基于视频技术的运动目标检测和跟踪算法研究
|
摘要
本文以视频道路交通监测系统中运动车辆的检测与跟踪为应用背景,对运动目标检测中背景更新、阴影消除、运动目标跟踪和摄像机自动定标等一些难点问题进行了深入的分析研究,提出了一些新的算法,主要内容如下：
1.分析了目前运动目标分割和检测的主要方法。包括运动优先的算法和分割优先的算法。提出了一种新的背景重建算法。算法以图像中任何一像素点背景出现概率最大为准则。特点是节省内存,跟新速度快,统计帧数多。实验验证可靠有效。
2.针对阴影干扰的消除,提出一种结合灰度信息和结构信息的阴影干扰消除算法,算法首先进行阴影类型判别,在此基础上,用统计的方法检测目标物与阴影的分界点,并用多个分界点中拟合一条分界线作为目标物与阴影的分割分界。取得较好的实验效果。
3.分析了目前运动目标跟踪的主要方法。提出一种结合面积校正的改进的目标跟踪算法。因为成像系统的原因,同一目标物在不同帧中处在不同的位置,面积也大小不同。给运动目标跟踪带来一定误差。本算法弥补了这一误差,结合用CM(1,1)模型进行预测。取得了较好的实验效果。
4.分析了摄像机定标的主要方法。在智能交通中的摄像机定标,可利用的先验知识是图像序列中的运动目标物是车辆,而其中占多数的是小轿车。假设小轿车的实际面积已知。本文提出一种利用这些先验知识的摄像机自动定标算法。实验效果可靠有效。
本文所提出的运动车辆检测、跟踪方法、摄像机自动定标算法和阴影干扰消除算法作为视觉监控领域的一种普遍方法,具有一定的理论意义和实用价值,可以推广到视觉监控的其他应用中,具有广阔的应用前景。
In this paper, the detection and tracking of moving vehicles in the visual road traffic detection system as application background, conducted in-depth analysis and study of the problem of background update, shadow elimination, moving object tracking and camera auto-calibration on moving target detection, proposed some new algorithms. The main content is as follows:
1. This paper analyzes of the current moving object segmentation and detection methods. Including the movement of priority algorithms and split the priority algorithm. Put forward a new algorithm of background reconstruction. Algorithm to image any pixel background probability criterion. Characteristic is to save memory, with the new speed, count the number of frames much. Experimental validation is reliable and effective.
2. For the elimination of shadow interference, puts forward a shadow interference cancellation algorithm that combination of gray information and the structure information, for shadow type discrimination, on this basis, using statistical methods to detect the target and shadow boundary, and using multiple cutoff point fitting a line as a target and shadow segmentation boundary, in orders to better experimental results.
3. Through the analysis of current target tracking method, puts forward a improved target tracking algorithm that combination area correction. Because of the imaging system, the same target gives some error of moving target tracking in different frames in a different location, different area size. The algorithm makes up for this error, combining with CM (1,1) model to forecast, and obtained a better experimental effect.
4. It analyzes the main methods of camera calibration. In the intelligent transportation of camera calibration, the available prior knowledge is of moving object in image sequence is the vehicle, which account for the majority of the cars. If the actual area of the car is known, this paper puts forward a CCD automatic calibration algorithm of using these priors knowledge. The experimental result is reliable and effective.
The proposed algorithms of moving vehicle detection, tracking, camera automatic calibration and shadow interference cancellation, have certain theory significance and practical value, can be extended to other applications in visual surveillance, and have broad application prospects.
1.分析了目前运动目标分割和检测的主要方法。包括运动优先的算法和分割优先的算法。提出了一种新的背景重建算法。算法以图像中任何一像素点背景出现概率最大为准则。特点是节省内存,跟新速度快,统计帧数多。实验验证可靠有效。
2.针对阴影干扰的消除,提出一种结合灰度信息和结构信息的阴影干扰消除算法,算法首先进行阴影类型判别,在此基础上,用统计的方法检测目标物与阴影的分界点,并用多个分界点中拟合一条分界线作为目标物与阴影的分割分界。取得较好的实验效果。
3.分析了目前运动目标跟踪的主要方法。提出一种结合面积校正的改进的目标跟踪算法。因为成像系统的原因,同一目标物在不同帧中处在不同的位置,面积也大小不同。给运动目标跟踪带来一定误差。本算法弥补了这一误差,结合用CM(1,1)模型进行预测。取得了较好的实验效果。
4.分析了摄像机定标的主要方法。在智能交通中的摄像机定标,可利用的先验知识是图像序列中的运动目标物是车辆,而其中占多数的是小轿车。假设小轿车的实际面积已知。本文提出一种利用这些先验知识的摄像机自动定标算法。实验效果可靠有效。
本文所提出的运动车辆检测、跟踪方法、摄像机自动定标算法和阴影干扰消除算法作为视觉监控领域的一种普遍方法,具有一定的理论意义和实用价值,可以推广到视觉监控的其他应用中,具有广阔的应用前景。
In this paper, the detection and tracking of moving vehicles in the visual road traffic detection system as application background, conducted in-depth analysis and study of the problem of background update, shadow elimination, moving object tracking and camera auto-calibration on moving target detection, proposed some new algorithms. The main content is as follows:
1. This paper analyzes of the current moving object segmentation and detection methods. Including the movement of priority algorithms and split the priority algorithm. Put forward a new algorithm of background reconstruction. Algorithm to image any pixel background probability criterion. Characteristic is to save memory, with the new speed, count the number of frames much. Experimental validation is reliable and effective.
