摘要
视觉信息是典型的非接触式传感信息。基于视觉信息的目标跟踪可以在不干涉观测目标,不对观测目标造成影响的前提下实现期望的功能。基于视觉信息的复杂环境中特定/非特定运动目标的可靠检测与鲁棒跟踪是当前备受关注的前沿方向。在实际应用中,观测数据集常含有大量离群数据,这就要求跟踪方法必须具有一定的鲁棒性。鲁棒性是跟踪算法实用化的前提。随着计算机硬件技术的发展,跟踪算法的实时性问题越来越多的依赖硬件方案解决;跟踪任务的核心问题,就是如何增强对各种应用环境和各种干扰因素的鲁棒性。研究如何提高复杂自然环境下运动目标检测与跟踪过程中的鲁棒性,不仅有助于实现和推广视觉信息的智能化自动处理,提升下一代移动机器人的智能行为,还将进一步推进人们对于生物视觉认知特性本身的认识。
本文从鲁棒性需求、鲁棒性描述、鲁棒性处理策略和鲁棒的跟踪算法设计与评估的角度对基于视觉信息的运动目标跟踪任务进行研究。分别从鲁棒统计学和生物认知特性出发,针对目标跟踪任务不同环节——背景建模和背景抑制、运动估计和运动跟踪、目标跟踪——中的不同鲁棒性需求,对传统的鲁棒估计子进行改进,提出新的跟踪策略和实现算法。实验表明,这些方法与现有的算法相比,在效率、精度、鲁棒性等方面都具有一定优势。
文章的主要工作和贡献如下:
(1)首先阐述鲁棒估计的基本含义和基本理论,介绍鲁棒统计学中关于估计子鲁棒性的几个关键概念——离群数据、溃点和影响函数,着重讨论本文使用的几种鲁棒估计子——中位数估计子、RASNAC估计子、M估计子——的基本原理和各自的优缺点;然后分析非参数化估计方法与鲁棒估计之间的本质联系,介绍几种典型的非参数估计方法,着重分析基于核密度估计的Mean-Shift的性能和收敛性,并给出了实验验证。
(2)以背景建模任务为示例,分析不同应用条件下的背景建模任务的鲁棒性需求,考察应用过程中干扰的引入原因,分析各种干扰现象相应的样本结构形态;为实现对多结构混杂数据的适应能力,本文对传统的RANSAC方法进行了改进,并首次将其推广到动态背景像素建模任务当中。通过MAD尺度估计子自适应估计阈值参数,经由随机采样、模型估计、模型数据扩充、多级建模的方式,使算法在保持高鲁棒性的同时仍能拥有较好的描述精度。在此基础上,采用三元组模型描述方式,以改进的多级RANSAC方法建立动态像素背景模型,以单端截尾均值估计子建立静态像素模型,并在一个统一的框架中快速更新。该方法有效的解决了RANSAC方法的固有缺陷,能容忍高比例的离群数据;该方法具有较好的描述能力,在保持算法准确性的前提下有较快的更新速度。通过对溃点的理论计算和统计分析验证了方法的鲁棒性,并与GMM估计、Median估计进行了对比。
(3)研究基于运动信息的目标跟踪方法,应用光流方法和Kalman方法进行跟踪实验并分析其不足之处。针对Kalman估计子不能克服外点的影响,难以解决的运动分析过程中的非线性、粗差的问题,结合Turkey型M-估计子对UKF的迭代过程进行改造。M-估计子是一类重要的鲁棒估计子,可以通过选择不同类型的损失函数,实现不同的鲁棒效果。提出了一种M-UKF估计方法,该方法将M-估计的加权原理应用到UKF的迭代递推的过程中,可以有效地减弱或消除观测值中粗差的影响;在解决了运动模型非线性估计的同时,能较好的克服离群数据的干扰,大大提高了估计的鲁棒性。结合包含运动信息在内的多层次信息,给出了一个人的精细轮廓的跟踪方法和比较实验。
(4)从生物视觉认知的角度对运动目标跟踪过程进行全面考察,提出了一种基于蛙眼认知特性的“模糊化区域理解”跟踪策略。首先详细分析了蛙眼视觉系统的行为特性、生理特性和神经特性,然后通过借鉴蛙眼认知的外部特性和神经生理特性,提出了一种与蛙眼跟踪方式类似的鲁棒跟踪策略;并以“模糊化区域理解”的方式,给出了这种跟踪策略的一种实现模式。将Mean-Shift滤波应用到“模糊化区域理解”的过程中,分析尺度参数解耦对理解效果的影响结果,并设计了一种自适应的局部尺度参数选择策略。最后,利用该方法解决存在背景场景突变、目标外观变化、环境光照变化、目标干扰运动等现象的复杂环境下的目标跟踪问题,提高跟踪方法对这些干扰因素的抵抗能力,并将该方法与传统的理解方法进行了对比。
Contributed to the non-contact characteristic,visual-information-based object detection and tracking tasks can be achieved without interfering desired objects.The detection and tracking of moving objects under dynamic scenes becomes one of the most significant topics in computer vision research.In realistic application,the observed data sets often contain high percentage of outliers,which make it necessary to use robust methods for estimation.For any practical tracking algorithms,robustness of the tracker must be concerned.Recently,with the rapid development of computer hardware,the requirements of real-time computing are more dependent on hardwares' performace.Then,robust problem,which still remains very difficlut,has been more and more essential and critical in tracking.The research on how to improve tracking robustness in complex natual circumstance,not only give benifit to the achievement and promotion of intelligent automatic visual information processing,but also will further promote the comprehension of biological visual understanding mechanism itself.
