基于MPM-MAP框架的运动目标分割与跟踪
|
摘要
运动目标分割与跟踪在军事、气象、地质、商业传媒等很多领域都有着广泛的应用,是模式识别、图像处理、计算机视觉等领域的重要课题。本文首先对运动目标分割与跟踪的研究现状进行了分析与总结,介绍了该领域现有的研究方法,取得的成就以及存在的问题。
本文采用最大后验边缘概率(MPM-MAP)算法实现运动目标分割,MPM-MAP算法是在最大后验概率(MAP)图像分割算法的基础上发展而来的。这类算法既能估计运动参数,又能分割出运动目标,具有结果准确,适应广泛的特点。MPM-MAP算法在形式上明确了通过两步估计运动参数和运动目标所对应的区域(支持区);采用二值标记场表示支持区,从而使计算简化。该算法比MAP算法和期望最大化(EM)算法更灵活,速度更快。
本文从MAP运动分割算法入手,详细介绍了MPM-MAP算法的理论框架,还分析了MPM-MAP算法与MAP算法及EM算法的区别。在此基础上本文对该框架中的数据平滑算法——基于马尔可夫随机场(MRF)模型的算法进行了改进。改进后的算法利用MPM-MAP算法中的二值标记表示法,统一更新图像标记场数据,通过均值滤波器实现MRF能量函数的计算,在保持算法平滑效果的同时提高了MRF算法的运行速度。
传统的MPM-MAP算法虽然运行速度比相近的MAP算法和EM算法有较大提高,但仍存在一些缺点。如缺乏有效的运动目标数和初始运动参数的估计方法;常采用的估计运动参数的最优化方法依赖于初值,对目标函数要求可导等。MRF平滑方法虽然效果很好,但用于迭代过程中时,即使是快速算法仍然运行时间较长。
针对以上缺点,本文提出了以下改进方法。本文改变了MPM-MAP算法中数据平滑项的定义,定义平滑项为运动目标备选像素的密度,选择备选像素密度最大的矩形区域为运动支持区。采用区域收缩算法实现图像平滑、去除噪声,该算法不仅可以消除噪声,还可以对运动目标定位并计算运动目标的特征矩形。区域收缩算法相对MRF算法具有运行速度快的优势。除可以用于支持区估计结果上,区域收缩算法也可以用于差分二值图像,本文采用连通区域包围盒与区域收缩算法相结合的方法估计初始支持区,将传统算法先假设运动参数再估计运动支持区的顺序改为先估计支持区后估计运动参数,提高了初始参数估计的准确性。
本文选择运动模型为6参数仿射模型。在区域收缩算法的基础上,本文提出一种基于矩形区域主轴的轴仿射模型。该模型通过矩形区域的两个主轴估计仿射运动参数,其优点主要有以下几点。一是在不影响运动参数估计准确性的前提下提高了运动估计的速度;二是使仿射运动参数具有明确的几何意义,容易确定一个初始参数的范围,使参数估计的最优化算法除传统的基于梯度的方法及随机最优化方法外,可以使用搜索类的算法。本文选择一种较新的取值有界的最优化算法—DIRECT算法实现运动参数的估计。该算法不要求目标函数可导,也不用假设初值。所以,轴仿射运动模型与DIRECT算法的结合提高了参数估计的准确性、稳定性和鲁棒性。
本文对上述算法与模型进行了详细介绍。最后,本文将上述算法应用于运动目标跟踪。本文的跟踪算法采用矩形表示法,基于区域收缩的MPM-MAP算法用于估计初始运动目标及运动参数。目标跟踪采用基于卡尔曼滤波的状态空间目标跟踪方法。状态为轴仿射参数,DIRECT算法的中间结果用于计算观测向量的协方差矩阵。实验结果表明,矩形表示法、轴仿射模型和DIRECT算法的结合有利于更好地实现运动目标跟踪。
本文提出的算法都经仿真实现,并证明可行。文中给出较详细的实验结果。
The segmentation and tracking of moving object are widely applied in many fields such as military affairs, weather, geography, commerce and media. They are very important research topics in pattern recognition, image processing and computer vision. The research status of moving object segmentation and tracking is analyzed and summarized in the dissertation. The approaches, achievements and problems of current works in this field are introduced then.
The maximizer of the posterior marginals-maximum a posteriori (MPM-MAP) algorithm is adopted to implement moving object segmentation in the dissertation. MPM-MAP is developed on the basis of maximum posterior probability (MAP) algorithm. This kind of algorithms can both estimate motion parameters and segment moving objects. These algorithms are featured by their accurate results and wide applications. MPM-MAP algorithm makes it clear in the form that motion parameters and regions corresponding to the moving objects (supporting regions) are estimated in two steps. The binary labeling field is used to represent the supporting regions, which simplifies the calculation. The MPM-MAP algorithm is more flexible and faster than MAP and expectation maximization (EM) algorithms.
With the MAP algorithm as the starting point, the theoretical frame of MPM-MAP algorithm is introduced in detail in the dissertation. The differences in MPM-MAP algorithm, MAP algorithm and EM algorithm are also analyzed in the dissertation. The smoothing algorithm in MPM-MAP based on Markov random (MRF) model is improved in the dissertation. In the improved MPM-MAP algorithm, the labeling field data are updated uniformly using the binary labeling representation and the MRF energy is computed by mean filter. Therefore, the improved algorithm heightens the speed of MRF algorithm while the smoothing effects remain the same as the traditional algorithms.
Although the traditional MPM-MAP algorithm is much faster than MAP and EM algorithm, some shortcomings still remain in it. For example, it lacks of the effective approaches to estimate the number of moving objects and the initial motion parameters; the most often used optimal methods for motion parameter estimation are dependent on the initial values; the objective functions are required to be differentiable. MRP model has a good smoothing effect but it seems to be slow in running speed during the iterations even though for the fastest MRF algorithm.
Aiming at the shortcomings mentioned above, some improvements are proposed in the dissertation. The smoothing term in MPM-MAP algorithm is changed and defined to be the density of pre-selected pixels belonging to the moving objects. The rectangular region with the maximum density is chosen as motion supporting region. The region shrinking algorithm is used to implement image smoothing and noise suppression. In addition to the noise suppression, this algorithm can locate the moving objects and compute the feature rectangles of the objects.
The region shrinking algorithm has the advantage of higher speed than MRF algorithm. It can also be used in binary difference images as well as the estimation of supporting regions. The bounding boxes of connected regions are combined with region shrinking algorithm to estimate initial supporting regions. The original algorithm calculates the motion parameters first and then supporting regions. Supporting regions are computed first and then the motion parameters in the proposed algorithm. Therefore the initial parameters are more accurate than the traditional algorithm.
The 6-parameter affine model is chosen as motion model in the dissertation. An axial affine model based on rectangular region is presented. This model describes affine motion by center translation, rotation and scaling of two main axes of a rectangular region. Its advantages are as follows. The first advantage is heightening the speed of motion estimation while keeping the accurate results as before. The second advantage is that it makes a clear geometric meaning for the affine parameters. The range of initial parameters is easy to be obtained. The optimal methods of parameter estimation can be chosen in searching approaches except the gradient-based and random optimal methods used before. A comparatively newer optimal approach with limited parameters—DIRECT algorithm is used to calculate the motion parameters. The method does not need a differentiable objective function and a set of assumed initial parameters. The combination of axis affine model and DIRECT algorithm improves the precision, stability and robustness of parameter estimation.
The model and algorithms mentioned above are described in detail in the dissertation. Finally these algorithms are used in moving object tracking. The representation of rectangular region is adopted in tracking. The initial regions of objects and motion parameters are computed by the MPM-MAP algorithm based on region shrinking. The tracking approach based on kalman filter is presented in the dissertation. The state of kalman filter is a set of axial affine parameters. The covariance matrix of the observed vectors is computed by the interim results of DIRECT algorithm. The experiment results show that the combination of rectangular representation, axial affine model and DIRECT algorithm favors the better tracking of moving objects.
The algorithms in the dissertation are simulated and proved to be feasible. The detailed experiment results are also given in the dissertation.