2. For the elimination of shadow interference, puts forward a shadow interference cancellation algorithm that combination of gray information and the structure information, for shadow type discrimination, on this basis, using statistical methods to detect the target and shadow boundary, and using multiple cutoff point fitting a line as a target and shadow segmentation boundary, in orders to better experimental results.
3. Through the analysis of current target tracking method, puts forward a improved target tracking algorithm that combination area correction. Because of the imaging system, the same target gives some error of moving target tracking in different frames in a different location, different area size. The algorithm makes up for this error, combining with CM (1,1) model to forecast, and obtained a better experimental effect.
4. It analyzes the main methods of camera calibration. In the intelligent transportation of camera calibration, the available prior knowledge is of moving object in image sequence is the vehicle, which account for the majority of the cars. If the actual area of the car is known, this paper puts forward a CCD automatic calibration algorithm of using these priors knowledge. The experimental result is reliable and effective.
The proposed algorithms of moving vehicle detection, tracking, camera automatic calibration and shadow interference cancellation, have certain theory significance and practical value, can be extended to other applications in visual surveillance, and have broad application prospects.
引文
[1]Coifman B, Beymer D,Mclauchlan P,Malik J.A real-time computer vision system for vehicle tracking and traffic Surveillanee.Transportation Research PartC,1998,6(4):271 — 288.
[2]Magee D.Traeking multiple vehicles using foreground,background and motion models.Image and Vision Computing,2004,22(2):143 — 155.
[3]Pai C, Tyan H., Liang Y., LiaoH.M., Chen S. Pedestrian detection and tracking at cross roads. Pattern Recognition,2004,37(5):1025-1034.
[4]Masoud O., Papanikolos N P. A novel method for traeking and counting Pedestrians in real-time using a singleea mera.IEEE Transactions on Vehicular Technology,2001,50(5):1267-1278.
[5]Wachter S.,Nagel H. Tracking persons in monocular image sequences.ComPuter Vision and Image Under-standing,1999,74(3):174-192.
[6]Nagel, H.H.Displacement vectors derived from second-order intensity variations in image sequences.Computer Graphics and Image Processing(1983),21:85-117.
[7]Mitiche A., Y.F.Wang.and J.K.Aggarwal.Experiments in computing optical flow whit gradient-based.multiconstraint method.Pattern Recognition(June 1987),20(2):173-79.
[8]Haralick, R.M.,and J.S.Lee.The facet approach to optical flow.In Image Uuderstanding Workshop(1993).
[9]Fleet, D.J.,and A.D.Jepson.Computeration of component image velocity from local phase information.lmnternational Journal of Computer Vision(1990),5:77-104.
[10]Barron, J.L., D.J.Fleet,and S.S.Beauchemin.Perforance of optical flow techniques.International Journal of Computer Vison(1994),12:43-77.
[11]Lee,O.,and Y.Wang.Motion compensated prediction using nodal based deformable block matching.Journal of Visual Communications and Image Represention(March 1995),6:26-34.
[12]Seferidis, V.,and M.Ghanbari.General approach to block matching motion estimation.Optical Engineering(July 1993),32:1464-74.
[13]Wang, Y,and O.Lee.Use of 2-D deformable mesh structures fir video compression.Part I-the synthesis problem:Mesh based function approximation and mapping.IEEE Trans.Circuits Syst.for Video Technology(Dec.1996),6:636-46.
[14]Wang,Y.,and O.Lee.Active mesh—a feature seeking and tracking image sequence representation scheme.IEEE Trans.Image Process. (Sept.1994),3:610-24.
[15]Altunbasak, Y.,and A.M.Tekalp.Occlusion-adaptive,content-based mesh design and forward tracking.IEEE Trans.Image Process.(Sept.1997),6:1270-80.