This dissertation discusses the theories and applications of moving object tracking through robustness requirements,robustness description,robust treatment strategies and robust tracking algorithms.We analysis the different sub-tasks of tracking,such as background modeling and background substraction,move estimation and move tracking,object tracking.And its different robustness requirements are taken into account.Traditional robust estimators are improved.New tracking tactic and algorithms,which based on robust statistics or biological technology,are presented. Experiments show that these algorithms compared with the existing algorithms,have an advantage on the efficiency,accuracy,robustness,and so on.
The main tasks and contributions of this thesis are:
(1) First,some fundamental concepts about estimation theory are introduced.The statistical definitions of robust estimator(such as outliers,breakdown point and influence function) are given and some robust statistics methods(such as Median, M-estimator,RANSAC) are discussed.Their respective advantages and limits are examined.Nonparametric statistics has a close relationship with robust estimation.We also analysis some nonparametric estimation method,focus on mean-shift's performance and convergence,and give experimental verification.
(2) Taking the task of background modeling as an example,its robustness requirements under different conditions are analyzed.We consider the reasons of noise in different applications;give a structural analysis of its sample set.To dealing with multiple structural contaminated data,the traditional RANSAC is improved by MAD estimator and multi-procession.On this basis,a novel robust background modeling algorithm is presented.The model is established by an improved Multi-RANSAC approach for dynamic background pixels and by one-tail trimmed mean estimation for static pixels.A three-component cell is derived for the model so that it can be updated quickly in a unified framework.The method effectively overcomes the inherent deficiency in RANSAC and can tolerat a high percentage of oulier.It proves right even when there are more than 70 percent outliers and is fit for extraventricular natural scenes.Quantitative evaluation and comparisons with GMM estimator and Median estimator verified that the proposed method has much better performance.
(3) M-estimator is one of the most important robust estimators,which can achieve different performance of robustness by choosing different loss function.In the process of estimating and tracking of moving object,the traditional Kalman filter-based method can't overcome the influence of outliers,and has trouble in the condition of nonlinear outliers and gross outliers.Aiming at this problem,we combine the Turkey M-estimator with Unscened Kalman Filter and present a new M-UKF tracking algorithms.It can not only solve the problem of estimating the nonlinear effection,but also overcome the interference of gross outliers.Simulation and experiments show its validity.
(4) After conducting a comprehensive inspection of object tracking process from the perspective of biological visual cognition,we develop a robust intelligent tracking tactic based on the intrinsic and extrinsic features of frog's visual system.It is achieved through a procession called as "fuzzy region understanding".Mean-Shift based-method is applied and the effect of scale-parameters is discussed.An adaptive local scale-parameter adjustment is presented.The proposed method has been applied in the sences which may have gross noises such as local scene break or object appearance variation or interference with movement.Experiments and comparisons with two traditional algorithms demonstrate the validity and robustness of our algorightm.
引文
[1]Hu,W.,et al.,A survey on visual surveillance of object motion and behaviors[J].IEEE Transactions on Systems,Man and Cybernetics Part C:Applications and Reviews,2004,34(3):334-352.
[2]Zaveri,M.A.,S.N.Merchant,and U.B.Desai.Air-borne approaching target detection and tracking in infrared image sequence[C].International Conference on Image Processing,Singapore,2004,5:1025-1028.
[3]Yoneyama,A.,C.H.Yeh,and C.C.Jay Kuo.Robust Vehicle Detection for Highway Surveillance via Rear-view Monitoring[C].San Diego,CA,United States:The International Society for Optical Engineering.2003.
[4]Heckenberg,D.Performance evaluation of vision-based high DOF human movement tracking:A survey and human computer interaction perspective[C].2006.New York,NY,United States:Institute of Electrical and Electronics Engineers Computer Society,Piscataway,NJ 08855-1331,United States.
[5]Hansen,D.W.and A.E.C.Pece,Eye tracking in the wild.Computer Vision and Image Understanding[J],2005.98(1):p.155-181.
[6]Trivedi,M.M,Gandhi,T,MaCall,J.Looking-in and looking-out of a vehicle:Computer-vision-based enhanced vehicle safety [J].IEEE Transactions on Intelligent Transportation Systems,2007,8(1):108-120
[7]C.-Y.Fang,S.-W.Chen,and C.-S.Fuh.Automatic change detection of driving environments in a vision-based driver assistance system[J].IEEE Trans.Neural Netw.2003,14(3):646-657.
[8]Michalopoulos,P.and J.Hourdakis.Review of non-intrusive advanced sensor devices for advanced traffic management systems and recent advances in video detection[C].Proceedings of the Institution of Mechanical Engineers.Part I:Journal of Systems and Control Engineering.2001,215(4):345-355.
