processing,2003,260~265
[15]纪筱鹏.智能交通系统中车辆视频检测、识别与跟踪方法的研究:[博士学位论文].中国海洋大学,2006
[16] C. Stauffer and W. E. L. Grimson.Learning patterns of activity using real-timetracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,vol.22,747~757
[17] C. Stauffer and W. E. L. Grimson.Adaptive background mixture models for real-timetracking.IEEE Conference on Computer Vision and Pattern Recognition,1999, vol.2,246~252
[18] Y. Sun and B. Yuan.Hierarchical GMM to handle sharp changes in moving objectdetection.Electronics Letters,2004,vol.40,801~802
[19] Q. Zang and R. Klette.Robust background subtraction and maintenance.InternationalConference on Pattern Recognition,2004,vol.2,90~93
[20] K T P. Pakorn and B. Richard.A real time adaptive visual surveillance system for trackinglow-resolution colour targets in dynamically changing scenes.Image and Vision Computing,2003,vol.21,913~929
[21] Richard P Wildes. A measure of motion salience for surveillance applications, ImageProcessing,1998,102~121
[22] Stringa E.Morphological change detection algorithms for surveillance applications. BritishMachine Vision Conference,2000,402~411
[23] Comport Andrew,Meill Maxime,Rives Patrick. An asymmetric real-time dense visuallocalisation and mapping system.2011,700~703
[24] Horprasert T, Harwood D, Davis L S. A statistical approach for real-time robust backgroundsubtraction and shadow detection. IEEE ICCV Frame-Rate Workshop,1999
[25] E. Salvador, A. Cavallaro, T. Ebrahimi, Shadow identification and classification usinginvariant color models, IEEE Signal Processing Society International Conference on Acoustics,Speech, and Signal Processing,2001,1~4
[26] P. Kumar, K. Sengupta, A. Lee etc. A comparative study of different color spaces forforeground and shadow detection for traffic monitoring system. IEEE International Conference onIntelligent Transportation System,2002,100~105
[27] Satadal Saha, Subhadip Basu, Mita Nasipuri, Dipak Kumar Basu. License plate localizationfrom vehicle images: an edge based multi-stage approach. International Journal of Recent Trendsin Engineering,2009,1(1):284~288
[28] Kaushik Deb, Heechul Lim, Suk-Ju Kang, Kang-Hyun Jo. An efcient method of vehiclelicense plate detection based on HSI color model and histogram. Lecture Notes in ComputerScience,2009,vol.5579:66~75
[29]戴青云,余英林.一种基于小波和形态学的车牌图像分割方法.中国图像图形学报，2000,5(5):411~415
[30] Jiyin Zhao,Ruirui Zheng, Min Li,Yin Li.License plate recognition based on geneticalgorithm. International Conference on Computer Science and SoftwareEngineering.2008,965~968
[31] Karungaru Stephen,Fukumi Minoru,Akamatsu Norio,Akashi Takuya.Detection andrecognition of vehicle license plates using template matching, genetic algorithms and neuralnetworks. International Journal of Innovative Computing, Information andControl,2009,5(7):1975~1985
[32]刘维一,盛益强,乔辉,方志良.特征点匹配法实现汽车牌照的快速识别.光电子.激光.2002,13(3):274~276
[33]葛宝臻,陈希明,张以漠.基于光电混合联合变换相关的汽车牌照识别方法的实验研究.光电子.激光,1999,6(10):248~251
[34]潘翔,叶修梓,张三元.基于小波的车牌汉字特征提取.中国图像图形学报,2003,8(10):1218~1222
[35] Lipton A.J, Fujiyoshi, H, Patil, R.S. Moving target classification and tracking fromreal-time video, IEEE Workshop on Applications of Computer Vision,1998,8~14
[36] Hou Tingbo,Wang Sen,Qin Hong.Vehicle matching and recognition under large variationsof pose and illumination. IEEE Conference on Computer Vision and PatternRecognition,2009,24~29
[37] Cutler R, Davis L. Robust real-time periodic motion detection, analysis, and applications.IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):781~796
[38] Selinger A,Wixson L. Classifying moving objects as rigid or non-rigid withoutcorrespondences. DAPRA Image Understanding Workshop,1998,1:341~358
[39]朱霞,朱继南,聂伟荣.基于形状统计量的地面运动车辆识别.弹道学报,2001,13(4):34~37
[40] Kanade, T., Collins, R, etc. Advances in cooperative multi-sensor video surveillance,DARPA Image Understanding Workshop,1998,3~24
[41] Xuguang Zhang,Honghai Liu,Xiaoli Li.Target tracking for mobile robot platforms viaobject matching and background anti matching. Robotics and Autonomous System,2010,58:1197~1206
[42] Roya Rad,Mansour Jamzad.Real-time classification and tracking of multiple vehicles inhighways.Pattern Recognition Letters,2005,26(10):1597~1607
[43] G.Iannizzotto,L.Vita.Real-time object tracking with models and affine transformations.Proceedings of International Conference on Image Processing. IEEE ComputerSociety,2000,316~318
[44] De Vylder Jonas,Aelterman Jan,Philips Wilfried.Robust active contour segmentation withan efficient global optimizer.13th International Conference on Advanced Concepts for IntelligentVision Systems.2011,195~206
[45] M.Kass,A.Witkin,D.Terzopoulos. Snakes:active contour models.International Journal ofComputer Vision,1988,1(3):163~169
[46]高琳,刘直芳,唐鹏.基于多信息综合的运动车辆跟踪方法,计算机工程与应用,2008,44(7):5~7
[47]何得平,朱光喜,赵广州,基于角特征和Mean-shift的车辆跟踪方法,计算机工程,2010,36(6):196~200
[48] B. Coifman, D. Beymer, P. McLauchlan, and J. Malik.A real-time computer vision systemfor vehicle tracking and traffic surveillance.Transportation Research Part C: EmergingTechnologies,1998,vol.6,271~288
[49]常发亮,马丽.遮挡情况下基于特征相关匹配的目标跟踪算法.中国图象图形学报,2006,11(6):877~882
[50]赵建伟,刘重庆.适用于遮挡问题的目标跟踪算法.计算机辅助设计与图形学学报,2003,15(9):1091~1095.