[16]Altunbasak, Y, and A.M.Tekalp.Colsed-form connectivity-preserving solutions for montion compensation using 2-D meshes.IEEE Trans.Image Process.(Sept.1997),6:1255-69.
[17]Chou,P.,and C.Brown.The theory and practice of Bayesian image labeling.International Journal of Computer Vision(1990),4:185-210.
[18]komarek, T.,and P.Pirsch.Array architecture for block matching algoritchms.IEEE Trans.Circuits and Systems(Oct.1989),36:269-77.
[19]Pirsch,P.,N.Demassieux,and W.Gehrke.VLSI architecture for video compression—a survey.IEEE(Feb.1995),83:220-46.
[20]Hang,H.-M.,Y.-M.Chou,and S.-C.Cheng.Motion estimation fo video coding standards.Journal of VLSI Signal Processing System for Signal,Image,and Video Technology(Nov.1997),17(2/3):113-36.
[21]Horn.B.K.P., and B.G.Schunck.Determining optical flow.Artifical intelligence(1981),17(1-3):185-203.
[22]Nagle,H.H.,and W.Enklemann.An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences.IEEE Trans.Pattern Anal.Machine Intel l.(Stpt.1986),8:565-93.
[23]Girod, B.Motion compensation:Visual aspects,accuracy,andfundamental limits.In M.I.Sezan and R.L.Lagenddijk,eds.,Motion Analysis and Image Sequence Processing.Boston:Kluwer Academic Publishers,1993,126-52.
[24]Jain.J.,and A.K.Jain.Displacement and its application in interframe image coding.IEEE Trans.Commun.(dec.1981),COM-19:1799-808.
[25]Koga, T,et al.Motion-compensated interframe coding for video conferencing.In Nat.Telecommun.Conf.(Nov.1981),G5.3.1-5, New Orleans, LA.
[26]Huang, T.S., and A.N.Netravali.Motion and structure from feature correspondences:A review. Proceedings of the IEEE(Feb.l994),82(2):252-68.
[27]Mataric M.J, Learning in Multi-Robot Systems, Adaptation and Learning inMulti-Agent Systems, Lecture Notes in Artificial Intelligence,1998,152-163.
[28]基于视频的车辆检测算法综述南京邮电大学学报第27卷第3期2007年6月.
[29]LIPTON A J,FUJIYOSHI H,PATIL R S.moving target classificaltion.and tracking from real-time void[C]//Proc of WACV'98.1998:8-14.
[30]COLLINS R T, LIPTON A J, KANADE T.A system for video surveillance and monitoring[R].Pittsburgh,USA:Camegie Mellon University,2000.
[31]潘薇,游志胜,王宁,基于模糊聚类和卡尔曼滤波的运动目标检测[J].计算机应用,2005,25(1)：123-124.
[32]陈朝阳,张桂林。基于图像对称差分的运动小目标检测方法[J].华中理工大学学报,1998,26(9)：34-35.
[33]张丽,李志能。基于阴影检测的HSV空间自适应背景模型的车辆追踪检测[J].中国图形图像学报,2003,8(7)：778-782.
[34]STAUFFER C,GRIMSON W E L.Adaptive background maxture models for real-time tracking[C]//Proc of CVPR'99.1999:246-252.
[35]Kumar P.,Sengupta K.,et al.A Comparative Study of Different Color Spaces for Foreground and Shadow Detection for Tafffic Monitoring System.Proceedings of 5th IEEE International Conference on Interlligent Transportation System.Singapore,2002,pp.100-105.
[36]kaewwTraKulPong P.,Boeden R.An improved adaptive background mixture model for real-time tracking with shadow detection.Proceeding of the 2nd European Workshop on Advanced Void Based Surveillance System.2001,pp1-5.
[37]Fung G.S.K.,Yung N.H.C.,et al.Effect moving cast shadow detection for monocular color image sequences.Proceedings of the 11th International Conference on Image Analysis and Processing.2001,pp.404-409.
[38]E.Salvador,A.Cavallaro,and T.Ebrahimi.Shadow Identification and Classification Using Invariant Color Models[A].Proc.IEEE Signal Processing Society International Conference on Acoustics,Speech and Signal Processing (ICASSP-2001),Salt Lake City (Utah-USA), May.2001(3).1545—1548.
[39]H.M.G Stokman and TH.Gevers, J.J.Koenderink, Color Measurement by Imaging Spectrometry, Computer Vision and Image Understanding,2000.236—249.
[40]Pan F,Wang X Y,Wang Q Q,Human detection based on head and shoulder features in intelligent surveillance system[J].Journal of Zhejiang University (Engineering Science),2004,38(4).397—401.
