双摄像机智能视频监控系统设计与实现
|
摘要
视频监控系统以其直观、方便、信息内容丰富的特点已成为各行各业安全防范系统的重要组成部分。本文针对目前视频监控系统对智能化、可靠性越来越高的要求,设计并构建了由一个全景摄像机和一个跟踪摄像机构成的双摄像机智能视频监控系统,并主要针对视频监控中常见的摄像机配准技术和运动目标跟踪技术两个方面进行了研究。
在摄像机配准方面,本文采用了基于图像匹配的方法。由于双摄像机观测到的图像之间存在着平移、旋转、尺度等变化对图像配准造成的困难,本文提出了使用基于尺度不变特征的SIFT(Scale Invariant Feature Transform)算法来进行摄像机配准的方法。在详细研究了算法的原理及实现过程后,通过实验寻找到匹配过程中的合适参数设置并验证了其在双摄像机配准上的可行性。
在视频目标跟踪方面,针对目标在场景中易被遮挡、丢失,监控系统的实时性、动背景等常见的问题,在详细研究了帧差混合算法以及基于颜色直方图的粒子滤波算法的原理及实现过程后,本文将帧差混合算法和粒子滤波算法结合使用,提出了一种稳健的视频目标跟踪方法并通过了实验的验证。
最后本文使用了VC++、OpenCV库和DirectShow的相关技术并结合软件工程设计中常用的白盒测试和黑盒测试法,完成了整个双摄像机视频监控系统平台的构建。
Video surveillance has become an important component in the Security fields because of its distinctive feature such as visualization, convenience and rich information. In view of the increasing requirements of intelligence and reliability in the current video surveillance, this paper designs and constructs a dual-camera intelligent video surveillance system which composed by a full-view-camera and a tracking-camera. A research has been made mainly focus on the two aspects of video surveillance, which are camera registration and moving-target tracking technology.
In the aspect of camera registration, this paper uses an image matching method, because of the existence of the translation, rotation, scale and other changes, the thesis proposes a method of camera registration based on the use of Scale-Invariant Features Transform(SIFT) algorithm. After a detailed research in the principle and process of the algorithm, suitable parameter settings are found in the match process through the experiments and its feasibility on the dual-camera registration is verified.
In the aspect of video tracking, in view of common problems, such as the target in the scene easily obscured, lost, the real-time demand of surveillance system, moving background, after a detailed research in the conterminous frames differencing algorithm and an adaptive color-based Particle Filter tracking algorithm, the thesis proposes a method by combining the two algorithms. The simulation results show that the method is rather robust.
Finally, a framework of video surveillance system has been developed on the platform of Visual C++, with OpenCV library and DirectShow technology. In the process of constructing system, White-Box testing and Black-Box testing were used to debug the program.
在摄像机配准方面,本文采用了基于图像匹配的方法。由于双摄像机观测到的图像之间存在着平移、旋转、尺度等变化对图像配准造成的困难,本文提出了使用基于尺度不变特征的SIFT(Scale Invariant Feature Transform)算法来进行摄像机配准的方法。在详细研究了算法的原理及实现过程后,通过实验寻找到匹配过程中的合适参数设置并验证了其在双摄像机配准上的可行性。
在视频目标跟踪方面,针对目标在场景中易被遮挡、丢失,监控系统的实时性、动背景等常见的问题,在详细研究了帧差混合算法以及基于颜色直方图的粒子滤波算法的原理及实现过程后,本文将帧差混合算法和粒子滤波算法结合使用,提出了一种稳健的视频目标跟踪方法并通过了实验的验证。
最后本文使用了VC++、OpenCV库和DirectShow的相关技术并结合软件工程设计中常用的白盒测试和黑盒测试法,完成了整个双摄像机视频监控系统平台的构建。
Video surveillance has become an important component in the Security fields because of its distinctive feature such as visualization, convenience and rich information. In view of the increasing requirements of intelligence and reliability in the current video surveillance, this paper designs and constructs a dual-camera intelligent video surveillance system which composed by a full-view-camera and a tracking-camera. A research has been made mainly focus on the two aspects of video surveillance, which are camera registration and moving-target tracking technology.
In the aspect of camera registration, this paper uses an image matching method, because of the existence of the translation, rotation, scale and other changes, the thesis proposes a method of camera registration based on the use of Scale-Invariant Features Transform(SIFT) algorithm. After a detailed research in the principle and process of the algorithm, suitable parameter settings are found in the match process through the experiments and its feasibility on the dual-camera registration is verified.