本文采用最大后验边缘概率(MPM-MAP)算法实现运动目标分割,MPM-MAP算法是在最大后验概率(MAP)图像分割算法的基础上发展而来的。这类算法既能估计运动参数,又能分割出运动目标,具有结果准确,适应广泛的特点。MPM-MAP算法在形式上明确了通过两步估计运动参数和运动目标所对应的区域(支持区);采用二值标记场表示支持区,从而使计算简化。该算法比MAP算法和期望最大化(EM)算法更灵活,速度更快。
本文从MAP运动分割算法入手,详细介绍了MPM-MAP算法的理论框架,还分析了MPM-MAP算法与MAP算法及EM算法的区别。在此基础上本文对该框架中的数据平滑算法——基于马尔可夫随机场(MRF)模型的算法进行了改进。改进后的算法利用MPM-MAP算法中的二值标记表示法,统一更新图像标记场数据,通过均值滤波器实现MRF能量函数的计算,在保持算法平滑效果的同时提高了MRF算法的运行速度。
传统的MPM-MAP算法虽然运行速度比相近的MAP算法和EM算法有较大提高,但仍存在一些缺点。如缺乏有效的运动目标数和初始运动参数的估计方法;常采用的估计运动参数的最优化方法依赖于初值,对目标函数要求可导等。MRF平滑方法虽然效果很好,但用于迭代过程中时,即使是快速算法仍然运行时间较长。
针对以上缺点,本文提出了以下改进方法。本文改变了MPM-MAP算法中数据平滑项的定义,定义平滑项为运动目标备选像素的密度,选择备选像素密度最大的矩形区域为运动支持区。采用区域收缩算法实现图像平滑、去除噪声,该算法不仅可以消除噪声,还可以对运动目标定位并计算运动目标的特征矩形。区域收缩算法相对MRF算法具有运行速度快的优势。除可以用于支持区估计结果上,区域收缩算法也可以用于差分二值图像,本文采用连通区域包围盒与区域收缩算法相结合的方法估计初始支持区,将传统算法先假设运动参数再估计运动支持区的顺序改为先估计支持区后估计运动参数,提高了初始参数估计的准确性。
本文选择运动模型为6参数仿射模型。在区域收缩算法的基础上,本文提出一种基于矩形区域主轴的轴仿射模型。该模型通过矩形区域的两个主轴估计仿射运动参数,其优点主要有以下几点。一是在不影响运动参数估计准确性的前提下提高了运动估计的速度;二是使仿射运动参数具有明确的几何意义,容易确定一个初始参数的范围,使参数估计的最优化算法除传统的基于梯度的方法及随机最优化方法外,可以使用搜索类的算法。本文选择一种较新的取值有界的最优化算法—DIRECT算法实现运动参数的估计。该算法不要求目标函数可导,也不用假设初值。所以,轴仿射运动模型与DIRECT算法的结合提高了参数估计的准确性、稳定性和鲁棒性。
本文对上述算法与模型进行了详细介绍。最后,本文将上述算法应用于运动目标跟踪。本文的跟踪算法采用矩形表示法,基于区域收缩的MPM-MAP算法用于估计初始运动目标及运动参数。目标跟踪采用基于卡尔曼滤波的状态空间目标跟踪方法。状态为轴仿射参数,DIRECT算法的中间结果用于计算观测向量的协方差矩阵。实验结果表明,矩形表示法、轴仿射模型和DIRECT算法的结合有利于更好地实现运动目标跟踪。
本文提出的算法都经仿真实现,并证明可行。文中给出较详细的实验结果。
The segmentation and tracking of moving object are widely applied in many fields such as military affairs, weather, geography, commerce and media. They are very important research topics in pattern recognition, image processing and computer vision. The research status of moving object segmentation and tracking is analyzed and summarized in the dissertation. The approaches, achievements and problems of current works in this field are introduced then.
The maximizer of the posterior marginals-maximum a posteriori (MPM-MAP) algorithm is adopted to implement moving object segmentation in the dissertation. MPM-MAP is developed on the basis of maximum posterior probability (MAP) algorithm. This kind of algorithms can both estimate motion parameters and segment moving objects. These algorithms are featured by their accurate results and wide applications. MPM-MAP algorithm makes it clear in the form that motion parameters and regions corresponding to the moving objects (supporting regions) are estimated in two steps. The binary labeling field is used to represent the supporting regions, which simplifies the calculation. The MPM-MAP algorithm is more flexible and faster than MAP and expectation maximization (EM) algorithms.
With the MAP algorithm as the starting point, the theoretical frame of MPM-MAP algorithm is introduced in detail in the dissertation. The differences in MPM-MAP algorithm, MAP algorithm and EM algorithm are also analyzed in the dissertation. The smoothing algorithm in MPM-MAP based on Markov random (MRF) model is improved in the dissertation. In the improved MPM-MAP algorithm, the labeling field data are updated uniformly using the binary labeling representation and the MRF energy is computed by mean filter. Therefore, the improved algorithm heightens the speed of MRF algorithm while the smoothing effects remain the same as the traditional algorithms.
Although the traditional MPM-MAP algorithm is much faster than MAP and EM algorithm, some shortcomings still remain in it. For example, it lacks of the effective approaches to estimate the number of moving objects and the initial motion parameters; the most often used optimal methods for motion parameter estimation are dependent on the initial values; the objective functions are required to be differentiable. MRP model has a good smoothing effect but it seems to be slow in running speed during the iterations even though for the fastest MRF algorithm.
Aiming at the shortcomings mentioned above, some improvements are proposed in the dissertation. The smoothing term in MPM-MAP algorithm is changed and defined to be the density of pre-selected pixels belonging to the moving objects. The rectangular region with the maximum density is chosen as motion supporting region. The region shrinking algorithm is used to implement image smoothing and noise suppression. In addition to the noise suppression, this algorithm can locate the moving objects and compute the feature rectangles of the objects.
The region shrinking algorithm has the advantage of higher speed than MRF algorithm. It can also be used in binary difference images as well as the estimation of supporting regions. The bounding boxes of connected regions are combined with region shrinking algorithm to estimate initial supporting regions. The original algorithm calculates the motion parameters first and then supporting regions. Supporting regions are computed first and then the motion parameters in the proposed algorithm. Therefore the initial parameters are more accurate than the traditional algorithm.
The 6-parameter affine model is chosen as motion model in the dissertation. An axial affine model based on rectangular region is presented. This model describes affine motion by center translation, rotation and scaling of two main axes of a rectangular region. Its advantages are as follows. The first advantage is heightening the speed of motion estimation while keeping the accurate results as before. The second advantage is that it makes a clear geometric meaning for the affine parameters. The range of initial parameters is easy to be obtained. The optimal methods of parameter estimation can be chosen in searching approaches except the gradient-based and random optimal methods used before. A comparatively newer optimal approach with limited parameters—DIRECT algorithm is used to calculate the motion parameters. The method does not need a differentiable objective function and a set of assumed initial parameters. The combination of axis affine model and DIRECT algorithm improves the precision, stability and robustness of parameter estimation.
The model and algorithms mentioned above are described in detail in the dissertation. Finally these algorithms are used in moving object tracking. The representation of rectangular region is adopted in tracking. The initial regions of objects and motion parameters are computed by the MPM-MAP algorithm based on region shrinking. The tracking approach based on kalman filter is presented in the dissertation. The state of kalman filter is a set of axial affine parameters. The covariance matrix of the observed vectors is computed by the interim results of DIRECT algorithm. The experiment results show that the combination of rectangular representation, axial affine model and DIRECT algorithm favors the better tracking of moving objects.
The algorithms in the dissertation are simulated and proved to be feasible. The detailed experiment results are also given in the dissertation.
引文
[1]D.Zhang,G.Lu.Segmentation of moving objects in image sequence:A review.Circuits Syst.Signal Process.2001,20:143-183P
[2]刘党辉,沈兰荪.视频运动对象分割技术的研究.电路与系统学报,2002,7(3):77-85页
[3]Roland Mech,Michael Wollborn.A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera..Signal Processing.1998,66(2):203-247P
[4]A.Neri,S.Colonnese,G.Russo,P.Ralone.Automatic Moving Object and Background Separation.Signal Processing 1998,66:249-232P.