[41]Kuo-Hua Lo and Mau-Tsuen Yang,Shadow Detection by Integrating Multiple Features,The 18 th International Conference on Pattern recognition,2006.
[42]J.Stauder, R.Mech and J.Ostermann.Detection of moving cast shadows for object segmentation.IEEE Transaction on multimedia,1999,1(1):65-76.
[43]王军利,王树根.一种基于RGB彩色空间的影像阴影检测方法.信息技术,2002,26(12)：7-9.
[44]I.Mikic, P.Cosman, G.Kogut and M.M.Trivedi.Moving shadow and object detection in traffic scenes, Proceedings of Int't Conference on Pattern Recognition.2000,1:321-324.
[45]Rita Cucchiara,et al.Improving shadow suppression in moving object detection with HSV color information.Proc.of the 4th International IEEE Conference on Intelligent Transportation System,2001.334-339.
[46]Rosin P L, Ellis T.Image difference threshold strategies and shadow detection.Proc.of the 6th British Machine Vision Conference,1994,347-356.
[47]刘勃,魏铭旭,周荷琴.交通场景中分块阴影检测算法研究[J].计算机工程2005 31(11)：160-162.
[48]M.Kilger.A shadow handler in a video-based real-time traffic monitoring system. Proceedings of IEEE Workshop on Applications of Computer Vision,1992.11-18.
[49]Z.Zhu, G.Xu.VISATRAM:a real-time vision system for automatic traffic monitoring.Image and Vision Computing.2000,18(10):781-794.
[50]Coifman,B.,Beymer,D.,Malik,J.A real-time computer vision system for vehicle tracking and traffic surveillance.Transport.Res.:Part C,1998,6(4):271-288.
[51]Malik,J.,Russell,S.Traffic surveillance and detection technology development:new traffic sensor technology final report.PATH research report UCB-ITS-PRR-97-6.Institute of Transportation Studies,University of California,Berkeley,1997.
[52]Frederic Leymarie, Martin D.Levine.Tracking Deformable Objects in the Plane Using an Active Contour Model.IEEE Transaction on Pattern Analysis and Machine Intelligence.1993,15(6):617-634.
[53]Marc Niethammer,Allen Tannenbaum,Sigurd Angenent.Daybank S J.3-D model-base vehicle tracking.IEEE Transaction on Automatic Control.2006,51(4):562-579.
[54]Yu Huang, Thomas S.Huang, Heinrch Nimann.A Region-Based Method for Model-Free object Tracking.International Conderence ob Pattern Recognition.2002:592-595.
[55]Gregory D.Hager, Peter N.Nelhumeur.Efficient Region Tracking With Parametic Models of Geometry and Illumination.IEEE Transaction on Pattern Analysis ans Machine Intelligence.
[56]Setchell, C.Applications of computer vision to road-traffic monitoring, Ph.D.thesis, Department of Computer Science, University of Bristol, Sept.1997.
[57]CollinsR.T, Yanxi Liu, Leordeanu M.Online selection of discriminative tracking features.IEEE Transation on Pattern Analysis ans Machine Interlligence.2005,27(10):1631-1643.
[58]Michail krinidis,Nikos Nikolaidis,Ioannis Pitas.2-D Feature-Point Selection and Tracking Using 3-D Physics.IEEE Transaction on Circuits ans Systems for Video Technology.2007,17(7):876-888.
[59]Yi-Sheng Yao,Chellappa R.Tracking a dynamic set of feature points.IEEE Transactions on Image Propcessing.1995,4(10):1382-1395.
[60]Roberts, J.M.Attentive visual tracking and trajectory estimation for dynamic scene segmentation, Ph.D.thesis, University of Southampton,1994.
[61]Shi, J.Tomasi, C.Good features to track.IEEE Conf. Comput. Vis. Pattern Recognit.,1994.593-600.
[62]Tsai R Y.An efficient and accurate camera calibration technique for 3D machine vision[J].proc CVPR86.364-374.
[63]Zheng you Zhang.A Flexible New Technique for Camera Caliration[J].Technial Report Micrsoft Reseaech Microsoft Corporation.2002.10.
[64]Faugeras O, Toscani G. The calibration problem for stereo. In:Proc CVPR'86, Miami Beach, FL, 1986.15 — 20.
[65]Tsai R Y. An efficient and accurate camera calibration technique for 3D machine vision. In:Proc CVPR'86, Miami Beach, FL,1986.364 — 374.
[66]Wei G Q, Ma S D. Implicit and explicit camera calibration:theory and experiments. IEEE Trans on PAMI,1994,16(5):469 — 480.