[51] N. Herodotou, K.N. Plataniotis, and A.N. Venetsanopoulos. A color segmentation schemefor object-based video coding. Proceedings of the IEEE Symposium on Advances in DigitalFiltering and Signal Processing,1998,25~29
[52] T. Horprasert, D. Harwood, and L.S. Davis. A statistical approach for real-time robustbackground subtraction and shadow detection. Proceedings of IEEE ICCV FRAME-RATEWorkshop,1999,1~19
[53] R.Cucchiara,C.Grana,M.Piccardi,A.Prati,and S.Sirotti. Improving shadow suppression inmoving object detection with HSV Color Information. Proceedings of IEEE Conference onIntelligent Transportation Systems,2001,334~339
[54] E.Salvador,A.Cavallaro,and T.Ebrahimi. Cast shadow segmentation using invariant colorfeatures. Computer Vision and Image Understanding,2004,vol.95,238~259
[55] S.Nadimi and B.Bhanu.Physical models for moving shadow and object detection in video.IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,vol.26,1079~1087
[56] A.Cavallaro,E.Salvador,and T.Ebrahimi. Shadow-aware object-based video processing.Vision,Image and Signal Processing,2005,152(4):398~406
[57] George S. K. Fung,Nelson H. C. Yung,Grantham K. H. Pang,Andrew H. S. Lai. Effectivemoving cast shadow detection for monocular color traffic image sequences. Optical Engineering,2002,41(6):1425~1440
[58] D.Xu,X.Li,Z.Liu,and Y.Yuan. Cast shadow detection in video segmentation. PatternRecognition Letters,2005,vol.26,91~99
[59] A.Leone,C.Distante,and F.Buccolieri. A shadow elimination approach in video-surveillancecontext. Pattern Recognition Letters,2006,27(5):345~355
[60] J.W.Hsieh,W.F.Hu,C.J.Chang,and Y S.Chen. Shadow elimination for effective movingobject detection by Gaussian shadow modeling. Image and Vision Computing,2003,21(6):505~516
[61] J.W.Hsieh,S.H.Yu,Y.S.Chen,and W.F.Hu. Automatic traffic surveillance system for vehicletracking and classification. IEEE Transactions on Intelligent Transportation Systems,2006,7(2):175~187
[62] A.Yoneyama,C.H.Yeh,and C.C.J.Kuo.Moving cast shadow elimination for robust vehicleextraction based on2D joint vehicle/shadow models. Proceedings of IEEE InternationalConference on Advanced Video and Signal Based Surveillance,2003,229~236
[63] I.Mikic,P.C.Cosman,G.T.Kogut,and M.M.Trivedi.Moving shadow and object detection intraffic scenes. Proceedings of International Conference on Pattern Recognition,2000,vol.1,321~324
[64] Y.Wang, T.Tan, and K F.Loe. A probabilistic method for foreground and shadowsegmentation. Proceedings of International Conference on Image Processing,2003,vol.3,937~940
[65] D.Toth,I.Stuke,A.Wagner,and T.Aach. Detection of moving shadows using mean shiftclustering and a significance test. Proceedings of International Conference on Pattern Recognition,2004,vol.4,260~263
[66] Stauder J,Mech R,Ostermann J. Detection of moving cast shadows for object segmentation.IEEE Transactior on Multimedia,1999,1(1):65~76
[67] Sohail Nadimi，Bir Bhanu.Moving shadow detection using a physics-based approach. The16th International Conference on Pattern Recognition,2002,701~704
[68] H.G.Barrow and J.M.Tenenbaum. Recovering intrinsic scene characteristics from images.Computer Vision System,1978,3~26
[69] M. F. Tappen, W. T. Freeman, and E. H. Adelson. Recovering intrinsic images from a singleimage. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(9):1459~1472
[70] Y.Weiss. Deriving intrinsic images from image sequences. Proceedings of InternationalConference on Computer Vision,2001,68~75
[71] G.D.Finlayson, S.D.Hordley, C.Lu and M.S.Drew. Removing shadows from images.Proceedings of the7th European Conference on Computer Vision,vol IV,2002,823~836
[72] G.D.Finlayson, M.S.Drew, and C.Lu. Intrinsic images by entropy minimization.In:Proceedings of European Conference on Computer Vision,2004. Vol III:582~595
[73] G.D.Finlayson, M.S.Drew, and C.Lu.On the removal of shadows from images.IEEETransactions on pattern analysis and machine intelligence,2006,28(1):59~68
[74] G.D.Finlayson, M.S.Drew, and C.Lu. Entropy minimization for shadow removal.International hournal of computer vision,2009,85(1),35~57
[75] D.W. Scott. Multivariate density estimation: theory, practice and visualization. Wiley andKegan Paul,1992
[76] Kameda Yoshinari and Minoh michihiko. A human motion estimation method using3-successive video frames. Proceedings of International Conference on Virtual Systems andMultimedia,1996,135~140
[77] Hantanglu I,Hatwood D,Davis L W. Real-time surveillance of people and their activities.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,22(8):809~830
[78] McKenna S et al.Tracking groups of people computer vision and image understanding.2000,80(1):42~56
[79] Bulas J, Cruz, Ali A T, Dagless E L. A temporal smoothing technique for real-time motiondetection. Proceedings of ECCV,1994:379~386
[80] Chaoqun Huang, Guowu Yuan, Dan Xu. Multi-target detection and tracking by gaussianmixture model and blob tracking analysis.Journal of Information and Computational Science.2009,6(6):2403~2410
[81] B. P. L. Lo and S. A. Velastin.Automatic congestion detection system for undergroundplatforms.Intelligent Multimedia, Video and Speech Processing,2001,158~161