[5]Turgay Celik,Hasan Demirel,Huseyin Ozkaramanli,Mustafa Uyguroglu.Fire detection using statistical color model in video sequences.Journal of Vision Communication & Image Representation.2007:1-9P
[6]杨莉,张弘,李玉山.视频运动对象的自动分割.计算机辅助设计与图形学学报.2004,16(3):301-306页
[7]赵明,李娜,陈纯.采用统计推断的自动视频对象分割.计算机辅助设计图形学学报,2003,15(3):318-333页
[8]陈韩锋,戚飞虎,视频对象分割中基于Gibbs随机场模型的时空分割结合方法,电子学报,2004,32(1):34-37页
[9]Manuele Bicego,Marco Cristani,Vittorio Murino.Unsupervised scene analysis:A hidden Markov model approach.Computer Vision and Image Understanding 2006,102:22-41P
[10]Feng-Yang Hsieh,Chin-Chuan Han,Nai-Shen Wu.A novel approach to the detection of small objects with low contrast.Signal Processing,2006,86:71-83P
[11]Youfu Wu,Jun Shen,Mo Dai.Traffic object detections and its action analysis.Pattern Recognition Letters.2005,26:1963-1984P
[12]L.Li,M.Leung,Integrating Intensity and Texture Differences for Change Detection,IEEE Trans.on Image Processing,2002,11(2):105-112P
[13]A.Colombari,A.Fusiello,V.Murino.Segmentation and tracking of multiple video objects.Pattern Recognition,2007,40:1307-1317P
[14]V.Mezaris,I.Kompatsiaris,M.G.Strintzis,Video Object Segmentation sing Bayes-Based Temporal Tracking and Trajectory-Based Region Merging,IEEE Trans.on Circuits System and Video Technology,2004,14(6):782-795P
[15]Liang-Hua Chen,Yu-Chun Lai.Extraction of video object with complex motion.Pattern Recognition Letters,2004,25:1285-1291P
[16]M.Kirchhof,U.Stilla.Detection of moving objects in airborne thermal videos.ISPRS Journal of Photogrammetry & Remote Sensing,2006,61:187-196P
[17]Gouze,A.,De Roover,C.,Macq,B.,Herbulot,A.,Debreuve,E.,Barlaud,M.Watershed-driven active contours for moving object segmentation.Proceeding of IEEE International Conference on Image Processing.2005(2):811-818P
[18]Young Sik Park,Eui Yoon Chung.Hierarchical spatiotemporal moving object segmentation based on a binary split algorithm.Optical Engineering.2003,42(1):245-254P
[19]S.Chien,Y.Huang,L.Chen,Predictive Watershed:A Fast Watershed Algorithm for Video Segmentation,IEEE Trans.on Circuits System and Video Technology,2003,13(5):453-461P
[20]崔明,孙守迁,潘云鹤.基于改进快速分水岭的图像区域融合.计算机辅助设计与图形学学报,2005,17(3):546-552页
[21]周军妮,曹剑中,刘波等.一种基于局部最小代价分水岭变换的图像分割新方法.光子学报,2005,34(1):142-145页
[22]杨高波,张兆杨,余圣发.一种基于小波分解和分水岭变换的视频对象自动分割算法.通信学报,2005,26(3):7-13页
[23]周军妮,曹剑中,刘波等.一种基于局部最小代价分水岭变换的图像分割新方法.光子学报,2005,34(1):142-145页
[24]杨文明,刘济林.时空联合视频对象分割.浙江大学博士学位论文,2006.
[25]E.Tuncel,L.Onural,Utilization of the Recursive Shortest Spanning Tree Algorithm for Video-object Segmentation 2-D Affine Motion Modeling,IEEE Trans.on Circuits System and Video Technology,2000,10(5):776-781P
[26]Chen,Tse-Wei;Hsu,Shou-Chieh;Chien,Shao-Yi.Robust Video Object Segmentation Based on K-Means Background Clustering and Watershed in Ill-Conditioned Surveillance Systems.Proceeding of 2007 IEEE International Conference on Multimedia and Expo,2007(7):787-790P
[27]Shah S.A.A.,Usman Naseem,M.Saif-ur-Rehman Karim,A.Motion Segmentation through Incremental Hierarchical Clustering.Proceeding of IEEE INMIC 2006,9thInternational Multitopic Conference,2006:781-785P
[28]Y.Deng,B.S.Manjunath,Unsupervised Segmentation of Color-Texture Regions in Images and Video,IEEE Trans.on Pattern Analysis and Machine Intelligence,2001 23(8):800-801P
[29]Jean Lorenceau,Anne Giersch,Peggy Series.Dynamic competition between contour integration and contour segmentation probed with moving stimuli.Vision Research,2005,45:103-116P.
[30]F.R.Mitiche,"A.Spatiotemporal motion boundary detection and motion boundary velocity estimation for tracking moving objects with a moving camera:a level sets PDEs approach with concurrent camera motion compensation." IEEE Trans.Image Processing,2004 13(11) 1473-1490P.
[31]Mezaris,V.,Kompatsiaris,I.,Strintzis,M.G.Video object segmentation using Bayes-based temporal tracking and trajectory-based region merging.IEEE Transactions on Circuits and Systems for Video Technology,2004,14(6):782-795P
[32]黄贤武,朱莉,仲兴荣等.一种新的基于时空马尔可夫随机场的运动目标分割技术.电子与信息学报.2006,28(2):367-371页
[33]Pakorn K.T.P.,Richard B.A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes. Image Vision Comput. 2003(21):913-929P
[34] Sun Y., Yuan B., Hierarchical GMM to handle sharp changes in moving object detection. Electron. Lett. 2004(40):801-802P
[35] Li L.Y., Huang, W.M., Gu, I.Y.H., Tian, Q. Statistical modeling of complex backgrounds for foreground object detection. IEEE Trans. Image Process.2004(13) 1459-1472P
[36] Wei Zhang , Xiang Zhong Fang, Xiaokang Yang. Moving vehicles segmentation based on Bayesian framework for Gaussian motion model.Pattern Recognition Letters 2006,27:956-967
[37] Gelgon M, Bouthemy P. A region-level motion-based graph representation and labeling for tracking a spatial image partition. Pattern Recognition 2000;33:725-40.
