基于视频序列图像的运动目标检测与跟踪
摘要
本文重点研究了目前运动目标检测与跟踪领域的一些常用方法,以数字图像处理技术和数字信号处理理论为基础,利用DirectShow构建了一个数字图像采集系统,根据实际应用情况编制了运动目标检测与跟踪实验软件,为运动检测与跟踪提供了算法实验平台和优化了硬件设计方案。
在运动目标检测方面,主要研究了帧间差分、背景差分和光流场的方法。本文根据所处理视频图像相邻帧具有相关性的特点,采用了帧间差分目标检测方法。在差分图像之前,先对图像进行滤波和平滑等降噪处理,再进行相邻帧差分以得到运动信息。在背景差分方法中设计了统计平均法及其改进型、中值滤波法、单高斯和多高斯混合模型法提取背景,针对不同复杂程度的背景使用不同的方法可以获得不同的效果。在介绍光流基本原理的基础上,提出了适合计算机快速运算的光流方程迭代解法。对检测目标灰度图像采用了直方图、最大熵、最大类间方差及自适应法多种阈值分割方法,将灰度图像转化成黑白二值图像。对目标粗糙的边缘轮廓和背景进行了数学形态学滤波,较好的除去背景噪声、提取目标轮廓,采用了投影法确定目标的位置和大小。提出了一种操作简便、运算速度快、检测精度高、易于移植到硬件实现的算法流程。
在运动目标跟踪方面,本文详细研究了相关匹配的ABS、SSDA、规一化和金字塔分层匹配算法,针对多点相关跟踪算法运算量大、实时性差的缺点,构建了一种改进的自适应阈值序列的SSDA模型。对模板在图像中按螺旋方式从中心向外遍历,并且只将对应二值化模板图像中像素值为1的像素参与匹配计算,使得匹配运算点完全集中在目标像素上,减少了计算量、提高了匹配精度和速度,同时采用模板尺寸修正及动态模板更新的方法,保证了跟踪的准确性。还研究了粒子滤波、卡尔曼预测确定运动目标下一预定位置,使用彩色直方图特征匹配进行确认,通过实验进行了分析比较。提出差分检测与主动轮廓跟踪相结合的方法,减少了计算迭代次数、提高了计算速度。
最后,对所研究算法进行了合理规化、优化建模,使用C++语言结合DirectShow组件,在Window XP环境的Visual Studio 2005平台上开发了基于视频序列图像运动目标检测与跟踪系统。通过该系统对研究场景进行实验,可以在算法的可靠性和实时性上得到量化比较结果,为设计应用系统提供了捷径。
The thesis research some techniques which is common in the area of moving object detection and tracking recently.By using DirectShow.a digital image sampling system has been built on the basis of digital image and digital signal processing theory.A software using for detection and tracking objects experimental is developped according practical application,that provide a playform for testing algorithms and optimize hardware designing solution for moving detection and tracking.
On moving object detection,main concern is consecutive frames difference、background difference and optical flow.Image is enhanced using fliter and smoothing forreducing noise before image difference.On background difference,the methods of statistical average、median filter、single Gaussian model and mixture Gaussian model arc designed to extracting the background.For various complexity background using different methods to getting different results.On describing basic principle of optical flow,provided an iterative algorithm for solution of optical flow equation,which is fitting for computer highspeed caculating.For gray image of moving object detection and transforming it to binary image,involved many threshold segmentation method such as histogram、maximum entropy、maximum between-cluster variance and adaptivemethod.Mathematical morphological filter is done to rough edges of object and back-ground efficiently reduced the background noise and extracted object contour.Using projection method to determine the location and size of object.A algorithm flow whichis simple and convenient for operating high-speed high quality of detecting precision and easily transplant for hardware implementation is presented.
On the motion tracking,correlation matching algorithm such as ABS,SSDA, nor-malization and pyramid delaminating matching are deeply studied in the thesis.Due to large computing of multiple point correlation tracking algorithm and bad realtime capability, an improved SSDA model on adaptive threshold sequence is constructed.Template moves in a spiral mode from center of the image to the outward,pixel in the corresponding binary template whose value is 1 is calculated and make matching operational points concentrate on object pixels,thus it reduces caculation and improvesmatching precision and speed.Also it guarantees the accuracy by using the method of dimension correction on template and dynamic template updating.In addition,particlefilter and kalman predietion are studied to determine the expected position about moving object,color histogram feature matehing is introduced to make confirmation,then analysis and comparison are obained through experiment.A method on differential detection combined with active contour tracking is presented,which reduces iteration times and improves calculation speed.