[82] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati. Detecting moving objects,ghosts, andshadows in video streams. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,vol.25,1337~1342
[83] D.Farin,P.H.N.de With,and W.Effelsberg.Robust background estimation for complex videosequences.Proceedings of IEEE International Conference on Image Processing,2003,vol.1,145~148
[84]刘勃,魏铭旭,周荷琴.一种基于区间分布的自适应背景提取算法.模式识别与人工智能,2005,18(3):316~321
[85] Suzuki H.,Matsumoto T.and ChuaL.O.A CNN hand written haracter recognizer.Int. JonCircuit Theory and Applications,1992, vol.20,601~612
[86] L. Koskinen, M.Laiho, A. Paasio and K.Halonen.MPEG-4based modifications for an CNNsegmentation chip.The7th Intenrational Workshop on CNN and Their Applications,2002,71~77
[87] P.Arena, A.Basile,L.Fortuna,M.E.Yalcin and J.Vandewalle. Watermarking on CNN-UM forimage and video authentication.The7th Intenrational Workshop on CNN and Their Appli-cations,2002,78~83
[88] Chug,L. O. and Y ang,L. Cellular neural networks:theory. IEEE Transactions on CircuitsSystems,1988,35(10):1257~1272
[89] Chua, L. O., Roska, T., Kozek, T., and Zarandy, A. The CNN paradigm.IEEE Transactionson Circuits and Systems-I:Fundamental Theory and Applications,1993,4(3):147~156
[90] Tejen Su, Cianpin Wei.Image noise cancellation using linear matrix in equality and cellularneural network. Optics Communications,2008,5706~5712
[91] Slark L K,Yu C.Denoising by optimal fuzzy thresholding in wavelet domain. ElectronicsLetters,2000,36(6):581~582
[92] Reilly Vladimir,Solmaz Berkan,Shah Mubarak.Geometric constraints for human detectionin aerial imagery.11th European Conference on Computer Vision,2010,6:252~265
[93]何玉钧，王梓蒴，尹成群，李永倩.利用平稳小波变换处理FBG传感信号.红外与激光工程,2011,40(11):2295~2300
[94] R.Cucchiara,M.Piccaidi,and P.Mello.Image analysis and rule-based reasoning for a trafficmonitoring system. IEEE Transactions on Intelligent Transportation Systems,2000,vol.1,119~130
[95] C.Gentile,O.Camps,and M.Sznaier. Segmentation for robust tracking in the presence ofsevere occlusion. IEEE Transactions on Image Processing,2004,vol.13,166~178
[96] J.Kang,I.Cohen,G.Medioni,and C.Yuan. Detection and tracking of moving objects from amoving platform in presence of strong parallax. Proceedings of IEEE International Conference onComputer Vision,2005,vol.1,10~17
[97]郁梅,王圣男,蒋刚毅.复杂交通场景中的车辆检测与跟踪新方法.光电工程.2005,32(2):67~70
[98]孙季丰,王成清.基于特征点光流和卡尔曼滤波的运动车辆跟踪.华南理工大学学报(自然科学版),2005,33(10):19~23
[99] N.K.Kanhere,S.J.Pundlik,and S.T.Birchfield. Vehicle segmentation and tracking from alow-angle off-axis camera.Proceedings of IEEE Conference on Computer Vision and PatternRecognition,2005,vol.2,1152~1157
[100] Har Iharakr Ishnan K,Schonfeld D. Fast object tracking using adaptive block matching.IEEE Transactions on Multimedia,2005,7(5):853~859
[101]张伟.基于视觉的运动车辆检测与跟踪:[博士学位论文].上海交通大学图像通信与信息处理研究所,2007
[102] C.C.C.Pang,W.W.L.Lam,and N.H.C.Yung.A novel method for resolving vehicle occlusionin a monocular traffic-image sequence.IEEE Transactions on Intelligent Transportation Systems,2004,vol.5,129~141
[103] X.F.Song and R.Nevatia.A model-based vehicle segmentation method for tracking.Proceedings of IEEE International Conference on Computer Vision,2005,vol.2,1124~1131
[104] J.G..Lou;T.N.Tan,W.M.Hu,H.Yang,and S.J.Maybank.3-D model-based vehicle tracking.IEEE Transactions on Image Processing,2005,vol.14,1561~1569
[105] Veeraraghavan,O.Masoud,and N.P.Papanikolopoulos.Computer vision algorithms forintersection monitoring. IEEE Transactions on Intelligent Transportation Systems,2003,vol.4,78~89
[106] S.Kamijo, Y.Matsushita, K.Ikeuchi, and M.Sakauchi. Traffic monitoring and accidentdetection at intersections. IEEE Transactions on Intelligent Transportation Systems,2000,vol.1,108~118
[107] C.L.Huang and W.C.Liao.A vision-based vehicle identification system. Proceedings ofInternational Conference on Pattern Recognition,2004,vol.4,364~367
[108]董鸿燕,沈振康,罗军,张志龙,倪为平.感知编组综述.计算机工程与应用,2007,43(14):9~13
[109] Wertheimer M．Untersuchungen zur lehre von der Gestalt ii:Psychologisehen Forschung，1923,4:301~350
[110] Koffka K. Principles of gestalt psychology.New York:Harcourt,1935
[111] Kohler W. Gestalt psychology.New York:Liveright,1929
[112] David G. Lowe. Perceptual organization and visual recognition. Kluwer AcademicPublishers, Boston, MA,1985
[113] David G. Lowe. Three-dimensional object recognition from single two-dimensional images.Artificial Intelligence,1987,31(3):355~395
[114] W. Eric L. Grimson. The combinatorics of heuristic search termination for objectrecognition in cluttered environments. IEEE Transactions on Pattern Analysis and MachineIntelligence,1991,13(9):920~935
[115] Zlatoff Nicolas,Tellez Bruno,Baskurt Atilla.Combining local belief from low-levelprimitives for perceptual grouping. Pattern Recognition,2008,1215~1229
[116] Xiao, Y.,Tien, D., Jia X.P. Region based perceptual grouping for road extraction from highresolution images.6th International Conference on Information Technology and Applications,2009,67~70
[117] Shimon Ullman and Amnon Sha’ashua. Structural saliency: the detection of globally salientstructures using a locally connected network. Technical Report A.I. Memo No.1061, MIT,Artificial Intelligence Laboratory,1988