[38] Rita Cucchiara, rea Prati, Roberto Vezzani. Real-time motion segmentation from moving cameras. Real-Time Imaging 2004(10): 127-143P
[39] J. B. Kim, H. J. Kim. Efficient region-based motion segmentation for a video monitoring system. Pattern Recognition Letters, 2003, 24:113-128P
[40] Y. Wang, K. Loe, T. Tan, et al. Spatiotemporal Video Segmentation Based on Graphical Models, IEEE Trans. on Image Processing, 2005,14(7):937-947P
[41] Eun Yi Kim , Se Hyun Park. Automatic video segmentation using genetic algorithms. Pattern Recognition Letters. 2006,27: 1252-1265P
[42] Beung-Chan Kim, Rae-Hong Park. A fast automatic VOP generation using boundary block segmentation.Real-Time Imaging 2004(10): 117-125
[43] Y. Tsaig, A. Averbuch, Automatic Segmentation of Moving Objects in Video Sequences: A Region Labeling Approach, IEEE Trans. on Circuits System and Video Technology, 2002, 12(7):597-612P
[44] S. Chien, Y. Huang, B. Hsieh, et al, Fast Video Segmentation Algorithm with Shadow Cancellation, Global Motion Compensation, and Adaptive Threshold Techniques, IEEE Trans. on Multimedia, 2004, 6(5):732-748P
[45] T. Papadimitriou, K. I. Diamantaras, M. G. Strintzis, Video Scene Segmentation Using Spatial Contours and 3-D Robust Motion Estimation,IEEE Trans.on Circuits System and Video Technology,2004,14(4):485-497P
[46]Haifeng Xu,A.A.Younis,M.R.Kabuka,Automatic Moving Object Extraction for Context Based Applications,IEEE Trans.on Circuits System and Video Technology,2004,14(6):796-812P
[47]P.C.Chen,J.J.Su,Y.P.Tsai.Coarse-To-Fine Video Object Segmentation By MAP Labeling of Watershed Regions,Bulletin of College of Engineering,National Taiwan University,2004,(9):25-34P
[48]Y.Tsai,C.Lai,Y.Hung,et al.A Bayesian Approach to Video Object on Circuits System and Video Segmentation via Merging 3-D Watershed Volumes,IEEE Trans.Technology,2005,15(1):175-180P
[49]D.Xu,J.Liu,X.Li,et al.Insignificant Shadow Detection for Video Segmentation,IEEE Trans.on Circuits System and video Technology,2005,15(8):1058-1064P
[50]陈韩锋,戚飞虎,视频对象分割中基于Gibbs随机场模型的时空分割结合方法,电子学报,2004,32(1):34-37页
[51]吴思,林守勋,张勇东,基于动态背景构造的视频运动对象自动分割.计算机学报,2005,28(8):1386-1392页
[52]A.Monnet,A.Mittal,N.Paragios,V.Ramesh.Background modeling and subtraction of dynamic scenes,in:Proceedings of the International Conference on Computer Vision,2003,:1305-1312P
[53]A.Mittal,N.Paragios.Motion-based background subtraction using adaptive kernel density estimation,in:Proceedings of the International Conference on Computer Vision and Pattern Recognition(CVPR),2004:302-309P
[54]L.Li,W.Huang,I.Y.H.Gu,Q.Tian.Statistical modeling of complex backgrounds for foreground object detection,IEEE Transactions on Image Processing 2004,13(11):38-44P
[55]Q.Z.Wu,H.Y.Cheng,B.S.Jeng.Motion detection via change-point detection for cumulative histograms of ratio images,Pattern Recognition Letters 2005,26(5):555-563P
[56]Wang T.,Chen G..A novel background modeling approach for accurate and real-time motionsegmentation.Proceeding of the 8th International Conference on Signal Processing,2006,2:231-234P
[57]S.N.Lim,A.Mittal,L.S.Davis,N.Paragios.Fast illuminationinvariant background subtraction using two views:error analysis,sensor placement and applications,in:Proceedings of the International Conference on Computer Vision and Pattern Recognition(CVPR),2005:1071-1078P
[58]E.Herrero-Jaraba,C.Orrite-Urunuela,J.Senar.Detected motion classification with a double-background and a neighborhood-based difference,Pattern Recognition Letters.2003,24:2079-2092P
[59]T.Thongkamwitoon,S.Aramvith,T.H.Chalidabhongse.Non-linear learning factor control for statistical adaptive background subtraction algorithm,Proceedings of the IEEE International Symposium on Circuits and Systems(ISCAS'05),May 23-26,Kobe,Japan,2005:3785-3788P
[60]Xiaopeng Ji,Zhiqiang Wei,Yewei Feng.Effective vehicle detection technique for trafficsurveillance systems.Journal of Vision Communication & Image Representation.2006,17:647-658
[61]A.Branca,G.Attolico,A.Distante,Cast shadow removing in foreground segmentation,in:Proceedings of the International Conference on Pattern recognition,Quebec,Canada,2002:212-253P
[62]T.H.Chalidabhongse,K.Kim,D.Harwood,L.S.Davis.A perturbation method for evaluating background subtraction algorithms,Proceedings of the Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance(VS-PETS 2003),2003:453-458P
[63]P.Spagnolo,T.D.Orazio,M.Leo,A.Distante.Moving object segmentation by background subtraction and temporal analysis.Image and Vision Computing 2006,24:411-423P
[64]Joachim Weickert,Andres Bruhn,Thomas Brox,Nils Papenberg.A Survey on Variational Optic Flow Methods for Small Displacements.Mathematical Models for Registration and Applications to Medical Imaging,Springer,2006(10):103-136P
[65]陈震,高满屯,沈允文.图象光流场计算技术研究进展.中国图象图形学报,2002,7(5):12-16页
[66]Jerry L.Potter.Velocity as a Cue to Segmentation.IEEE Trans.on Systems,Man and Cybernetics 1983(5):390-394P
[67]Daniel Cremers,Christoph Schnorr.Statistical shape knowledge in variational motion segmentation.Image and Vision Computing,2003,21:77-86P
[68]D.Cremers.Nonlinear Dynamical Shape Priors for Level Set Segmentation.Proceedings of IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2007(6).
[69]T.Brox,D.Cremers.On the Statistical Interpretation of the Piecewise Smooth Mumford-Shah Functional,Proceeding of International Conference on Scale Space and Variational Methods in Computer Vision,Springer,LNCS,2007,4485(5):203-213P
[70]A.Mansouri,J.Konrad.Multiple motion segmentation with level sets,IEEE Trans.Image Process.,2003,12(2):201-220P
[71]C.Vazquez,A.Mansouri,A.Mitiche.Approximation of images by basis functions for multiple region segmentation with level sets,Int.Conf.on Image Processing,ICIP04,2004:549-552P.
[72]H.Sekkati,A.Mitiche.Joint dense 3D interpretation and multiple motion segmentation of temporal image sequences:a variational framework with active curve evolution and level sets,presented at the Int.Conf.Image Processing,Singapore,2004:443-448P
[73]H.Sekkati,A.Mitiche.Joint optical flow estimation,segmentation,and 3D interpretation with level sets.Computer Vision and Image Understanding,2006(103) 89-100P
[74]Hicham Sekkati,Amar Mitiche.Concurrent 3-D Motion Segmentation and 3-D Interpretation of Temporal Sequences of Monocular Images.IEEE Trans.on image processing,2006,15(3):89-93P
[75]王长军,朱善安.基于统计模型和GVF-Snake的运动检测与跟踪,浙江大学学报(A1),2006,40(2):249-253页
[76]王长军,朱善安.基于统计模型和GVF-Snake的彩色目标检测与跟踪.中国图象图形学报(A1),2006,11(1):p.13-18页
[77]P.-C.Chung,C.-L.Huang,E.-L.Chen.A region-based selective optical flowback-projection for genuine motion vector estimation.Pattern Recognition,2007,40:1066-1077P
[78]John Y.A.Wang.Layered Representation for Motion Analysis.Proceedings of the IEEE Computer Vision and Pattern Recognition Conference,1993:361-366P
[79]Y.Weiss.Smoothness in layers:motion segmentation using nonparametric mixture estimation.Proc.IEEE Conf.Comput.Vision Pattern Recogn.San Juan,Puerto Rico,1997:520-527P
[80]Robles-Kelly A.,Bors A.,Hancock E.Hierarchical iterative eigendecomposition for motion segmentation.IEEE ICIP,2001,2:363-366P
[81]Jean Gao,Ninad Thakoor,Sungyong Jung.A Motion Field Reconstruction Scheme for Smooth Boundary Video Object Segmentation.In Proceeding of 2004 International Conference on Image Processing,2004:321-328P
[82]M.Black,P.Anandan.The robust estimation of multiple motions:parametric,piecewise-smooth flow fields.Computer Vision,Image Understanding,1996,63(1):75-104P
[83]Hongshi Yan,Tardi Tjahjadi.Multiple Motion Segmentation through a Highly Robust Estimator.2004 IEEE International Conference on Systems and Man,Cybernetics.2004:612-616P
[84]Yeon-Ho Kima,Aleix M.Martnez,Avi C.Kaka.Robust motion estimation under varying illumination.Image and Vision Computing,2005,23:365-375P
[85]Tao,H.,Sawhney,H.,Kumar,R.Dynamic layer representation with applications to tracking, in IEEE Conference on Computer Vision and Pattern Recognition,2000,: 11:134-141.
[86] Wei Zeng, , Jun Du, Wen Gao, Qingming Huang. Robust moving object segmentation on H.264/AVC compressed video using the block-based MRF model. Real-Time Imaging, 2005,11: 290-299P
[87] A. G. Amitha Perera, Glen Brooksby, Anthony Hoogs, Gianfranco Doretto.Moving Object Segmentation using Scene Understanding. Proceeding of 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW06), 2006:201-207P
[88] Paul Smith,etc. Layered Motion Segmentation and Depth Ordering by Tracking Edges. IEEE Trans. on pattern analysis and machine intelligence,2004, 26(4): 4-12P
[89] David Murry, Bernard Buxton. Scene segmentation from visual motion using global optimization. IEEE PAMI 1994,9(2)
[90] Michael M. Chang, A. Murat Tekalp, M. Ibrahim Sezan. An Algorithm for Simultaneous Motion Estimation and Segmentation. IEEE Int. Conf. On Acoustics, Speech and Signal Processing, ICASSP'94, Adelaide, Australia,April 1994:221-224P.
