视觉跟踪新方法及其应用研究
|
摘要
视觉跟踪技术是计算机视觉领域的一个重要课题，在军事制导、视频监控、机器人视觉导航、人机交互、以及医疗诊断等许多方面有着广泛的应用前景。视觉跟踪的主要研究目的是使计算机能够模拟人类视觉运动感知功能，并赋予机器辨识视频中运动目标的能力，为视频分析和理解提供重要的数据依据。近年来，随着计算机技术和传感器技术的快速发展，视觉跟踪技术吸引了大量研究人员的关注，成为热点研究问题，相继提出了许多有效的新理论和优秀跟踪算法。然而，视频目标跟踪往往由于复杂背景、光照变化、目标旋转、遮挡和运动随机性等因素变得非常困难，在理论和应用上仍然存在着许多不完善和尚待解决的问题。所以要开发出真正鲁棒、精确、稳定和实用的视觉跟踪方法依然面临着巨大挑战，并且具有重要的理论意义和实用价值。
本文在研究传统视觉目标跟踪方法的基础上，重点瞄准两种主流跟踪算法：粒子滤波和均值漂移，结合学术前沿知识，提出新的思想和方法，提高目标跟踪的准确度和鲁棒性。论文的主要内容和成果概括如下：
首先，以粒子滤波为跟踪框架，提出了四种新的视觉跟踪算法。
(1)为了提高粒子采样质量和视频跟踪算法的精度，提出球粒子滤波视觉跟踪算法。将球状采样方式引入到粒子更新过程中很好地保证状态空间中粒子的有效性。与传统粒子滤波算法相比较，这种采样方式能够利用少量粒子实现分布多样性的同时，有效克服了粒子退化现象。小球迭代运动可以使粒子集朝较大后验概率分布区域移动。球粒子滤波算法不依赖系统状态模型特性可以理想实现运动状态不规则的机动目标跟踪。该算法能够有效提高了粒子利用率，具有较好的跟踪精度。
(2)针对传统粒子滤波算法中容易发生的退化现象和粒子贫化问题，提出多区域采样目标跟踪方法。该算法将目标模板用多个重叠子区域划分，每个子区域对应一个采样窗口，根据采样子区域置信度能有效估计出跟踪目标的真实状态，子区域的互补性和阶段唯一性能很好地保证采样粒子有效性和状态空间质量，从而提高目标跟踪的精确度。该算法能有效缓解目标跟踪中的粒子退化和贫化问题，利用有效粒子提高跟踪精度。
(3)针对传统视觉跟踪算法在目标发生遮挡时容易发生偏离或失败的缺陷，提出了一种新的抗遮挡自适应粒子滤波目标跟踪方法。在粒子传播过程中，利用目标SSD残差所生成的高似然区域能自适应地调整状态空间中的粒子采样区域范围和采样粒子数量，使跟踪中粒子采样覆盖目标的各种状态可能性，全面提高状态空间质量。预测状态和粒子估计状态通过噪声协方差很好地融合起来，能够较有效地解决了遮挡情况下的跟踪问题，使目标定位更加精确。粒子数量的自适应不仅能很好地提高跟踪精度,而且在一定程度上降低了计算代价。此算法对跟踪目标遮挡具有较好的容错性和跟踪鲁棒性，能有效实现复杂场景下的目标跟踪。
(4)为了克服目前大多数观测模型在小样本空间中鲁棒性不高的弱点，在粒子滤波框架下提出基于局部特征组合的粒子滤波视频跟踪算法。局部特征能更有效描述目标模板细节信息，可降低特征匹配中目标形变、光照变化和部分遮挡的影响。该方法借鉴混合高斯模型思想，采用多模式描述有效局部观测信息，这种融合策略更加准确可靠，能够较好地通过最新观测减轻了粒子退化现象，从而提高目标跟踪效率。小样本空间一定程度上降低了粒子数量和计算代价。该算法相比单一特征或一般多特征融合跟踪算法具有优越性。
其次，提出了两个改进算法用于提高均值漂移算法性能。
(1)针对Mean Shift跟踪算法中模板匹配问题，提出了特征贡献度概念，有效摒弃背景和噪声因素干扰，使重要性特征在匹配中起到关键作用；且利用结构二值分布图携带空间结构信息的优点，很好地避免了统计特征的匹配误差，在一定程度上提高了跟踪的精度和鲁棒性。
(2)针对传统均值漂移跟踪算法在目标特征提取、模板匹配度量和带宽固定方面存在缺陷，文中提出了一种新的双环Mean shift视频跟踪算法。该方法采用万向椭圆的特征提取方式，能更有效地抑制背景信息影响，较好地提高目标模型质量。引入双环描述因子能够突出目标本身特征权重，改善图像匹配峰值特性；并且通过双环之间的关系自适应地更新核函数的带宽。该算法在目标具有明显尺度变化、姿态扭曲和部分遮挡的情况下，可以获得准确和鲁棒的跟踪效果。
Visual tracking is an important topic in the field of computer vision，it has a wide rangeof application in military guidance, visual surveillance, visual navigation of robots,human-computer interaction and medical diagnose, etc. The goal of visual tracking is toenable the computer to imitate the motion sensibility of human vision, perceive the movingtarget in a video, and provide and important data source for visual analysis and understanding.In recent years, with the rapid growth of the computer techniques and sensor techniques,visual tracking has attracted many researchers’ attention, has become a very popular researchproblem. A lot of new theories and excellent visual object tracking methods have beenproposed. However, Visual target tracking often become very difficult due to many factorssuch as complex background, illumination variation, object rotation, occlusion and randommotion. Many problems and difficulties in theory research and in applications are stillunsolved. It’s great challenge to build a robust, precise, stable and practical visual trackingalgorithm, which is both theoretically and practically valuable.
On the basis of traditional visual tracking methods, the thesis aims to two mainalgorithms: particle filter and mean shift. It combines academic frontiers and presents newidea and method to improve the accuracy and robustness of object tracking. The maincontents and contributions of this dissertation are summarized as follows:
Firstly, four new visual tracking algorithms with a framework using particle filter areproposed.
(1) In order to improve the quality of particle sampling and the accuracy of visualtracking, a ball particle filter algorithm for visual tracking is proposed. Ball sampling modeintroduced can guarantee the valid particles in state-space. Compared to the conventionalparticle filter, the proposed method used much fewer particles to ameliorate the diversity ofdistribution, and overcame the degeneration problem effectively. By iterative motion of ball,particles are moved towards regions where they have larger values of posterior densityfunction. Ball particle filter which does not depend on state-mode can track maneuver objectwhich movement is irregular. The proposed method can improve the efficiency of particlesand achieves preferable precision of tracking.
(2) A particle filter for object tracking based on multi-region sampling is proposed tosolve the problems of degeneracy phenomenon and particle impoverishment introduced bytraditional particle filter algorithm. The proposed method uses some overlapping sub-regionsto divide the target model, and each sub-region corresponds to a sampling windows. The truestate of target can be estimated by the confidence of each sub-region. The complementary andstage uniqueness of sub-region can guarantee the validity of particles and the quality ofstate-space. Thereby, the accuracy of object tracking is improved. The proposed methodrelieves effectively the sample degradation and poverty problems, improves the accuracy ofvisual tracking by effective particles.
(3) A new anti-occlusion method for object tracking is presented to solve the problemthat traditional visual tracking algorithm often deviates or loses the targets under occlusions. The high likelihood areas generated by the SSD residual can adjust the range and quantity ofparticle sampling in the state-space. The sampling method can cover various possibilities ofobject state and improve the quality of the state-space exploration in the diffusion process ofthe particle filter. The object state of forecast and estimation fused by noise covariance canachieve reliable tracking performance under occlusion and gain the optimal location of object.The adaptive quantity of particle sampling not only can improve the precision, but also canreduce the computational load in a certain extent effectively. The proposed method has strongrobust and error-tolerance to occlusion of tracking objects, and has good performances undercomplex background.
(4) In order to avoid the poor robustness based on most of present observation models insmall sample space, a particle filter algorithm for visual tracking based on partial featurecombination is proposed. Partial features can represent the detail of target template effectively,and can alleviate the affection of object deformation, illumination change and partialocclusion in feature matching. The proposed method employs the idea of mixture of Gaussianand uses multiple modes to represent valid partial observation information. The strategy offusion is more precise and reliable, thus can overcome the degeneracy problem by newmeasurement and improve the efficiency of object tracking. The small sample space canreduce quantity of particle and computational load in a certain extent. The proposed method ismore effective than tracking algorithm with single feature or common multi-features fusion.
Secondly, two improved algorithms are proposed to improve the performance of meanshift.
(1) Considering the issue of template matching within the Mean Shift framework, thispaper proposes a concept of feature contribution. It can effectively reduce the influence ofbackground feature and noise, make importance feature play a key role. In addition, binarydistribution of structure introduced can effectively reduce the error of statistical features byspecial information and improve the tracking accuracy and robustness in a certain extent.
(2) A new tracking algorithm based on double-ring Mean Shift is proposed in this paperto solve the deficiency of target representation, template similarity measure and fixedkernel-bandwidth in traditional Mean Shift tracking algorithm. The feature extraction modelbased on universal elliptical region is used in this algorithm to reduce the influence ofbackground feature and improve the quality of target model effectively. Double-ringdescriptor is presented to emphasize the importance of target feature and improve the peakmodality of matching function. The proposed method can update the bandwidth ofkernel-function adaptively by the relationship of double-ring. The proposed tracking approachis robust and invariant to scale, pose and partial occlusions.