Finally,it does reasonable planning and optimization modeling to the algorithm.Byusing c++ language combined with DireelShow component,a system based on video sequence image moving target detection and tracking is developed on Visual Studio 2005 platform in Window XP enviroment.By experiment of the research,we can getquantization of the algorithm in respect of relability and realtime,simultaneous,a shortcut is provided to design application system.
在运动目标检测方面,主要研究了帧间差分、背景差分和光流场的方法。本文根据所处理视频图像相邻帧具有相关性的特点,采用了帧间差分目标检测方法。在差分图像之前,先对图像进行滤波和平滑等降噪处理,再进行相邻帧差分以得到运动信息。在背景差分方法中设计了统计平均法及其改进型、中值滤波法、单高斯和多高斯混合模型法提取背景,针对不同复杂程度的背景使用不同的方法可以获得不同的效果。在介绍光流基本原理的基础上,提出了适合计算机快速运算的光流方程迭代解法。对检测目标灰度图像采用了直方图、最大熵、最大类间方差及自适应法多种阈值分割方法,将灰度图像转化成黑白二值图像。对目标粗糙的边缘轮廓和背景进行了数学形态学滤波,较好的除去背景噪声、提取目标轮廓,采用了投影法确定目标的位置和大小。提出了一种操作简便、运算速度快、检测精度高、易于移植到硬件实现的算法流程。
在运动目标跟踪方面,本文详细研究了相关匹配的ABS、SSDA、规一化和金字塔分层匹配算法,针对多点相关跟踪算法运算量大、实时性差的缺点,构建了一种改进的自适应阈值序列的SSDA模型。对模板在图像中按螺旋方式从中心向外遍历,并且只将对应二值化模板图像中像素值为1的像素参与匹配计算,使得匹配运算点完全集中在目标像素上,减少了计算量、提高了匹配精度和速度,同时采用模板尺寸修正及动态模板更新的方法,保证了跟踪的准确性。还研究了粒子滤波、卡尔曼预测确定运动目标下一预定位置,使用彩色直方图特征匹配进行确认,通过实验进行了分析比较。提出差分检测与主动轮廓跟踪相结合的方法,减少了计算迭代次数、提高了计算速度。
最后,对所研究算法进行了合理规化、优化建模,使用C++语言结合DirectShow组件,在Window XP环境的Visual Studio 2005平台上开发了基于视频序列图像运动目标检测与跟踪系统。通过该系统对研究场景进行实验,可以在算法的可靠性和实时性上得到量化比较结果,为设计应用系统提供了捷径。
The thesis research some techniques which is common in the area of moving object detection and tracking recently.By using DirectShow.a digital image sampling system has been built on the basis of digital image and digital signal processing theory.A software using for detection and tracking objects experimental is developped according practical application,that provide a playform for testing algorithms and optimize hardware designing solution for moving detection and tracking.
On moving object detection,main concern is consecutive frames difference、background difference and optical flow.Image is enhanced using fliter and smoothing forreducing noise before image difference.On background difference,the methods of statistical average、median filter、single Gaussian model and mixture Gaussian model arc designed to extracting the background.For various complexity background using different methods to getting different results.On describing basic principle of optical flow,provided an iterative algorithm for solution of optical flow equation,which is fitting for computer highspeed caculating.For gray image of moving object detection and transforming it to binary image,involved many threshold segmentation method such as histogram、maximum entropy、maximum between-cluster variance and adaptivemethod.Mathematical morphological filter is done to rough edges of object and back-ground efficiently reduced the background noise and extracted object contour.Using projection method to determine the location and size of object.A algorithm flow whichis simple and convenient for operating high-speed high quality of detecting precision and easily transplant for hardware implementation is presented.