[91] Patrick Bouthemy, Edouard Francois. Motion Segmentation and Qualitative Dynamic Scene Analysis from an Image Sequence. International Journal of Computing Vision, 1993, 10(2): 157- 182P.
[92] Jie Wei, Izidor Gertner. MRF-MAP-MFT visual object segmentation based on motion boundary field. Pattern Recognition Letters, 2003, 24:3125-3139P
[93] Ashwani Kumar, Sumana Gupta. A novel probabilistic approach for real time motion segmentation and tracking. International Symposium on Signal Processing and its Applications (ISSPA), Kuala Lumpur, Malaysia, 2001(8)13-16P
[94] C.Demonceuux, D.Kachi-Akkouche. Fast motion estimation and motion segmentation using multi-scale approach. Proceeding of 2004 International Conference on Image Processing (ICIP), 2004, 1(24-27): 377 - 380P
[95] Konrad Schindler. Spatially consistent 3D motion segmentation. Proceeding of ICIP 2005. IEEE International Conference on Image Processing, 2005,3,11-14( III): 409-412P
[96] EunYi Kim, Keechul Jung. Genetic algorithms for video segmentation.Pattern Recognition , 2005,38 :59-73P
[97] F.Calderon,J. L. Marroquin. The MPM - MAP algorithm for motion segmentation. Computer Vision and Image Understanding , 2004, 95: 165 -183P
[98] Veenman C, Reinders M, Backer E. Resolving motion correspondence for densely moving points. IEEE Trans. Part. Analy. Mach. Intell. 2001,23(1):54-72P
[99] Xin Wang, Masanori Sugisaka, Wenli Xu. Feature Point-Based Object Tracking. IEEE Transactions on Electronics, Information and Systems,2004,124(8): 1585-1591P
[100] Shafique K., Shah M. A non-iterative greedy algorithm for multi-frame point correspondence. In IEEE International Conference on Computer Vision (ICCV). 2003:110-115P
[101] Jinman Kang, Cohen, I., Medioni, G, Chang Yuan. Detection and tracking of moving objects from a moving platform in presence of strong parallax.Proceeding of Tenth IEEE International Conference on Computer Vision(ICCV 2005), 2005,1(10): 10 - 17P
[102] Ediz Polat, Mohammed Yeasin, Rajeev Sharma. A 2D/3D model-based object tracking framework. Pattern Recognition, 2003, 36(9): 2127-2141P
[103] Vidal R., Ma Y. A unified algebraic approach to 2-d and 3-d motion segmentation. In European Conference on Computer Vision (ECCV). 2004:1-15.
[104] Birchfield S. Elliptical head tracking using intensity gradients and color histograms. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1998:232-237P
[105] Schweitzer H., Bell J. W., Wu F. Very fast template matching. In European Conference on Computer Vision (ECCV). 2002:358-372P
[106] Fieguth P., Terzopoulos D. Color-based tracking of heads and other mobile objects at video frame rates. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1997:21-27P
[107] Comaniciu D., Ramesh V, Meer P. Kernel-based object tracking. IEEE Trans. Patt. Analy. Mach. Intell. 2003,25: 564-575P
[108] B. Han, D. Comaniciu, Y. Zhu, L.S. Davis: Sequential Kernel Density Approximation: Application to Real-Time Visual Tracking, IEEE Trans.Pattern Analysis Machine Intell., 2007(1): 22-30P
[109] Jepson A., Fleet D., Elmaraghi T. 2003. Robust online appearance models for visual tracking. IEEE Trans. Part. Analy. Mach. Intell. 2003,25, 10:1296-1311P
[110] Tao H., Sawhney H., Kumar R. Object tracking with bayesian estimation of dynamic layer representations. IEEE Trans. Patt. Analy. Mach. Intell. 2002,24(1): 75-89P
[111] Isard M.and Maccoremick J. Bramble: A bayesian multiple-blob tracker. In IEEE International Conference on Computer Vision (ICCV). 2001: 34-41P
[112] Black M., Jepson A. Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. Int. J. Comput.Vision 1998,26,(1): 63-84P
[113] Avidan S. Support vector tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8): 1064- 1072P
[114] F. R. Schmidt, Eno Toppe, D. Cremers, Y. Boykov. Efficient Shape Matching via Graph Cuts. Proceeding of Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), Springer, LNCS,2007, 4679(8): 39-54P
[115] Kang J., Cohen I., Medioni G. Object reacquisition using geometric invariant appearance model. In International Conference on Pattern Recongnition (ICPR). 2004,759-762.
[116]Sato K.,Aggarwal J.Temporal spatio-velocity transform and its application to tracking and interaction.Comput.Vision Image Understand.2004,96,2,100-128P
[117]Tsechpenakis,G.,Tsapatsoulis,N.,& Kollias,S.Probabilistic boundary-based contour tracking with snakes in natural cluttered video sequences.International Journal of Image and Graphics,2004,4(3):469-498P
[118]Sang-Cheo Park,Sung-Hoon Lim,Bong-Kee Sin,Seong-Whan Lee.Tracking non-rigid objects using probabilistic Hausdorff distance matching.Pattern Recognition,2005,38:2373-2384P
[119]Shin-Hyoung Kim,Jong Whan Jang.Object contour tracking using snakes in stereo image sequences.IEEE International Conference on Image Processing(ICIP 2005),2005,2(9):414-417P
[120]D.Cremers.Dynamical statistical shape priors for level set based tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(8):1262-1273P
[121]Yilmaz A.,Shafique K.,Shah.M.Target tracking in airborne forward looking imagery.J.Image Vision Comput.2003,21(7):623-635P
[122]Gablonsky J.M.,An implementation of the DIRECT algorithm.Technical Report,Center for Research in Scientific Computation,North Carolina State University,august 1998.
[123]Bjorkman M.,Holmstrom K.Global Optimization Using the DIRECT Algorithm in Matlab.Center for Mathematical Modeling Department of Mathematics and Physics.Malardalen University,Sweden.AMO Advanced Modeling and Optimization 1999,1(2).
[124]Gablonsky J.M.Modifications of the DIRECT Algorithm.PhD Thesis.North Carolina State University,Raleigh,North Carolina,2001.
[125]S.A.Piyawskii.An algorithm for finding the absolute extremum of a function.USSR Computational Mathematics and Mathematical Physics,1972,(12):57-67P
[126]R.G.Strongin.On the convergence of an algorithm for finding a global extremum.Engineering Cybernetics,1973(11):549-555P
[127]G.R.Wood,B.P.Zhang.Estimation of the Lipschitz Constant of a Function.Journal of Optimization Theory and Applications,1996,8(1):91-103 P
[128]C.D.Perttunen D.R.Jones,B.E.Stuckman.Lipschitzian optimization without the lipschitz constant.Journal of Optimization Theory and Application,1993,79(1):157-181P
[129]J.M.Gablonsky,C.T.Kelley.A locally-biased form of the direct algorithm.Journal of Global Optimization,2001,21:27-37P
[130]D.R.Jones,C.D.Perttunen,B.E.Stuckmann.Lipschitzian optimization without the lipschitz constant.Journal of Optimization Theory and Applications,1993,79:157-162P
[131]J.M.Gablonsky,C.T.Kelley.A locally-biased form of the DIRECT algorithm.Technical Report CRSC-TR00-31,Center for Research in Scientific Computation,North Carolina State University,December 2000.
[132]Finkel D.E.,Kelley C.T.,Convergence Analysis of the DIRECT algorithm.North Carolina State University,Center for Research in Scientific Computation and Department of Mathematics,Raleigh,2004,7
[133]包红强,张兆扬.一种基于区域Gibbs势能函数的视频运动对象分割算法.通信学报.2005,26(6):57-61页
[2]刘党辉,沈兰荪.视频运动对象分割技术的研究.电路与系统学报,2002,7(3):77-85页
[3]Roland Mech,Michael Wollborn.A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera..Signal Processing.1998,66(2):203-247P
[4]A.Neri,S.Colonnese,G.Russo,P.Ralone.Automatic Moving Object and Background Separation.Signal Processing 1998,66:249-232P.