[9]Y.zhu,D.Comaniciu,M.Pellkofer,T.Koehler.Passing Vehicle Detection from Dynamic Background Using Robust Information Fusion[C].2004 IEEE Intelligent Transportation Systems Conference,2004:564-569.
[10]Mejias,L.,et al.,Visual servoing of an autonomous helicopter urban areas using feature tracking[J].Journal of Field Robotics,2006.23(3-4):185-199.
[11]Zhou,Y.,et al.,A robust lane detection and tracking method based on computer vision[J].Measurement Science and Technology.2006,17(4):736-745.
[12]Meijering,E.,I.Smal,and G.Danuser,Tracking in molecular bioimaging[J].IEEE Signal Processing Magazine.2006,23(3):46-53.
[13]Heckenberg,D.Performance evaluation of vision-based high DOF human movement tracking:A survey and human computer interaction perspective[C].2006 Conference on Computer Vision and Pattern Recognition Workshops.New York,NY,NJ 08855-1331,United States.
[14]H.Wang,Robust Motion Estimation in Video Coding at Low Bit-rate[C].International Conference on Robotics Intelligent Systems and Signal Processing,Proceedings of the 2003 IEEE,2003:794-798.
[15]D.Edgington,et al.Automated event detection in underwater video[C],in Proc.Visual Form.2001,pp.759-768.
[16]Bunyak,F.and S.R.Subramanya,Maintaining trajectories of salient objects for robust visual tracking[A],in Image Analysis and Recognition[C].Springer-Verlag Berlin:Berlin.2005,.820-827.
[17].胡玉锁,陈会勇,陈宗海,基于鲁棒统计量的运动检测与目标跟踪策略[J],系统仿真学报,2006,18(2):439-443
[18].方伟,陈会勇,陈宗海,基于非参数二维熵的主动轮廓模型[J],模式识别与人工智能,2005,18(6):717-722
[19]Connolly,C.A new integrated robot vision system form FANUC robotics[J].Industrial Robot.2007,34(2):103-106.
[20]Medioni,G.Robust real-time vision for a personal service robot[J].Computer Vision and Image Understanding,2007,108(1-2):196-203.
[21]R.Collins,et al.A system for video surveillance and monitoring:VSAM final report[R].Carnegie Mellon University,Technical Report:CMU-RI-TR-00-12,2000.
[22]A.Singh,Digital change detection techniques using remotely-sensed data[A].Int.J.Remote Sens[C].1989,10(6):989-1003.
[23]P.Coppin and M.Bauer.Digital change detection in forest ecosystems with remote sensing imagery.[J],Remote Sens.Rev.1996,13:207-234.
[24]Richard J.R.,et al.Image change detection algorighms:A systematic survey[J].IEEE Transactions on Image Processing.2005,14(3):294-307.
[25]R.Collins,A.Lipton,and T.Kanade.Introductin to the special section on video surveillance[J].IEEE Trans.Pattern Anal.Mach.Intell.2000,22(8):745-746.
[26]Regazzoni C,Ramesh V,Foresti GL.Special issue on video communications,processing,and understanding for third generation surveillance systemiC].Proc.of the IEEE,2001,89(10):1355-1539.
[27]Yang,M.-H.,D.J.Kriegman,and N.Ahuja,Detecting faces in images:A survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002.24(1):34-58.
[28]Sun,Z.,G.Bebis,and R.Miller,On-road vehicle detection:A review[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006.28(5):694-711.
[29]Trucco,E.and K.Plakas,Video tracking:A concise survey[J].IEEE Journal of Oceanic Engineering,2006.31(2):520-529.
[30]Moeslund,T.B.,A.Hilton,and V.Kruger,A survey of advances in vision-based human motion capture and analysis[J].Computer Vision and Image Understanding,2006.104(2-3 SPEC ISS):90-126.
[31]王亮,胡卫明,谭铁牛.人运动的视觉分析综述[J].计算机学报.2002,25(3):225-237.
[32]http://www.863.org.cn/863_105/applyguide/guide_infotech/200704060001.html
[33]http://www.973.gov.cn/ReadCont.aspx?aid=383
[34]Robert M.Haralick.Computer vision theory:The lack thereof[J].Computer Vision,Graphics,and Image Processing.November-December 1986,36(2-3):372-386
[35]Z.Zivkovic,F.Heijden,Efficient Adaptive Density Estimation per Image Pixel for The Task of Background Subtraction[J],Pattern Recognition Letters,2006,27(7):773-780
[36]H.Z.Wang,D.Suter,A Novel Robust Statistical Method for Background Initialization and Visual Surveillance[C],in Computer Vision- ACCV 2006,Springer-Verlag Berlin,Pt I:328-337
[37]王建宇等,背景变化鲁棒的自适应视觉跟踪目标模型[J],软件学报,2006,17(5):1001-1008.