[118] Rakesh Mohan and Ramakant Nevatia. Segmentation and description based on perceptualorganization. IEEE Conference on Computer Vision and Pattern Recognition,1989,333~341
[119] Rakesh Mohan and Ramakant Nevatia. Perceptual organization for scene segmentation anddescription. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(6):616~635
[120]刘俊义,王润生.基于骨架层次分解的目标的图表示.计算机学报,2001,24(6):633~637
[121] Sudeep Sarkar and Kim L. Boyer. Automated design of bayesian perceptual inferencenetworks. Technical Report SAMPL-93-03, SAMPL-Lab, Department of ElectricalEngineering,OSU,1993
[122] Sudeep Sarkar and Kim L. Boyer. Integration inference and management of spatialinformation using bayesian networks: perceptual organization. IEEE Transactions on PatternAnalysis and Machine Intelligence,1993,15(3):256~274
[123] Sudeep Sarkar and Kim L. Boyer. Using perceptual inference networks to manage visionprocesses. Computer Vision, Graphics, and Image Processing: Image Understanding,1995,62(1):27~46
[124] Gideon Guy and Gerard Medioni. Inferring global perceptual contours from local features.International Journal of Computer Vision,1996,20(1/2):113~133
[125] Sudeep Sarkar and Kim L. Boyer. Quantitative measures of change based on featureorganization: eigenvalues and eigenvectors. IEEE Conference on Computer Vision and PatternRecognition,1996,478~483
[126] Charles T.Zahn.Graph-theoretical methods for detecting and describing gestalt clusters.IEEE Transactions on Computers,1971,20(1):68~86
[127] P. Perona and W. Freeman. A factorization approach to grouping. In European Conferenceon Computer Vision,1998,655~670
[128] Arnon Amir and Michael Lindenbaum. A generic grouping algorithm and its quantitativeanalysis. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(3):168~186
[129] Bernd Fischer and Joachim M. Buhmann. Path-based clustering for grouping of smoothcurves and texture segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(4):513~518
[130] Xiaofeng Ren and Jitendra Malik. A probabilistic multi-scale model for contour completionbased on image statistics. European Conference on Computer Vision,2002,312~327
[131] James Elder and Steven Zucker. The effect of contour closure on the rapid discrimination oftwo-dimensional shapes. Vision Research,1993,(33):981~991
[132] James H. Elder and Steven W. Zucker. A measure of closure. Technical Report93-2,McGillResearch Centre for Intelligent Machines,1994
[133] Song Wang, Toshiro Kubota, and Jeffrey Mark Siskind. Salient boundary detection usingratio contour. Neural Information Processing Systems Conference,2003,1571~1578
[134] Williams L R, Jacobs D W. Stochastic completion fields: a neural model of illusory contourshape and salience. Neural Computation,1997,9(4):837~858
[135] Mahamud S, Williams L R, Thornber K K, Xu K. Segmentaion of multiple salient closedcontour from real images. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(4):433~444
[136] David W. Jacobs. Robust and efficient detection of salient convex groups. IEEETransactions on Pattern Analysis and Machine Intelligence,1996,18(1):23~37
[137] Luo Xingzhi, Bhandarkar, Suchendra M.Tracking of multiple objects using optical flowbased multiscale elastic matching.9th European Conference on Computer Vision,2006,203~217
[138] Kalman, R. E. A new approach to linear filtering and prediction problems. Transactions ofthe ASME-Journal of Basic Engineering.1960,vol.82,35~45
[139] Kalman, R. E., Bucy R. S.New results in linear filtering and prediction theory, Transactionsof the ASME-Journal of Basic Engineering,1961,vol.83,95~107
[140] Omar Javed and Mubarak Shah.Tracking and object classification for automatedsurveillance, European Conference on Computer Vision,2002,343~357
[141] Kanizsa G. Organization in vision.New York:Praeger,1979
[142]荆其诚，焦书兰，喻柏林等.色度学.北京:科学出版社,1979
[143] Wu Z,Leahy R. An optimal grapht heoretic approach to data clustering:theory and itsapplication to image segmentation.IEEE Transactions on Pattern Analysis and MachineIntelligence,1993,15(11):1101~1113
[144] Shi J,Malik J. Normalized cuts and image segmentation. IEEE Transactions on PatternAnalysis and Machine Intelligence,2000,22(8):888~905
[145] Hagen L, Kahng A B. New spectral methods for ratio cut partitioning and clustering. IEEETransactions on Computer Aided Design,1992,11(9):1074~1085
[146] Sarkar S, Soundararajan P. Supervised learning of large perceptual organization: graphspectral partitioning and learning automata. IEEE Transaction on Pattern Analysis and MachineIntelligence,2000,22(5):504~525
[147] Ding C,He X,Zha H,et al. Spectral Min-Max cut for graph partitioning and data clustering.IEEE Conference on Data Mining,2001,107~114
[148] Meila M, Xu L. Multiway cuts and spectral clustering. U.Washington Technical Reports,2003
[149] Xu Linli,Li Wenye,Schuurmans Dale.Fast normalized cut with linear constraints. IEEEComputer Society Conference on Computer Vision and Pattern Recognition Workshops.2009,2866~2873
[150] Mukherjee Lopamudra,Singh Vikas,Peng Jiming,Hinrichs Chris.Learning kernels forvariants of normalized cuts: Convex relaxations and applications, IEEE Computer SocietyConference on Computer Vision and Pattern Recognition.2010,3145~3152
[2] AUTOSCOPE-2020Video Vehicle Detection System, Econolite Control Products, Inc.