[5]Turgay Celik,Hasan Demirel,Huseyin Ozkaramanli,Mustafa Uyguroglu.Fire detection using statistical color model in video sequences.Journal of Vision Communication & Image Representation.2007:1-9P
[6]杨莉,张弘,李玉山.视频运动对象的自动分割.计算机辅助设计与图形学学报.2004,16(3):301-306页
[7]赵明,李娜,陈纯.采用统计推断的自动视频对象分割.计算机辅助设计图形学学报,2003,15(3):318-333页
[8]陈韩锋,戚飞虎,视频对象分割中基于Gibbs随机场模型的时空分割结合方法,电子学报,2004,32(1):34-37页
[9]Manuele Bicego,Marco Cristani,Vittorio Murino.Unsupervised scene analysis:A hidden Markov model approach.Computer Vision and Image Understanding 2006,102:22-41P
[10]Feng-Yang Hsieh,Chin-Chuan Han,Nai-Shen Wu.A novel approach to the detection of small objects with low contrast.Signal Processing,2006,86:71-83P
[11]Youfu Wu,Jun Shen,Mo Dai.Traffic object detections and its action analysis.Pattern Recognition Letters.2005,26:1963-1984P
[12]L.Li,M.Leung,Integrating Intensity and Texture Differences for Change Detection,IEEE Trans.on Image Processing,2002,11(2):105-112P
[13]A.Colombari,A.Fusiello,V.Murino.Segmentation and tracking of multiple video objects.Pattern Recognition,2007,40:1307-1317P
[14]V.Mezaris,I.Kompatsiaris,M.G.Strintzis,Video Object Segmentation sing Bayes-Based Temporal Tracking and Trajectory-Based Region Merging,IEEE Trans.on Circuits System and Video Technology,2004,14(6):782-795P
[15]Liang-Hua Chen,Yu-Chun Lai.Extraction of video object with complex motion.Pattern Recognition Letters,2004,25:1285-1291P
[16]M.Kirchhof,U.Stilla.Detection of moving objects in airborne thermal videos.ISPRS Journal of Photogrammetry & Remote Sensing,2006,61:187-196P
[17]Gouze,A.,De Roover,C.,Macq,B.,Herbulot,A.,Debreuve,E.,Barlaud,M.Watershed-driven active contours for moving object segmentation.Proceeding of IEEE International Conference on Image Processing.2005(2):811-818P
[18]Young Sik Park,Eui Yoon Chung.Hierarchical spatiotemporal moving object segmentation based on a binary split algorithm.Optical Engineering.2003,42(1):245-254P
[19]S.Chien,Y.Huang,L.Chen,Predictive Watershed:A Fast Watershed Algorithm for Video Segmentation,IEEE Trans.on Circuits System and Video Technology,2003,13(5):453-461P
[20]崔明,孙守迁,潘云鹤.基于改进快速分水岭的图像区域融合.计算机辅助设计与图形学学报,2005,17(3):546-552页
[21]周军妮,曹剑中,刘波等.一种基于局部最小代价分水岭变换的图像分割新方法.光子学报,2005,34(1):142-145页
[22]杨高波,张兆杨,余圣发.一种基于小波分解和分水岭变换的视频对象自动分割算法.通信学报,2005,26(3):7-13页
[23]周军妮,曹剑中,刘波等.一种基于局部最小代价分水岭变换的图像分割新方法.光子学报,2005,34(1):142-145页
[24]杨文明,刘济林.时空联合视频对象分割.浙江大学博士学位论文,2006.
[25]E.Tuncel,L.Onural,Utilization of the Recursive Shortest Spanning Tree Algorithm for Video-object Segmentation 2-D Affine Motion Modeling,IEEE Trans.on Circuits System and Video Technology,2000,10(5):776-781P
[26]Chen,Tse-Wei;Hsu,Shou-Chieh;Chien,Shao-Yi.Robust Video Object Segmentation Based on K-Means Background Clustering and Watershed in Ill-Conditioned Surveillance Systems.Proceeding of 2007 IEEE International Conference on Multimedia and Expo,2007(7):787-790P
[27]Shah S.A.A.,Usman Naseem,M.Saif-ur-Rehman Karim,A.Motion Segmentation through Incremental Hierarchical Clustering.Proceeding of IEEE INMIC 2006,9thInternational Multitopic Conference,2006:781-785P
[28]Y.Deng,B.S.Manjunath,Unsupervised Segmentation of Color-Texture Regions in Images and Video,IEEE Trans.on Pattern Analysis and Machine Intelligence,2001 23(8):800-801P
[29]Jean Lorenceau,Anne Giersch,Peggy Series.Dynamic competition between contour integration and contour segmentation probed with moving stimuli.Vision Research,2005,45:103-116P.
[30]F.R.Mitiche,"A.Spatiotemporal motion boundary detection and motion boundary velocity estimation for tracking moving objects with a moving camera:a level sets PDEs approach with concurrent camera motion compensation." IEEE Trans.Image Processing,2004 13(11) 1473-1490P.
[31]Mezaris,V.,Kompatsiaris,I.,Strintzis,M.G.Video object segmentation using Bayes-based temporal tracking and trajectory-based region merging.IEEE Transactions on Circuits and Systems for Video Technology,2004,14(6):782-795P
[32]黄贤武,朱莉,仲兴荣等.一种新的基于时空马尔可夫随机场的运动目标分割技术.电子与信息学报.2006,28(2):367-371页
[33]Pakorn K.T.P.,Richard B.A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes. Image Vision Comput. 2003(21):913-929P
[34] Sun Y., Yuan B., Hierarchical GMM to handle sharp changes in moving object detection. Electron. Lett. 2004(40):801-802P
[35] Li L.Y., Huang, W.M., Gu, I.Y.H., Tian, Q. Statistical modeling of complex backgrounds for foreground object detection. IEEE Trans. Image Process.2004(13) 1459-1472P
[36] Wei Zhang , Xiang Zhong Fang, Xiaokang Yang. Moving vehicles segmentation based on Bayesian framework for Gaussian motion model.Pattern Recognition Letters 2006,27:956-967
[37] Gelgon M, Bouthemy P. A region-level motion-based graph representation and labeling for tracking a spatial image partition. Pattern Recognition 2000;33:725-40.