[67]Wei G Q, Ma S D. Camera calibration by vanishing point and cross ratio. In:Proc IEEE Int Conf ASSP'89, Glasgow Scotland,1989.1630 — 1633.Maybank S J, Faugeras O. A theory.
[68]Faugras O, Luong Q-T,Maybank S.Camera Self-calibration:Theory and experiments[J].In:Proc.ECCV'92,1992,321-334.
[69]Hartley R.Euclider reconstruction from uncalibrated view[J].In:Application of Invariance in Computer Vision.LNCS825.1994.237-256.
[70]刘侍钢,吴成可,唐丽,贾静.加权迭代射影重建法[J].计算机科学.2005,32(10)：187-199.
[71]刘侍钢,吴成可,唐丽,贾静.基于对偶绝对二次曲面变换的自定标方法[J].系统工程与电子技术,2005,27(2)：212-214.
[72]刘侍钢,吴成可,唐丽,严尧平.一种基于线性迭代自定标方法[J].电子学报,2004,32(10)：1716-1719.
[73]Luong, Q.T,Veillon,T.Canonic Representations for the Geomtres of Multiple Projective Views[A].Technical Report,University of California.Berkeley.1993.
[74]Maybank S J, Faugeras O. A theory of self-calibration of a moving camera. Int J Computer Vision, 1992,8(2):123-151.
[75]Ma S D. A self-calibration technique for active vision system. IEEE Trans on Robot Automat,1996, 12(1):114-120.
[76]杨长江,汪威,胡占义.一种基于主动视觉的摄像机内参数自定标方法[J],计算机学报.1998,21(5)：428-434.
[77]K.Karmann, A.Brandt,R.Gerl.Moving object segmentation based on adaptive reference images.Signal Processing:Theories and Applications,1990,5(9):951-954.
[78]M.Boninsegna, A.Bozzoli.A Tunable algorithm to update a reference image. Signal Processing:Image Communication,2000,16(4):353-365.
[79]A.Lai, N.Yung.A fast and accurate Scoreboard algorithm for estimating stationary backgrounds in an image sequence.Proceedings of IEEE International Symposium on Circuits and Systems, 1998,241-244.
[80]R.Cucchiara, C.Grana,M.Piccardi,et al.Statistic and knowledge-based moving object detection in traffic scenes.Proceedings of IEEE Intelligent Transportation Systems,2000.27-32.
[81]Y.K.Jung, Y.S.Ho.Traffic parameter extraction using video-based vehicle tracking.Proceedings of IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems,1999.764-769.
[82]C.Stauffer, W.Eric L.Grimson.Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[83]C.Jiang and M.O.Ward, shadow identification[J],Proceedings of IEEE Int'Conference on Computer Vision and Pattern Recognition.1992.606—612.
[84]Stauffer C,Grimson W.E.L.,"Adaptive background mixture models for real-time tracking"in Proceeding,1999 IEEE Computer Society Conference on Compute Vision and Pattern Recognition,IEEE Comput.Soc.Part Vol.2.1999.
[85]史忠科,曹力.交通检图像检测与分析,科学出版社,2007年.
[86]邓聚龙.灰预测与灰决策。武汉：华中科技大学出版社,2002.9.
[87]袁基炜,史忠科.一种基于灰色预测模型GM(1,1)的运动车辆跟踪方法,控制与决策,2006,21(3)：300-304.
[88]Milan Sonka, Vaclav Hlavac, Roger Boyl.艾海舟,武勃等译,图像处理、分析与机器视觉(第二版),北京：人民邮电出版社,2003.
[2]Magee D.Traeking multiple vehicles using foreground,background and motion models.Image and Vision Computing,2004,22(2):143 — 155.
[3]Pai C, Tyan H., Liang Y., LiaoH.M., Chen S. Pedestrian detection and tracking at cross roads. Pattern Recognition,2004,37(5):1025-1034.
[4]Masoud O., Papanikolos N P. A novel method for traeking and counting Pedestrians in real-time using a singleea mera.IEEE Transactions on Vehicular Technology,2001,50(5):1267-1278.
[5]Wachter S.,Nagel H. Tracking persons in monocular image sequences.ComPuter Vision and Image Under-standing,1999,74(3):174-192.
[6]Nagel, H.H.Displacement vectors derived from second-order intensity variations in image sequences.Computer Graphics and Image Processing(1983),21:85-117.
[7]Mitiche A., Y.F.Wang.and J.K.Aggarwal.Experiments in computing optical flow whit gradient-based.multiconstraint method.Pattern Recognition(June 1987),20(2):173-79.
[8]Haralick, R.M.,and J.S.Lee.The facet approach to optical flow.In Image Uuderstanding Workshop(1993).