[3]朱志刚,徐光佑.VISATARAM:全天候自动交通检测视觉系统.北京智能交通系统发展趋势国际学术研讨会论文集,1997,97~101
[4] P. Shi, E. G. Jones, and Q. Zhu. Median model for background subtraction in intelligenttransportation system. Imaging Processing: Algorithms and Systems III,2004,vol.5298:168~176
[5] D. Farin, P. H. N. de With, and W. Effelsberg. Robust background estimation for complexvideo sequences.IEEE International Conference on Image Processing,2003,vol.1,145~148
[6] S. S. Cheung and C. Kamath.Robust techniques for background subtraction in urban trafficvideo. Visual Communications and Image Processing,2004,vol.5308, no.2,881~892
[7] Y. Sun and B. Yuan.Hierarchical GMM to handle sharp changes in moving object detection.Electronics Letters,2004,vol.40,801~802
[8] Reilly Vladimir,Idrees Haroon,Shah Mubarak. Detection and tracking of large number oftargets in wide area surveillance.11th European Conference on Computer Vision,2010,3:186~199
[9]张辉,王强,徐光祐,朱志刚.运动目标的快速检测、跟踪和判别.清华大学学报(自然科学版),2002,42(10):1401~1404
[10] L W. Tsai, J W. Hsieh, and K C. Fan.Vehicle detection using normalized color and edgemap. International Conference on Image Processing,2005,vol.2,598~601
[11] O. Javed, S. Ali, and M. Shah.Online detection and classification of moving objects usingprogressively improving detectors. IEEE Conference on Computer Vision and Pattern Recognition,2005,vol.1,696~701
[12] A. Yoneyama, C. H. Yeh, and C. C. J. Kuo.Robust vehicle detection for highwaysurveillance via rear-view monitoring. Applications of Digital Image Processing XXVI,2003,vol.5203,21~32
[13] F. E. Alsaqre and B. Z. Yuan.Moving object segmentation for video surveillance andconferencing applications. International Conference on Communication Technology,2003, vol.2,1856~1859
[14] S. Barotti, L. Lombardi, and P. Lombardi.Multi-module switching and fusion for robustvideo surveillance. International Conference on Image Analysis and Processing,2003,260~265
[15]纪筱鹏.智能交通系统中车辆视频检测、识别与跟踪方法的研究:[博士学位论文].中国海洋大学,2006
[16] C. Stauffer and W. E. L. Grimson.Learning patterns of activity using real-timetracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,vol.22,747~757
[17] C. Stauffer and W. E. L. Grimson.Adaptive background mixture models for real-timetracking.IEEE Conference on Computer Vision and Pattern Recognition,1999, vol.2,246~252
[18] Y. Sun and B. Yuan.Hierarchical GMM to handle sharp changes in moving objectdetection.Electronics Letters,2004,vol.40,801~802
[19] Q. Zang and R. Klette.Robust background subtraction and maintenance.InternationalConference on Pattern Recognition,2004,vol.2,90~93
[20] K T P. Pakorn and B. Richard.A real time adaptive visual surveillance system for trackinglow-resolution colour targets in dynamically changing scenes.Image and Vision Computing,2003,vol.21,913~929
[21] Richard P Wildes. A measure of motion salience for surveillance applications, ImageProcessing,1998,102~121
[22] Stringa E.Morphological change detection algorithms for surveillance applications. BritishMachine Vision Conference,2000,402~411
[23] Comport Andrew,Meill Maxime,Rives Patrick. An asymmetric real-time dense visuallocalisation and mapping system.2011,700~703
[24] Horprasert T, Harwood D, Davis L S. A statistical approach for real-time robust backgroundsubtraction and shadow detection. IEEE ICCV Frame-Rate Workshop,1999
[25] E. Salvador, A. Cavallaro, T. Ebrahimi, Shadow identification and classification usinginvariant color models, IEEE Signal Processing Society International Conference on Acoustics,Speech, and Signal Processing,2001,1~4
[26] P. Kumar, K. Sengupta, A. Lee etc. A comparative study of different color spaces forforeground and shadow detection for traffic monitoring system. IEEE International Conference onIntelligent Transportation System,2002,100~105
[27] Satadal Saha, Subhadip Basu, Mita Nasipuri, Dipak Kumar Basu. License plate localizationfrom vehicle images: an edge based multi-stage approach. International Journal of Recent Trendsin Engineering,2009,1(1):284~288
[28] Kaushik Deb, Heechul Lim, Suk-Ju Kang, Kang-Hyun Jo. An efcient method of vehiclelicense plate detection based on HSI color model and histogram. Lecture Notes in ComputerScience,2009,vol.5579:66~75
[29]戴青云,余英林.一种基于小波和形态学的车牌图像分割方法.中国图像图形学报，2000,5(5):411~415
[30] Jiyin Zhao,Ruirui Zheng, Min Li,Yin Li.License plate recognition based on geneticalgorithm. International Conference on Computer Science and SoftwareEngineering.2008,965~968
[31] Karungaru Stephen,Fukumi Minoru,Akamatsu Norio,Akashi Takuya.Detection andrecognition of vehicle license plates using template matching, genetic algorithms and neuralnetworks. International Journal of Innovative Computing, Information andControl,2009,5(7):1975~1985
[32]刘维一,盛益强,乔辉,方志良.特征点匹配法实现汽车牌照的快速识别.光电子.激光.2002,13(3):274~276
[33]葛宝臻,陈希明,张以漠.基于光电混合联合变换相关的汽车牌照识别方法的实验研究.光电子.激光,1999,6(10):248~251
[34]潘翔,叶修梓,张三元.基于小波的车牌汉字特征提取.中国图像图形学报,2003,8(10):1218~1222
[35] Lipton A.J, Fujiyoshi, H, Patil, R.S. Moving target classification and tracking fromreal-time video, IEEE Workshop on Applications of Computer Vision,1998,8~14
[36] Hou Tingbo,Wang Sen,Qin Hong.Vehicle matching and recognition under large variationsof pose and illumination. IEEE Conference on Computer Vision and PatternRecognition,2009,24~29
[37] Cutler R, Davis L. Robust real-time periodic motion detection, analysis, and applications.IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):781~796
[38] Selinger A,Wixson L. Classifying moving objects as rigid or non-rigid withoutcorrespondences. DAPRA Image Understanding Workshop,1998,1:341~358
[39]朱霞,朱继南,聂伟荣.基于形状统计量的地面运动车辆识别.弹道学报,2001,13(4):34~37
[40] Kanade, T., Collins, R, etc. Advances in cooperative multi-sensor video surveillance,DARPA Image Understanding Workshop,1998,3~24
[41] Xuguang Zhang,Honghai Liu,Xiaoli Li.Target tracking for mobile robot platforms viaobject matching and background anti matching. Robotics and Autonomous System,2010,58:1197~1206
[42] Roya Rad,Mansour Jamzad.Real-time classification and tracking of multiple vehicles inhighways.Pattern Recognition Letters,2005,26(10):1597~1607
[43] G.Iannizzotto,L.Vita.Real-time object tracking with models and affine transformations.Proceedings of International Conference on Image Processing. IEEE ComputerSociety,2000,316~318
[44] De Vylder Jonas,Aelterman Jan,Philips Wilfried.Robust active contour segmentation withan efficient global optimizer.13th International Conference on Advanced Concepts for IntelligentVision Systems.2011,195~206
[45] M.Kass,A.Witkin,D.Terzopoulos. Snakes:active contour models.International Journal ofComputer Vision,1988,1(3):163~169
[46]高琳,刘直芳,唐鹏.基于多信息综合的运动车辆跟踪方法,计算机工程与应用,2008,44(7):5~7
[47]何得平,朱光喜,赵广州,基于角特征和Mean-shift的车辆跟踪方法,计算机工程,2010,36(6):196~200
[48] B. Coifman, D. Beymer, P. McLauchlan, and J. Malik.A real-time computer vision systemfor vehicle tracking and traffic surveillance.Transportation Research Part C: EmergingTechnologies,1998,vol.6,271~288
[49]常发亮,马丽.遮挡情况下基于特征相关匹配的目标跟踪算法.中国图象图形学报,2006,11(6):877~882
[50]赵建伟,刘重庆.适用于遮挡问题的目标跟踪算法.计算机辅助设计与图形学学报,2003,15(9):1091~1095.