本文在研究传统视觉目标跟踪方法的基础上，重点瞄准两种主流跟踪算法：粒子滤波和均值漂移，结合学术前沿知识，提出新的思想和方法，提高目标跟踪的准确度和鲁棒性。论文的主要内容和成果概括如下：
首先，以粒子滤波为跟踪框架，提出了四种新的视觉跟踪算法。
(1)为了提高粒子采样质量和视频跟踪算法的精度，提出球粒子滤波视觉跟踪算法。将球状采样方式引入到粒子更新过程中很好地保证状态空间中粒子的有效性。与传统粒子滤波算法相比较，这种采样方式能够利用少量粒子实现分布多样性的同时，有效克服了粒子退化现象。小球迭代运动可以使粒子集朝较大后验概率分布区域移动。球粒子滤波算法不依赖系统状态模型特性可以理想实现运动状态不规则的机动目标跟踪。该算法能够有效提高了粒子利用率，具有较好的跟踪精度。
(2)针对传统粒子滤波算法中容易发生的退化现象和粒子贫化问题，提出多区域采样目标跟踪方法。该算法将目标模板用多个重叠子区域划分，每个子区域对应一个采样窗口，根据采样子区域置信度能有效估计出跟踪目标的真实状态，子区域的互补性和阶段唯一性能很好地保证采样粒子有效性和状态空间质量，从而提高目标跟踪的精确度。该算法能有效缓解目标跟踪中的粒子退化和贫化问题，利用有效粒子提高跟踪精度。
(3)针对传统视觉跟踪算法在目标发生遮挡时容易发生偏离或失败的缺陷，提出了一种新的抗遮挡自适应粒子滤波目标跟踪方法。在粒子传播过程中，利用目标SSD残差所生成的高似然区域能自适应地调整状态空间中的粒子采样区域范围和采样粒子数量，使跟踪中粒子采样覆盖目标的各种状态可能性，全面提高状态空间质量。预测状态和粒子估计状态通过噪声协方差很好地融合起来，能够较有效地解决了遮挡情况下的跟踪问题，使目标定位更加精确。粒子数量的自适应不仅能很好地提高跟踪精度,而且在一定程度上降低了计算代价。此算法对跟踪目标遮挡具有较好的容错性和跟踪鲁棒性，能有效实现复杂场景下的目标跟踪。
(4)为了克服目前大多数观测模型在小样本空间中鲁棒性不高的弱点，在粒子滤波框架下提出基于局部特征组合的粒子滤波视频跟踪算法。局部特征能更有效描述目标模板细节信息，可降低特征匹配中目标形变、光照变化和部分遮挡的影响。该方法借鉴混合高斯模型思想，采用多模式描述有效局部观测信息，这种融合策略更加准确可靠，能够较好地通过最新观测减轻了粒子退化现象，从而提高目标跟踪效率。小样本空间一定程度上降低了粒子数量和计算代价。该算法相比单一特征或一般多特征融合跟踪算法具有优越性。
其次，提出了两个改进算法用于提高均值漂移算法性能。
(1)针对Mean Shift跟踪算法中模板匹配问题，提出了特征贡献度概念，有效摒弃背景和噪声因素干扰，使重要性特征在匹配中起到关键作用；且利用结构二值分布图携带空间结构信息的优点，很好地避免了统计特征的匹配误差，在一定程度上提高了跟踪的精度和鲁棒性。
(2)针对传统均值漂移跟踪算法在目标特征提取、模板匹配度量和带宽固定方面存在缺陷，文中提出了一种新的双环Mean shift视频跟踪算法。该方法采用万向椭圆的特征提取方式，能更有效地抑制背景信息影响，较好地提高目标模型质量。引入双环描述因子能够突出目标本身特征权重，改善图像匹配峰值特性；并且通过双环之间的关系自适应地更新核函数的带宽。该算法在目标具有明显尺度变化、姿态扭曲和部分遮挡的情况下，可以获得准确和鲁棒的跟踪效果。
Visual tracking is an important topic in the field of computer vision，it has a wide rangeof application in military guidance, visual surveillance, visual navigation of robots,human-computer interaction and medical diagnose, etc. The goal of visual tracking is toenable the computer to imitate the motion sensibility of human vision, perceive the movingtarget in a video, and provide and important data source for visual analysis and understanding.In recent years, with the rapid growth of the computer techniques and sensor techniques,visual tracking has attracted many researchers’ attention, has become a very popular researchproblem. A lot of new theories and excellent visual object tracking methods have beenproposed. However, Visual target tracking often become very difficult due to many factorssuch as complex background, illumination variation, object rotation, occlusion and randommotion. Many problems and difficulties in theory research and in applications are stillunsolved. It’s great challenge to build a robust, precise, stable and practical visual trackingalgorithm, which is both theoretically and practically valuable.
On the basis of traditional visual tracking methods, the thesis aims to two mainalgorithms: particle filter and mean shift. It combines academic frontiers and presents newidea and method to improve the accuracy and robustness of object tracking. The maincontents and contributions of this dissertation are summarized as follows:
Firstly, four new visual tracking algorithms with a framework using particle filter areproposed.
(1) In order to improve the quality of particle sampling and the accuracy of visualtracking, a ball particle filter algorithm for visual tracking is proposed. Ball sampling modeintroduced can guarantee the valid particles in state-space. Compared to the conventionalparticle filter, the proposed method used much fewer particles to ameliorate the diversity ofdistribution, and overcame the degeneration problem effectively. By iterative motion of ball,particles are moved towards regions where they have larger values of posterior densityfunction. Ball particle filter which does not depend on state-mode can track maneuver objectwhich movement is irregular. The proposed method can improve the efficiency of particlesand achieves preferable precision of tracking.
(2) A particle filter for object tracking based on multi-region sampling is proposed tosolve the problems of degeneracy phenomenon and particle impoverishment introduced bytraditional particle filter algorithm. The proposed method uses some overlapping sub-regionsto divide the target model, and each sub-region corresponds to a sampling windows. The truestate of target can be estimated by the confidence of each sub-region. The complementary andstage uniqueness of sub-region can guarantee the validity of particles and the quality ofstate-space. Thereby, the accuracy of object tracking is improved. The proposed methodrelieves effectively the sample degradation and poverty problems, improves the accuracy ofvisual tracking by effective particles.
(3) A new anti-occlusion method for object tracking is presented to solve the problemthat traditional visual tracking algorithm often deviates or loses the targets under occlusions. The high likelihood areas generated by the SSD residual can adjust the range and quantity ofparticle sampling in the state-space. The sampling method can cover various possibilities ofobject state and improve the quality of the state-space exploration in the diffusion process ofthe particle filter. The object state of forecast and estimation fused by noise covariance canachieve reliable tracking performance under occlusion and gain the optimal location of object.The adaptive quantity of particle sampling not only can improve the precision, but also canreduce the computational load in a certain extent effectively. The proposed method has strongrobust and error-tolerance to occlusion of tracking objects, and has good performances undercomplex background.
(4) In order to avoid the poor robustness based on most of present observation models insmall sample space, a particle filter algorithm for visual tracking based on partial featurecombination is proposed. Partial features can represent the detail of target template effectively,and can alleviate the affection of object deformation, illumination change and partialocclusion in feature matching. The proposed method employs the idea of mixture of Gaussianand uses multiple modes to represent valid partial observation information. The strategy offusion is more precise and reliable, thus can overcome the degeneracy problem by newmeasurement and improve the efficiency of object tracking. The small sample space canreduce quantity of particle and computational load in a certain extent. The proposed method ismore effective than tracking algorithm with single feature or common multi-features fusion.
Secondly, two improved algorithms are proposed to improve the performance of meanshift.
(1) Considering the issue of template matching within the Mean Shift framework, thispaper proposes a concept of feature contribution. It can effectively reduce the influence ofbackground feature and noise, make importance feature play a key role. In addition, binarydistribution of structure introduced can effectively reduce the error of statistical features byspecial information and improve the tracking accuracy and robustness in a certain extent.
(2) A new tracking algorithm based on double-ring Mean Shift is proposed in this paperto solve the deficiency of target representation, template similarity measure and fixedkernel-bandwidth in traditional Mean Shift tracking algorithm. The feature extraction modelbased on universal elliptical region is used in this algorithm to reduce the influence ofbackground feature and improve the quality of target model effectively. Double-ringdescriptor is presented to emphasize the importance of target feature and improve the peakmodality of matching function. The proposed method can update the bandwidth ofkernel-function adaptively by the relationship of double-ring. The proposed tracking approachis robust and invariant to scale, pose and partial occlusions.
引文
[1]马颂德,张正友.计算机视觉[M].北京:科学出版社,1998.
[2] Marr D,姚国正等译.视觉计算理论[M].北京:科学出版社,1988.
[3] Blake A, Yuille A. Active Vision. Cambridge: MIT Press,1992.
[4]候志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617.
[5]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,(3):225-237.
[6] Yilmaz A, Javed O, Shah M. Object tracking: a Survey[J]. ACM Computing Surveys,2006,38(4):1-45.
[7] Jepson A D, Fleet D J, El-Maraghi T F. Robust online appearance models for visual tracking[C].IEEE Conference on Computer Vision and Pattern Recognition,2001:415-422.
[8] Doulamis A D. Optimal content-based video decomposition for interactive video navigation[J]. IEEETransactions on Circuits and System for video Technology,2004,14(6):757-775.
[9] Guerrero J, Salcudean S E, McEwen J A, et al. Real-time vessel segmentation and tracking forultrasound imaging applications[J]. IEEE Transactions on Medical Imaging,2007,26(8):1079-1090.
[10] Espiau B, Chaumete F, Rives P. A new approach to visual servoing in robotics[J]. IEEE transactionson Robotics and Automation,1992,8(3):313-326.