[9]Fleet, D.J.,and A.D.Jepson.Computeration of component image velocity from local phase information.lmnternational Journal of Computer Vision(1990),5:77-104.
[10]Barron, J.L., D.J.Fleet,and S.S.Beauchemin.Perforance of optical flow techniques.International Journal of Computer Vison(1994),12:43-77.
[11]Lee,O.,and Y.Wang.Motion compensated prediction using nodal based deformable block matching.Journal of Visual Communications and Image Represention(March 1995),6:26-34.
[12]Seferidis, V.,and M.Ghanbari.General approach to block matching motion estimation.Optical Engineering(July 1993),32:1464-74.
[13]Wang, Y,and O.Lee.Use of 2-D deformable mesh structures fir video compression.Part I-the synthesis problem:Mesh based function approximation and mapping.IEEE Trans.Circuits Syst.for Video Technology(Dec.1996),6:636-46.
[14]Wang,Y.,and O.Lee.Active mesh—a feature seeking and tracking image sequence representation scheme.IEEE Trans.Image Process. (Sept.1994),3:610-24.
[15]Altunbasak, Y.,and A.M.Tekalp.Occlusion-adaptive,content-based mesh design and forward tracking.IEEE Trans.Image Process.(Sept.1997),6:1270-80.
[16]Altunbasak, Y, and A.M.Tekalp.Colsed-form connectivity-preserving solutions for montion compensation using 2-D meshes.IEEE Trans.Image Process.(Sept.1997),6:1255-69.
[17]Chou,P.,and C.Brown.The theory and practice of Bayesian image labeling.International Journal of Computer Vision(1990),4:185-210.
[18]komarek, T.,and P.Pirsch.Array architecture for block matching algoritchms.IEEE Trans.Circuits and Systems(Oct.1989),36:269-77.
[19]Pirsch,P.,N.Demassieux,and W.Gehrke.VLSI architecture for video compression—a survey.IEEE(Feb.1995),83:220-46.
[20]Hang,H.-M.,Y.-M.Chou,and S.-C.Cheng.Motion estimation fo video coding standards.Journal of VLSI Signal Processing System for Signal,Image,and Video Technology(Nov.1997),17(2/3):113-36.
[21]Horn.B.K.P., and B.G.Schunck.Determining optical flow.Artifical intelligence(1981),17(1-3):185-203.
[22]Nagle,H.H.,and W.Enklemann.An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences.IEEE Trans.Pattern Anal.Machine Intel l.(Stpt.1986),8:565-93.
[23]Girod, B.Motion compensation:Visual aspects,accuracy,andfundamental limits.In M.I.Sezan and R.L.Lagenddijk,eds.,Motion Analysis and Image Sequence Processing.Boston:Kluwer Academic Publishers,1993,126-52.
[24]Jain.J.,and A.K.Jain.Displacement and its application in interframe image coding.IEEE Trans.Commun.(dec.1981),COM-19:1799-808.
[25]Koga, T,et al.Motion-compensated interframe coding for video conferencing.In Nat.Telecommun.Conf.(Nov.1981),G5.3.1-5, New Orleans, LA.
[26]Huang, T.S., and A.N.Netravali.Motion and structure from feature correspondences:A review. Proceedings of the IEEE(Feb.l994),82(2):252-68.
[27]Mataric M.J, Learning in Multi-Robot Systems, Adaptation and Learning inMulti-Agent Systems, Lecture Notes in Artificial Intelligence,1998,152-163.
[28]基于视频的车辆检测算法综述南京邮电大学学报第27卷第3期2007年6月.
[29]LIPTON A J,FUJIYOSHI H,PATIL R S.moving target classificaltion.and tracking from real-time void[C]//Proc of WACV'98.1998:8-14.
[30]COLLINS R T, LIPTON A J, KANADE T.A system for video surveillance and monitoring[R].Pittsburgh,USA:Camegie Mellon University,2000.
[31]潘薇,游志胜,王宁,基于模糊聚类和卡尔曼滤波的运动目标检测[J].计算机应用,2005,25(1)：123-124.
[32]陈朝阳,张桂林。基于图像对称差分的运动小目标检测方法[J].华中理工大学学报,1998,26(9)：34-35.
[33]张丽,李志能。基于阴影检测的HSV空间自适应背景模型的车辆追踪检测[J].中国图形图像学报,2003,8(7)：778-782.
[34]STAUFFER C,GRIMSON W E L.Adaptive background maxture models for real-time tracking[C]//Proc of CVPR'99.1999:246-252.
[35]Kumar P.,Sengupta K.,et al.A Comparative Study of Different Color Spaces for Foreground and Shadow Detection for Tafffic Monitoring System.Proceedings of 5th IEEE International Conference on Interlligent Transportation System.Singapore,2002,pp.100-105.