[38]P.Guha,et al,A Multiscale Co-linearity Statistic Based Approach to Robust Background Modeling[C],in Computer Vision-ACCV 2006,Springer-Verlag Berlin,Pt I.:297-306
[39]M.Heikkila,M.Pietikainen,A Texture-Based Method for Modeling The Background and Detecting Moving Objects[J],IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):657-662
[40]王智灵,陈宗海,周露平,基于多信息层次的鲁棒背景建模方法[C],系统仿真技术及其应用,2007,9:303-306.
[41]Wren,C.R.,et al.Pfinder:real-time tracking of the human body[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(7):780-785.
[42]N.Friedman,S.Russel.Image segmentation in video sequences:a probabilistic approach[A].Proc.13th Conf.on Uncertainty in Artificial Intelligence[C].San Francisco.1997:175-181.
[43]C.Stauffer and W.E.L.Grimson.Adaptive Background Mixture Models for Real-Time Tracking[A].Proc.IEEE CS Conf.Computer Vision and Pattern Recognition[C].Colorado Springs,1999:246-252,.
[44]C.Stauffer and W.E.L.Grimson.Learning patterns of activity using real-time tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[45]Magee,D.R.,Tracking multiple vehicles using foreground,background and motion models[J].Image and Vision Computing.2004,22(2):143-155.
[46]J.-W.Hsieh,W.-F.Hu,C.-J.Chang,and Y.-S.Chen.Shadow elimination for effective moving object detection by Gaussian shadow modeling[J].Image and Vision Computing.2003,21(6):505-516.
[47]O.Javed,K.Shafique,and M.Shah,A hierarchical approach to robust background subtraction using color and gradient information[A].Proc.IEEE Workshop Motion Video Computing[C],Orlando,2002:22-27.
[48]A.Elgammal,R.Duraiswami,D.Harwood,and L.S.Davis.Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance[C].Proceedings of the IEEE.2002,90(7):1151-1163.
[49]Mittal A,Paragios N.Motion-based background subtraction using adaptive kernel density estimation[A].IEEE Conference in Computer Vision and Pattern Recognition[C].2004(2):304-309.
[50]I.Haritaoglu,D.Harwood,and L.S.Davis.W-4:Real-time surveillance of people and their activities[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(8):809-830.
[51]胡玉锁,陈宗海.一种新的基于线性EIV模型的鲁棒估计算法[J].计算机研究与发展.2006,43(3):483-488.
[52]胡玉锁,陈会勇,陈宗海.基于鲁棒统计学的运动检测与目标跟踪策略[J].系统仿真学报.2006,18(2):439-443.
[53]L.Li,W.Huang,I.Y.-H.Gu,and Q.Tian.Statistical modeling of complex backgrounds for foreground object detection[J].IEEE Transactions on Image Processing.2004,13(11):1459-1472.
[54]Collins R,Lin Y.On-Line selection of discriminative tracking features[A].In:Lee SW,ed.Proc.of the IEEE Conf.on Computer Vision[C].Nice:IEEE Computer Society,2003.346-352.
[55]Kass M,Witkin A,Terzopoulos D.Snakes:Active Contour Models[J].International Journal of Computer Vision,1987,1(4):321-331.
[56]Gevers,T.,2004.Robust segmentation and tracking of colored objects in video[J].IEEE Transactions on Circuits and Systems for Video Technology,14(6):776-781.
[57]Seo,K.-H.,Shin,J.-H.,Kim,W.and Lee,J.-J.Real-time object tracking and segmentation using adaptive color snake model[J].International Journal of Control,Automation and Systems,2006,4(2):236-246.
[58]陈宗海,方伟,陈会勇,王智灵,基于分布匹配的主动轮廓模型及其图像分割算法[J],吉林大学学报,已录用;
[59]Haritaoglu,I.,Cutler,R.,Harwood,D.and Davis,L.S.Backpack:Detection of people carrying objects using silhouettes[J].Computer Vision and Image Understanding,2001,81(3):385-397.
[60]T.F.Cootes,C.J.Taylor.Active Shape Models - 'Smart Snakes'[A].In Proc.British Machine Vision Conference[C].1992:266-275.
[61]Nascimento,J.C.and Marques,J.S.Robust shape tracking in the presence of cluttered background[J].IEEE Transactions on Multimedia,2004,6(6):852-861.
[62]Kim,W.and Lee,J.-J.Object tracking based on the modular active shape model[J].Mechatronics,2005,15(3):371-402.
[63]T.F.Cootes,G.J.Edwards,and C.J.Taylor.Active Appearance Models[J].IEEE Transactions on Pattern Analysis and Machine Intellegence,2001,23(6):681-685.
[64]Birkbeck,N.and Jagersand,M.Visual tracking using Active Appearance Models[A].Proceedings - 1st Canadian Conference on Computer and Robot Vision[C].Canada,2004,pp.2-9.
[65]Zhou,S.K.,Chellappa,R.and Moghaddam,B.Visual tracking and recognition using appearance- aptive models in particle filters[J].IEEE Transactions on Image Processing,2004,13(11):1491-1506.
[66]Irani M,Anandan P.A unified approach to moving object detection in 2Dand 3D scenes[J].IEEE Trans.on Pattern analysis and machineintelligence(S0162-8828),1998,20(6):577-589.