In the aspect of video tracking, in view of common problems, such as the target in the scene easily obscured, lost, the real-time demand of surveillance system, moving background, after a detailed research in the conterminous frames differencing algorithm and an adaptive color-based Particle Filter tracking algorithm, the thesis proposes a method by combining the two algorithms. The simulation results show that the method is rather robust.
Finally, a framework of video surveillance system has been developed on the platform of Visual C++, with OpenCV library and DirectShow technology. In the process of constructing system, White-Box testing and Black-Box testing were used to debug the program.
引文
[1]宋磊等.视频监控系统概述[J].测控技术,2003 Vol.5:33-35
[2]王莹莹.智能视频监控粉墨登场.中国计算机用户.2006 Vol.10:40-41
[3]智能视觉监控技术的研究.http://www.zhineng.com.cn/Html/2007-04-08/7121.shtml
[4]交通场景的车辆定位与跟踪.hnp://www.jhsafe.com/safe/anicle
[5]IBM T.J.Watson Research Center.IBM Smart Surveillance System(S3):An open and extensible architecture for smart video surveillance,http://research.microsoft.com/iccv2005/demo/IBM_S3/IBMS3_ICCV05Demo.PDF
[6]Grady Booth,James Rumbaugh,Ivar Jacobson.The Unified Modeling Language User Guide,Second Edition.Addison-Wesley.2005
[7]高岩,李新.利用UML对基于3G的车辆监控系统的建模.厦门大学学报,2005Vol.44:294-297
[8]刘晓华等.UML基础及Visio建模.电子工业出版社,2004
[9]林立春 林琼麒等.PLC串口通信的MSComm与API实现.第八届工业仪表与自动化学术会议,2007,192-196
[10]王海红 李万山等.利用MSComm控件实现微机与GPS-OEM板的串口通信.中国控制与决策学术年会论文集,2000,876-879
[11]许宏竹.基于DirectShow的流媒体的应用和研究.北京邮电大学硕士研究生学位论文,2007
[12]黄颖.基于DirectShow的视频播放系统研究与实现.华中科技大学硕士学位论文,2006
[13]Jeffrey S.Beis,David G.Lowe.Shape Indexing Using Approximate Nearest-Neighbour Search in High-DimensionalSpaces.Proceedings of the IEEE 1997 Computer Society Conference on Computer Vision and Pattem Recognition,1997,1000-1006
[14]David G.Lowe.Distinctive Image Features from Scale-Invariant Keypoints.Intemational Journal of Computer Vision 60,2004,91-110
[15]杨广林 孔令富等.双摄像机系统对移动目标的跟踪.机器人Vol.29:2007.3,133-139
[16]王军 张明柱.图像匹配算法的研究进展.大气与环境光学学报.Vol.2:2007.1,11-15
[17]王国美 陈孝威.SIFT特征匹配算法研究.盐城工学院学报,Vol.20:2007.6,1-10
[18]Jason Meltzer,Ming-Hsuan Yang,Rakesh Gupta,Multiple view feature descriptors from image sequences via kernel principal component analysis[J],ECCV(1),2004:215-227
[19]Badenas J.,Pla F.,Sanchiz JM.Motion-based segmentation and region tracking in image sequences[J].Pattern Recognition,2001,34(3):661-670
[20]Jae-Soo Lee,Jung-Hwan Ko,Eun-Soo Kim,Real-time stereo object tracking system by using block matching algorithm and optical binary phase extraction joint transform correlator[J].Optics Communications,2001,191:191-202
[21]Frederic Dambreville.Jean-Pierre Le Cadre.Spatio-temporal multi-mode information management for moving target detection[J].Information Fusion.2004,5(3):169-178
[22]J.Barron,D.Fleet,and S.Beauchemin,"Performance of Optical Flow Techniques",International Journal of Computer Vision,Vol.12,No.1,pp.42-77,1994
[23]N.Ohta and K.Kanatani,"Moving object detection from optical flow without empirical thresholds",IEICE Transactions on Information and Systems,Vol.E81-D,No.2,pp.243-245.1998
[24]S.Yamamoto,Y.Mac,Y.Shirai,J.Miura,"Realtime multiple object tracking based on optical flows",Robotics and Automation,1995.Proceedings,1995 IEEE International Conference on,Vol.3,pp.2328-2333,21-27 May 1995