[36]kaewwTraKulPong P.,Boeden R.An improved adaptive background mixture model for real-time tracking with shadow detection.Proceeding of the 2nd European Workshop on Advanced Void Based Surveillance System.2001,pp1-5.
[37]Fung G.S.K.,Yung N.H.C.,et al.Effect moving cast shadow detection for monocular color image sequences.Proceedings of the 11th International Conference on Image Analysis and Processing.2001,pp.404-409.
[38]E.Salvador,A.Cavallaro,and T.Ebrahimi.Shadow Identification and Classification Using Invariant Color Models[A].Proc.IEEE Signal Processing Society International Conference on Acoustics,Speech and Signal Processing (ICASSP-2001),Salt Lake City (Utah-USA), May.2001(3).1545—1548.
[39]H.M.G Stokman and TH.Gevers, J.J.Koenderink, Color Measurement by Imaging Spectrometry, Computer Vision and Image Understanding,2000.236—249.
[40]Pan F,Wang X Y,Wang Q Q,Human detection based on head and shoulder features in intelligent surveillance system[J].Journal of Zhejiang University (Engineering Science),2004,38(4).397—401.
[41]Kuo-Hua Lo and Mau-Tsuen Yang,Shadow Detection by Integrating Multiple Features,The 18 th International Conference on Pattern recognition,2006.
[42]J.Stauder, R.Mech and J.Ostermann.Detection of moving cast shadows for object segmentation.IEEE Transaction on multimedia,1999,1(1):65-76.
[43]王军利,王树根.一种基于RGB彩色空间的影像阴影检测方法.信息技术,2002,26(12)：7-9.
[44]I.Mikic, P.Cosman, G.Kogut and M.M.Trivedi.Moving shadow and object detection in traffic scenes, Proceedings of Int't Conference on Pattern Recognition.2000,1:321-324.
[45]Rita Cucchiara,et al.Improving shadow suppression in moving object detection with HSV color information.Proc.of the 4th International IEEE Conference on Intelligent Transportation System,2001.334-339.
[46]Rosin P L, Ellis T.Image difference threshold strategies and shadow detection.Proc.of the 6th British Machine Vision Conference,1994,347-356.
[47]刘勃,魏铭旭,周荷琴.交通场景中分块阴影检测算法研究[J].计算机工程2005 31(11)：160-162.
[48]M.Kilger.A shadow handler in a video-based real-time traffic monitoring system. Proceedings of IEEE Workshop on Applications of Computer Vision,1992.11-18.
[49]Z.Zhu, G.Xu.VISATRAM:a real-time vision system for automatic traffic monitoring.Image and Vision Computing.2000,18(10):781-794.
[50]Coifman,B.,Beymer,D.,Malik,J.A real-time computer vision system for vehicle tracking and traffic surveillance.Transport.Res.:Part C,1998,6(4):271-288.
[51]Malik,J.,Russell,S.Traffic surveillance and detection technology development:new traffic sensor technology final report.PATH research report UCB-ITS-PRR-97-6.Institute of Transportation Studies,University of California,Berkeley,1997.
[52]Frederic Leymarie, Martin D.Levine.Tracking Deformable Objects in the Plane Using an Active Contour Model.IEEE Transaction on Pattern Analysis and Machine Intelligence.1993,15(6):617-634.
[53]Marc Niethammer,Allen Tannenbaum,Sigurd Angenent.Daybank S J.3-D model-base vehicle tracking.IEEE Transaction on Automatic Control.2006,51(4):562-579.
[54]Yu Huang, Thomas S.Huang, Heinrch Nimann.A Region-Based Method for Model-Free object Tracking.International Conderence ob Pattern Recognition.2002:592-595.
[55]Gregory D.Hager, Peter N.Nelhumeur.Efficient Region Tracking With Parametic Models of Geometry and Illumination.IEEE Transaction on Pattern Analysis ans Machine Intelligence.
[56]Setchell, C.Applications of computer vision to road-traffic monitoring, Ph.D.thesis, Department of Computer Science, University of Bristol, Sept.1997.
[57]CollinsR.T, Yanxi Liu, Leordeanu M.Online selection of discriminative tracking features.IEEE Transation on Pattern Analysis ans Machine Interlligence.2005,27(10):1631-1643.
[58]Michail krinidis,Nikos Nikolaidis,Ioannis Pitas.2-D Feature-Point Selection and Tracking Using 3-D Physics.IEEE Transaction on Circuits ans Systems for Video Technology.2007,17(7):876-888.
[59]Yi-Sheng Yao,Chellappa R.Tracking a dynamic set of feature points.IEEE Transactions on Image Propcessing.1995,4(10):1382-1395.