[67]艾斯卡尔·艾木都拉,陈颖,贾振红.基于概率加权求和投影的多维信号检测技术研究[J].电子学报.2005,33(7):1331-1333.
[68]Paragios,N.and Deriche,R.,2005.Geodesic active regions and level set methods for motion estimation and tracking.Computer Vision and Image Understanding,97(3):259-282.
[69]Zheng,J.,Li,B.,Zhou,B.and Li,W.Fast motion detection based on accumulative optical flow and double background model[A].Computational Intelligence and Security,Pt 2,Proceedings[C].Lecture Notes in Artificial Intelligence.Springer-Verlag Berlin,Berlin,pp.291-296.2005.
[70]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[J].系统工程和电子技术.2005,27(3):422-426.
[71]Meyer D,Denzler J.and Miemann H.Model based extraction of articulated objects in image sequences for gait analysis[A].In:Proc IEEE International Conference on Image Processing[C].California.1997:78-81.
[72]Bruno,M.G.S.Bayesian methods for multiaspect target tracking in image sequences[J].IEEE Transactions on Signal Processing,2004,52(7):1848-1861.
[73]Zhang,J.and Zhang,Z.Application of a strong tracking finite-difference extended Kalman filter to eye tracking[A].Lecture Notes in Computer Science[C].Springer Verlag,Heidelberg,D-69121,Germany,Kunming,China,2006,pp.1170-1179.
[74]Gustafsson F,et al.Particle filters for positioning,navigation,and tracking[J].IEEE Trans,on Signal Processing,2002,50(2):425-437.
[75]Kang,H.-G and Kim,D.Real-time multiple people tracking using competitive condensation[J].Pattern Recognition,2005,38(7):1045-1058.
[76]Zhou,S.K.,CheUappa,R.and Moghaddam,B.Visual tracking and recognition using appearance-adaptive models in particle filters[J].IEEE Transactions on Image Processing,2004,13(11):1491-1506.
[77]R.D.Martin,C.J.Masreliez.Robust estimation via Stochastic Approximation[J].IEEE Trans.Information Theory,1975,IT-21(3):263-271
[78]J.W.Turkey,T.E.Harris.Statistical Res[Z].Group,Princeton Univ.,Princeton,N.J.,Memo.Rep.31,1949
[79]Tukey J.W..Contributions to Probability and Statistics[M].ch:A survey of sampling from contaminated distributions,Stanford,Calif:Stanford University Press,1960:448-485
[80]Huber P J.Robust statistics:A review[J].Annals of Mathematical Statistics,1972,43(3):1041-1067
[81]P.J.Rousseeuw.Least median of squares regression[J].J.Amer.Statist.Assoc,1984,79(388):871-880
[82]R.D.Martin.Robust Estimation of Signal Amplitude[J].IEEE Trans.Information Theory,1972,IT-18:596-606
[83]F.Hample.The influence curve and its role in robust estimation[J].J.Am.Statis Assoc,1974,69(346):383-393
[84]F.Hample.Contribution to the theory of robust estimation[D].Berkeley:University of California,1968
[85]PJ.Huber.A robust version of the probability ratio test[J].Annals of Mathematical Statistics,1965,36:1753-1758
[86]M.P.Wand,MJones.Kernel Smoothing[Z].Chapman and Hall,1995
[87]W.H.M.Muller,S.Sperlich,A.Werwatz.Nonparametric and semiparametric models and introduction[Z].Lecture Degree,Institute of Statistique,2004
[88]Theo G,M.Hans-Georg.Kernel estimation of regression functions[A].In Smoothing Techniques for Curve Estimation[C],Lecture Notes in Mathematics,New York:Springer-Verlag, 1979,757:23-68
[89]Delaigle A,I.Gijbels.Bootstrap bandwidth selection in kernel density estimation from a contaminated sample[J].Inst.Statist.Math.,2004,56(1):19-47
[90]Zhang X,M.L.King,R.J.Hyndman.Bandwidth Selection for Multivariate Kernel Density Estimation Using MCMC[R].Monash University Department of Econometrics and Business Statistics,2004.