[11] Collins R T, Lipton A J, Kanade T, et al. Introduction to the special section on video surveillance[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):745-746.
[12] Moeslund T, Granum E. A survey of computervision-based human motion capture[J]. ComputerVison and Image Understanding,2001,81:231-268.
[13] Pai C J, Tyan H R, Liang Y M, et al. Pedestrian detection and tracking at crossroads[J]. PatternRecognition,2004,37(5):1025-1034.
[14] Hsieh J, Yu S, Chen Y, et al. Automatic traffic surveillance system for vehicle tracking andclassification[J]. IEEE Transactions on Intelligent Transportation systems,2006,7(2):175-187.
[15] Tang C W. Spatiotemporal visual considerations for video coding[J]. IEEE Transactions onMultimedia,2007,9(2):231-238.
[16] Remondino F.3-D reconstruction of static human body shape from image sequence[J]. ComputerVision and Image Understanding,2004,93(1):65-85.
[17]陈睿,刘国翌,赵国英,等.基于序列蒙特卡罗方法的3D人体运动跟踪[J].计算机辅助设计与图形学学报,2005,17(1):85-92.
[18]安国成,高建坡,吴镇扬.基于多观测模型的粒子滤波头部跟踪算法[J].中国图象图形学报,2009,14(1):106-111.
[19]牛长锋.复杂背景下视频运动目标跟踪的研究[D]:[博士学位论文].北京:北京理工大学,2010.
[20]陈远.复杂场景中视觉运动目标检测与跟踪[D]:[博士学位论文].武汉:华中科技大学,2008.
[21]徐治非.视频监控中运动目标检测与跟踪方法研究[D]:[博士学位论文].上海:上海交通大学,2009.
[22]王书朋.视频目标跟踪算法研究[D]:[博士学位论文].西安:西安电子科技大学,2009.
[23] Roch R F, Evans D C. ATRAN terrain sensing guidance the grand-daddy system[C]. Procceedings ofthe Society of Photo-optical Instrumentation Engineers, Image Processing for Missile Guidance, SanSiege California,1950,238:2-9.
[24] Eppler W M, Drius G. Two dimensional photographic autocorrelation of pictures and alphabetletters[C]. Proceedings3rd London Symposium on Information Theory, New York,1956:34-36.
[25] Ghaffary B K, Sawchuk A A. A survey of new techniques for image registration and mapping[C].Proceedings of the SPIE: Applications of Digital Image Processing,1983,432:222-239.
[26] Horn B K P, Schunck B G. Determining optical flow[J].Artificial Intelligence,1981,17(1):185-203.
[27] Okada R, Shirai Y, Miura J. Object tracking based on optical flow and depth[C]. Proceedings ofIEEE/SICE/RSJ international conference on MFI,1996:565-571.
[28]甘明刚，陈杰，刘劲等.一种基于三帧差分和边缘信息的运动目标检测方法[J].电子与信息学报，2010,32(4)：894-897.
[29] Monnet A, Mittal A, Paragios N, et al. Background modeling and subtraction of dynamic scenes[C].Proceedings of9th IEEE International Conference on Computer Vision,2003,2:1305-1312.
[30]刘翔.基于光流场算法的运动估计方法研究[J].无线电工程,2006,4(36):17-20.
[31] Markandey V, Reid A, Wang S. Motion estimation for moving target detection[J]. IEEE Transactionson Aerospace and Electronic Systems,1996,32(3):866-874.
[32] Murray D W, Buxton B E. Scene segmentation from visual motion using global optimization[J].IEEE Transactions Pattern Analysis and Machine Intelligence,1987,9:220-228.
[33] Meyer F, Bouthemy P. Region-based tracking using affine motion models in long imagesequences[J]. CVGIP: Image understanding,1994,60(2):119-140.
[34] Bascle B, Deriche R. Region tracking through image sequences[C]. Proceedings of IEEEInternational Conference of Computer Vision,1995,302-307.
[35] Hager G, Belhumeur P. Efficient region tracking with parametric models of geometry andillumination[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,1998,20(10):1025-1039.
[36] Wu Y, Huang T S. Robust visual tracking by integrating multiple cues based on co-inferencelearning[J]. International Journal of Computer Vision,2004,58(1):55-71.
[37] Kaneko T, Hori O. Feature selection for reliable tracking using template matching[C]. Proceedingsof IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR’03.Madison, Wisconsin, USA: IEEE Press,2003,1:796-802.
[38] Mitra P, Murthy C, Pal S. Unsupervised feature selection using feature similarity[J]. IEEETransaction on Pattern Analysis and Machine Intelligence,2002,24(3):301-312.
[39]王永忠,梁彦,赵春晖,等.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(4):393-399.
[40] Tissainayagam P, Suter D. Object tracking in image sequences using point feature[J]. PatternRecognition,2005,38(1):105-113.
[41] Nickels K, Hutchinsion S. Estimating uncertainty in SSD-based feature tracking[J]. Image andVision Computing,2002,20(1):47-58.
[42] Yu Z, Jain A K, Dubuisson-Jolly M. Object tracking using deformable templates[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(5):544-549.
[43]王洪元，周则明，王平安，等.一种改进Snake模型的边缘检测算法[J].南京理工大学学报,2003,4(27):359-399.
[44] Paragios N, Deriche R. Geodesic active contours and level set for the detection and tracking ofmoving objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(3):266-280.
[45]龚永义,罗笑南,黄辉,等.基于单水平集的多目标轮廓提取[J].计算机学报,2007,30(1):120-128.
[46] Koschan A, Kang S, Paik J, et al. Color active shape models for tracking non-rigid objects [J].Pattern Recognition Letters,2003,24(11):1751-1765.
[47] Hu W M, Tan T N, Wang L, et al. A survey on visual surveillance of object motion and behaviors[C].IEEE Transactions on Systems, Man, and Cybernetics-Part C: Applications and Reviews,2004,34(3):334-352.
[48]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,2003.
[49] Shalom Y B, Fortman T. Tracking and data association[M]. New York: Acadenmic Press,1998.
[50] Huang C M, Liu D, Fu L C. Visual tracking in cluttered environments using the visual probabilisticdata association filter[J]. IEEE Transactions on Robotics,2006,22(6):1292-1297.
[51] Williams O, Blake A, Cipolla R. Sparse Bayesian learing for efficient visual tracking[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27(8):1292-1304.
[52]孙伟.基于粒子滤波的视频目标跟踪关键技术及应用研究[D]:[博士学位论文].西安:西安电子科技大学,2009.
[53] Schmidt S F. The Kalman Filter: Its recognition and development for aerospace applications[J].Journal of Guidance and Control,1981,4(1):4-7.
[54] Kalman R E. A new approach to linear filtering and prediction problems[J]. Transactions of theASME-Journal of basic engineering,1960,82:35-45.
[55] Anders E N. A constrained extended Kalman Filter for target tracking [C]. Proceedings of the IEEEInternational Conference of Radar, Philadelphia, USA，2004：123-127.
[56] Julier S J, Uhlmann J K. Unscented filtering and nonlinear estimation[J]. Proceedings of the IEEE,2004,92(3):401-422.
[57] Wu Y X, Wu M P, Hu D W, et al. Unscented Kalman Filtering for additive noise case: augmentedversus nonaugmented[J]. IEEE Signal Processing Letters,2005,12(5):357-360.
[58]王法胜,赵清杰.一种用于解决非线性滤波问题的新型粒子滤波算法[J].计算机学报,2008,31(2):346-352.
[59]杨小军,潘泉,王睿.粒子滤波进展与展望[J].控制理论与应用,2006,23(2):261-267.
[60] Perez P, Vermaak J, Blake A. Data fusion for visual tracking with particles[J]. Proceedings of theIEEE,2004,92(3):495-513.
[61] Noguer M F, Sanfeliu A, Samaras D. Dependent multiple cue integration for robust tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(4):670-685.
[62] Zhou Q M, Aggarwal J K. Object tracking in an outdoor environment using fusion of features andcameras[J]. Image and Vision Computing,2006,24(11):1244-1255.
[63] Han B, Davis L S. Probabilistic fusion-based parameter estimation for visual tracking[J]. ComputerVision and Image Understanding,2009,113(4):435-445.
[64] Wang J, Yagi Y. Integrating color and shape-texture features for adaptive real-time object tracking[J].IEEE Transactions on Image Processing,2008,17(2):235-240.
[65] Shan C, Tan T, Wei Y. Real-time hand tracking using a mean shift embedded particle filter[J]. PatternRecognition,2007,40(7):1958-1970.
[66] Brasnett P, Mihayhova L, Bull D. Sequential Monte Carlo tracking by fusing multiple cues in videosequences[J]. Image Vision Computing,2007,25(8):1217-1227.
[67] Babenko B, Yang M H, Belongie S. Robust Object Tracking with Online Multiple InstanceLearning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1619-1632.
[68]袁广林,薛模根,谢恺,等.基于核函数粒子滤波和多特征自适应融合的目标跟踪[J].计算机辅助设计与图形学学报,2009,2l(12):1774-1784.
[69]田纲.基于多特征融合的Mean shift目标跟踪技术研究[D]:[博士学位论文].武汉:武汉大学,2011.
[70] Collins R, Lipton A, Kanade T, et-al. A system for video surveillance and monitoring: VSAM finalreport[R]. CMU-RI-TR-00-12, Robotic Institute Carnegie Mellon University,2000.
[71] Fujiyoshi H, Kanade T. VSAM: Video surveillance and monitoring project[J]. Journal of the Instituteof Image Information and Television Engineers,2003,57(9):1068-1072.