On the motion tracking,correlation matching algorithm such as ABS,SSDA, nor-malization and pyramid delaminating matching are deeply studied in the thesis.Due to large computing of multiple point correlation tracking algorithm and bad realtime capability, an improved SSDA model on adaptive threshold sequence is constructed.Template moves in a spiral mode from center of the image to the outward,pixel in the corresponding binary template whose value is 1 is calculated and make matching operational points concentrate on object pixels,thus it reduces caculation and improvesmatching precision and speed.Also it guarantees the accuracy by using the method of dimension correction on template and dynamic template updating.In addition,particlefilter and kalman predietion are studied to determine the expected position about moving object,color histogram feature matehing is introduced to make confirmation,then analysis and comparison are obained through experiment.A method on differential detection combined with active contour tracking is presented,which reduces iteration times and improves calculation speed.
Finally,it does reasonable planning and optimization modeling to the algorithm.Byusing c++ language combined with DireelShow component,a system based on video sequence image moving target detection and tracking is developed on Visual Studio 2005 platform in Window XP enviroment.By experiment of the research,we can getquantization of the algorithm in respect of relability and realtime,simultaneous,a shortcut is provided to design application system.
引文
[1]胡家升.光学工程导论(第二版).大连:大连理工大学出版社,2005.
[2]James A.Ratches,C.P.Walters,Rudolf G.Buser et al.Aided and automatic target recognition based upon sensory inputs from image forming systems.IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(9):1004-1019.
[3]Collins R,Lipton A,Kanade T et al.A system for video surveillance and monitoring.Report CMU-RI-TR-00-12,Robotics Institute,Carnegie Mellon University,May,2000.
[4]Smith E,Richards C A.Visual tracking for intelligent vehicle-highway systems.IEEE Transactions on Vehicular Technology.1996,45(4):744-758.
[5]Gibert A.L.A real-time video tracking system.IEEE Transaction on Pattern Analysisand Machine Intelligence.1980,4:3-20.
[6]杨宜禾,周维真.成像跟踪技术导论.西安:西安电子科技大学出版社,1992.
[7]陈伟.智能交通图像识别系统的研究:(硕士学位论文).杭州:浙江大学,2002.
[8]田晓冬,赵海啸,孙运达.基于视觉的目标提取方法综述.网络通讯与安全.2007,27(3):361-364.
[9]段德军,向健勇,孙勃.基于FPGA的实时图像跟踪系统.红外技术.2004,26(5):58-61.
[10]L.Wang,W.M.Hu,T.N.Tan.Recent developments in human motion analysis.Pattern Cognition.2003,36(3):585-601.
[11]万缨,韩毅,卢汉青.运动目标检测算法的探讨.计算机仿真.2006,23(10):221-226.
[12]Needham C J,Boyle R D.Tracking multiple sports players through occlusion.Congestion and Scale.In British Machine Vision Conference,2001,1:93-102.
[13]Elgammal A,Harwood D,Davis L.Non-parametric model for background subtraction.In European Conference on Computer Vision,2000:751-767.
[14]林洪文,姚作梁,涂丹筹.基于减背景技术的运动目标检测方法研究.国防科技大学学报.2003,25(3):66-69.
[15]代科学,李国辉,涂丹等.监控视频运动目标检测减背景技术研究现状与展望.中国图象图形学报.2006,11(7):917-919.
[16]Horn B K P,Schunck B G.Determining optical flow.Artificial Intelligence.1981,17(10):185-203.
[17]李金宗,原磊,李冬冬.一种基于特征光流检测的运动目标跟踪方法.系统工程与电子技术.2005,27(3):422-426.
[18]黄士科,陶琳,第大序.一种改进的基于光流的运动目标检测方法.华中科技大学学报.2005,33(5):39-41.
[19]KIMJB,KIM HJ.Efficient region-based motion segmentation for a video monitoring system.Pattern Recognition Letters.2003,24(1-3):113-128.
[20]杨威,张田文.复杂景物环境下运动目标检测的新方法.计算机研究与发 展.1998,35(8):724-728.
[21]Stauffer C,Grimson W.Learning patterns of activity using real-time tracking,IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(8):747-757.
[22]刘洁,张东来.关于自适应高斯混合背景模型的更新算法的研究.微计算机信息.2006,22(22):241-242.
[23]M.Kass,A.Witkin,D.Terzopoulos.Snakes:Active contour models.In Proceedings of the 1st international Conference on Computer Vision.London:IEEE computer Society Perss,1987.