[60]Roberts, J.M.Attentive visual tracking and trajectory estimation for dynamic scene segmentation, Ph.D.thesis, University of Southampton,1994.
[61]Shi, J.Tomasi, C.Good features to track.IEEE Conf. Comput. Vis. Pattern Recognit.,1994.593-600.
[62]Tsai R Y.An efficient and accurate camera calibration technique for 3D machine vision[J].proc CVPR86.364-374.
[63]Zheng you Zhang.A Flexible New Technique for Camera Caliration[J].Technial Report Micrsoft Reseaech Microsoft Corporation.2002.10.
[64]Faugeras O, Toscani G. The calibration problem for stereo. In:Proc CVPR'86, Miami Beach, FL, 1986.15 — 20.
[65]Tsai R Y. An efficient and accurate camera calibration technique for 3D machine vision. In:Proc CVPR'86, Miami Beach, FL,1986.364 — 374.
[66]Wei G Q, Ma S D. Implicit and explicit camera calibration:theory and experiments. IEEE Trans on PAMI,1994,16(5):469 — 480.
[67]Wei G Q, Ma S D. Camera calibration by vanishing point and cross ratio. In:Proc IEEE Int Conf ASSP'89, Glasgow Scotland,1989.1630 — 1633.Maybank S J, Faugeras O. A theory.
[68]Faugras O, Luong Q-T,Maybank S.Camera Self-calibration:Theory and experiments[J].In:Proc.ECCV'92,1992,321-334.
[69]Hartley R.Euclider reconstruction from uncalibrated view[J].In:Application of Invariance in Computer Vision.LNCS825.1994.237-256.
[70]刘侍钢,吴成可,唐丽,贾静.加权迭代射影重建法[J].计算机科学.2005,32(10)：187-199.
[71]刘侍钢,吴成可,唐丽,贾静.基于对偶绝对二次曲面变换的自定标方法[J].系统工程与电子技术,2005,27(2)：212-214.
[72]刘侍钢,吴成可,唐丽,严尧平.一种基于线性迭代自定标方法[J].电子学报,2004,32(10)：1716-1719.
[73]Luong, Q.T,Veillon,T.Canonic Representations for the Geomtres of Multiple Projective Views[A].Technical Report,University of California.Berkeley.1993.
[74]Maybank S J, Faugeras O. A theory of self-calibration of a moving camera. Int J Computer Vision, 1992,8(2):123-151.
[75]Ma S D. A self-calibration technique for active vision system. IEEE Trans on Robot Automat,1996, 12(1):114-120.
[76]杨长江,汪威,胡占义.一种基于主动视觉的摄像机内参数自定标方法[J],计算机学报.1998,21(5)：428-434.
[77]K.Karmann, A.Brandt,R.Gerl.Moving object segmentation based on adaptive reference images.Signal Processing:Theories and Applications,1990,5(9):951-954.
[78]M.Boninsegna, A.Bozzoli.A Tunable algorithm to update a reference image. Signal Processing:Image Communication,2000,16(4):353-365.
[79]A.Lai, N.Yung.A fast and accurate Scoreboard algorithm for estimating stationary backgrounds in an image sequence.Proceedings of IEEE International Symposium on Circuits and Systems, 1998,241-244.
[80]R.Cucchiara, C.Grana,M.Piccardi,et al.Statistic and knowledge-based moving object detection in traffic scenes.Proceedings of IEEE Intelligent Transportation Systems,2000.27-32.
[81]Y.K.Jung, Y.S.Ho.Traffic parameter extraction using video-based vehicle tracking.Proceedings of IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems,1999.764-769.
[82]C.Stauffer, W.Eric L.Grimson.Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[83]C.Jiang and M.O.Ward, shadow identification[J],Proceedings of IEEE Int'Conference on Computer Vision and Pattern Recognition.1992.606—612.
[84]Stauffer C,Grimson W.E.L.,"Adaptive background mixture models for real-time tracking"in Proceeding,1999 IEEE Computer Society Conference on Compute Vision and Pattern Recognition,IEEE Comput.Soc.Part Vol.2.1999.
[85]史忠科,曹力.交通检图像检测与分析,科学出版社,2007年.
[86]邓聚龙.灰预测与灰决策。武汉：华中科技大学出版社,2002.9.
[87]袁基炜,史忠科.一种基于灰色预测模型GM(1,1)的运动车辆跟踪方法,控制与决策,2006,21(3)：300-304.
[88]Milan Sonka, Vaclav Hlavac, Roger Boyl.艾海舟,武勃等译,图像处理、分析与机器视觉(第二版),北京：人民邮电出版社,2003.