[72] http://www-sop.inria.fr/orion/ADVISOR/
[73] Haritaoglu I, Harwood D, Davis L S. W4: Real-time surveillance of people and their activities[J].IEEE Transactions Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[74] Ferryman J. AVITRACK: Aircraft surroundings, categorized vehicles&individuals tracking forapron activity model interpretation&check[C]. In IEEE International Conference on ComputerVision and Pattern Recognition, San Diego, USA,2005.
[75] Andrade E, Blunsden S, Fisher R. Simulation of crowd problems for computer vision[C]. Proceedingof First International Workshop on Crowd Simulation,2005:71-80.
[76]焦波.面向智能视频监控的运动目标检测与跟踪方法研究[D]:[博士学位论文].长沙：国防科学技术大学，2009.
[77]邸男,朱明.一种复杂背景下的实时目标跟踪算法[J].中国图象图形学报,2008,13(9):1759-1766.
[78]尹宏鹏.基于计算机视觉的运动目标跟踪算法研究[D]:[博士学位论文].重庆:重庆大学,2009.
[79]文志强.基于均值偏移算法的运动目标跟踪技术的研究[D]:[博士学位论文].长沙:中南大学,2008.
[80]张波.基于粒子滤波的图像跟踪算法研究[D]:[博士学位论文].上海:上海交通大学,2007.
[81]王勇.基于统计方法的运动目标检测与跟踪技术研究[D]:[博士学位论文].武汉:华中科技大学,2009.
[82] Zhou S K, Chellappa R, Moghaddan B. Visual tracking and recognition using appearance-adaptivemodels in particle filters[J]. IEEE Transactions on Image Processing,2004,13(11):1491-1506.
[83] Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis［J］. IEEETransactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[84] Isard M, Blake A. Condensation-conditional density propagation for visual tracking[J]. InternationalJournal of Computer Vision,1998,29(1):5-28.
[85] Doucet A, Godsill S, Andrieu C. On sequential Monte Carlo sampling methods for Bayesianfiltering[J]. Statist Computer,2000,10:197-208.
[86]盛骤等,概率论与数理统计[M].北京:高等教育出版社,1989.
[87] Welch G, Bishop G. An introduction to the Kalman Filter[R]. TR95-041,Department of ComputerScience University of North Carolina at Chapel Hill, NC27599-3175Updated2004,4:1-16.
[88] Djuric P M, Kotecba J H, Zhang J Q, et al. Particle filtering[J].IEEE Signal Processing Magazine,2003:19-38.
[89] Handschin J E, Mayne D Q. Monte carlo techniques to estimate the conditional expectation inmulti-stage non-linear filtering[J]. International Journal of Control,1969,9(5):547-559.
[90] Kitagawa G. Monte Carlo filter and smoother for non-Gaussian nonlinear state space models[J].Journal of Computational and Graphical Statistics,1996,5(1):1-25.
[91]李庆扬,关治,白峰杉.数值计算原理[M].北京：清华大学出版社,2000.
[92] Gordon N J, Salmond D J, Smith A F M. Novel approach to nonlinear/non-Gaussian Bayesian stateestimation[J]. In IEEE Proceedings on Radar and Signal Processing,1993,140(4):107-113.
[93] Banerjee A, Burlina P. Efficient particle filtering via sparse kernel density estimation[J]. IEEETransactions on Image Processing,2010,19(9):2480-2490.
[94]宁小磊,王宏力,徐宏林,等.加权逼近粒子滤波算法及其应用[J].控制理论与应用,2011,28(1):118-124.
[95] Fukunage K，Hostetler L D. The estimation of the gradient of a density function with application inpattern recognition[J]. IEEE Transactions on Information Theory,1975,21(1):32-40.
[96] Cheng Y. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,1995,17(8):790-799.
[97] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[J]. IEEE Transaction on PatternAnalysis and Machine Intelligence,2003,25(5):564-577.
[98]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.
[99] Fashing M, Tomasi C. Mean Shift is a bound optimization[J]. IEEE Transactions on Pattern Analysisand Machine Intelligence,2005,27(3):471-474.
[100]朱胜利. Mean Shift及相关算法在视频跟踪中的研究[D]:[博士学位论文].杭州：浙江大学，2006.
[101]王江涛.基于视频的目标检测、跟踪及其行为识别研究[D]:[博士学位论文].南京：南京理工大学，2008.
[102]王芳林.稳健视觉跟踪算法中的关键问题研究[D]:[博士学位论文].上海：上海交通大学，2009.
[103] Li P H, Zhang T W. Visual contour tracking based on sequential importance sampling/resamplingalgorithm[C]. Proceedings of the16th International Conference on Pattern Recognition, Canada:IEEE Computer Society,2002,2:564-568.
[104]胡昭华.基于粒子滤波的视频目标跟踪技术研究[D]:[博士学位论文].南京：南京理工大学，2008.
[105]张焱,张志龙,沈振康,等.基于动态显著性特征的粒子滤波多目标跟踪算法[J].电子学报,2008,39(12):2305-2311.
[106] Gustafsson F, Gunnarsson F, Bergman N, et al. Particle filters for positioning, navigation andtracking[J]. IEEE Transactions on Signal Processing,2002,50(2):425-437.
[107]胡士强,敬忠良.粒子滤波算法综述[J].控制与决策,2005,20(4):361-365.
[108] Pitt M K, Shephard N. Filtering via simulation: Auxiliary particle filters[J]. Journal of the AmericanStatistical Association,1999,94(2):590-599.
[109] Khan Z, Balch T, Dellaert F. MCMC-based particle filtering for tracking a variable number ofinteracting targets[J]. Transactions on Pattern Analysis and Machine Intelligence,2005,27(11):1805-1819.
[110] Kotecha J H, Djuric P M. Gaussian particle filtering[J]. IEEE Transactions on Signal Processing,2003,51(10):2592-2601.
[111] Lehn-Schioler T, Erdogmus D, Principe J C. Parzen particle filters[C]. Proceedings of InternationalConference on Acoustics, Speech, and Signal Processing, Montreal, Canada,2004(V):781-784.
[112] Bouaynaya N, Schonfeld D. On the optimality of motion-based particle filtering[J]. IEEETransactions on Circuits and Systems for Video Technology,2009,19(7):1068-1072.
[113] Yee Y, Reilly J P, Kirubarajan T, et al. Approximate conditional mean particle filtering forlinear/nonlinear dynamic state space models[J]. IEEE Transactions on Signal Processing,2008,56(12):5790-7803.
[114] Yao A B, Wang G J, Lin X G, et al. An incremental bhattacharyya dissimilarity measure for particlefiltering[J]. Pattern Recognition,2010,43(4):1244-1256.
[115] Campillo F, Rossi V. Convolution particle filter for parameter estimation in general state-spacemodels[J]. IEEE Transactions on Aerospace and Electronic Systems,2009,45(3):1063-1072.
[116] Chang C, Ansari R. Kernel particle filter for visual tracking[J]. IEEE Signal Processing Letters,2005,12(3):242-245.
[117]姚红革,齐华,郝重阳.复杂情形下目标跟踪的自适应粒子滤波算法[J].电子与信息学报,2009,31(2):275-278.
[118]宋宇,孙富春,李庆玲.移动机器人的改进无迹粒子滤波蒙特卡罗定位算法[J].自动化学报,2010,36(6):851-857.
[119]杨淑莹,吴涛,张迎,等.基于模拟退火的粒子滤波在目标跟踪中的应用[J].光电子·激光,2011,(8):1236-1240.
[120]余孟泽,刘正熙,骆键,等.基于改进粒子滤波的鲁棒目标跟踪算法[J].光电子·激光,2011,(5):766-771.
[121]李静,陈兆乾,陈世福. EM-GMPF:一种基于EM的混合高斯粒子滤波器算法[J].计算机研究与发展,2005,42(7):1210-1216.
[122] Bimbo A D, Dini F. Particle filter-based visual tracking with a first order dynamic model anduncertainty adaptation[J]. Computer Vision and Image Understanding,2011,115(6):771-786.
[123] Nejhum S M S, Ho J, Yang M H. Online visual tracking with histograms and articulating blocks[J].Computer Vision and Image Understanding,2010,114(8)：901-914.
[124] Chu J K, Li R H, Li Q Y, et al. A visual Attention Model for Robot Object Tracking[J]. InternationalJournal of Automation and Computing,2010,7(2):39-46.
[125] Han Z J, Ye Q X, Jiao J B. Combined feature evaluation for adaptive visual object tracking[J].Computer Vision and Image Understanding,2011,115(1):69-80.
[126]郭康德,张明敏,孙超,等.基于视觉技术的三维指尖跟踪算法[J].计算机研究与发展,2010,47(6):1013-1019.
[127] Chang I C, Lin S Y.3D human motion tracking based on a progressive particle filter[J]. PatternRecognition,2010,43(10):3621-3635.
[128] Mei X, Ling H B. Robust visual tracking and vehicle classification via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(11):2259-2272.
[129]安国成,张凤军,王宏安,等.多窗口目标跟踪算法[J].计算机研究与发展,2011,48(11):2023-2030.
[130]刘晨光,刘家锋,黄剑华,等.基于多特征融合的分块采样粒子滤波算法在人体姿态跟踪中的应用[J].计算机研究与发展,2011,48(12):2359-2368.
[131] Li B, Yan W. Road tracking using particle filters with partition sampling and auxiliary variables[J].Computer Vision and Image Understanding,2011,115(10):1463-1471.
[132] Chen Y, Wang J Z. A region-based fuzzy feature matching approach to content-based imageretrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(9):1252-1267.