[24]Williams D J,Shah M.A fast algorithm for active contours and curvature estimat ion.Graphics and Image Processing.1992,55(1):14-26.
[25]Canny J.A computational approach to edge del et ion.IEEE Transations on Patten Analysis and Machisis and Machine Intelligence.1986,8(6):679-698.
[26]Ba-Ngu Vo,Sumeetpal Singh,Arnaud Doucet.Sequential monte carlo implementation of the Phd filter for multi-target tracking,ISIF.2003:792-799.
[27]Caifeng Shan,Yucheng Wei,Tieniu Tan et al.Real time hand tracking hy combining particle filtering and mean shift.Sixth IEEE International Conference on Automatic Face and Gesture Recognition.2004:669-670.
[28]朱虾等编著.数字图像处理基础.北京:科学出版社,2005.
[29]贾永红.数字图像处理.武汉:武汉大学出版社,2003.
[30]章毓晋.图象处理利分析.北京:清华大学出版社,1999.
[31]Barron J,Fleet D,Beauchemin S.Performance of optical flow techniques.International Journal of Computer Vision.1994,12(1):42-57.
[32]潘石柱,殳伟群,王星.基于自适应背景的实时运动物体检测.计算机应用.2004,24(10):94-96.
[33]Hanzi Wang,David Suter.A consensus-based method for tracking:Modelling backgrounds cenario and foreground appearance.Pattern Recognition.2007,40(4):1091-1105.
[34]K.P.Karmann,A.Brandt.Moving object recognition using an adaptive background memory.In:Ⅴ.Cappellini(Ed.).Time-Varying Image Processing and Moving Object Recogni-tion.The Netherlands Amsterdam:Elsevier,1990,2.
[35]C.StauOer,W.Grimson.Adaptive background mixture models for realtime tracking.Proceedings of the IEEE CS Conference on Computer Vision and Pattern Recognition.1999,2(1):246-252.
[36]S.Arseneau,J.R.Cooperstock.Real-time image segmentation for action recognition.Proceedings of the IEEE PaciAc Rim Conference on Communications,Computers and Signal Processing.1999:86-89.
[37]A.Elgammal,D.Harwood,L.S.David.Non-parametric hackground model for background subtraction.Proceedings of the Sixth European Conference on Computer Vision.2000.
[38]C.Eveland,K.Konolige,R.Bones.Background Modeling for segmentation of videorate stereo sequences.Proc.CVPR' 98.1998.
[39]C.Stauffer,W,E.L.Grimson.Learning patterns of activity using real-time tracking.IEEE Trans.on PAMI.2000,22(8):747-757.
[40]I.Pavlidis,V.Morellas,P.Tsiamyrtzis et al.Urban surveillance systems:From the laboratory to the commercial world.Proceedings of the IEEE.2001,89(10):1478-1497.
[41]Udupa,Jayaram K,LeBlanc et al.A framework for evaluating image segmentation algorithms,Computerized Medical Imaging and Graphics,2006,30(2):75-87.
[42]Yang Xuan,Liang Dequn,Yang Hai jun.Edge detection using image feature detector.Signal Processing,1998,ICSP'98.Fourth International Conference on.1998,2:1121-1124.
[43]韩思奇,王蕾.图像分割的阈值法综述.系统工程与电子技术.2002,6(24):91-102.
[44]Otsn N.A threshold selection method from gray-level histogram.IEEE Trans.on SMC-9.1979,9(3):62-66.
[45]杜奇,向键勇,袁胜养.一种改进的最大类间方差法.红外技术.2003,25(5):33-36.
[46]T.Pun.A new method for gray-level picture thresholding using the entropy of the histogam.Signal Processing.1980,2(3):223-237.
[47]侯志强,韩崇昭.视觉跟踪技术综述.自动化学报.2006,32(4):603-617.
[48]Hager G,Belhumeur P.Efficient region tracking with parametric models of geometry and illumination.IEEE Transactions on Pattern Analysis and Machine Intelligence.1998,20(10):1025-1039.
[49]Dorin Comaniciu,Visvanathan Ramesh,Peter Meet,Kernel-based object tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence.2003,24(5):564-577.