[25]Y.Z.Hsu,H.H.Nagel,and G.Rebers,"New Likelihood Test Methods for Change Detection in Image Sequence",Computer Vision,Graphics,and Image Processing,Vol.26,pp.73-106,1984
[26]P.L.Rosin and T.Ellis,"Image Difference Threshold Strategies and Shadow Detection",In Processing of the British Machine Vision Conference,pp.347-356,1995
[27]叶中付,李厚强等.一种基于高阶累积量的运动目标检测新方法,计算机工程与应用,No.18,PP.102-105,2002
[28]K.Toyama,J.Krumm,B.Brurnitt,and B.Meyers,"Wallflower:Principles and practice of background",Image Analysis and Processing,2001.Proceeding 11th International Conference on,pp.78-83,Sep 2001
[29]Ying Ren,Chin-Seng Chua,Yeong-Khing Ho,"Motion detection with non-stationary background",Image Analysis and Processing,2001.Proceedings.11th International Conference on,pp.78-83,Sep 2001
[30]Collins R,et al.A system for video surveillance and monitoring:VSAM final report.Carnegie Mellon University's Technical Report.2000
[31]危水根等.一种基于时间差分运动检测的改进方法.南昌航空工业学院学报.2005,3:15-19
[32]YBar2Shalom,X R Li.Estimation and Tracking:Principles,Techniques and Software.Artech House,Boston,MA,1993
[33]Mo Pachter,P R Chandler.Universal Linearization Concept for Extended Kalman filters.IEEE Trans.on Aerospace and Electronic Systems,1993,29(3):946-961
[34]T L Song,J L Speyer.A Stochastic Analysis of a Modified Gain Extended Kalman Filter with Application to Estimation with Beating Only Measurements.IEEE Trans.on Automatic Control,1985,30(10):940-940
[35]A Doucet,S Godsil,and C Andrien.On Sequential Monte Carlo Sampling Methods for Bayesian Filtering.Statistics and Compution,2000,10(3):197-208
[36]www.intel.com/technology/computing/opencv/index.htm
[37]罗志勇,张会汀.基于DirectShow与DMO的视频采集与编码实现.计算机工程.2005,31(14).193-195
[38]刘亚,艾海舟,徐光佑.一种基于背景模型的运动目标检测与跟踪算法.信息与控制.2002,4(31).315-319
[39]刘阳.基于粒子滤波的机器人视觉跟踪研究与实现 大连理工大学硕士学位论文2007
[40]A Doucet,S Godsil,and C Andrien.On Sequential Monte Carlo Sampling Methods for Bayesian Filtering.Statistics and Compution,2000,10(3):197-208
[41]Liu J S,Chen R,Sequential Monte Carlo methods for dynamical systems.Journal of the Naerican Statistical Association,1998,93:1032-1044
[42]Haritaoglu.I.,Harwood,D.,Davis,etc.A real time system for detecting and tracking people[J].Proceedings of Third IEEE Intemational Conference on Automatic Face and Gesture Recognition,1998:222-227
[43]Stringa,E.and Regazzoni,C.S.Real-time video-shot detection for scene surveillance applications[J].IEEE Transactions on Image Processing,2000,9(1):69-79
[44]Toyama,K.,Krumm,J.,Brurnmitt,etc.Wallflower:principles and practice of background maintenance[J].The Proceedings of the Seventh IEEE International Conference on Computer Vision,1999,1:255-261
[45]C.Stauffer,W.Eric,L.Grimson.Learning patterns of activity using real-time tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757
[46]V.Markandey,A.Reid,S.Wang.Motion estimation for moving target detection[J].IEEE Transactions on Aerospace and Electronic Systems,1996,32(3):866-874
[47]Katja Nummiaro,Esther Koller-Meier and Luc Van Gool.A Color-based Particle Filter.First Intemational Workshop on Generative-Model-Based Vision,2002,1:53-60
[48]陈付幸,王润生.基于射影空间的视觉基础矩阵鲁棒估计[J].机器人,2005,27(6):545-549
[49]赵向阳,杜利民.一种全自动稳健的图像拼接融合算法[J].中国图像图形学报,2004,9(4):417-42
[50]陆其明.DirectShow开发指南.清华大学出版社,2003
[51]赵俊.智能视频监控系统关键技术研究.西安电子科技大学硕士学位论文.2007
[52]http://www.open-image.org/