[133] Nguyen H T, Worring M, Van D R. Occlusion robust adaptive template tracking[C]. Proceedings ofthe8th International Conference on Computer Vision, Vancouver, Canada,2001:678-683.
[134]甘明刚,陈杰,王亚楠,等.基于Mean Shift算法和NMI特征的目标跟踪算法研究[J].自动化学报,2010,36(9):1332-1336.
[135] Karavasilis V, Nikou C, Likas C. Visual tracking by adaptive Kalman Filtering and Mean Shift[J].Lecture Notes in Computer Science, Artificial Intelligence: Theories, Models and Applications,2010,6040:153-162.
[136] Stuffer C, Grimson W E L. Learning patterns of activity using real-time tracking[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[137] Nummiaro K, Koller M E, Gool L V. An adaptive color-based particle flter[J]. Image and VisionComputing,2003,21(1):99-110.
[138] Yang T, Li S Z, Pan Q, et al. Real-time multiple objects tracking with occlusion handling in dynamicscenes[C]. Computer Vision and Pattern Recognition, San Diego,2005:970-975.
[139] Nailk N, Patil S, Joshi S. A fragment based scale adaptive tracker with partial occlusion handling[C].IEEE Conference on TENCON, Singapore,2009,1:1-6.
[140] Phadke G. Robust multiple target tracking under occlusion using fragmented mean shift and KalmanFilter[C].2011International Conference on Communications and Signal Process-ing, Kerala,2:517-521.
[141]颜佳,吴敏渊,陈淑珍,等.应用Mean Shift和分块的抗遮挡跟踪[J].光学精密工程,2010,18(6):1413-1419.
[142]齐美彬,张莉,蒋建国,等.分块跟踪中的目标模板更新方法[J].中国图象图形学报,2011,16(6):976-982.
[143] Liu H, Yu Z, Zha H B, et al. Robust human tracking based on multi-cue integration and mean-shift[J].Pattern Recognition Letters,2009,30(7):827-837.
[144] Leichter I, Lindenbaum M, Rivlin E. Tracking by affine kernel transformations using color andboundary cues[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(1):164-171.
[145] Hu J S, Juan C W, Wang J J. A spatial-color mean-shift object tracking algorithm with scale andorientation estimation[J]. Pattern Recognition Letters,2008,29(16):2165-2173.
[146] Wang H Z, Suter D, Schindler K, et al. Adaptive object tracking based on an effective appearancefilter[J]. IEEE Transactions on Pattern Analysis and Machine intelligence,2007,29(9):1661-1667.
[147]覃剑,曾孝平,李勇明.基于边界力的Mean-Shift核窗宽自适应算法[J].软件学报,2009,20(7):1726-1734.
[148] Leichter I, Lindenbaum M M, Rivin E. Mean Shift tracking with multiple reference colorhistograms[J]. Computer Vision and Image Understanding,2010,114(3):400-408.
[149] Birchfield S T， Rangarajan S. Spatiograms versus histograms for region-based tracking[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. San Diego,California, United States: IEEE,2005,6(2):1158-1163.
[150] Collins R T, Liu Y, Leordeanu M. Online selection of discriminative tacking features[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27(10):1631-1643.
[151] Haritaoglu I, Flickner M. Detection and tracking of shopping groups in stores[C]. Proceeding of the2001IEEE Computer Vision and Pattern Recognition,2001,1(12):8-14.
[152] Li S X, Chang H X, Zhu C F. Adaptive pyramid mean shift for global real-time visual tracking[J].Image and Vision Computing,2010,28(3):424-437.
[153]章毓晋.图像工程(第二版)[M].北京:清华大学出版社,2007:168-171.
[154]沈悦,吴小俊.基于模糊隶属关系的Mean Shift图像跟踪改进算法[J].电子信息学报,2008,30(11):2688-2692.
[155] Babu R V, Perez P, Bouthemy P. Robust tracking with motion estimation and local kernel-basedcolor modeling[J]. Image and Vision Computing,2007,25(8):1205-1216.
[156]沈志熙,杨欣,黄席樾.均值漂移算法中的目标模型更新方法研究[J].自动化学报,2009,35(5):478-483.
[157] Qi Z, Zhi Y, Hai T. Differential earth mover’s distance with its applications to visual tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(2):274-287.
[158] Chung Y S, Jung S U, Ba Y L, et al. Face feature extraction using elliptical model based backgrounddeletion and generalized FEM[C]. Proceedings of the2007Third International IEEE Conference onSignal-Image Technologies and Internet-Based System,2007,(9):757-762.
[159] Birchfield S. An elliptical head tracker[C].31st Asilomar Conference on Signals, Systems andComputers,1997,(11):1710-1714.
[160] Bradski G R. Computer vision face tracking for use in a perceptual user interface[C]. IEEEWorkshop on Application of Computer Vision, New York: IEEE,1998:214-219.
[161] Collins R T. Mean-Shift blob tracking through scale space[C]. Proceedings of IEEE InternationalConference on Computer Vision and Pattern Recognition,2003:234-240.
[162]彭宁嵩,杨杰,刘志,等. Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9):1542-1550.
[163] Feng Z R, Lu N, Jinag P. Posterior probability measure for image matching[J]. Pattern recognition,2008,(41):2422-2433.
[164]吕娜.图像匹配与跟踪研究[D]:[博士学位论文].西安：西安交通大学，2008.
[165] Nguyen H, Smeulders A. Robust tracking using foreground-background texture discrimination[J].International Journal of Computer Vision,2006,69(3):277-293.
[166] Zhu G P, Zeng Q S, Wang C H. Efficient edge-based object tracking[J]. Pattern Recognition,2006,39(11):2223-2226.
[167] Buenaposada J, Munoz E, Baumela L. Efficient illumination independent appearance-based facetracking[J]. Image and Vision Computing,2009,27(5):560-578.
[168]张华.运动目标跟踪算法的若干方法研究[D]:[硕士学位论文].南京:南京理工大学,2008.
[169]卢晓鹏.视频序列中目标跟踪技术研究[D]:[博士学位论文].北京:中国科学院研究生院（电子学研究所）,2007.
[170]姚剑敏.粒子滤波跟踪方法研究[D]:[博士学位论文].长春:中国科学院研究生院（长春光学精密机械与物理研究所）,2004.
[171]单勇.复杂条件下视频运动目标检测和跟踪[D]:[博士学位论文].长沙:国防科学技术大学,2006.
[172]崔彦.序列图像中运动目标检测与跟踪技术研究[D]:[硕士学位论文].西安:西安电子科技大学硕士论文,2009.
[173] Perez P, Hue C, Vermaak J, et al Color-based probabilistic tracking[C]. Proceedings of the EuropeanConference on Computer Vision, Copenhagen, Denmark, May28-31,2002:661-675.
[174] Town C. Multi-sensory and multi-modal fusion for sentient computing[J]. International Journal ofComputer Vision,2007,71(2):235-253.
[175]王欢,王江涛,任明武,等.一种鲁棒的多特征融合目标跟踪新算法[J].中国图象图形学报,2009,14(3):489-498.
[176]钟小品,薛建儒,郑南宁,等.基于融合策略自适应的多线索跟踪方法[J].电子与信息学报,2007,29(5):1017-1021.
[177]姚剑敏,杨春建,刘经场,等.多特征融合的非线性目标跟踪算法[J].光电工程,2008,35(3):5-9.
[178]顾鑫,王海涛,汪凌峰,等.基于不确定性度量的多特征融合跟踪[J].自动化学报,2011,37(5):550-559.
[179] Li Y, Ai H, Huang C, et al. Robust head tracking with particles based on multiple cues[C].Proceedings of the9th European Conference on Computer Vision Workshop on Human-ComputerInteraction, Graz, Austria,2006:29-39.
[180]曾慧,穆志纯,王秀青.一种鲁棒的图像局部特征区域的描述方法[J].自动化学报2011,37(6):658-664.
[181]王永忠,梁彦,潘泉,等.基于自适应混合高斯模型的时空背景建模[J].自动化学报,2009,35(4):371-378.
[182]王瑜,穆志纯,付冬梅,等.基于小波变换和规范型纹理描述子的人耳识别[J].电子学报,2010,38(1):239-243.
[183]李晓华,沈兰荪.基于小波压缩域的统计纹理特征提取方法[J].电子学报,2003,31(12A):2123-2126.
[184]贾慧星,章毓晋.基于梯度方向直方图特征的多核跟踪[J].自动化学报,2009,35(10):1283-1289.
[185] Dala N, Triggs B. Histograms of oriented gradients for human detection[C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition, San Diego, USA,2005:886-893.
[186] Moore S, Bowden R. Local binary patterns for multi-view facial expression recognition[J].Computer Vision and Image Understanding,2011,115(4):541-558.
[187] Ojala T, Pietik inen M, Harwood D. A comparative study of texture measures with classificationbased on feature distributions[J]. Pattern Recognition,1996,29(1):51-59.
[188] Ojala T, Pietik inen M, M enp T. Multiresolution grayscale and rotation invariant textureclassification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2002,24(7):971-987.
[2] Marr D,姚国正等译.视觉计算理论[M].北京:科学出版社,1988.
[3] Blake A, Yuille A. Active Vision. Cambridge: MIT Press,1992.
[4]候志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617.
[5]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,(3):225-237.
[6] Yilmaz A, Javed O, Shah M. Object tracking: a Survey[J]. ACM Computing Surveys,2006,38(4):1-45.
[7] Jepson A D, Fleet D J, El-Maraghi T F. Robust online appearance models for visual tracking[C].IEEE Conference on Computer Vision and Pattern Recognition,2001:415-422.