[50]江和平,陈洪光,李飚.基于对应像素距离度量的图像匹配跟踪算法.弹道学报.2005,9(17):40-47.
[51]Alabama.Hybrid correlation algorithm-a bridge between feature matching and imagecorrelation.Redstone Arsenal.1979,11.
[52]牛刚,梁伟.基于特征像素统计的图像相关匹配算法.微计算机信息.2005,21(11):103-104.
[53]Jia,Zhen,Balasuriya et al.Target tracking with bayesian fusion based template matching.Proceedings-International Conference on Image Processing.IEEE International Conference on Image Processing 2005.ICIP 2005,2005,2:826-829.
[54]Cho,Jae-Soo,Yun et al.Selective-attention correlation measure for precision videotracking.IEICE Transactions on Information and Systems.2005,E88(5):1041-1049.
[55]张万清.飞航导弹电视导引头.北京:宇航出版社,1994,114-169.
[56]Mohammad Gharavi-Alkhansari.A Fast globally optimal algorithm for template matching using low-resolution pruning.IEEE Trans on Image Processing.2001,10(4):526-533.
[57]薛利军,李白田,李英才.一种基于图像分层的快速相关匹配算法.计算机工程与科学.2006,28(7):65-66.
[58]Hammersley J M,Morton K W.Poor man's monte carlo.Journal of the Royal Statistical Society B.1954,16:23-38.
[59]Gordon N J,Salmond D J,Smith A F M.Novel approach to non-linear/non-gaussian ba-yesian state estimation.IEE Proeeedings-F,1993,140(2):107-113.
[60]Liu J S,Chen R.Sequential monte carlo methods for dynamic systems.Journal of the American Statistical Association.1998,93:1032-1044.
[61]Doucet A,Godsill S,Andrieu C.On sequential monte cario sampling methods for bayesian filtering.Statistics and Computing.2000,10:197-208.
[62]R.V.Merwe,A.Doucet,N.D.Freitas et al.The unscented particle filter.Technical Report Cued/F-INFEN6/TR380.Engineering Department,Cambridge University,200.
[63]Yong Rui,Yunqiang Chen.Better proposal distributions:object tracking using unscented particle filter.Proceedings of Computer Society Conference on Computer Vision and Pattern Recognition.2001,2:8-14.
[64]杨淑莹.图像模式识别.北京:清华大学出版社,2005.
[65]陆宗骐,金登男.Visual C++.NET图像处理编程.北京:清华大学出版社,2006.
[66]钟志光,卢君,刘伟荣.Visual C++.NET数字图像处理实例与解析.北京:清华大学出版社,2003.
[67]陆其明.DirectShow实务精选.北京:科学出版社,2004.
[2]James A.Ratches,C.P.Walters,Rudolf G.Buser et al.Aided and automatic target recognition based upon sensory inputs from image forming systems.IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(9):1004-1019.
[3]Collins R,Lipton A,Kanade T et al.A system for video surveillance and monitoring.Report CMU-RI-TR-00-12,Robotics Institute,Carnegie Mellon University,May,2000.
[4]Smith E,Richards C A.Visual tracking for intelligent vehicle-highway systems.IEEE Transactions on Vehicular Technology.1996,45(4):744-758.
[5]Gibert A.L.A real-time video tracking system.IEEE Transaction on Pattern Analysisand Machine Intelligence.1980,4:3-20.
[6]杨宜禾,周维真.成像跟踪技术导论.西安:西安电子科技大学出版社,1992.
[7]陈伟.智能交通图像识别系统的研究:(硕士学位论文).杭州:浙江大学,2002.
[8]田晓冬,赵海啸,孙运达.基于视觉的目标提取方法综述.网络通讯与安全.2007,27(3):361-364.
[9]段德军,向健勇,孙勃.基于FPGA的实时图像跟踪系统.红外技术.2004,26(5):58-61.
[10]L.Wang,W.M.Hu,T.N.Tan.Recent developments in human motion analysis.Pattern Cognition.2003,36(3):585-601.
[11]万缨,韩毅,卢汉青.运动目标检测算法的探讨.计算机仿真.2006,23(10):221-226.
[12]Needham C J,Boyle R D.Tracking multiple sports players through occlusion.Congestion and Scale.In British Machine Vision Conference,2001,1:93-102.