[53]Koichiro D,et al.Object tracking by the mean-shift of regional color distribution combined with the particle-filter algorithm.Proceeding of the 17th International Conference on Pattern Recognition,3:506-509
[54]赵锋伟,李吉成,沈振康.景象匹配技术研究[J]。系统工程与电子技术,2002,24(12):110-113
[55]王红梅,张科,李言俊.图像匹配研究进展[J].计算机工程与应用,2004,19:42-44
[56]李俊山,沈绪榜.图像匹配技术研究[J].微电子学与计算机,2000,2:10-14
[2]王莹莹.智能视频监控粉墨登场.中国计算机用户.2006 Vol.10:40-41
[3]智能视觉监控技术的研究.http://www.zhineng.com.cn/Html/2007-04-08/7121.shtml
[4]交通场景的车辆定位与跟踪.hnp://www.jhsafe.com/safe/anicle
[5]IBM T.J.Watson Research Center.IBM Smart Surveillance System(S3):An open and extensible architecture for smart video surveillance,http://research.microsoft.com/iccv2005/demo/IBM_S3/IBMS3_ICCV05Demo.PDF
[6]Grady Booth,James Rumbaugh,Ivar Jacobson.The Unified Modeling Language User Guide,Second Edition.Addison-Wesley.2005
[7]高岩,李新.利用UML对基于3G的车辆监控系统的建模.厦门大学学报,2005Vol.44:294-297
[8]刘晓华等.UML基础及Visio建模.电子工业出版社,2004
[9]林立春 林琼麒等.PLC串口通信的MSComm与API实现.第八届工业仪表与自动化学术会议,2007,192-196
[10]王海红 李万山等.利用MSComm控件实现微机与GPS-OEM板的串口通信.中国控制与决策学术年会论文集,2000,876-879
[11]许宏竹.基于DirectShow的流媒体的应用和研究.北京邮电大学硕士研究生学位论文,2007
[12]黄颖.基于DirectShow的视频播放系统研究与实现.华中科技大学硕士学位论文,2006
[13]Jeffrey S.Beis,David G.Lowe.Shape Indexing Using Approximate Nearest-Neighbour Search in High-DimensionalSpaces.Proceedings of the IEEE 1997 Computer Society Conference on Computer Vision and Pattem Recognition,1997,1000-1006
[14]David G.Lowe.Distinctive Image Features from Scale-Invariant Keypoints.Intemational Journal of Computer Vision 60,2004,91-110
[15]杨广林 孔令富等.双摄像机系统对移动目标的跟踪.机器人Vol.29:2007.3,133-139
[16]王军 张明柱.图像匹配算法的研究进展.大气与环境光学学报.Vol.2:2007.1,11-15
[17]王国美 陈孝威.SIFT特征匹配算法研究.盐城工学院学报,Vol.20:2007.6,1-10
[18]Jason Meltzer,Ming-Hsuan Yang,Rakesh Gupta,Multiple view feature descriptors from image sequences via kernel principal component analysis[J],ECCV(1),2004:215-227
[19]Badenas J.,Pla F.,Sanchiz JM.Motion-based segmentation and region tracking in image sequences[J].Pattern Recognition,2001,34(3):661-670
[20]Jae-Soo Lee,Jung-Hwan Ko,Eun-Soo Kim,Real-time stereo object tracking system by using block matching algorithm and optical binary phase extraction joint transform correlator[J].Optics Communications,2001,191:191-202
[21]Frederic Dambreville.Jean-Pierre Le Cadre.Spatio-temporal multi-mode information management for moving target detection[J].Information Fusion.2004,5(3):169-178
[22]J.Barron,D.Fleet,and S.Beauchemin,"Performance of Optical Flow Techniques",International Journal of Computer Vision,Vol.12,No.1,pp.42-77,1994
[23]N.Ohta and K.Kanatani,"Moving object detection from optical flow without empirical thresholds",IEICE Transactions on Information and Systems,Vol.E81-D,No.2,pp.243-245.1998
[24]S.Yamamoto,Y.Mac,Y.Shirai,J.Miura,"Realtime multiple object tracking based on optical flows",Robotics and Automation,1995.Proceedings,1995 IEEE International Conference on,Vol.3,pp.2328-2333,21-27 May 1995
[25]Y.Z.Hsu,H.H.Nagel,and G.Rebers,"New Likelihood Test Methods for Change Detection in Image Sequence",Computer Vision,Graphics,and Image Processing,Vol.26,pp.73-106,1984
[26]P.L.Rosin and T.Ellis,"Image Difference Threshold Strategies and Shadow Detection",In Processing of the British Machine Vision Conference,pp.347-356,1995
[27]叶中付,李厚强等.一种基于高阶累积量的运动目标检测新方法,计算机工程与应用,No.18,PP.102-105,2002