[51] N. Herodotou, K.N. Plataniotis, and A.N. Venetsanopoulos. A color segmentation schemefor object-based video coding. Proceedings of the IEEE Symposium on Advances in DigitalFiltering and Signal Processing,1998,25~29
[52] T. Horprasert, D. Harwood, and L.S. Davis. A statistical approach for real-time robustbackground subtraction and shadow detection. Proceedings of IEEE ICCV FRAME-RATEWorkshop,1999,1~19
[53] R.Cucchiara,C.Grana,M.Piccardi,A.Prati,and S.Sirotti. Improving shadow suppression inmoving object detection with HSV Color Information. Proceedings of IEEE Conference onIntelligent Transportation Systems,2001,334~339
[54] E.Salvador,A.Cavallaro,and T.Ebrahimi. Cast shadow segmentation using invariant colorfeatures. Computer Vision and Image Understanding,2004,vol.95,238~259
[55] S.Nadimi and B.Bhanu.Physical models for moving shadow and object detection in video.IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,vol.26,1079~1087
[56] A.Cavallaro,E.Salvador,and T.Ebrahimi. Shadow-aware object-based video processing.Vision,Image and Signal Processing,2005,152(4):398~406
[57] George S. K. Fung,Nelson H. C. Yung,Grantham K. H. Pang,Andrew H. S. Lai. Effectivemoving cast shadow detection for monocular color traffic image sequences. Optical Engineering,2002,41(6):1425~1440
[58] D.Xu,X.Li,Z.Liu,and Y.Yuan. Cast shadow detection in video segmentation. PatternRecognition Letters,2005,vol.26,91~99
[59] A.Leone,C.Distante,and F.Buccolieri. A shadow elimination approach in video-surveillancecontext. Pattern Recognition Letters,2006,27(5):345~355
[60] J.W.Hsieh,W.F.Hu,C.J.Chang,and Y S.Chen. Shadow elimination for effective movingobject detection by Gaussian shadow modeling. Image and Vision Computing,2003,21(6):505~516
[61] J.W.Hsieh,S.H.Yu,Y.S.Chen,and W.F.Hu. Automatic traffic surveillance system for vehicletracking and classification. IEEE Transactions on Intelligent Transportation Systems,2006,7(2):175~187
[62] A.Yoneyama,C.H.Yeh,and C.C.J.Kuo.Moving cast shadow elimination for robust vehicleextraction based on2D joint vehicle/shadow models. Proceedings of IEEE InternationalConference on Advanced Video and Signal Based Surveillance,2003,229~236
[63] I.Mikic,P.C.Cosman,G.T.Kogut,and M.M.Trivedi.Moving shadow and object detection intraffic scenes. Proceedings of International Conference on Pattern Recognition,2000,vol.1,321~324
[64] Y.Wang, T.Tan, and K F.Loe. A probabilistic method for foreground and shadowsegmentation. Proceedings of International Conference on Image Processing,2003,vol.3,937~940
[65] D.Toth,I.Stuke,A.Wagner,and T.Aach. Detection of moving shadows using mean shiftclustering and a significance test. Proceedings of International Conference on Pattern Recognition,2004,vol.4,260~263
[66] Stauder J,Mech R,Ostermann J. Detection of moving cast shadows for object segmentation.IEEE Transactior on Multimedia,1999,1(1):65~76
[67] Sohail Nadimi，Bir Bhanu.Moving shadow detection using a physics-based approach. The16th International Conference on Pattern Recognition,2002,701~704
[68] H.G.Barrow and J.M.Tenenbaum. Recovering intrinsic scene characteristics from images.Computer Vision System,1978,3~26
[69] M. F. Tappen, W. T. Freeman, and E. H. Adelson. Recovering intrinsic images from a singleimage. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(9):1459~1472
[70] Y.Weiss. Deriving intrinsic images from image sequences. Proceedings of InternationalConference on Computer Vision,2001,68~75
[71] G.D.Finlayson, S.D.Hordley, C.Lu and M.S.Drew. Removing shadows from images.Proceedings of the7th European Conference on Computer Vision,vol IV,2002,823~836
[72] G.D.Finlayson, M.S.Drew, and C.Lu. Intrinsic images by entropy minimization.In:Proceedings of European Conference on Computer Vision,2004. Vol III:582~595
[73] G.D.Finlayson, M.S.Drew, and C.Lu.On the removal of shadows from images.IEEETransactions on pattern analysis and machine intelligence,2006,28(1):59~68
[74] G.D.Finlayson, M.S.Drew, and C.Lu. Entropy minimization for shadow removal.International hournal of computer vision,2009,85(1),35~57
[75] D.W. Scott. Multivariate density estimation: theory, practice and visualization. Wiley andKegan Paul,1992
[76] Kameda Yoshinari and Minoh michihiko. A human motion estimation method using3-successive video frames. Proceedings of International Conference on Virtual Systems andMultimedia,1996,135~140
[77] Hantanglu I,Hatwood D,Davis L W. Real-time surveillance of people and their activities.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,22(8):809~830
[78] McKenna S et al.Tracking groups of people computer vision and image understanding.2000,80(1):42~56
[79] Bulas J, Cruz, Ali A T, Dagless E L. A temporal smoothing technique for real-time motiondetection. Proceedings of ECCV,1994:379~386
[80] Chaoqun Huang, Guowu Yuan, Dan Xu. Multi-target detection and tracking by gaussianmixture model and blob tracking analysis.Journal of Information and Computational Science.2009,6(6):2403~2410
[81] B. P. L. Lo and S. A. Velastin.Automatic congestion detection system for undergroundplatforms.Intelligent Multimedia, Video and Speech Processing,2001,158~161