[91]Wang H.,D.Suter.Robust adaptive-scale parametric model estimation for computer vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(11):1459-1474
[92]Rymar,I.V.,V.A.Simakhin.Adaptive robust estimates of shift and scale parameters[A].International Society for Optical Engineering [C].Tomsk,Russian Federation:International Society for Optical Engineering,2006,61601:616010
[93]K.Fukunaga,L.D.Hostetler.The estimation of the gradien of a density function,with applications in pattern recognition [J].IEEE Trans.Information Theory,1975,21:2-40
[94]Allen J.G,R.Y.D.Xu,J.S.Jin.Mean shift object tracking for a SIMD computer[A].ICrTA[C],1,2005:692-697
[95]Comaniciu D.,R Meer.Mean shift:a robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619
[96]Comaniciu D.,P.Meer.Mean shift analysis and applications[A].The Proceedings of the Seventh IEEE International Conference on Computer Vision[C],1999,2:1197-1203
[97]J.Illingworth,J.kittler.A survey of the hough transform[J].Computer Vision and Graphics Image Processing,1988,44(1):87-116
[98]L.Xu,E.Oja,P.Kultanen.A new curve detection method:Randomized Hough transform (RHT)[J].IEEE Pattern Recognit.Lett,1990,11(5):331-338
[99]Ballard D.H..Generalizing the Hough transform to detect arbitrary edges[J].Pattern Recognition,1981,13(2):111-122
[100]Charalampidis D.,V.P.Jilkov,T.M.Nguyen.Enhanced Image Feature Extraction for Object Tracking[A].2005 7th International Conference on Information Fusion[C],2005:1569-1575
[101]Kiryati,et al..A Probabilistic Hough transform[J].Pattern Recognit,1991,24(4):303-316
[102]Fengrong S.,L.Jiren.Fast Hough transform algorithm[J].Chinese J.Comput,2001,24(10):1102-1109
[103]Govindu V.M..Robustness in motion averaging[A].7th Asian Conference on Computer Vision[C].Hyderabad,India:Springer Verlag,Heidelberg,2006,3852:457-466
[104]Qian G,R.Chellappa,Q.Zheng.Robust Bayesian Cameras Motion Estimation Using Random Sampling[A].2004 International Conference on Image Processing[C].2004:1361-1364
[105]Kim,J.-H.,J.H.Han.Outlier correction from uncalibrated image sequence using the Triangulation method[J].Pattern Recognition,2006,39(3):394-404
[106]J.Black M.,P.Anandan.A framework for the robust estimation of optical flow[A].Fourth International Conf.on Computer Vision,ICCV-93[C].Berlin,Germany:May 1993:231-236
[107]Demonceaux C.,D.Kachi-Akkouche.Motion detection using wavelet analysis and hierarchical Markov models[A].Spatial Coherence for Visual Motion Analysis - First International Workshop[C].Prague,Czech Republic:Springer Verlag,Heidelberg,2006,3667:64-75
[108]H.Wang,D.Snter.Variable Bandwidth QMDPE and Its Application in Robust Optic Flow Estimation[A].In 9th IEEE International Conference on Computer Vision[C].Nice,France:Proc.Int'l J.Computer Vision,2003:178-183ⅰ
[109]T.Tommasini,et al..Robust feature tracking in tmderwater video sequences[A].Oceans Conference Record[C].Nice,Fr.:IEEE,1998,1:46-50
[110]R B.G..Computer Video Face Tracking for use in a Perceptual User Interface[A].In:Proc.of the 4th IEEE Workshop on Applications of Computer Vision[C].1998:19-21
[111]Comanicin D.,V.Ramesh,P.Meet.Real-time tracking of non-rigid objects using Mean shift[A].Proceedings IEEE Conference on Computer Vision and Pattern Recoguition[C].2000.2:142-149
[112]Kaplan A,E.Rivlin,I.Shimshoni.Robust feature matching across widely separated color images[J].ICPR,2004,2:136-139
[113]Askar H,Li Xiaofeng,Li Zaiming.Performance analysis of dim moving point target detection algorithms[A].International Conference on Communications,Circuits and Systems and West Sino Expositions.2002 IEEE[C].2002,2,229-242.
[114]Al-Hamadi,A.,R.Niese,and B.Michaelis.A robust approach for contour extraction and tracking of moving objects in video sequences[A].International Conference on Signal Processing,Pattern Reconition,and Applications[C],Rhodes,Greece.2003:336-341.
[115]R.L格列高里.视觉心理学[M].北京示范大学出版社,1986.
[116]杨雄里.视觉的神经机制[M].上海科技大学出版社,1996.
[117]Lettvin,J.Y.,Maturana,H.R.,McCulloch,W.S.,and Pitts,W.H.What the Frog's Eye Tells the Frog's Brain[C].Proc.Inst.Radio Engr.1959.47:1940-1951.Reprinted in The Mind:Biological Approaches to ires Functions[M].edited by Warren S.McCulloch,MIT Press.1968:233-258.
[118]David Ingle.Disinhibition of Tectal Neurons by Pretectal Lesions in the Frog[J].Science,1973,180:422-424.
[119]http://www.ibp.ac.cn/c/faculty/03/shurongwang.html.
[120]福岛邦彦.视觉生理与仿生学[M].科学出版社,1980.
[121]赵亮,王天珍,刘永红.青蛙视觉行为与计算机模拟概述[J].武汉理工大学学报(信息与管理工程版),2003,25(4):5-9
[122]D.J.Hand.Data Mining:Statistics and More?[J].The Am.Statistician,1998,52(2):112-118.
[123]J.R.M.Hosking,E.P.D.Pednault,and M.Sudan.A Statistical Perspective on Data Mining[J].Future Generation Computer Systems,1997,13:117-134.
[124].陈会勇,胡玉锁,陈宗海,基于恒定曲率变化的主动轮廓模型[J],中国图象图形学报,2006,11(6):827-833
[125]王智灵,周露平,陈宗海,针对不同信息特征的鲁棒背景建模技术分析[J],模式识别与人工智能,已录用
[126]周露平,王智灵,陈宗海,基于M-估计的UKF算法及其在运动估计中的应用[J],模式识别与人工智能,2007,20(6):849-854
[127]王智灵,陈宗海,周露平,视觉图像理解中的定性方法研究[C],系统仿真技术及其应用,2006,8:797-800.