[8] Doulamis A D. Optimal content-based video decomposition for interactive video navigation[J]. IEEETransactions on Circuits and System for video Technology,2004,14(6):757-775.
[9] Guerrero J, Salcudean S E, McEwen J A, et al. Real-time vessel segmentation and tracking forultrasound imaging applications[J]. IEEE Transactions on Medical Imaging,2007,26(8):1079-1090.
[10] Espiau B, Chaumete F, Rives P. A new approach to visual servoing in robotics[J]. IEEE transactionson Robotics and Automation,1992,8(3):313-326.
[11] Collins R T, Lipton A J, Kanade T, et al. Introduction to the special section on video surveillance[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):745-746.
[12] Moeslund T, Granum E. A survey of computervision-based human motion capture[J]. ComputerVison and Image Understanding,2001,81:231-268.
[13] Pai C J, Tyan H R, Liang Y M, et al. Pedestrian detection and tracking at crossroads[J]. PatternRecognition,2004,37(5):1025-1034.
[14] Hsieh J, Yu S, Chen Y, et al. Automatic traffic surveillance system for vehicle tracking andclassification[J]. IEEE Transactions on Intelligent Transportation systems,2006,7(2):175-187.
[15] Tang C W. Spatiotemporal visual considerations for video coding[J]. IEEE Transactions onMultimedia,2007,9(2):231-238.
[16] Remondino F.3-D reconstruction of static human body shape from image sequence[J]. ComputerVision and Image Understanding,2004,93(1):65-85.
[17]陈睿,刘国翌,赵国英,等.基于序列蒙特卡罗方法的3D人体运动跟踪[J].计算机辅助设计与图形学学报,2005,17(1):85-92.
[18]安国成,高建坡,吴镇扬.基于多观测模型的粒子滤波头部跟踪算法[J].中国图象图形学报,2009,14(1):106-111.
[19]牛长锋.复杂背景下视频运动目标跟踪的研究[D]:[博士学位论文].北京:北京理工大学,2010.
[20]陈远.复杂场景中视觉运动目标检测与跟踪[D]:[博士学位论文].武汉:华中科技大学,2008.
[21]徐治非.视频监控中运动目标检测与跟踪方法研究[D]:[博士学位论文].上海:上海交通大学,2009.
[22]王书朋.视频目标跟踪算法研究[D]:[博士学位论文].西安:西安电子科技大学,2009.
[23] Roch R F, Evans D C. ATRAN terrain sensing guidance the grand-daddy system[C]. Procceedings ofthe Society of Photo-optical Instrumentation Engineers, Image Processing for Missile Guidance, SanSiege California,1950,238:2-9.
[24] Eppler W M, Drius G. Two dimensional photographic autocorrelation of pictures and alphabetletters[C]. Proceedings3rd London Symposium on Information Theory, New York,1956:34-36.
[25] Ghaffary B K, Sawchuk A A. A survey of new techniques for image registration and mapping[C].Proceedings of the SPIE: Applications of Digital Image Processing,1983,432:222-239.
[26] Horn B K P, Schunck B G. Determining optical flow[J].Artificial Intelligence,1981,17(1):185-203.
[27] Okada R, Shirai Y, Miura J. Object tracking based on optical flow and depth[C]. Proceedings ofIEEE/SICE/RSJ international conference on MFI,1996:565-571.
[28]甘明刚，陈杰，刘劲等.一种基于三帧差分和边缘信息的运动目标检测方法[J].电子与信息学报，2010,32(4)：894-897.
[29] Monnet A, Mittal A, Paragios N, et al. Background modeling and subtraction of dynamic scenes[C].Proceedings of9th IEEE International Conference on Computer Vision,2003,2:1305-1312.
[30]刘翔.基于光流场算法的运动估计方法研究[J].无线电工程,2006,4(36):17-20.
[31] Markandey V, Reid A, Wang S. Motion estimation for moving target detection[J]. IEEE Transactionson Aerospace and Electronic Systems,1996,32(3):866-874.
[32] Murray D W, Buxton B E. Scene segmentation from visual motion using global optimization[J].IEEE Transactions Pattern Analysis and Machine Intelligence,1987,9:220-228.
[33] Meyer F, Bouthemy P. Region-based tracking using affine motion models in long imagesequences[J]. CVGIP: Image understanding,1994,60(2):119-140.
[34] Bascle B, Deriche R. Region tracking through image sequences[C]. Proceedings of IEEEInternational Conference of Computer Vision,1995,302-307.
[35] Hager G, Belhumeur P. Efficient region tracking with parametric models of geometry andillumination[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,1998,20(10):1025-1039.
[36] Wu Y, Huang T S. Robust visual tracking by integrating multiple cues based on co-inferencelearning[J]. International Journal of Computer Vision,2004,58(1):55-71.
[37] Kaneko T, Hori O. Feature selection for reliable tracking using template matching[C]. Proceedingsof IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR’03.Madison, Wisconsin, USA: IEEE Press,2003,1:796-802.
[38] Mitra P, Murthy C, Pal S. Unsupervised feature selection using feature similarity[J]. IEEETransaction on Pattern Analysis and Machine Intelligence,2002,24(3):301-312.
[39]王永忠,梁彦,赵春晖,等.基于多特征自适应融合的核跟踪方法[J].自动化学报,2008,34(4):393-399.
[40] Tissainayagam P, Suter D. Object tracking in image sequences using point feature[J]. PatternRecognition,2005,38(1):105-113.
[41] Nickels K, Hutchinsion S. Estimating uncertainty in SSD-based feature tracking[J]. Image andVision Computing,2002,20(1):47-58.
[42] Yu Z, Jain A K, Dubuisson-Jolly M. Object tracking using deformable templates[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(5):544-549.
[43]王洪元，周则明，王平安，等.一种改进Snake模型的边缘检测算法[J].南京理工大学学报,2003,4(27):359-399.
[44] Paragios N, Deriche R. Geodesic active contours and level set for the detection and tracking ofmoving objects[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(3):266-280.
[45]龚永义,罗笑南,黄辉,等.基于单水平集的多目标轮廓提取[J].计算机学报,2007,30(1):120-128.
[46] Koschan A, Kang S, Paik J, et al. Color active shape models for tracking non-rigid objects [J].Pattern Recognition Letters,2003,24(11):1751-1765.
[47] Hu W M, Tan T N, Wang L, et al. A survey on visual surveillance of object motion and behaviors[C].IEEE Transactions on Systems, Man, and Cybernetics-Part C: Applications and Reviews,2004,34(3):334-352.
[48]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,2003.
[49] Shalom Y B, Fortman T. Tracking and data association[M]. New York: Acadenmic Press,1998.
[50] Huang C M, Liu D, Fu L C. Visual tracking in cluttered environments using the visual probabilisticdata association filter[J]. IEEE Transactions on Robotics,2006,22(6):1292-1297.
[51] Williams O, Blake A, Cipolla R. Sparse Bayesian learing for efficient visual tracking[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27(8):1292-1304.
[52]孙伟.基于粒子滤波的视频目标跟踪关键技术及应用研究[D]:[博士学位论文].西安:西安电子科技大学,2009.
[53] Schmidt S F. The Kalman Filter: Its recognition and development for aerospace applications[J].Journal of Guidance and Control,1981,4(1):4-7.
[54] Kalman R E. A new approach to linear filtering and prediction problems[J]. Transactions of theASME-Journal of basic engineering,1960,82:35-45.
[55] Anders E N. A constrained extended Kalman Filter for target tracking [C]. Proceedings of the IEEEInternational Conference of Radar, Philadelphia, USA，2004：123-127.
[56] Julier S J, Uhlmann J K. Unscented filtering and nonlinear estimation[J]. Proceedings of the IEEE,2004,92(3):401-422.
[57] Wu Y X, Wu M P, Hu D W, et al. Unscented Kalman Filtering for additive noise case: augmentedversus nonaugmented[J]. IEEE Signal Processing Letters,2005,12(5):357-360.
[58]王法胜,赵清杰.一种用于解决非线性滤波问题的新型粒子滤波算法[J].计算机学报,2008,31(2):346-352.
[59]杨小军,潘泉,王睿.粒子滤波进展与展望[J].控制理论与应用,2006,23(2):261-267.
[60] Perez P, Vermaak J, Blake A. Data fusion for visual tracking with particles[J]. Proceedings of theIEEE,2004,92(3):495-513.
[61] Noguer M F, Sanfeliu A, Samaras D. Dependent multiple cue integration for robust tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(4):670-685.
[62] Zhou Q M, Aggarwal J K. Object tracking in an outdoor environment using fusion of features andcameras[J]. Image and Vision Computing,2006,24(11):1244-1255.
[63] Han B, Davis L S. Probabilistic fusion-based parameter estimation for visual tracking[J]. ComputerVision and Image Understanding,2009,113(4):435-445.
[64] Wang J, Yagi Y. Integrating color and shape-texture features for adaptive real-time object tracking[J].IEEE Transactions on Image Processing,2008,17(2):235-240.
[65] Shan C, Tan T, Wei Y. Real-time hand tracking using a mean shift embedded particle filter[J]. PatternRecognition,2007,40(7):1958-1970.
[66] Brasnett P, Mihayhova L, Bull D. Sequential Monte Carlo tracking by fusing multiple cues in videosequences[J]. Image Vision Computing,2007,25(8):1217-1227.
[67] Babenko B, Yang M H, Belongie S. Robust Object Tracking with Online Multiple InstanceLearning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1619-1632.
[68]袁广林,薛模根,谢恺,等.基于核函数粒子滤波和多特征自适应融合的目标跟踪[J].计算机辅助设计与图形学学报,2009,2l(12):1774-1784.