[28]K.Toyama,J.Krumm,B.Brurnitt,and B.Meyers,"Wallflower:Principles and practice of background",Image Analysis and Processing,2001.Proceeding 11th International Conference on,pp.78-83,Sep 2001
[29]Ying Ren,Chin-Seng Chua,Yeong-Khing Ho,"Motion detection with non-stationary background",Image Analysis and Processing,2001.Proceedings.11th International Conference on,pp.78-83,Sep 2001
[30]Collins R,et al.A system for video surveillance and monitoring:VSAM final report.Carnegie Mellon University's Technical Report.2000
[31]危水根等.一种基于时间差分运动检测的改进方法.南昌航空工业学院学报.2005,3:15-19
[32]YBar2Shalom,X R Li.Estimation and Tracking:Principles,Techniques and Software.Artech House,Boston,MA,1993
[33]Mo Pachter,P R Chandler.Universal Linearization Concept for Extended Kalman filters.IEEE Trans.on Aerospace and Electronic Systems,1993,29(3):946-961
[34]T L Song,J L Speyer.A Stochastic Analysis of a Modified Gain Extended Kalman Filter with Application to Estimation with Beating Only Measurements.IEEE Trans.on Automatic Control,1985,30(10):940-940
[35]A Doucet,S Godsil,and C Andrien.On Sequential Monte Carlo Sampling Methods for Bayesian Filtering.Statistics and Compution,2000,10(3):197-208
[36]www.intel.com/technology/computing/opencv/index.htm
[37]罗志勇,张会汀.基于DirectShow与DMO的视频采集与编码实现.计算机工程.2005,31(14).193-195
[38]刘亚,艾海舟,徐光佑.一种基于背景模型的运动目标检测与跟踪算法.信息与控制.2002,4(31).315-319
[39]刘阳.基于粒子滤波的机器人视觉跟踪研究与实现 大连理工大学硕士学位论文2007
[40]A Doucet,S Godsil,and C Andrien.On Sequential Monte Carlo Sampling Methods for Bayesian Filtering.Statistics and Compution,2000,10(3):197-208
[41]Liu J S,Chen R,Sequential Monte Carlo methods for dynamical systems.Journal of the Naerican Statistical Association,1998,93:1032-1044
[42]Haritaoglu.I.,Harwood,D.,Davis,etc.A real time system for detecting and tracking people[J].Proceedings of Third IEEE Intemational Conference on Automatic Face and Gesture Recognition,1998:222-227
[43]Stringa,E.and Regazzoni,C.S.Real-time video-shot detection for scene surveillance applications[J].IEEE Transactions on Image Processing,2000,9(1):69-79
[44]Toyama,K.,Krumm,J.,Brurnmitt,etc.Wallflower:principles and practice of background maintenance[J].The Proceedings of the Seventh IEEE International Conference on Computer Vision,1999,1:255-261
[45]C.Stauffer,W.Eric,L.Grimson.Learning patterns of activity using real-time tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757
[46]V.Markandey,A.Reid,S.Wang.Motion estimation for moving target detection[J].IEEE Transactions on Aerospace and Electronic Systems,1996,32(3):866-874
[47]Katja Nummiaro,Esther Koller-Meier and Luc Van Gool.A Color-based Particle Filter.First Intemational Workshop on Generative-Model-Based Vision,2002,1:53-60
[48]陈付幸,王润生.基于射影空间的视觉基础矩阵鲁棒估计[J].机器人,2005,27(6):545-549
[49]赵向阳,杜利民.一种全自动稳健的图像拼接融合算法[J].中国图像图形学报,2004,9(4):417-42
[50]陆其明.DirectShow开发指南.清华大学出版社,2003
[51]赵俊.智能视频监控系统关键技术研究.西安电子科技大学硕士学位论文.2007
[52]http://www.open-image.org/
[53]Koichiro D,et al.Object tracking by the mean-shift of regional color distribution combined with the particle-filter algorithm.Proceeding of the 17th International Conference on Pattern Recognition,3:506-509
[54]赵锋伟,李吉成,沈振康.景象匹配技术研究[J]。系统工程与电子技术,2002,24(12):110-113
[55]王红梅,张科,李言俊.图像匹配研究进展[J].计算机工程与应用,2004,19:42-44
[56]李俊山,沈绪榜.图像匹配技术研究[J].微电子学与计算机,2000,2:10-14