[82] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati. Detecting moving objects,ghosts, andshadows in video streams. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,vol.25,1337~1342
[83] D.Farin,P.H.N.de With,and W.Effelsberg.Robust background estimation for complex videosequences.Proceedings of IEEE International Conference on Image Processing,2003,vol.1,145~148
[84]刘勃,魏铭旭,周荷琴.一种基于区间分布的自适应背景提取算法.模式识别与人工智能,2005,18(3):316~321
[85] Suzuki H.,Matsumoto T.and ChuaL.O.A CNN hand written haracter recognizer.Int. JonCircuit Theory and Applications,1992, vol.20,601~612
[86] L. Koskinen, M.Laiho, A. Paasio and K.Halonen.MPEG-4based modifications for an CNNsegmentation chip.The7th Intenrational Workshop on CNN and Their Applications,2002,71~77
[87] P.Arena, A.Basile,L.Fortuna,M.E.Yalcin and J.Vandewalle. Watermarking on CNN-UM forimage and video authentication.The7th Intenrational Workshop on CNN and Their Appli-cations,2002,78~83
[88] Chug,L. O. and Y ang,L. Cellular neural networks:theory. IEEE Transactions on CircuitsSystems,1988,35(10):1257~1272
[89] Chua, L. O., Roska, T., Kozek, T., and Zarandy, A. The CNN paradigm.IEEE Transactionson Circuits and Systems-I:Fundamental Theory and Applications,1993,4(3):147~156
[90] Tejen Su, Cianpin Wei.Image noise cancellation using linear matrix in equality and cellularneural network. Optics Communications,2008,5706~5712
[91] Slark L K,Yu C.Denoising by optimal fuzzy thresholding in wavelet domain. ElectronicsLetters,2000,36(6):581~582
[92] Reilly Vladimir,Solmaz Berkan,Shah Mubarak.Geometric constraints for human detectionin aerial imagery.11th European Conference on Computer Vision,2010,6:252~265
[93]何玉钧，王梓蒴，尹成群，李永倩.利用平稳小波变换处理FBG传感信号.红外与激光工程,2011,40(11):2295~2300
[94] R.Cucchiara,M.Piccaidi,and P.Mello.Image analysis and rule-based reasoning for a trafficmonitoring system. IEEE Transactions on Intelligent Transportation Systems,2000,vol.1,119~130
[95] C.Gentile,O.Camps,and M.Sznaier. Segmentation for robust tracking in the presence ofsevere occlusion. IEEE Transactions on Image Processing,2004,vol.13,166~178
[96] J.Kang,I.Cohen,G.Medioni,and C.Yuan. Detection and tracking of moving objects from amoving platform in presence of strong parallax. Proceedings of IEEE International Conference onComputer Vision,2005,vol.1,10~17
[97]郁梅,王圣男,蒋刚毅.复杂交通场景中的车辆检测与跟踪新方法.光电工程.2005,32(2):67~70
[98]孙季丰,王成清.基于特征点光流和卡尔曼滤波的运动车辆跟踪.华南理工大学学报(自然科学版),2005,33(10):19~23
[99] N.K.Kanhere,S.J.Pundlik,and S.T.Birchfield. Vehicle segmentation and tracking from alow-angle off-axis camera.Proceedings of IEEE Conference on Computer Vision and PatternRecognition,2005,vol.2,1152~1157
[100] Har Iharakr Ishnan K,Schonfeld D. Fast object tracking using adaptive block matching.IEEE Transactions on Multimedia,2005,7(5):853~859
[101]张伟.基于视觉的运动车辆检测与跟踪:[博士学位论文].上海交通大学图像通信与信息处理研究所,2007
[102] C.C.C.Pang,W.W.L.Lam,and N.H.C.Yung.A novel method for resolving vehicle occlusionin a monocular traffic-image sequence.IEEE Transactions on Intelligent Transportation Systems,2004,vol.5,129~141
[103] X.F.Song and R.Nevatia.A model-based vehicle segmentation method for tracking.Proceedings of IEEE International Conference on Computer Vision,2005,vol.2,1124~1131
[104] J.G..Lou;T.N.Tan,W.M.Hu,H.Yang,and S.J.Maybank.3-D model-based vehicle tracking.IEEE Transactions on Image Processing,2005,vol.14,1561~1569
[105] Veeraraghavan,O.Masoud,and N.P.Papanikolopoulos.Computer vision algorithms forintersection monitoring. IEEE Transactions on Intelligent Transportation Systems,2003,vol.4,78~89
[106] S.Kamijo, Y.Matsushita, K.Ikeuchi, and M.Sakauchi. Traffic monitoring and accidentdetection at intersections. IEEE Transactions on Intelligent Transportation Systems,2000,vol.1,108~118
[107] C.L.Huang and W.C.Liao.A vision-based vehicle identification system. Proceedings ofInternational Conference on Pattern Recognition,2004,vol.4,364~367
[108]董鸿燕,沈振康,罗军,张志龙,倪为平.感知编组综述.计算机工程与应用,2007,43(14):9~13
[109] Wertheimer M．Untersuchungen zur lehre von der Gestalt ii:Psychologisehen Forschung，1923,4:301~350
[110] Koffka K. Principles of gestalt psychology.New York:Harcourt,1935
[111] Kohler W. Gestalt psychology.New York:Liveright,1929
[112] David G. Lowe. Perceptual organization and visual recognition. Kluwer AcademicPublishers, Boston, MA,1985
[113] David G. Lowe. Three-dimensional object recognition from single two-dimensional images.Artificial Intelligence,1987,31(3):355~395
[114] W. Eric L. Grimson. The combinatorics of heuristic search termination for objectrecognition in cluttered environments. IEEE Transactions on Pattern Analysis and MachineIntelligence,1991,13(9):920~935
[115] Zlatoff Nicolas,Tellez Bruno,Baskurt Atilla.Combining local belief from low-levelprimitives for perceptual grouping. Pattern Recognition,2008,1215~1229
[116] Xiao, Y.,Tien, D., Jia X.P. Region based perceptual grouping for road extraction from highresolution images.6th International Conference on Information Technology and Applications,2009,67~70
[117] Shimon Ullman and Amnon Sha’ashua. Structural saliency: the detection of globally salientstructures using a locally connected network. Technical Report A.I. Memo No.1061, MIT,Artificial Intelligence Laboratory,1988