[38] Rita Cucchiara, rea Prati, Roberto Vezzani. Real-time motion segmentation from moving cameras. Real-Time Imaging 2004(10): 127-143P
[39] J. B. Kim, H. J. Kim. Efficient region-based motion segmentation for a video monitoring system. Pattern Recognition Letters, 2003, 24:113-128P
[40] Y. Wang, K. Loe, T. Tan, et al. Spatiotemporal Video Segmentation Based on Graphical Models, IEEE Trans. on Image Processing, 2005,14(7):937-947P
[41] Eun Yi Kim , Se Hyun Park. Automatic video segmentation using genetic algorithms. Pattern Recognition Letters. 2006,27: 1252-1265P
[42] Beung-Chan Kim, Rae-Hong Park. A fast automatic VOP generation using boundary block segmentation.Real-Time Imaging 2004(10): 117-125
[43] Y. Tsaig, A. Averbuch, Automatic Segmentation of Moving Objects in Video Sequences: A Region Labeling Approach, IEEE Trans. on Circuits System and Video Technology, 2002, 12(7):597-612P
[44] S. Chien, Y. Huang, B. Hsieh, et al, Fast Video Segmentation Algorithm with Shadow Cancellation, Global Motion Compensation, and Adaptive Threshold Techniques, IEEE Trans. on Multimedia, 2004, 6(5):732-748P
[45] T. Papadimitriou, K. I. Diamantaras, M. G. Strintzis, Video Scene Segmentation Using Spatial Contours and 3-D Robust Motion Estimation,IEEE Trans.on Circuits System and Video Technology,2004,14(4):485-497P
[46]Haifeng Xu,A.A.Younis,M.R.Kabuka,Automatic Moving Object Extraction for Context Based Applications,IEEE Trans.on Circuits System and Video Technology,2004,14(6):796-812P
[47]P.C.Chen,J.J.Su,Y.P.Tsai.Coarse-To-Fine Video Object Segmentation By MAP Labeling of Watershed Regions,Bulletin of College of Engineering,National Taiwan University,2004,(9):25-34P
[48]Y.Tsai,C.Lai,Y.Hung,et al.A Bayesian Approach to Video Object on Circuits System and Video Segmentation via Merging 3-D Watershed Volumes,IEEE Trans.Technology,2005,15(1):175-180P
[49]D.Xu,J.Liu,X.Li,et al.Insignificant Shadow Detection for Video Segmentation,IEEE Trans.on Circuits System and video Technology,2005,15(8):1058-1064P
[50]陈韩锋,戚飞虎,视频对象分割中基于Gibbs随机场模型的时空分割结合方法,电子学报,2004,32(1):34-37页
[51]吴思,林守勋,张勇东,基于动态背景构造的视频运动对象自动分割.计算机学报,2005,28(8):1386-1392页
[52]A.Monnet,A.Mittal,N.Paragios,V.Ramesh.Background modeling and subtraction of dynamic scenes,in:Proceedings of the International Conference on Computer Vision,2003,:1305-1312P
[53]A.Mittal,N.Paragios.Motion-based background subtraction using adaptive kernel density estimation,in:Proceedings of the International Conference on Computer Vision and Pattern Recognition(CVPR),2004:302-309P
[54]L.Li,W.Huang,I.Y.H.Gu,Q.Tian.Statistical modeling of complex backgrounds for foreground object detection,IEEE Transactions on Image Processing 2004,13(11):38-44P
[55]Q.Z.Wu,H.Y.Cheng,B.S.Jeng.Motion detection via change-point detection for cumulative histograms of ratio images,Pattern Recognition Letters 2005,26(5):555-563P
[56]Wang T.,Chen G..A novel background modeling approach for accurate and real-time motionsegmentation.Proceeding of the 8th International Conference on Signal Processing,2006,2:231-234P
[57]S.N.Lim,A.Mittal,L.S.Davis,N.Paragios.Fast illuminationinvariant background subtraction using two views:error analysis,sensor placement and applications,in:Proceedings of the International Conference on Computer Vision and Pattern Recognition(CVPR),2005:1071-1078P
[58]E.Herrero-Jaraba,C.Orrite-Urunuela,J.Senar.Detected motion classification with a double-background and a neighborhood-based difference,Pattern Recognition Letters.2003,24:2079-2092P
[59]T.Thongkamwitoon,S.Aramvith,T.H.Chalidabhongse.Non-linear learning factor control for statistical adaptive background subtraction algorithm,Proceedings of the IEEE International Symposium on Circuits and Systems(ISCAS'05),May 23-26,Kobe,Japan,2005:3785-3788P
[60]Xiaopeng Ji,Zhiqiang Wei,Yewei Feng.Effective vehicle detection technique for trafficsurveillance systems.Journal of Vision Communication & Image Representation.2006,17:647-658
[61]A.Branca,G.Attolico,A.Distante,Cast shadow removing in foreground segmentation,in:Proceedings of the International Conference on Pattern recognition,Quebec,Canada,2002:212-253P
[62]T.H.Chalidabhongse,K.Kim,D.Harwood,L.S.Davis.A perturbation method for evaluating background subtraction algorithms,Proceedings of the Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance(VS-PETS 2003),2003:453-458P
[63]P.Spagnolo,T.D.Orazio,M.Leo,A.Distante.Moving object segmentation by background subtraction and temporal analysis.Image and Vision Computing 2006,24:411-423P
[64]Joachim Weickert,Andres Bruhn,Thomas Brox,Nils Papenberg.A Survey on Variational Optic Flow Methods for Small Displacements.Mathematical Models for Registration and Applications to Medical Imaging,Springer,2006(10):103-136P
[65]陈震,高满屯,沈允文.图象光流场计算技术研究进展.中国图象图形学报,2002,7(5):12-16页
[66]Jerry L.Potter.Velocity as a Cue to Segmentation.IEEE Trans.on Systems,Man and Cybernetics 1983(5):390-394P
[67]Daniel Cremers,Christoph Schnorr.Statistical shape knowledge in variational motion segmentation.Image and Vision Computing,2003,21:77-86P
[68]D.Cremers.Nonlinear Dynamical Shape Priors for Level Set Segmentation.Proceedings of IEEE Conference on Computer Vision and Pattern Recognition(CVPR),2007(6).
[69]T.Brox,D.Cremers.On the Statistical Interpretation of the Piecewise Smooth Mumford-Shah Functional,Proceeding of International Conference on Scale Space and Variational Methods in Computer Vision,Springer,LNCS,2007,4485(5):203-213P
[70]A.Mansouri,J.Konrad.Multiple motion segmentation with level sets,IEEE Trans.Image Process.,2003,12(2):201-220P
[71]C.Vazquez,A.Mansouri,A.Mitiche.Approximation of images by basis functions for multiple region segmentation with level sets,Int.Conf.on Image Processing,ICIP04,2004:549-552P.
[72]H.Sekkati,A.Mitiche.Joint dense 3D interpretation and multiple motion segmentation of temporal image sequences:a variational framework with active curve evolution and level sets,presented at the Int.Conf.Image Processing,Singapore,2004:443-448P
[73]H.Sekkati,A.Mitiche.Joint optical flow estimation,segmentation,and 3D interpretation with level sets.Computer Vision and Image Understanding,2006(103) 89-100P
[74]Hicham Sekkati,Amar Mitiche.Concurrent 3-D Motion Segmentation and 3-D Interpretation of Temporal Sequences of Monocular Images.IEEE Trans.on image processing,2006,15(3):89-93P
[75]王长军,朱善安.基于统计模型和GVF-Snake的运动检测与跟踪,浙江大学学报(A1),2006,40(2):249-253页
[76]王长军,朱善安.基于统计模型和GVF-Snake的彩色目标检测与跟踪.中国图象图形学报(A1),2006,11(1):p.13-18页
[77]P.-C.Chung,C.-L.Huang,E.-L.Chen.A region-based selective optical flowback-projection for genuine motion vector estimation.Pattern Recognition,2007,40:1066-1077P
[78]John Y.A.Wang.Layered Representation for Motion Analysis.Proceedings of the IEEE Computer Vision and Pattern Recognition Conference,1993:361-366P
[79]Y.Weiss.Smoothness in layers:motion segmentation using nonparametric mixture estimation.Proc.IEEE Conf.Comput.Vision Pattern Recogn.San Juan,Puerto Rico,1997:520-527P
[80]Robles-Kelly A.,Bors A.,Hancock E.Hierarchical iterative eigendecomposition for motion segmentation.IEEE ICIP,2001,2:363-366P
[81]Jean Gao,Ninad Thakoor,Sungyong Jung.A Motion Field Reconstruction Scheme for Smooth Boundary Video Object Segmentation.In Proceeding of 2004 International Conference on Image Processing,2004:321-328P
[82]M.Black,P.Anandan.The robust estimation of multiple motions:parametric,piecewise-smooth flow fields.Computer Vision,Image Understanding,1996,63(1):75-104P
[83]Hongshi Yan,Tardi Tjahjadi.Multiple Motion Segmentation through a Highly Robust Estimator.2004 IEEE International Conference on Systems and Man,Cybernetics.2004:612-616P
[84]Yeon-Ho Kima,Aleix M.Martnez,Avi C.Kaka.Robust motion estimation under varying illumination.Image and Vision Computing,2005,23:365-375P
[85]Tao,H.,Sawhney,H.,Kumar,R.Dynamic layer representation with applications to tracking, in IEEE Conference on Computer Vision and Pattern Recognition,2000,: 11:134-141.
[86] Wei Zeng, , Jun Du, Wen Gao, Qingming Huang. Robust moving object segmentation on H.264/AVC compressed video using the block-based MRF model. Real-Time Imaging, 2005,11: 290-299P
[87] A. G. Amitha Perera, Glen Brooksby, Anthony Hoogs, Gianfranco Doretto.Moving Object Segmentation using Scene Understanding. Proceeding of 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW06), 2006:201-207P
[88] Paul Smith,etc. Layered Motion Segmentation and Depth Ordering by Tracking Edges. IEEE Trans. on pattern analysis and machine intelligence,2004, 26(4): 4-12P
[89] David Murry, Bernard Buxton. Scene segmentation from visual motion using global optimization. IEEE PAMI 1994,9(2)
[90] Michael M. Chang, A. Murat Tekalp, M. Ibrahim Sezan. An Algorithm for Simultaneous Motion Estimation and Segmentation. IEEE Int. Conf. On Acoustics, Speech and Signal Processing, ICASSP'94, Adelaide, Australia,April 1994:221-224P.