[128]吴亮,陈宗海,王智灵,徐萧萧,基于字符形态匹配的车牌字符识别方法[C],系统仿真技术及其应用,2007,9:808-810.
[129]王智灵,陈宗海,具有生物智能的动态场景下运动目标鲁棒跟踪方法[A],模式识别研究进展[C],CCPR,2007,89-95
[130]王智灵,陈宗海,徐萧萧,吴亮,基于蛙眼视觉特性的运动目标模糊化区域理解跟踪方法[J],自动化学报,已录用
[131]王智灵,陈宗海,张硕奇,路婷婷,罗杨宇,李成荣,基于多信息的人目标的精细轮廓跟踪[C],系统仿真技术及其应用(SSTA),2008,10:829-833
[132]陈宗海,文锋,王智灵,基于自适应评价的非线性系统神经网络控制[J],控制与决策,2007,22(7):765-768
[133]G.Casella,R.L.Berger.Statistical Inference(second edition)[M].North Scituate,MA:Duxbury Press,2002
[134]P.Meer,Emerging Topics in Computer Vision,Robust Techniques for Computer Vision[R].Prentice Hall,2004.
[135]F.Hampel,Robust statistics:a brief introduction and overview[R],in Robust Statistics and Fuzzy Techniques in Geodesy and GIS,2001
[136]R.D.Martin,C.J.Masreliez.Robust estimation via Stochastic Approximation[J].IEEE Trans.Information Theory,1975,IT-21(3):263-271
[137]D.F.Andrews,Robust estimates of location:survey and advances[M],Princeton University Press,1972.
[138]Peter J.Huber,Robust statistics[M],Wiley-Interscience,2004.
[139]PJ.Rousseeuw and A.Leroy.Robust Regression and Outlier Dectection[M].John Wiley &Sons,1987.
[140]C.V.Stewart.Robust Parameter Estimation in Computer Vision[J].SIAM Rev,1999,41(3):513-537.
[141]Z.Zhang.Parameter estimation techniques:A tutorial with application to conic fitting[J].Image and Vision Computing,1997,15(1):59-764
[142]Krivulin N..An analysis of the Least Median of Squares regression problem[A].Proc.10th Symp.on Computational Statistics[C],Neuch(?)atel,Switzerland:Aug.,1992,1:471-476
[143]B.W.Silverman,Density Estimation for Statistics and Data Analysis[R].Chapman and Hall,1986
[144]D,D..Rank-Based Robust Analysis of Linear Models[J].Exposition and Statistical Science,1988,3:239-271
[145]狄昂照,随机逼近[M].北京:科学技术出版社,1994
[146]陈希孺,赵林城,线性模型中的M方法[M].上海科学技术出版社,1996
[147]Fischler,M.A.and R.C.Bolles.Random Sample Consensus - a Paradigm for Model-Fitting with Applications to Image-Analysis and Automated Cartography[J].Communications of the ACM,1981,24(6):381-395
[148]Godenshluger,A.and A.Zeevi,The Hough Transform Estimator,Annals of Statistics,2004,32(5):1908-1932.
[149]Veelart,P.and K.Teelen.Consensus sets for affine transformation uncertainty polytopes.Computers and Graphics.2006,30(1):77-85.
[150]Stewart,C.V.MINPRAN:A new robust estimator for computer vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995.17(10):925-938.
[151]Zhuang,X.,T.Wang,and P.Zhang.A highly robust estimator through partially likelihood function modeling and its application in computer vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992.14(1):19-35.
[152]J.V.Miller and C.V.Stewart.MUSE:Robust surface fitting using unbiased scale estimates[A].In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].San Francisco.pp.300-306,1996.
[153]X.Yu,T.D.Bui,and A.Krzyzak.Robust estimation for range image segmentation and reconstruction[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1994,16(5): 530-538.
[154]Leung,Y.,MaJ.H.,Zhang,W.X.A new method for mining regression classes in large data sets[J].IEEE Transaction on Pattern Analysis and Machine Intelligence.2001,23:5-21.
[155]Wang,H.and D.Suter.MDPE:A very robust estimator for model fitting and range image segmentation^].International Journal of Computer Vision,2004.59(2):139-166.
[156]胡玉锁．计算机视觉中的鲁棒估计方法[D]．合肥：中国科学技术大学,2004
[157]Cheng Y.Z.Mean shift,mode seeking,and clustering.IEEE Transaction on Pattern Analysis and Machine Intelligence,1995,17(8):790-799
[158]K.Toyama,J.Krumm,B.Brumitt,and B.Meyers.Wallflower:Principles and practice of background maintenance[A].Proceedings of the IEEE International Conference on Computer Vision[C].Kerkyra,Greece.1999(1):255-261.
[159]V.Stewart.C.Bias in Robust Estimation Caused by Discontinuities and Multiple Structres[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(8):818-833
[160]K.Kim,et al,Real-time foreground-background segmentation using codebook model[J].Real-Time Imaging.2005.11(3):172-185.