[13]Elgammal A,Harwood D,Davis L.Non-parametric model for background subtraction.In European Conference on Computer Vision,2000:751-767.
[14]林洪文,姚作梁,涂丹筹.基于减背景技术的运动目标检测方法研究.国防科技大学学报.2003,25(3):66-69.
[15]代科学,李国辉,涂丹等.监控视频运动目标检测减背景技术研究现状与展望.中国图象图形学报.2006,11(7):917-919.
[16]Horn B K P,Schunck B G.Determining optical flow.Artificial Intelligence.1981,17(10):185-203.
[17]李金宗,原磊,李冬冬.一种基于特征光流检测的运动目标跟踪方法.系统工程与电子技术.2005,27(3):422-426.
[18]黄士科,陶琳,第大序.一种改进的基于光流的运动目标检测方法.华中科技大学学报.2005,33(5):39-41.
[19]KIMJB,KIM HJ.Efficient region-based motion segmentation for a video monitoring system.Pattern Recognition Letters.2003,24(1-3):113-128.
[20]杨威,张田文.复杂景物环境下运动目标检测的新方法.计算机研究与发 展.1998,35(8):724-728.
[21]Stauffer C,Grimson W.Learning patterns of activity using real-time tracking,IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(8):747-757.
[22]刘洁,张东来.关于自适应高斯混合背景模型的更新算法的研究.微计算机信息.2006,22(22):241-242.
[23]M.Kass,A.Witkin,D.Terzopoulos.Snakes:Active contour models.In Proceedings of the 1st international Conference on Computer Vision.London:IEEE computer Society Perss,1987.
[24]Williams D J,Shah M.A fast algorithm for active contours and curvature estimat ion.Graphics and Image Processing.1992,55(1):14-26.
[25]Canny J.A computational approach to edge del et ion.IEEE Transations on Patten Analysis and Machisis and Machine Intelligence.1986,8(6):679-698.
[26]Ba-Ngu Vo,Sumeetpal Singh,Arnaud Doucet.Sequential monte carlo implementation of the Phd filter for multi-target tracking,ISIF.2003:792-799.
[27]Caifeng Shan,Yucheng Wei,Tieniu Tan et al.Real time hand tracking hy combining particle filtering and mean shift.Sixth IEEE International Conference on Automatic Face and Gesture Recognition.2004:669-670.
[28]朱虾等编著.数字图像处理基础.北京:科学出版社,2005.
[29]贾永红.数字图像处理.武汉:武汉大学出版社,2003.
[30]章毓晋.图象处理利分析.北京:清华大学出版社,1999.
[31]Barron J,Fleet D,Beauchemin S.Performance of optical flow techniques.International Journal of Computer Vision.1994,12(1):42-57.
[32]潘石柱,殳伟群,王星.基于自适应背景的实时运动物体检测.计算机应用.2004,24(10):94-96.
[33]Hanzi Wang,David Suter.A consensus-based method for tracking:Modelling backgrounds cenario and foreground appearance.Pattern Recognition.2007,40(4):1091-1105.
[34]K.P.Karmann,A.Brandt.Moving object recognition using an adaptive background memory.In:Ⅴ.Cappellini(Ed.).Time-Varying Image Processing and Moving Object Recogni-tion.The Netherlands Amsterdam:Elsevier,1990,2.
[35]C.StauOer,W.Grimson.Adaptive background mixture models for realtime tracking.Proceedings of the IEEE CS Conference on Computer Vision and Pattern Recognition.1999,2(1):246-252.
[36]S.Arseneau,J.R.Cooperstock.Real-time image segmentation for action recognition.Proceedings of the IEEE PaciAc Rim Conference on Communications,Computers and Signal Processing.1999:86-89.
[37]A.Elgammal,D.Harwood,L.S.David.Non-parametric hackground model for background subtraction.Proceedings of the Sixth European Conference on Computer Vision.2000.
[38]C.Eveland,K.Konolige,R.Bones.Background Modeling for segmentation of videorate stereo sequences.Proc.CVPR' 98.1998.
[39]C.Stauffer,W,E.L.Grimson.Learning patterns of activity using real-time tracking.IEEE Trans.on PAMI.2000,22(8):747-757.
[40]I.Pavlidis,V.Morellas,P.Tsiamyrtzis et al.Urban surveillance systems:From the laboratory to the commercial world.Proceedings of the IEEE.2001,89(10):1478-1497.
[41]Udupa,Jayaram K,LeBlanc et al.A framework for evaluating image segmentation algorithms,Computerized Medical Imaging and Graphics,2006,30(2):75-87.
[42]Yang Xuan,Liang Dequn,Yang Hai jun.Edge detection using image feature detector.Signal Processing,1998,ICSP'98.Fourth International Conference on.1998,2:1121-1124.
[43]韩思奇,王蕾.图像分割的阈值法综述.系统工程与电子技术.2002,6(24):91-102.
[44]Otsn N.A threshold selection method from gray-level histogram.IEEE Trans.on SMC-9.1979,9(3):62-66.
[45]杜奇,向键勇,袁胜养.一种改进的最大类间方差法.红外技术.2003,25(5):33-36.
[46]T.Pun.A new method for gray-level picture thresholding using the entropy of the histogam.Signal Processing.1980,2(3):223-237.
[47]侯志强,韩崇昭.视觉跟踪技术综述.自动化学报.2006,32(4):603-617.
[48]Hager G,Belhumeur P.Efficient region tracking with parametric models of geometry and illumination.IEEE Transactions on Pattern Analysis and Machine Intelligence.1998,20(10):1025-1039.
[49]Dorin Comaniciu,Visvanathan Ramesh,Peter Meet,Kernel-based object tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence.2003,24(5):564-577.
[50]江和平,陈洪光,李飚.基于对应像素距离度量的图像匹配跟踪算法.弹道学报.2005,9(17):40-47.
[51]Alabama.Hybrid correlation algorithm-a bridge between feature matching and imagecorrelation.Redstone Arsenal.1979,11.
[52]牛刚,梁伟.基于特征像素统计的图像相关匹配算法.微计算机信息.2005,21(11):103-104.
[53]Jia,Zhen,Balasuriya et al.Target tracking with bayesian fusion based template matching.Proceedings-International Conference on Image Processing.IEEE International Conference on Image Processing 2005.ICIP 2005,2005,2:826-829.
[54]Cho,Jae-Soo,Yun et al.Selective-attention correlation measure for precision videotracking.IEICE Transactions on Information and Systems.2005,E88(5):1041-1049.
[55]张万清.飞航导弹电视导引头.北京:宇航出版社,1994,114-169.
[56]Mohammad Gharavi-Alkhansari.A Fast globally optimal algorithm for template matching using low-resolution pruning.IEEE Trans on Image Processing.2001,10(4):526-533.
[57]薛利军,李白田,李英才.一种基于图像分层的快速相关匹配算法.计算机工程与科学.2006,28(7):65-66.
[58]Hammersley J M,Morton K W.Poor man's monte carlo.Journal of the Royal Statistical Society B.1954,16:23-38.
[59]Gordon N J,Salmond D J,Smith A F M.Novel approach to non-linear/non-gaussian ba-yesian state estimation.IEE Proeeedings-F,1993,140(2):107-113.
[60]Liu J S,Chen R.Sequential monte carlo methods for dynamic systems.Journal of the American Statistical Association.1998,93:1032-1044.
[61]Doucet A,Godsill S,Andrieu C.On sequential monte cario sampling methods for bayesian filtering.Statistics and Computing.2000,10:197-208.
[62]R.V.Merwe,A.Doucet,N.D.Freitas et al.The unscented particle filter.Technical Report Cued/F-INFEN6/TR380.Engineering Department,Cambridge University,200.
[63]Yong Rui,Yunqiang Chen.Better proposal distributions:object tracking using unscented particle filter.Proceedings of Computer Society Conference on Computer Vision and Pattern Recognition.2001,2:8-14.
[64]杨淑莹.图像模式识别.北京:清华大学出版社,2005.
[65]陆宗骐,金登男.Visual C++.NET图像处理编程.北京:清华大学出版社,2006.
[66]钟志光,卢君,刘伟荣.Visual C++.NET数字图像处理实例与解析.北京:清华大学出版社,2003.
[67]陆其明.DirectShow实务精选.北京:科学出版社,2004.