[91] Patrick Bouthemy, Edouard Francois. Motion Segmentation and Qualitative Dynamic Scene Analysis from an Image Sequence. International Journal of Computing Vision, 1993, 10(2): 157- 182P.
[92] Jie Wei, Izidor Gertner. MRF-MAP-MFT visual object segmentation based on motion boundary field. Pattern Recognition Letters, 2003, 24:3125-3139P
[93] Ashwani Kumar, Sumana Gupta. A novel probabilistic approach for real time motion segmentation and tracking. International Symposium on Signal Processing and its Applications (ISSPA), Kuala Lumpur, Malaysia, 2001(8)13-16P
[94] C.Demonceuux, D.Kachi-Akkouche. Fast motion estimation and motion segmentation using multi-scale approach. Proceeding of 2004 International Conference on Image Processing (ICIP), 2004, 1(24-27): 377 - 380P
[95] Konrad Schindler. Spatially consistent 3D motion segmentation. Proceeding of ICIP 2005. IEEE International Conference on Image Processing, 2005,3,11-14( III): 409-412P
[96] EunYi Kim, Keechul Jung. Genetic algorithms for video segmentation.Pattern Recognition , 2005,38 :59-73P
[97] F.Calderon,J. L. Marroquin. The MPM - MAP algorithm for motion segmentation. Computer Vision and Image Understanding , 2004, 95: 165 -183P
[98] Veenman C, Reinders M, Backer E. Resolving motion correspondence for densely moving points. IEEE Trans. Part. Analy. Mach. Intell. 2001,23(1):54-72P
[99] Xin Wang, Masanori Sugisaka, Wenli Xu. Feature Point-Based Object Tracking. IEEE Transactions on Electronics, Information and Systems,2004,124(8): 1585-1591P
[100] Shafique K., Shah M. A non-iterative greedy algorithm for multi-frame point correspondence. In IEEE International Conference on Computer Vision (ICCV). 2003:110-115P
[101] Jinman Kang, Cohen, I., Medioni, G, Chang Yuan. Detection and tracking of moving objects from a moving platform in presence of strong parallax.Proceeding of Tenth IEEE International Conference on Computer Vision(ICCV 2005), 2005,1(10): 10 - 17P
[102] Ediz Polat, Mohammed Yeasin, Rajeev Sharma. A 2D/3D model-based object tracking framework. Pattern Recognition, 2003, 36(9): 2127-2141P
[103] Vidal R., Ma Y. A unified algebraic approach to 2-d and 3-d motion segmentation. In European Conference on Computer Vision (ECCV). 2004:1-15.
[104] Birchfield S. Elliptical head tracking using intensity gradients and color histograms. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1998:232-237P
[105] Schweitzer H., Bell J. W., Wu F. Very fast template matching. In European Conference on Computer Vision (ECCV). 2002:358-372P
[106] Fieguth P., Terzopoulos D. Color-based tracking of heads and other mobile objects at video frame rates. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1997:21-27P
[107] Comaniciu D., Ramesh V, Meer P. Kernel-based object tracking. IEEE Trans. Patt. Analy. Mach. Intell. 2003,25: 564-575P
[108] B. Han, D. Comaniciu, Y. Zhu, L.S. Davis: Sequential Kernel Density Approximation: Application to Real-Time Visual Tracking, IEEE Trans.Pattern Analysis Machine Intell., 2007(1): 22-30P
[109] Jepson A., Fleet D., Elmaraghi T. 2003. Robust online appearance models for visual tracking. IEEE Trans. Part. Analy. Mach. Intell. 2003,25, 10:1296-1311P
[110] Tao H., Sawhney H., Kumar R. Object tracking with bayesian estimation of dynamic layer representations. IEEE Trans. Patt. Analy. Mach. Intell. 2002,24(1): 75-89P
[111] Isard M.and Maccoremick J. Bramble: A bayesian multiple-blob tracker. In IEEE International Conference on Computer Vision (ICCV). 2001: 34-41P
[112] Black M., Jepson A. Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. Int. J. Comput.Vision 1998,26,(1): 63-84P
[113] Avidan S. Support vector tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8): 1064- 1072P
[114] F. R. Schmidt, Eno Toppe, D. Cremers, Y. Boykov. Efficient Shape Matching via Graph Cuts. Proceeding of Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), Springer, LNCS,2007, 4679(8): 39-54P
[115] Kang J., Cohen I., Medioni G. Object reacquisition using geometric invariant appearance model. In International Conference on Pattern Recongnition (ICPR). 2004,759-762.
[116]Sato K.,Aggarwal J.Temporal spatio-velocity transform and its application to tracking and interaction.Comput.Vision Image Understand.2004,96,2,100-128P
[117]Tsechpenakis,G.,Tsapatsoulis,N.,& Kollias,S.Probabilistic boundary-based contour tracking with snakes in natural cluttered video sequences.International Journal of Image and Graphics,2004,4(3):469-498P
[118]Sang-Cheo Park,Sung-Hoon Lim,Bong-Kee Sin,Seong-Whan Lee.Tracking non-rigid objects using probabilistic Hausdorff distance matching.Pattern Recognition,2005,38:2373-2384P
[119]Shin-Hyoung Kim,Jong Whan Jang.Object contour tracking using snakes in stereo image sequences.IEEE International Conference on Image Processing(ICIP 2005),2005,2(9):414-417P
[120]D.Cremers.Dynamical statistical shape priors for level set based tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(8):1262-1273P
[121]Yilmaz A.,Shafique K.,Shah.M.Target tracking in airborne forward looking imagery.J.Image Vision Comput.2003,21(7):623-635P
[122]Gablonsky J.M.,An implementation of the DIRECT algorithm.Technical Report,Center for Research in Scientific Computation,North Carolina State University,august 1998.
[123]Bjorkman M.,Holmstrom K.Global Optimization Using the DIRECT Algorithm in Matlab.Center for Mathematical Modeling Department of Mathematics and Physics.Malardalen University,Sweden.AMO Advanced Modeling and Optimization 1999,1(2).
[124]Gablonsky J.M.Modifications of the DIRECT Algorithm.PhD Thesis.North Carolina State University,Raleigh,North Carolina,2001.
[125]S.A.Piyawskii.An algorithm for finding the absolute extremum of a function.USSR Computational Mathematics and Mathematical Physics,1972,(12):57-67P
[126]R.G.Strongin.On the convergence of an algorithm for finding a global extremum.Engineering Cybernetics,1973(11):549-555P
[127]G.R.Wood,B.P.Zhang.Estimation of the Lipschitz Constant of a Function.Journal of Optimization Theory and Applications,1996,8(1):91-103 P
[128]C.D.Perttunen D.R.Jones,B.E.Stuckman.Lipschitzian optimization without the lipschitz constant.Journal of Optimization Theory and Application,1993,79(1):157-181P
[129]J.M.Gablonsky,C.T.Kelley.A locally-biased form of the direct algorithm.Journal of Global Optimization,2001,21:27-37P
[130]D.R.Jones,C.D.Perttunen,B.E.Stuckmann.Lipschitzian optimization without the lipschitz constant.Journal of Optimization Theory and Applications,1993,79:157-162P
[131]J.M.Gablonsky,C.T.Kelley.A locally-biased form of the DIRECT algorithm.Technical Report CRSC-TR00-31,Center for Research in Scientific Computation,North Carolina State University,December 2000.
[132]Finkel D.E.,Kelley C.T.,Convergence Analysis of the DIRECT algorithm.North Carolina State University,Center for Research in Scientific Computation and Department of Mathematics,Raleigh,2004,7
[133]包红强,张兆扬.一种基于区域Gibbs势能函数的视频运动对象分割算法.通信学报.2005,26(6):57-61页