[69]田纲.基于多特征融合的Mean shift目标跟踪技术研究[D]:[博士学位论文].武汉:武汉大学,2011.
[70] Collins R, Lipton A, Kanade T, et-al. A system for video surveillance and monitoring: VSAM finalreport[R]. CMU-RI-TR-00-12, Robotic Institute Carnegie Mellon University,2000.
[71] Fujiyoshi H, Kanade T. VSAM: Video surveillance and monitoring project[J]. Journal of the Instituteof Image Information and Television Engineers,2003,57(9):1068-1072.
[72] http://www-sop.inria.fr/orion/ADVISOR/
[73] Haritaoglu I, Harwood D, Davis L S. W4: Real-time surveillance of people and their activities[J].IEEE Transactions Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[74] Ferryman J. AVITRACK: Aircraft surroundings, categorized vehicles&individuals tracking forapron activity model interpretation&check[C]. In IEEE International Conference on ComputerVision and Pattern Recognition, San Diego, USA,2005.
[75] Andrade E, Blunsden S, Fisher R. Simulation of crowd problems for computer vision[C]. Proceedingof First International Workshop on Crowd Simulation,2005:71-80.
[76]焦波.面向智能视频监控的运动目标检测与跟踪方法研究[D]:[博士学位论文].长沙：国防科学技术大学，2009.
[77]邸男,朱明.一种复杂背景下的实时目标跟踪算法[J].中国图象图形学报,2008,13(9):1759-1766.
[78]尹宏鹏.基于计算机视觉的运动目标跟踪算法研究[D]:[博士学位论文].重庆:重庆大学,2009.
[79]文志强.基于均值偏移算法的运动目标跟踪技术的研究[D]:[博士学位论文].长沙:中南大学,2008.
[80]张波.基于粒子滤波的图像跟踪算法研究[D]:[博士学位论文].上海:上海交通大学,2007.
[81]王勇.基于统计方法的运动目标检测与跟踪技术研究[D]:[博士学位论文].武汉:华中科技大学,2009.
[82] Zhou S K, Chellappa R, Moghaddan B. Visual tracking and recognition using appearance-adaptivemodels in particle filters[J]. IEEE Transactions on Image Processing,2004,13(11):1491-1506.
[83] Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis［J］. IEEETransactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[84] Isard M, Blake A. Condensation-conditional density propagation for visual tracking[J]. InternationalJournal of Computer Vision,1998,29(1):5-28.
[85] Doucet A, Godsill S, Andrieu C. On sequential Monte Carlo sampling methods for Bayesianfiltering[J]. Statist Computer,2000,10:197-208.
[86]盛骤等,概率论与数理统计[M].北京:高等教育出版社,1989.
[87] Welch G, Bishop G. An introduction to the Kalman Filter[R]. TR95-041,Department of ComputerScience University of North Carolina at Chapel Hill, NC27599-3175Updated2004,4:1-16.
[88] Djuric P M, Kotecba J H, Zhang J Q, et al. Particle filtering[J].IEEE Signal Processing Magazine,2003:19-38.
[89] Handschin J E, Mayne D Q. Monte carlo techniques to estimate the conditional expectation inmulti-stage non-linear filtering[J]. International Journal of Control,1969,9(5):547-559.
[90] Kitagawa G. Monte Carlo filter and smoother for non-Gaussian nonlinear state space models[J].Journal of Computational and Graphical Statistics,1996,5(1):1-25.
[91]李庆扬,关治,白峰杉.数值计算原理[M].北京：清华大学出版社,2000.
[92] Gordon N J, Salmond D J, Smith A F M. Novel approach to nonlinear/non-Gaussian Bayesian stateestimation[J]. In IEEE Proceedings on Radar and Signal Processing,1993,140(4):107-113.
[93] Banerjee A, Burlina P. Efficient particle filtering via sparse kernel density estimation[J]. IEEETransactions on Image Processing,2010,19(9):2480-2490.
[94]宁小磊,王宏力,徐宏林,等.加权逼近粒子滤波算法及其应用[J].控制理论与应用,2011,28(1):118-124.
[95] Fukunage K，Hostetler L D. The estimation of the gradient of a density function with application inpattern recognition[J]. IEEE Transactions on Information Theory,1975,21(1):32-40.
[96] Cheng Y. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,1995,17(8):790-799.
[97] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[J]. IEEE Transaction on PatternAnalysis and Machine Intelligence,2003,25(5):564-577.
[98]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.
[99] Fashing M, Tomasi C. Mean Shift is a bound optimization[J]. IEEE Transactions on Pattern Analysisand Machine Intelligence,2005,27(3):471-474.
[100]朱胜利. Mean Shift及相关算法在视频跟踪中的研究[D]:[博士学位论文].杭州：浙江大学，2006.
[101]王江涛.基于视频的目标检测、跟踪及其行为识别研究[D]:[博士学位论文].南京：南京理工大学，2008.
[102]王芳林.稳健视觉跟踪算法中的关键问题研究[D]:[博士学位论文].上海：上海交通大学，2009.
[103] Li P H, Zhang T W. Visual contour tracking based on sequential importance sampling/resamplingalgorithm[C]. Proceedings of the16th International Conference on Pattern Recognition, Canada:IEEE Computer Society,2002,2:564-568.
[104]胡昭华.基于粒子滤波的视频目标跟踪技术研究[D]:[博士学位论文].南京：南京理工大学，2008.
[105]张焱,张志龙,沈振康,等.基于动态显著性特征的粒子滤波多目标跟踪算法[J].电子学报,2008,39(12):2305-2311.
[106] Gustafsson F, Gunnarsson F, Bergman N, et al. Particle filters for positioning, navigation andtracking[J]. IEEE Transactions on Signal Processing,2002,50(2):425-437.
[107]胡士强,敬忠良.粒子滤波算法综述[J].控制与决策,2005,20(4):361-365.
[108] Pitt M K, Shephard N. Filtering via simulation: Auxiliary particle filters[J]. Journal of the AmericanStatistical Association,1999,94(2):590-599.
[109] Khan Z, Balch T, Dellaert F. MCMC-based particle filtering for tracking a variable number ofinteracting targets[J]. Transactions on Pattern Analysis and Machine Intelligence,2005,27(11):1805-1819.
[110] Kotecha J H, Djuric P M. Gaussian particle filtering[J]. IEEE Transactions on Signal Processing,2003,51(10):2592-2601.
[111] Lehn-Schioler T, Erdogmus D, Principe J C. Parzen particle filters[C]. Proceedings of InternationalConference on Acoustics, Speech, and Signal Processing, Montreal, Canada,2004(V):781-784.
[112] Bouaynaya N, Schonfeld D. On the optimality of motion-based particle filtering[J]. IEEETransactions on Circuits and Systems for Video Technology,2009,19(7):1068-1072.
[113] Yee Y, Reilly J P, Kirubarajan T, et al. Approximate conditional mean particle filtering forlinear/nonlinear dynamic state space models[J]. IEEE Transactions on Signal Processing,2008,56(12):5790-7803.
[114] Yao A B, Wang G J, Lin X G, et al. An incremental bhattacharyya dissimilarity measure for particlefiltering[J]. Pattern Recognition,2010,43(4):1244-1256.
[115] Campillo F, Rossi V. Convolution particle filter for parameter estimation in general state-spacemodels[J]. IEEE Transactions on Aerospace and Electronic Systems,2009,45(3):1063-1072.
[116] Chang C, Ansari R. Kernel particle filter for visual tracking[J]. IEEE Signal Processing Letters,2005,12(3):242-245.
[117]姚红革,齐华,郝重阳.复杂情形下目标跟踪的自适应粒子滤波算法[J].电子与信息学报,2009,31(2):275-278.
[118]宋宇,孙富春,李庆玲.移动机器人的改进无迹粒子滤波蒙特卡罗定位算法[J].自动化学报,2010,36(6):851-857.
[119]杨淑莹,吴涛,张迎,等.基于模拟退火的粒子滤波在目标跟踪中的应用[J].光电子·激光,2011,(8):1236-1240.
[120]余孟泽,刘正熙,骆键,等.基于改进粒子滤波的鲁棒目标跟踪算法[J].光电子·激光,2011,(5):766-771.
[121]李静,陈兆乾,陈世福. EM-GMPF:一种基于EM的混合高斯粒子滤波器算法[J].计算机研究与发展,2005,42(7):1210-1216.
[122] Bimbo A D, Dini F. Particle filter-based visual tracking with a first order dynamic model anduncertainty adaptation[J]. Computer Vision and Image Understanding,2011,115(6):771-786.
[123] Nejhum S M S, Ho J, Yang M H. Online visual tracking with histograms and articulating blocks[J].Computer Vision and Image Understanding,2010,114(8)：901-914.
[124] Chu J K, Li R H, Li Q Y, et al. A visual Attention Model for Robot Object Tracking[J]. InternationalJournal of Automation and Computing,2010,7(2):39-46.
[125] Han Z J, Ye Q X, Jiao J B. Combined feature evaluation for adaptive visual object tracking[J].Computer Vision and Image Understanding,2011,115(1):69-80.
[126]郭康德,张明敏,孙超,等.基于视觉技术的三维指尖跟踪算法[J].计算机研究与发展,2010,47(6):1013-1019.
[127] Chang I C, Lin S Y.3D human motion tracking based on a progressive particle filter[J]. PatternRecognition,2010,43(10):3621-3635.
[128] Mei X, Ling H B. Robust visual tracking and vehicle classification via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(11):2259-2272.
[129]安国成,张凤军,王宏安,等.多窗口目标跟踪算法[J].计算机研究与发展,2011,48(11):2023-2030.