[118] Rakesh Mohan and Ramakant Nevatia. Segmentation and description based on perceptualorganization. IEEE Conference on Computer Vision and Pattern Recognition,1989,333~341
[119] Rakesh Mohan and Ramakant Nevatia. Perceptual organization for scene segmentation anddescription. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(6):616~635
[120]刘俊义,王润生.基于骨架层次分解的目标的图表示.计算机学报,2001,24(6):633~637
[121] Sudeep Sarkar and Kim L. Boyer. Automated design of bayesian perceptual inferencenetworks. Technical Report SAMPL-93-03, SAMPL-Lab, Department of ElectricalEngineering,OSU,1993
[122] Sudeep Sarkar and Kim L. Boyer. Integration inference and management of spatialinformation using bayesian networks: perceptual organization. IEEE Transactions on PatternAnalysis and Machine Intelligence,1993,15(3):256~274
[123] Sudeep Sarkar and Kim L. Boyer. Using perceptual inference networks to manage visionprocesses. Computer Vision, Graphics, and Image Processing: Image Understanding,1995,62(1):27~46
[124] Gideon Guy and Gerard Medioni. Inferring global perceptual contours from local features.International Journal of Computer Vision,1996,20(1/2):113~133
[125] Sudeep Sarkar and Kim L. Boyer. Quantitative measures of change based on featureorganization: eigenvalues and eigenvectors. IEEE Conference on Computer Vision and PatternRecognition,1996,478~483
[126] Charles T.Zahn.Graph-theoretical methods for detecting and describing gestalt clusters.IEEE Transactions on Computers,1971,20(1):68~86
[127] P. Perona and W. Freeman. A factorization approach to grouping. In European Conferenceon Computer Vision,1998,655~670
[128] Arnon Amir and Michael Lindenbaum. A generic grouping algorithm and its quantitativeanalysis. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(3):168~186
[129] Bernd Fischer and Joachim M. Buhmann. Path-based clustering for grouping of smoothcurves and texture segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(4):513~518
[130] Xiaofeng Ren and Jitendra Malik. A probabilistic multi-scale model for contour completionbased on image statistics. European Conference on Computer Vision,2002,312~327
[131] James Elder and Steven Zucker. The effect of contour closure on the rapid discrimination oftwo-dimensional shapes. Vision Research,1993,(33):981~991
[132] James H. Elder and Steven W. Zucker. A measure of closure. Technical Report93-2,McGillResearch Centre for Intelligent Machines,1994
[133] Song Wang, Toshiro Kubota, and Jeffrey Mark Siskind. Salient boundary detection usingratio contour. Neural Information Processing Systems Conference,2003,1571~1578
[134] Williams L R, Jacobs D W. Stochastic completion fields: a neural model of illusory contourshape and salience. Neural Computation,1997,9(4):837~858
[135] Mahamud S, Williams L R, Thornber K K, Xu K. Segmentaion of multiple salient closedcontour from real images. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(4):433~444
[136] David W. Jacobs. Robust and efficient detection of salient convex groups. IEEETransactions on Pattern Analysis and Machine Intelligence,1996,18(1):23~37
[137] Luo Xingzhi, Bhandarkar, Suchendra M.Tracking of multiple objects using optical flowbased multiscale elastic matching.9th European Conference on Computer Vision,2006,203~217
[138] Kalman, R. E. A new approach to linear filtering and prediction problems. Transactions ofthe ASME-Journal of Basic Engineering.1960,vol.82,35~45
[139] Kalman, R. E., Bucy R. S.New results in linear filtering and prediction theory, Transactionsof the ASME-Journal of Basic Engineering,1961,vol.83,95~107
[140] Omar Javed and Mubarak Shah.Tracking and object classification for automatedsurveillance, European Conference on Computer Vision,2002,343~357
[141] Kanizsa G. Organization in vision.New York:Praeger,1979
[142]荆其诚，焦书兰，喻柏林等.色度学.北京:科学出版社,1979
[143] Wu Z,Leahy R. An optimal grapht heoretic approach to data clustering:theory and itsapplication to image segmentation.IEEE Transactions on Pattern Analysis and MachineIntelligence,1993,15(11):1101~1113
[144] Shi J,Malik J. Normalized cuts and image segmentation. IEEE Transactions on PatternAnalysis and Machine Intelligence,2000,22(8):888~905
[145] Hagen L, Kahng A B. New spectral methods for ratio cut partitioning and clustering. IEEETransactions on Computer Aided Design,1992,11(9):1074~1085
[146] Sarkar S, Soundararajan P. Supervised learning of large perceptual organization: graphspectral partitioning and learning automata. IEEE Transaction on Pattern Analysis and MachineIntelligence,2000,22(5):504~525
[147] Ding C,He X,Zha H,et al. Spectral Min-Max cut for graph partitioning and data clustering.IEEE Conference on Data Mining,2001,107~114
[148] Meila M, Xu L. Multiway cuts and spectral clustering. U.Washington Technical Reports,2003
[149] Xu Linli,Li Wenye,Schuurmans Dale.Fast normalized cut with linear constraints. IEEEComputer Society Conference on Computer Vision and Pattern Recognition Workshops.2009,2866~2873
[150] Mukherjee Lopamudra,Singh Vikas,Peng Jiming,Hinrichs Chris.Learning kernels forvariants of normalized cuts: Convex relaxations and applications, IEEE Computer SocietyConference on Computer Vision and Pattern Recognition.2010,3145~3152