[161]Z.Hongxun and X.De.Fusing color and texture features for background model[C].International Conference on Fuzzy Systems and knowledge Discovery,Xi'an,China:2006:887-893.
[162]J.Rymel,et al.Adaptive eigen-backgrounds for object detection[C].International Conference on Image Processing,Singapore.2004(3):1847-1850.
[163]PJ.Rousseeuw and A.M.Leroy.Robust Regression and Outlier Detection[M].New York:Wiley-Interscience,1987.
[164]Julier S.,J.Uhlmann,H.F.Durrant-Whyte.A New Method for the Nonlinear Transformation of Means and Covariances in Filters and Estimations[J].IEEE Transactions on Automatic Control,2000,45(3):477-482
[165]Welch G,G Bishop.An Introduction to the Kalman Filter[Online],Available:http://www.cs.unc.edu/~welch,2004.
[166]JJulier S.,J.ICUhlmann.A New Extensiton of the Kalman Filter to Nonlinear Systems[A].the 11th Int Symp on Aerospace/Defence Sensing,Simulation and Controls[C].Orlando,Florida:Procof AeroSense,1997,3068:182-193
[167]Chan S.C.,Z.G Zhang,K.W.Tse.A new robust Kalman filter algorithm under outliers and system uncertainties[J].ISCAS,2005 (5):4317-4320
[168]U.Voss H.,J.Timmer,J.Kurths.Nonlinear dynamical Systems Identification from Uncertain and Indirect Measurements[J].International Journal of Bifurcation and Chaos,2004,14(6):1905-1933
[169]Maturana,H.R.Number of fibres in the optic nerve and the number of ganglion cells in the retina of Anurans[J].Nature 138:1406-1407,1959
[170]Grusser,O.-J,and Grusser-Cornehls,U.Neurophysiology of the Anuran Visual System.In Frog Neurobiology - A Handbook[M],edited by R Llinas and W.Precht.Springer-Verlag:New York.1976:297-385
[171]http://www.neurocomputing.org/FrogEye.aspx
[172]Wiener.N.控制论——或关于在动物和机器中控制和通讯的科学[M].郝季仁译.科学出版社出版.1963.
[173]http://www.ibp.ac.cn/c/03/01.html
[174]SaintMarc P,Chen J.S,Medioni G..Adaptive smoothing:A general tool for early vision[J].IEEE Transaction on Pattern Analysis and Machine Intelligence.1991,13(6):514-529
[175]Barash D.A fundamental relationship between bilateral filtering,adaptive smoothing,and the nonlinear diffusion equation[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2002,24(6):844-847
[176]文志强,蔡自兴.Mean Shift算法的收敛性分析[J].软件学报,2007,18(2):205-212
[177]Sheather S.J,Jones M.C.A reliable data-based bandwidth selection method for kenel density estimation[J].Journal of the Royal Statistical Society,Series B,1991,53(3):683-690
[178]Ramanan D,Forsyth D.A.,and Zisserman A.Tracking people by learning their appearance[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007.29(1):65-81
[179]Chow T.Y.,and Lam K.M.,Mean-shift based mixture model for face detection in color image[C].In Proc IEEE Conference on Image Processing,Singapore,2004:601-604.
[180]Aho A.C,Donner K,Helenius S,etc.Visual Performance of Toad at Low Light Levels:Retinal Ganglion Cell Responses and Prey-Catching Accuracy[J].Journal of Comparative Physiology A,1993,172:671-682.
[181]吴喜之,非参数统计[M].北京:中国统计出版社,1999
[182]J.Julier,S.,The Scaled Unscented Transformation[A].2002 American Control Conference[C],Anchorage Alaska:IEEE,2002,6:4555-4559
[183]K.Okuma,A.Taleghani,N.de Freitas,J.J.Little,D.G.Lowe.A boosted particle filter:Multitarget detection and tracking[A].European Conference on Computer Vision[C].2004,3021:28-39
[184]马颂德,张正友,计算机视觉:计算理论与算法基础[M],北京-科学出版社,1998
[185]周露平,鲁棒估计及其在目标跟踪中的应用[D],合肥:中国科学技术大学出版社,2007
[186]王智灵,陈宗海,张硕奇,路婷婷,罗杨宇,李成荣,基于多层次信息的人的轮廓建模与跟踪仿真研究[J],系统仿真学报,已录用。
[187]Wang Zhi-Ling,Chen Zong-Hai,A Robust Estimation Algorithm for Multiple-Structral Data[J],Systems Engineering and Electronics,Submit;
[188]Wang Zhi-Ling,Chen Zong-Hai,Chen Hui-Yong,A Novel Robust Background Model Algorithm for Complex Natural Scenes[C],2009' World Summit on Genetic and Evolutionary Computation,Submit.
[189]王智灵,陈宗海,路婷婷,张硕奇,罗杨宇,李成荣,基于全局光流的夺目标检测与跟踪[C],系统仿真技术及其应用(SSTA),2008,10:265-268;
[190]盛捷,张瑜,王智灵,朱明清,陈宗海,Mean Shift算法优化带宽的自动搜索[J],系统仿真学报,已投稿。