[130]刘晨光,刘家锋,黄剑华,等.基于多特征融合的分块采样粒子滤波算法在人体姿态跟踪中的应用[J].计算机研究与发展,2011,48(12):2359-2368.
[131] Li B, Yan W. Road tracking using particle filters with partition sampling and auxiliary variables[J].Computer Vision and Image Understanding,2011,115(10):1463-1471.
[132] Chen Y, Wang J Z. A region-based fuzzy feature matching approach to content-based imageretrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(9):1252-1267.
[133] Nguyen H T, Worring M, Van D R. Occlusion robust adaptive template tracking[C]. Proceedings ofthe8th International Conference on Computer Vision, Vancouver, Canada,2001:678-683.
[134]甘明刚,陈杰,王亚楠,等.基于Mean Shift算法和NMI特征的目标跟踪算法研究[J].自动化学报,2010,36(9):1332-1336.
[135] Karavasilis V, Nikou C, Likas C. Visual tracking by adaptive Kalman Filtering and Mean Shift[J].Lecture Notes in Computer Science, Artificial Intelligence: Theories, Models and Applications,2010,6040:153-162.
[136] Stuffer C, Grimson W E L. Learning patterns of activity using real-time tracking[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[137] Nummiaro K, Koller M E, Gool L V. An adaptive color-based particle flter[J]. Image and VisionComputing,2003,21(1):99-110.
[138] Yang T, Li S Z, Pan Q, et al. Real-time multiple objects tracking with occlusion handling in dynamicscenes[C]. Computer Vision and Pattern Recognition, San Diego,2005:970-975.
[139] Nailk N, Patil S, Joshi S. A fragment based scale adaptive tracker with partial occlusion handling[C].IEEE Conference on TENCON, Singapore,2009,1:1-6.
[140] Phadke G. Robust multiple target tracking under occlusion using fragmented mean shift and KalmanFilter[C].2011International Conference on Communications and Signal Process-ing, Kerala,2:517-521.
[141]颜佳,吴敏渊,陈淑珍,等.应用Mean Shift和分块的抗遮挡跟踪[J].光学精密工程,2010,18(6):1413-1419.
[142]齐美彬,张莉,蒋建国,等.分块跟踪中的目标模板更新方法[J].中国图象图形学报,2011,16(6):976-982.
[143] Liu H, Yu Z, Zha H B, et al. Robust human tracking based on multi-cue integration and mean-shift[J].Pattern Recognition Letters,2009,30(7):827-837.
[144] Leichter I, Lindenbaum M, Rivlin E. Tracking by affine kernel transformations using color andboundary cues[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(1):164-171.
[145] Hu J S, Juan C W, Wang J J. A spatial-color mean-shift object tracking algorithm with scale andorientation estimation[J]. Pattern Recognition Letters,2008,29(16):2165-2173.
[146] Wang H Z, Suter D, Schindler K, et al. Adaptive object tracking based on an effective appearancefilter[J]. IEEE Transactions on Pattern Analysis and Machine intelligence,2007,29(9):1661-1667.
[147]覃剑,曾孝平,李勇明.基于边界力的Mean-Shift核窗宽自适应算法[J].软件学报,2009,20(7):1726-1734.
[148] Leichter I, Lindenbaum M M, Rivin E. Mean Shift tracking with multiple reference colorhistograms[J]. Computer Vision and Image Understanding,2010,114(3):400-408.
[149] Birchfield S T， Rangarajan S. Spatiograms versus histograms for region-based tracking[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. San Diego,California, United States: IEEE,2005,6(2):1158-1163.
[150] Collins R T, Liu Y, Leordeanu M. Online selection of discriminative tacking features[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27(10):1631-1643.
[151] Haritaoglu I, Flickner M. Detection and tracking of shopping groups in stores[C]. Proceeding of the2001IEEE Computer Vision and Pattern Recognition,2001,1(12):8-14.
[152] Li S X, Chang H X, Zhu C F. Adaptive pyramid mean shift for global real-time visual tracking[J].Image and Vision Computing,2010,28(3):424-437.
[153]章毓晋.图像工程(第二版)[M].北京:清华大学出版社,2007:168-171.
[154]沈悦,吴小俊.基于模糊隶属关系的Mean Shift图像跟踪改进算法[J].电子信息学报,2008,30(11):2688-2692.
[155] Babu R V, Perez P, Bouthemy P. Robust tracking with motion estimation and local kernel-basedcolor modeling[J]. Image and Vision Computing,2007,25(8):1205-1216.
[156]沈志熙,杨欣,黄席樾.均值漂移算法中的目标模型更新方法研究[J].自动化学报,2009,35(5):478-483.
[157] Qi Z, Zhi Y, Hai T. Differential earth mover’s distance with its applications to visual tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(2):274-287.
[158] Chung Y S, Jung S U, Ba Y L, et al. Face feature extraction using elliptical model based backgrounddeletion and generalized FEM[C]. Proceedings of the2007Third International IEEE Conference onSignal-Image Technologies and Internet-Based System,2007,(9):757-762.
[159] Birchfield S. An elliptical head tracker[C].31st Asilomar Conference on Signals, Systems andComputers,1997,(11):1710-1714.
[160] Bradski G R. Computer vision face tracking for use in a perceptual user interface[C]. IEEEWorkshop on Application of Computer Vision, New York: IEEE,1998:214-219.
[161] Collins R T. Mean-Shift blob tracking through scale space[C]. Proceedings of IEEE InternationalConference on Computer Vision and Pattern Recognition,2003:234-240.
[162]彭宁嵩,杨杰,刘志,等. Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9):1542-1550.
[163] Feng Z R, Lu N, Jinag P. Posterior probability measure for image matching[J]. Pattern recognition,2008,(41):2422-2433.
[164]吕娜.图像匹配与跟踪研究[D]:[博士学位论文].西安：西安交通大学，2008.
[165] Nguyen H, Smeulders A. Robust tracking using foreground-background texture discrimination[J].International Journal of Computer Vision,2006,69(3):277-293.
[166] Zhu G P, Zeng Q S, Wang C H. Efficient edge-based object tracking[J]. Pattern Recognition,2006,39(11):2223-2226.
[167] Buenaposada J, Munoz E, Baumela L. Efficient illumination independent appearance-based facetracking[J]. Image and Vision Computing,2009,27(5):560-578.
[168]张华.运动目标跟踪算法的若干方法研究[D]:[硕士学位论文].南京:南京理工大学,2008.
[169]卢晓鹏.视频序列中目标跟踪技术研究[D]:[博士学位论文].北京:中国科学院研究生院（电子学研究所）,2007.
[170]姚剑敏.粒子滤波跟踪方法研究[D]:[博士学位论文].长春:中国科学院研究生院（长春光学精密机械与物理研究所）,2004.
[171]单勇.复杂条件下视频运动目标检测和跟踪[D]:[博士学位论文].长沙:国防科学技术大学,2006.
[172]崔彦.序列图像中运动目标检测与跟踪技术研究[D]:[硕士学位论文].西安:西安电子科技大学硕士论文,2009.
[173] Perez P, Hue C, Vermaak J, et al Color-based probabilistic tracking[C]. Proceedings of the EuropeanConference on Computer Vision, Copenhagen, Denmark, May28-31,2002:661-675.
[174] Town C. Multi-sensory and multi-modal fusion for sentient computing[J]. International Journal ofComputer Vision,2007,71(2):235-253.
[175]王欢,王江涛,任明武,等.一种鲁棒的多特征融合目标跟踪新算法[J].中国图象图形学报,2009,14(3):489-498.
[176]钟小品,薛建儒,郑南宁,等.基于融合策略自适应的多线索跟踪方法[J].电子与信息学报,2007,29(5):1017-1021.
[177]姚剑敏,杨春建,刘经场,等.多特征融合的非线性目标跟踪算法[J].光电工程,2008,35(3):5-9.
[178]顾鑫,王海涛,汪凌峰,等.基于不确定性度量的多特征融合跟踪[J].自动化学报,2011,37(5):550-559.
[179] Li Y, Ai H, Huang C, et al. Robust head tracking with particles based on multiple cues[C].Proceedings of the9th European Conference on Computer Vision Workshop on Human-ComputerInteraction, Graz, Austria,2006:29-39.
[180]曾慧,穆志纯,王秀青.一种鲁棒的图像局部特征区域的描述方法[J].自动化学报2011,37(6):658-664.
[181]王永忠,梁彦,潘泉,等.基于自适应混合高斯模型的时空背景建模[J].自动化学报,2009,35(4):371-378.
[182]王瑜,穆志纯,付冬梅,等.基于小波变换和规范型纹理描述子的人耳识别[J].电子学报,2010,38(1):239-243.
[183]李晓华,沈兰荪.基于小波压缩域的统计纹理特征提取方法[J].电子学报,2003,31(12A):2123-2126.
[184]贾慧星,章毓晋.基于梯度方向直方图特征的多核跟踪[J].自动化学报,2009,35(10):1283-1289.
[185] Dala N, Triggs B. Histograms of oriented gradients for human detection[C]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition, San Diego, USA,2005:886-893.
[186] Moore S, Bowden R. Local binary patterns for multi-view facial expression recognition[J].Computer Vision and Image Understanding,2011,115(4):541-558.
[187] Ojala T, Pietik inen M, Harwood D. A comparative study of texture measures with classificationbased on feature distributions[J]. Pattern Recognition,1996,29(1):51-59.
[188] Ojala T, Pietik inen M, M enp T. Multiresolution grayscale and rotation invariant textureclassification with local binary patterns[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2002,24(7):971-987.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |