虚拟空间会议立体图像匹配技术及应用研究
|
摘要
虚拟空间会议(Virtual Space Teleconferencing,VST)系统是虚拟现实技术与计算机网络和多媒体相结合的产物,它突破了传统的地域观念,利用虚拟现实技术,将不同地点与会终端的局部会场合成一个共同的虚拟空间,与会者以化身(avatar)的形式在这个虚拟空间中,通过化身在虚拟空间中定位、观察、操纵虚拟空间的实体、与其他用户进行交互等方式“共享同一空间”,具有身临其境之感。因而又被称为“终极会议系统(Ultimate Teleconferencing System)”。为了达到具有眼神接触、凝视感知的真实会议系统,构建具有实时性和逼真感的与会者的化身是VST的研究热点。本文着重研究了VST中与会者的化身建模、三维重建、立体图像匹配等演示技术,运用了超小波、随机数学和偏微分方程等理论,提出了多种立体图像匹配方法并构建一个虚拟空间会议的原型系统。主要研究内容如下:
首先针对立体图像的区域匹配中,遮掩、区域变形及光照条件会对匹配算法造成很大的影响,传统的顺序性约束、惟一性约束、外极线约束和邻域约束并不能很好地解决这些问题,而近几年提出的相对位置约束却能解决其中大部分问题,但对于区域的遮掩情况依然效果不佳。并且当对多个候选区域进行最佳匹配选择时,通常依靠区域的单一参量进行判别,但受到视点的变换时效果并不理想。本文提出一种结合已匹配区域参量构造视差梯度函数的立体图像区域匹配方法,该方法摒弃了现有算法中单一参量不稳定的特性;此外提出了基于Zernike矩、中心环投影曲线相关、小波变换及分形维的立体图像区域匹配方法。实验结果证明,针对于区域的半遮掩、变形和细微差别等情况,本文的算法都具备更好的识别性能,是一种行之有效的区域匹配算法。
其次基于曲波变换是继小波变换后的一种新型的多尺度分析方法,它能够更好的描述图像中曲线状和超平面的奇异性问题,本文把曲波变换系数作为图像匹配中的基元,并结合图像分割原理和马尔可夫随机场(MRF)模型,提出了一种新的基于Markov模型和曲波的立体图像匹配方法,该方法克服了基于图像灰度的匹配方法在平滑区域或细节匮乏处无法得到正确视差的弊端,并使得视差图在物体内部平滑并保持边缘处的不连续性。实验结果表明,本文提出的算法无论从视觉评价上还是视差图客观指标来看,都取得更优的结果。
再次本文运用偏微分方程理论提出一种改进的立体图像匹配的正则化方法。先分析了匹配点对在不同相对位置下对匹配项产生的影响;接着提出了适用于视差图的各向异性的热扩散方程,它不仅继承了Alvarez定义的正则项对初始视差图内部平滑和保持边缘不连续的特性,还引入了图像的噪声屏蔽函数和二阶方向导数来分别控制对应视差图中不同区域的扩散速度和角点处的扩散方向;通过本文定义的正则项和匹配项构造新的能量函数,并把基于区域匹配算法得到的视差图作为初始值,数值求解相应的最小能量泛函。实验结果表明无论从视觉效果上还是重构深度图的判别上,本文的算法均为优秀。
由于视差图反映了图像中各个景物的深度信息量,因此视差图的边缘并非是对应图像的边缘。而现有的正则化方法中能量函数的正则项都依照图像梯度场对初始视差图内部进行平滑并保持边缘的不连续性,这导致最终获取的密集视差图不仅不能准确分辨物体边缘且平滑区域具有较多的图像边界残留痕迹。光流反映了目标物体的运动状态且包含的运动边界与物体边界相吻合,但光流计算中的正则项使其在边界上是模糊不准确的,因此本文采用了多分辨率框架下由粗到精的分级策略来计算大基线时左右图像中的光流场,并结合图像边界和光流来确定准确的运动边界,提出了一种融合光流信息的正则化方法,该方法利用携带景物深度信息的光流场构造了融合光流信息的各向同性和异性的视差图正则项。通过与现有方法进行实验比较,提高了最终获得的视差图的质量。
最后在前面理论和实验的基础上建立了一个虚拟空间会议的原型系统,实现了虚拟会场的构造、显示与漫游、与会者的视频对象提取与合成、基于视线的中间视生成等主要功能。
Virtual Space Teleconferencing System (VST) is a synthesis of many kinds of techniques: Virtual Reality, Computer Network, Multimedia, etc. It combines different local conference spaces into one virtual space breaking through the traditional perspective about conference. Participants appear in computer-generated virtual spaces as avatars in VST, and these avatars can locate, view, manipulate virtual objects, communicate with others face to face, so participants could share 'the same space' and do cooperative work. VST is also named Ultimate Teleconferencing System. This dissertation concentrates on the display technique such as: conventioneer avatar modeling, 3D reconstruction, stereo image matching. Super-wavelets, stochastic mathematic and partial differential equation theory are used, many stereo image matching methods are presented and a virtual space teleconference prototype system is designed. The main research points in this paper are as follows:
Firstly, existing stereo images regional matching methods will be affected by the factors such as regions occlusion, regions warping and lighting condition, so the traditional constraint conditions, like order constraint, unique constraint , epipolar constraint and adjacent constraint, may be violated by these cases. In past few years a new algorithm based on the relative position constraint (RPC) between regions is proposed which can overcome most of problem mentioned above, but it has not satisfying performance in matching occluded objects in the stereo images. And only single parameter of region is usually used to judge during selection of a best region among multiple candidate regions, but its performance is not satisfying because of the view angle transform. In order to choose the best matching region, a method that combining with the parameter of matched region to construct disparity gradient function is presented, which casts away the instability of existing algorithms that judge by single parameter. Furthermore regional matching methods based on zernike moments, center ring-projection, wavelet transform and fractal dimension theory are proposed. Finally, the proposed region matching algorithm is illustrated with many synthesized stereo images, and the superior recognition performance to the case of regions deforming, regions occlusion and regions slight difference is experimentally verified.
Secondly, curvelet transform is a new multi-scale analysis method based on wavelet transform, it is better suitable for describing of those images that have curve or super plane singularities. In this paper a new stereo matching algorithm based on markov random field and curvelet transform is proposed which takes curvelet transform coefficients as the image matching primitive and combines image segmentation principle with markov random field model. The approach not only overcomes these defects that image matching algorithm based on gray level can not get accurate disparity of areas where are smooth or lack of details, but also smoothes disparity inside the object boundaries and keeps the discontinuities across the boundaries. Finally, the superior visual effect and evaluation indexes of our algorithm are experimentally verified.
Thirdly an improved regularization method of stereo matching is proposed. Above all, the effects of matching pairs at various relative positions to the attachment item are analyzed. then anisotropic heat diffusion equation adapts to disparity map is presented, which inherite from the ability of the Alvarez defining regularization item that keeping the discontinuities across the boundaries of the image and smoothing disparity inside the boundary, in addition image noise shielded function and second order direct ional derivative are introduced to separately control disparity diffusion velocity of different area and diffusion direction of edge position. At last, new energy function according to our approach is defined, adopting the output of the area stereo matching method as the initial value, steepest descent is exploited to solve the energy functional. Experiment results demonstrate the effectiveness of our approach, both in the visual effect and 3D depth retrieval.
The edge of disparity map which reflect the sceneries' depth information are not equivalent to corresponding image edge. But in the current regularization methods, regularization item of the energy function smoothes the interior domain and keeps the boundaries discontinuity of disparity map according to the gradient field of image, it leads the finial dense disparity map can not clearly distinguish the object edge and retain much traces of image edge in the smooth area. The motion state of target is mirrored by optical flow among which moving boundaries are identical with the target edge, but the regularization item of optical flow calculation causes the result inaccurate at the image edge, so the coarse-to-fine classifying strategy in the multi resolution frame is applied to calculate the optical flow for wide baseline stereo pairs, then precise moving boundaries are obtained through the union of image edge and optical flow, the regularization method fusing the optical flow is presented, isotropic and anisotropic regularization items of disparity map fusing optical flow information are constructed. At last, new energy function according to our approach is defined and compared with current methods. Experimental results demonstrate the better performance of our approach both in the visual effect and the disparity map evaluation indexes.
Lastly, the VST prototype system is designed on the basis of textual theory and experiment, the function such as: virtual meeting hall creating and divagation, conventioneer video object extraction and synthesizing, intermediate view image creation are realized.
首先针对立体图像的区域匹配中,遮掩、区域变形及光照条件会对匹配算法造成很大的影响,传统的顺序性约束、惟一性约束、外极线约束和邻域约束并不能很好地解决这些问题,而近几年提出的相对位置约束却能解决其中大部分问题,但对于区域的遮掩情况依然效果不佳。并且当对多个候选区域进行最佳匹配选择时,通常依靠区域的单一参量进行判别,但受到视点的变换时效果并不理想。本文提出一种结合已匹配区域参量构造视差梯度函数的立体图像区域匹配方法,该方法摒弃了现有算法中单一参量不稳定的特性;此外提出了基于Zernike矩、中心环投影曲线相关、小波变换及分形维的立体图像区域匹配方法。实验结果证明,针对于区域的半遮掩、变形和细微差别等情况,本文的算法都具备更好的识别性能,是一种行之有效的区域匹配算法。
其次基于曲波变换是继小波变换后的一种新型的多尺度分析方法,它能够更好的描述图像中曲线状和超平面的奇异性问题,本文把曲波变换系数作为图像匹配中的基元,并结合图像分割原理和马尔可夫随机场(MRF)模型,提出了一种新的基于Markov模型和曲波的立体图像匹配方法,该方法克服了基于图像灰度的匹配方法在平滑区域或细节匮乏处无法得到正确视差的弊端,并使得视差图在物体内部平滑并保持边缘处的不连续性。实验结果表明,本文提出的算法无论从视觉评价上还是视差图客观指标来看,都取得更优的结果。
再次本文运用偏微分方程理论提出一种改进的立体图像匹配的正则化方法。先分析了匹配点对在不同相对位置下对匹配项产生的影响;接着提出了适用于视差图的各向异性的热扩散方程,它不仅继承了Alvarez定义的正则项对初始视差图内部平滑和保持边缘不连续的特性,还引入了图像的噪声屏蔽函数和二阶方向导数来分别控制对应视差图中不同区域的扩散速度和角点处的扩散方向;通过本文定义的正则项和匹配项构造新的能量函数,并把基于区域匹配算法得到的视差图作为初始值,数值求解相应的最小能量泛函。实验结果表明无论从视觉效果上还是重构深度图的判别上,本文的算法均为优秀。
由于视差图反映了图像中各个景物的深度信息量,因此视差图的边缘并非是对应图像的边缘。而现有的正则化方法中能量函数的正则项都依照图像梯度场对初始视差图内部进行平滑并保持边缘的不连续性,这导致最终获取的密集视差图不仅不能准确分辨物体边缘且平滑区域具有较多的图像边界残留痕迹。光流反映了目标物体的运动状态且包含的运动边界与物体边界相吻合,但光流计算中的正则项使其在边界上是模糊不准确的,因此本文采用了多分辨率框架下由粗到精的分级策略来计算大基线时左右图像中的光流场,并结合图像边界和光流来确定准确的运动边界,提出了一种融合光流信息的正则化方法,该方法利用携带景物深度信息的光流场构造了融合光流信息的各向同性和异性的视差图正则项。通过与现有方法进行实验比较,提高了最终获得的视差图的质量。
最后在前面理论和实验的基础上建立了一个虚拟空间会议的原型系统,实现了虚拟会场的构造、显示与漫游、与会者的视频对象提取与合成、基于视线的中间视生成等主要功能。
Virtual Space Teleconferencing System (VST) is a synthesis of many kinds of techniques: Virtual Reality, Computer Network, Multimedia, etc. It combines different local conference spaces into one virtual space breaking through the traditional perspective about conference. Participants appear in computer-generated virtual spaces as avatars in VST, and these avatars can locate, view, manipulate virtual objects, communicate with others face to face, so participants could share 'the same space' and do cooperative work. VST is also named Ultimate Teleconferencing System. This dissertation concentrates on the display technique such as: conventioneer avatar modeling, 3D reconstruction, stereo image matching. Super-wavelets, stochastic mathematic and partial differential equation theory are used, many stereo image matching methods are presented and a virtual space teleconference prototype system is designed. The main research points in this paper are as follows:
Firstly, existing stereo images regional matching methods will be affected by the factors such as regions occlusion, regions warping and lighting condition, so the traditional constraint conditions, like order constraint, unique constraint , epipolar constraint and adjacent constraint, may be violated by these cases. In past few years a new algorithm based on the relative position constraint (RPC) between regions is proposed which can overcome most of problem mentioned above, but it has not satisfying performance in matching occluded objects in the stereo images. And only single parameter of region is usually used to judge during selection of a best region among multiple candidate regions, but its performance is not satisfying because of the view angle transform. In order to choose the best matching region, a method that combining with the parameter of matched region to construct disparity gradient function is presented, which casts away the instability of existing algorithms that judge by single parameter. Furthermore regional matching methods based on zernike moments, center ring-projection, wavelet transform and fractal dimension theory are proposed. Finally, the proposed region matching algorithm is illustrated with many synthesized stereo images, and the superior recognition performance to the case of regions deforming, regions occlusion and regions slight difference is experimentally verified.
Secondly, curvelet transform is a new multi-scale analysis method based on wavelet transform, it is better suitable for describing of those images that have curve or super plane singularities. In this paper a new stereo matching algorithm based on markov random field and curvelet transform is proposed which takes curvelet transform coefficients as the image matching primitive and combines image segmentation principle with markov random field model. The approach not only overcomes these defects that image matching algorithm based on gray level can not get accurate disparity of areas where are smooth or lack of details, but also smoothes disparity inside the object boundaries and keeps the discontinuities across the boundaries. Finally, the superior visual effect and evaluation indexes of our algorithm are experimentally verified.
Thirdly an improved regularization method of stereo matching is proposed. Above all, the effects of matching pairs at various relative positions to the attachment item are analyzed. then anisotropic heat diffusion equation adapts to disparity map is presented, which inherite from the ability of the Alvarez defining regularization item that keeping the discontinuities across the boundaries of the image and smoothing disparity inside the boundary, in addition image noise shielded function and second order direct ional derivative are introduced to separately control disparity diffusion velocity of different area and diffusion direction of edge position. At last, new energy function according to our approach is defined, adopting the output of the area stereo matching method as the initial value, steepest descent is exploited to solve the energy functional. Experiment results demonstrate the effectiveness of our approach, both in the visual effect and 3D depth retrieval.
The edge of disparity map which reflect the sceneries' depth information are not equivalent to corresponding image edge. But in the current regularization methods, regularization item of the energy function smoothes the interior domain and keeps the boundaries discontinuity of disparity map according to the gradient field of image, it leads the finial dense disparity map can not clearly distinguish the object edge and retain much traces of image edge in the smooth area. The motion state of target is mirrored by optical flow among which moving boundaries are identical with the target edge, but the regularization item of optical flow calculation causes the result inaccurate at the image edge, so the coarse-to-fine classifying strategy in the multi resolution frame is applied to calculate the optical flow for wide baseline stereo pairs, then precise moving boundaries are obtained through the union of image edge and optical flow, the regularization method fusing the optical flow is presented, isotropic and anisotropic regularization items of disparity map fusing optical flow information are constructed. At last, new energy function according to our approach is defined and compared with current methods. Experimental results demonstrate the better performance of our approach both in the visual effect and the disparity map evaluation indexes.
Lastly, the VST prototype system is designed on the basis of textual theory and experiment, the function such as: virtual meeting hall creating and divagation, conventioneer video object extraction and synthesizing, intermediate view image creation are realized.
引文
[1] Abigail S, Bill B. Using Spatial Cues To Improve Videoconferencing[J]. CHI '92,.Videotape in CHI'92 Video Proceedings, 1992: 651-652.
[2] Ichikawa Y., Okada K., Jeong G., Tanaka S, Matushita, Y.MAJIC "Videoeonferencing System: Experiments, Evaluation and Improvement"[J]. ECSCW'95,1995.
[3] Jefferson H ,Brian S. CU-SeeMe VR Immersive Desktop Teleconferencing [J], ACM Multimedia 1996
[4] Gonzalez, D, Arns, L. AG virtual reality. Presented at the Access Grid~(TM)[J]. San Francisco, 2005.
[5] Regenbrecht H, Ott C, Wagner M, Lum T, Kohler P, Wilke W, Mueller E, An Augmented Virtuality Approach to 3D Videoconferencing[C]. Proceedings of the Second IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR '03) 2003.
[6] Billinghurst M, Bowskill J, Jessop M, Morphett J. Real World Teleconferencing[J]. Proceedings ofISWC'98, IEEE Press, pp. 76-83
[7] Prince S,. Cheok AD, Farbiz F, Williamson T, Johnson N, Billinghurst M, Kato H. Real-Time 3D Interaction for Augmented and Virtual Reality[J]. SIGGRAPH'02 Sketches
[8] Ishii H, Kobayashi M, Arita K. ClearBoard: A Seamless Medium for Shared Drawing and Conversation with Eye Contact[J]. Communications of the ACM, Vol. 37, No.8, August 1994, 83-97
[9] Fumio K, Tsutomu M, Nobuyoshi T.Virtual Space Teleconferencing "Communication with Realistic Sensations"[J]. IEEE International Workshop on Robot and Human Communication 0-7803-2904-x/95 1995.
[10] Christian P, Kunz M.Construction of a Three-sided Immersive Telecollaboration System VR[R]. 2003,. 37-44.
[11] Simon J. Gibbs C A, Christian J. TELEPORT - Towards immersive copresence [J]. Multimedia Systems 1999, 7(3): 214-221.
[12] Stefan A, Alex W, Michael B. Reflection of Presence: Toward More Natural and Responsive Telecollaboration[J]. Proc. SPIE Multimedia Networks, 3228A, 1997.
[13] Kensaku H, Kentaro F, Hiroshi S, Kenichi O. e-MulCS : Multi-Party Conference System with Virtual Space and the Intuitive Input Interface [C]. the International Symposium on Applications and the(SAINT'04)2004
[14]Bruce C,Thomas M.The Coliseum Immersive Teleconferencing System[J].Published in and presented at the International Workshop on Immersive Telepresence,Juan Les Pins,France,6 2002
[15]Wen Lin,Yao-Jen Chang,Chi-MingWang,Yung-Chang Chen,Ming-Ting Sun.A Standard-Compliant Virtual Meeting System with Active Video Object Tracking[J].EURASIP Journal on Applied Signal Processing:2002,6,622-634.
[16]Kauff P,Schreer O.An immersive 3-D video-conferencing system using shared virtual team user environments[J].ACM Conf.Collaborative Virtual Environments,2002.
[17]Gemmell J,Zitnick C.L.,Kang T,Toyama K.,Seitz S.Gaze-awareness for Videoconferencing:A Software Approach[J].IEEE Multimedia,2000,7(4):26-35.
[18]Chris G,Steve B.Virtual Reality Tele-conferencing:Implementation and Experience[C]..Fourth European Conference on Computer Supported Cooperative Work(ECSCW'95),1995.
[19]Mortlock A N,Machin D,McConnell S,Sheppard P J.Virtual Conferencing[J].Telepresence,Kluwer Academic Publishers,Boston,1999,.209-225.
[20]Xin Wang,X-Conference:Reinventing a Teleconferencing System[J].Program in Media Arts and Sciences 2002
[21]H.Towles,W.-C Chen,R.Yang,S.-U Kum,H.Fuchs,N.Kelshikar,J.Mulligan,K.Daniilidis,L.Bolden,B.Zelesnik,A.Sadagic,and J.Lanier,3-D tele-collaboration over internet2[J],in Proc.Int.Workshop Immersive Telepresence,Juan-les-Pins,France,Dec.6,2002
[22]Chen W.C.Toward a compelling sensation of telepresence:Demonstrating a portal to a distant(static)office[C],in Proc.IEEE Conf.Visualization,Salt Lake City,UT,Oct.8-13,2000,.377-383.
[23]Jane M,Xenophon Z,Nikhil K,Kostas D.Stereo-Based Environment Scanning for Immersive Telepresence[J].IEEE Transactions on Circuits And Systems For Video Technology.2004,14(3).
[24]Celso S K,Ruigang Y,Anselmo L.Combining Approximate Geometry with View-Dependent Texture Mapping-A Hybrid Approach to 3D Video Teleconferencing[C].Proceedings of the XV Brazilian Symposium on Computer Graphics and Image Processing,2002.
[25]Hom B K P.Shape from Shading:A Method for Obtaining the Shape of a SmoothOpaque Object from one View[D].PhD thesis, MIT, 1970.
[26] Lkeuehi I K Horn B.K.P. .Numerical shape from shading and occluding boundaries[J]. Arti_cial Intelligence, 1981,17(3): 141 -184.
[27] Pentland A P. Local shading analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1984,6: 170-187
[28] Lee C.H, Rosenfeld A. Improved methods of estimating shape from shading using the light source coordinate system[J]. Arti_cial Intelligenee.1985.26:125-143.
[29] Tsai P S, Shah M.Shape from shading using linear approximation[J]. Image and Vision Computing Journal.1994,12(8):487-498.
[30] Akimoto T, Suenaga Y, Wallace R S. Automatic 3d facial models[J]. IEEE Computer Graphics and Applications, 1993.13(5): 16-22.
[31] Lee A W E, Sweldens W, Sehroder P, Cowsar L , Dobkin D. Maps:Multiresolution adaptive Parameterization of sufaces[J]. Proe.of SIGGRAPH'98,1998,95-104.
[32] Parke F I. Computer generated animation of faces[C]. In ACM National Conferenee,1972.
[33] Van Beek P J L,.Reinders M J T, Sankur B, Van Der Lubbe J C.A.Semantic segmentation of videophone image sequenees[C].in Proe.of SPIE Int.Conf. on Visual Communieations and Image processing, 1992,1182-1193.
[34] Ip H.S, Yin L.Constructing a 3d individualized head model from two orthogonal views[J]. The Visual Computer. 1996. (12):254-266.
[35]. Zheng J Y. Acquiring 3-d models from sequences of contours [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1994.16(2): 163-178.
[36] Liu Z, Zhang Z, Jacobs C, Cohen M. Rapid Modeling of Animated Faces From Video. Technical Report[R]. Microsoft Research. 2000,9-21
[37] Laurentini A. The visual hull concept for silhouette based image understanding[J]. IEEE PAMI. 1994.16(2): 150-162.
[38] Lee Y, Terzopoulos D, Waters K. Realistic modeling for facial animation[C]. In: SIGGRAPH Conference Proceedings, Los Angeles, USA, 1995, 55-62
[39] Martin W N, Aggarwal J K. Volumetric descriptions of objects from multiple views [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1983,5(2):150-158.
[40] Frisken S, Perly R, Rockwood A. Adaptively sampled distance fields:a general representation of shape for computer. In:Akeley K.ed.Proceedings of the SIGGRAPH 2000.NewYork:ACM Press, 2000.249-254.
[41]Peny R,Frisken S.Kizamu:A system for sculpting digital characters[R]In:Fiume,E.ed.Proeeedings of the SIGGRAPH2001 NewYork:ACM Press,2001.47-56.
[42]Matusik W,Buehler C,MeMillan L.Polyhedral visual hulls for real-time rendering[C].In:Myskowski K.,Gortler S,eds.Proceedings of the 12~(th)EurograPhics Workshop on Rendering.Wien:Springer-Verlag,2001.115-125.
[43]Blanz V,Vetter T.A morphable model for the synthesis of 3d faces.InComputer GraPhies[C].Annual Conference Series,SIGGRAPH99proeeedings,187-194
[44]Fua P,Miccio C..From regular images to animated heads:A least squares approach.In European conference on Computer Vision.1995,188-202.
[45]Fua P,Miccio C.Animated heads from ordinary images:A least-squares approach.Computer Vision and Image Understanding.1999,75(3):247-259.
[46]Fua P,Plaenkers R,Thalmann D..From synthesis to analysis:Fitting human animation models to image data.In Computer Graphics International,Albeta.Canada,1999.
[47]Zi cheng Liu,Ying Shan,Zheng you Zhang:Expressive expression mapping with ratio images[C].In siggraph'01 Conference Proceedings.271-276.
[48]Nagel.H Constraints for the estimation of displacement vector fields from image sequences[C].Proc.Eighth Int.Joint Conf.on Artificial Intelligence(IJCAI '83.Karlsruhe,August 1983,945-951.
[49]Chai Douglas,Ngan King N.Locating facial region of a head-and-shouders color image[C].Proc 3rd IEEE International Conference on Automatic Face and Gesture Recognition.1998,124-129.
[50]韩锦成,施鹏飞,莫玉龙.基于差值图像及子波变换的人脸检测方法.上海交通大学学报.1999,33(11):1381-1385.
[51]Agarwala A,Hertzmann A,Seitz S,et al,Keyframe-based tracking for rotoscoping and animation[C],Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,Los Angeles.2004:584-591.
[52]Chuang Y Y,Agarwala A,Curless B,et al.Video matting of complex scenes[C].Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,San Antonio,Texas.2002:243-248.
[53]Chuang Y Y.New models and methods for matting and compositing[D].Seattle:University of Washington,2004.
[54]Black M J,Anandan P.The robust estimation of multiple motions:parametric and piecewise-smooth flow fields[J].Computer Vision and Image Understanding,1996,63(1):75-104.
[55]ApostoloffN,Fitzgibbon A W.Bayesian video matting using learnt image priors[C].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,Washington D C.2004,407-414.
[56]McGurie M,Matusik W,Pfister H.Defocus video matting[C].Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,Los Angeles,2005:567-576
[57]Wang J,Bhat P,Colbum A.Interactive video cutout[C].Computer Graphics Proceedings.Annual Conference Series,ACM SIGGRAPH,Los Angeles.2005.585-594.
[58]Li Y,Sun J,Shum H Y.Video object cut and paste[C].Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,Los Angeles.2005.595 -600.
[59]隋婧,金伟其.双目立体视觉技术的实现及其进展.电子技术应用.2004,(10):4-6
[60]骆艳,张兆扬.一种基于立体视邻接帧时空相关性的最小代价函数帧估计算法.电子学报.2003,31(10):1513-1517.
[61]贾云得.机器视觉[M].北京:科学出版社,2001.
[62]Scharstein D,Szeliski R.A taxonimy and evaluation of dense two-frame stereo correspondence algorithms[J].IJCV,2002,47(1/2/3):7-42.
[63]陈棣湘,罗飞路,潘孟春.立体视觉测量中的图像匹配策略的研究[J].光学技术,2002,5:392-394.
[64]Kuijper A,I.M.J Florack.on the creations of critical points in scale space with applications to modical image analysis[J].UU-CS,2001,25:316-319.
[65]Moravec H P.Towards automatic visual obstacle avoidance[A].Proc.5th Int.Joint Conf.Aritifical Intell[C].Cambridge,MA,1977.
[66]Raymond Van Ee,Cliftom M Schor Unconstrainted stereoscopic matching of lines [J].Vision Research,2000.40:151-162.
[67]Lcaiza H,Triboulet J,Lelandais S,et al.Matching segments in stereoscopic vision [J].IEEE Instrumentation & Measurement.2001,03:37 - 42.
[68]Supa B J,Kiariquist W N.Patch- based stereo in general binocular viewing[J].Theory and Experiment,PAMI,1997,(19)3:247-252.
[69]Prince S J D.Eagle R D.Weighted directed energy model for human stereo correspondence[J].Vision Research,2000,40:151-162.
[70]Kisworo M,Venkatesh S.West modeling edges at subpixel accuracy using local energy approach[J].Theory and Experment,PAMI,1994,16(4):405-410
[71]He C,Dong J Y,Zheng Y F,et al.Object tracking using Gabor wavelet transform and the golden section algorithm[R].2002.
[72]Maitre H,etal.Using models to improve stereo reconstruction[J].IEEE Trans.on PAMI,1992,149(2):269-277.
[73]Jenkin M,etal,The measurement of binocular disparity in computational process in human vision[M].Ablex.NewJersey:Prentice -Hall,1988.
[74]Robson J G,Receptive fields:neural espresentation of the spatialand intensive attributes of the visual images[Z].Handbook of Preception,NewYork:Academic press,1985,5:81-116.
[75]Terzopoulos D.The computer of visible - surface representations[J].IEEE Trans.on PAMI,1988,10(40):417-438.
[76]Ohta Y,et al.Stereo by two - level dynamic programming[A].Proc.of 9th IJCAI [C].1985:1120-1124.
[77]Julesz T B.Stereoscopic vision[C].Vision Res.1986,26:1601-1612.
[78]Sanger T D.Stereo disparity computation using gabor filter[D].Nethedand:Delft University of Technology,1988.
[79]游素亚,柳健,万发贯.基于小波变换相位的立体匹配系统[J].信息与控制,1994,(5):28-31.
[80]贾波.视差图误差检测与校正的通用算法[J].清华大学学报,2000,40(1):28-31.
[81]Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window,theory and experiment[J].Proc IEEE PAMI,1994,16(9):920 -932.
[82]徐颜军,杜利民,候自强.基于相位的尺度自适应立体匹配方法[J].电子学报,1999.27:38-41.
[83]Scharstein D,Szeliski R.A texonomy and evaluation of dense two-frame stereo correspondence algorithms[J].IJCV,2002:47(1/2/3):551-554.
[84]Mumford David.M athematic theo ries of shape:Do they model percep tion[J].In:Proc.Geometric Methods in Computer Vision,SPIE,1991.1570:2-10
[85]Grimson W Eric,Huttenlcher Daniel P.On the sensitivity of Hough transform for object recognition[J].IEEE Trans.PAMI,1990,12(3):255- 274
[86]Derek CW Pao,Hon F L i,Jayakumar R.Shape recognition using the straight line Hough transform: Theory and generalization[J]. IEEE Trans. PAM I, 1992,14 (11): 1076-1089
[87] Gorman J W , Mirchell O R, Kuhl F P. Partial shape recognition using dynamic programming[J]. IEEE Trans. PAMI, 1988,10 (2): 257-266
[88] McConnell Ross, Kwok Ronald, Curlander John C, Kober W, Pang Shirley S. ψ -s correlation and dynamic time warping: Two methods for tracking ice floes in sar image[J]. IEEE Trans. Geoscience and Remote Sensing ,1991,29(6): 1004-1012
[89] Wolfson Haim J. On curve matching[J]. IEEE Trans. PAM I,1990,12(5): 483-489
[90] Ansari N, Delp E J. On the distribution of a deforming triangle[J]. Pattern Recognition, 1990,23 (12): 1333-1341
[91] Lamdan Y, Schwarz J T, Wolfson H J. Affine invariant model-based object recognition[J]. IEEE Trans. Robotics Automn, 1990, 6 (5): 578-589
[92] Jain A K, Zhong Y, Lak shmanan S. Objectmatching using deformable templates[J]. IEEE Trans. PAMI, 1996,18(3): 267-278
[93] Sclaroff Stan. Deformable prototypes for encoding shape categories in image database[J]. Pattern Recog nition, 1997,30 (4): 627-641
[94] Del Bimbo Alberto, Pala Pietro. Visual image retrieval by elesticmatching of user sketchs[J]. IE E E Trans. PAMI ,1997,19 (2) : 121-132.
[95] Wang Yong-Mei. Boundary finding with correspondence using statistical shape models[J]. In: Proc. IEEE CVPR,1998.338-345.
[96] Lai K, Chin R. Deformable Contours: Modeling and extraction[J].IEEE Trans. PAMI, 1995,17 (11): 1084-1090
[97] Ding Xian-Feng, Kong Wei-Xing, Lu Han-Qing, Ma Song-De. Genetic algorithm for partial shape recognition[J]. Beijing Mathmatics, 1998,4 (2): 182-188
[98] Yang Q , Ma S-D. Shape matching using Schwarz representation[J]. Pattern Recognition, 1999,32(6): 1039-1047
[99] EI Ansari M,Masmoudi L,Radouane L.A new region matching method for stereoscopic images[J].Pattern Recognition Letters, 2000,21(4):283-294.
[100] Vinet L, Gagalowicz Al. Region matching using neighborhood consistency[C]. In: Proceedings of the 8th Congress of Form Recognition and Artificial Intelligence, Lyon Villeurbanne, 1991, 2:821-826.
[101] Zagrouba E , Krey C. Region matching by adjacency propagation in stereo vision [C]. In : Proceedings of the 2nd International Conference on Automation, Robotics and Computer Vision, Hyatt Regency, Singapore, 1992.851-855.
[102]夏永泉,刘正东,杨静宇.不变矩方法在区域匹配中的应用[J].计算机辅助设与图形学学报,2005,17(10):2152-2156.
[103]S B Pollard,J E W Mayhew,and J P Frisby.A stereo correspondence algorithm using a disparity gradient limit[J].Perception,1985,14:449-470.
[104]Hu MK.Pattern recognition by moment invariants[C].Proc.IRE,1961;49(9):14-28.
[105]Teague MR.Image analysis via the general theory of moments[3].Opt.Soc.Amer,1980;70(8):920-930.
[106]Boyce JF,Hossack WJ.Moment invariants for pattern recognition[J].Pattern Recognition Lett.1983;1(5-6):451-455.
[107]Abu-Mostafa YS,Psaltis D.Recognitive aspects of moment invariants[J].IEEE Trans.Pattern Anal.Machine Intell,1984;PAMI - 6(11):698-706.
[108]Yoshida Y,Wu Y.Classification of rotated and scaled texture images using invariants based on spectral moments[J]IEICE Trans.Fundamentals,1998;E81A (8):1661-1666.
[109]Shen DG;Horace HS.Discriminative wavelet shape descriptors for recognition of Depattems[J].Pattern recognition,1999;32:151-165.
[110]Yang Z,Cohen F.Cross - weighted moments and affine invariants for image registration and matching[3].IEEE Trans.PAMI,1999;21(8):804-814.
[111]Wong RY.Scene matching with invariant moments[J].Computer Graphics and Image Processing,1978;8(1):16-24.
[112]Wang WH,Chen YC.Histogram matching by moment normalization[J].IEICE Trans.Inf.&Syst,1997;E80 - D(7):746-750.
[113]Dudani AS,Breeding KJ,Mcghee RB.Aircraft identification by moment invafiants[J].IEEE Transactions on Computers,1977;26(1):39-46.
[114]Mertzios BG,Tsirikolias K.Statistical shape discrimination and clustering using an efficient set of moments[J].Pattem Recognition Letters,1993;14:517 - 522.
[115]Trier OD,Jain AK,Taxt T.Feature extraction methods for character ecognition a survey[J].Pattern Recognition,1996;29(4):641- 662.
[116]Chim YC,Kassim AA,Ibrahim Y.Character recognition using statistical moments[J].Image and Vision Computing,1999;17:299-307.
[117]Sluzek A.Identification and inspection of 2 - D objects using new moment-based shape descriptors[J].Pattern Recognition Letters,1995;16:687-697.
[118]Mandal MK,Aboulnasr T,Panehanathan S.Image indexing using moments and wavelets[J].IEEE Trans.on Consumer Electronics,1996;42(3):557- 565
[119]Kim YS,Kim WY.Content - based trademark retrieval system using a visually salient feature[J].Image and Vision Computing,1998;16:931-939
[120]Teague M.Image analysis via the general theory of moments[J].Opt Soc Amer,1980,70(8):920-930.
[121]Yuan Y.Tang,Bing F.Li,nong Ma,and JimingLiu.Ring-projection-wavelet -fractal signatures:a novel approach to feature exraction[J].IEEE transactions on circuits and systems-Ⅱ:1998,45(8):1130-1134.
[122]Rittscher C,Kato J,Joga S.A probabilistic background model for tracking[Z].ECCV,Dublin Ireland,2000.
[123]Ridder A,Munkelt O,Kirchner H.A daptive Kalman-filtering[Z].ICRAM' 95,Istanbul,1995.
[124]Weng J.Image match ing using the windowed Fourier hase[J].Int J Computer Vision,1993,11(3):211-236.
[125]Fleet D,Jepson A.Stability of phase information[J].IEEE Trans PAMI,1993,15(12):1253-1268.
[126]Geman Stuart,Geman Donald.Stochastic relaxation,gibbs distributions,and the Bayesian restoration of images[J].IEEE Transactions on Pattern Analysis and Machine Intelligenc PAMI,1984,6:721-741
[127]王勇,吴立德.图像恢复和边缘提取的后验均值方法[J].电子学报,1994,22(2):70-76.
[128]Woontack Woo,Antonio Ortega.Stereo image compression with disparity compensation using the MRF model[A].Proc.SPIE VCIP[C].Orlando,FL;SPIE,1996,28-41.
[129]安平,张兆扬.基于立体摄像几何特性的视差匹配快速算法[J].上海大学学报,2000,6(5):399-403.
[130]李峰.关于立体匹配技术的研究[D].上海:上海交通大学,1999,6:1-5.
[131]Ahmed Y A,et al.New stereo matching algorithm[A].SPIE 3639[C].San Jose,California,1999.170-177.
[132]Redert A,et al.Correspondence estimation in image pairs[J].IEEE Signal Processing Magazine,1999,16(3):47-54.
[133]Qin J,Hayes M H.Stereo image coding[A].A projection approach,SPIE 3309[C].San Jose CA:1998.894-901.
[134]Sethuraman S,et al.A Multiresolution region based segmentation scheme for stereoscopic image sequence compression[A].Proc SPIE EI-Digital Video Compression:Algorithms and Technologies[C].1995.2419(2):265-274.
[135]LIN C W,et al.Hierarchical disparity estimation using spatial correlation[J].IEEE Trans on Consumer Electronics,1998,44(3):630-637.
[136]Su J K,Mersereau R i.Non-iterative rate-constrained motion estimation for OBMC[A].Proc IEEE ICIP[C].1997.33-36.
[137]Orchard M,SULLIVAN G.Overlapped block motion compensation:an estimation-theoretic approach[J].IEEE Trans on IP,1994,5(3):693-699.
[138]Marr D,Poggio T,Cooperative Computation of Stereo Disparity[J].Science,1976,194(4):209-236.
[139]Orchard M,SULLIVAN G.Overlapped block motion compensation:an estimation-theoretic approach[J].IEEE Trans on IP,1994,5(3):693-699.
[140]陈君,戚飞虎.一种新的基于特征点的立体匹配算法[J].中国图像图形学报,2005.10(11):1411-1414.
[141]Burr P,Julesz B.A Gradient Limit for Binocular Fusion[J].Science,1980,208(9):615-617.
[142]Pollard S,Porrill J,Mayhew J,et al.Disparity Gradient,Lipschitz Continuity,and Computing Binocular Correspondence[C].The Third International Symposium.Massachusetts:MIT Press,1986:19-26.
[143]Zhang Z,Shan Y,A Progressive Scheme for Stereo Matching[C],Springer LNCS 2018:3D Structure from Images-SMILE 2000.Berlin:Springer Yerlag,2001:68-85.
[144]Candes E J,Donoho D L.Curvelet A surprisingly ective nonadaptive representation for objects with edges,in Curve and Surface Fitting:SaintMalo[C]A.Cohen,C.Rabut,and L.L.Schumaker,Eds.Nashville,TN:Van2derbilt Univ.Press,1999
[145]Besag J.Spatial Interactions and the Statistical Analysis of Lattice Systems.Journal ofthe Royal Statistical Society(Series B),1974。 36(2):192-236
[146]刘伟强.陈鸿,夏德深.基于马尔可夫随机场的快速图像分割.中国图像图形 学报,.2001,6(3):228 233
[147]Geman S,Geman D.Stochastic Relaxation,Gibbs Distributions,and the Bayesian Restoration of Images.IEEE Trans on Pattern Analysis and Machine Intelligence,1984,6(6):721-741
[148]Bouman C,Sauer K.A Generalized Gaussian Image Model for Edge Preserving MAP Estimation.IEEE Trans on Image Processing,1993,2(3):296-310
[149]Derin H.Elliott H.Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields.IEEE Trans on Pattem Analysis and Machine Intelligence,1987,9(1):3955
[150]EI Baz A,Farag A A.Parameter Estimation in Gibbs-Markov Image Models.In z Proe of the 6th International Conference on Information Fusion.Queensland,Australia,2003,934-942
[151]Moiler J.Aspects of Spatial Statistics Stochastic Geometry and Markov Chain Monte Carlo Methods.Ph.D Dissertation.Faculty of Engineering and Science,Aalborg University,Aalborg,Denmark.1998
[152]Deseombes X,Morris R,Zerubia J,Berthod M.Estimation of Markov Random Field Prior Parameters Using Markov Chain Monte Carlo Maximum likelihood.IEEE Trans on Image Processing,1999,8(7):954-963
[153]章毓晋.图像分割[M].北京:科学出版社,2001.9-19.
[154]黄宁,朱慧敏,张守融.一种采用高斯隐马尔可夫随机场模型的遥感图像分类算法[J].电子信息学报.2003,1(25):50-53.
[155]Wang Z,Boy ik AC,SIMONCELLIEP.Structural approaches toimage quality assessment[A].Handbook of Image and Video Processing(A1 Bovik,eds.)[C],second edition,Academic Press,May 2005.
[156]邱茂林,马颂德,李毅.计算机视觉中摄象机定标[J].综述自动化学报.2000,26(1):43—45.[157]吴剑,王广志,丁海曙,骆文博.三维测量系统中线性CCD相机的直接线性变换[J].清华大学学报(自然科学版).2004.[158]Weng J,Cohen P,Herniou M.Camera calibration with distortion models and accuracy evaluation.IEEE Trans.PAMI.1992,14(10):965-980.[159]Martins H A,Birk J R,Kelley R B.Camera models based on data from two calibration planes[J].Computer Graphics Image Processing.1981.17(2):173-180.[160]Tikhonov A N,Arsenin V Y,Solutions of Ill-Posed Problems[J].John Wiley Sons,Washington,D.C.,1977.
[161]Perona P,Malik J,Scale space and edge detection using anisotropic diffusion[J].IEEE Trans.Pattern Anal.Intell.1990 12,629-639.
[162]Geman D,Reynolds G,Constrained restoration and the recovery of discontinuities[J].IEEE Trans.Pattern Anal.Mach.Intell.1992,14,367-383.
[163]Rudin L I,Osher S,Fatemi E,Nonlinear total variation based noise removal algorithms[D].Physica D,1992 60,259-268.
[164]Charbonnier P,Blanc_Feraud L,Aubert G,Barlaud M,Two deterministic half-quadratic regularization algorithms for computed imaging[J].Proc.IEEE Int.Conf.Image Processing(ICIP_94,Austin,1994(2),13-16),IEEE Computer Society Press,Los Alamitos,168-172.
[165]Nagel H H,Enkelmann W,An investigation of smoothness constraints for the estimation of displacement vector fields from images sequences[J].IEEE Trans.Pattern Anal Intell.1986 8,565-593.
[166]Alvarez L,Deriche R,S'anchez J,and Weickert J.Dense disparity map estimation respecting image derivatives:a PDE and scale-space based approach[J].Journal of Visual Communication and Image Representation,2002,13(1/2):3-21.
[167]Perona P,Malik J.Scale-space and edge detection using anisotropic diffusion[J].IEEETrans.PatternAnal.MachineIntell,1990,12(7):629-639
[168]杜啸晓,施鹏飞,杨新,严京旗.一种改进的偏微分方程图像平滑方法.上海交通大学学报2001,35(2):201-204.
[169]Anderson GL,Netravali AN.Image restoration based on a subjective riterion[J].IEEE Trans.Syst,Man,Cybern,SMC,1976,6(12).
[170]HORN B,SCHUNCK B.Determining optical flow[J].Artificial Intelligence,1981,17(4):1852203.
[171]Nagel H H,En Kelmann W.An investigation of smoothness constraint s for the estimation of displacement vector fields from image sequences[J]IEEE Trans on Pattern Analysis and Machine Intelligence,1986,8(5):5652593.
[172]En Kelmann W.investigations of multigrid algorithms for the estimation of optical flow fields in image sequences[J].Comp.Vis.Graph Image Proc.1988,43:1502177.
[173]Fogel S V.Estimation of velocity vector fields from Time-varying image sequences[J].CVGIP:Image Understanding,1991,53:2532287.
[174]Nagel H H.Constrains for the estimation of displacement vector fields from image sequences[AS.In:Proceeding IJCAI' 283[C],Karlsruhe,Germany,1983:945-951.
[175]Tretiak O,Pastor L.Velocity estimation from image sequences with second order differential operators[A].In:Proceedings Internation Conference on Pattern Recognition[C].Montreal,Canada,1984:16-19.
[176]Otte M,Nagel H H.Estimation of optical flow based on higher order spatio temporal derivatives in interlaced and non-interlaced image sequences[J].Artificial Intelligence,1995,78(2):5-43.
[177]Wohn K,Divis L S,Thrift P.Motion estimation based on multiple local constraints and nonlinear smoothing[J].Pattern Recognition,1983,16(6):563-570.
[178]Terzopoulos D.Regularization of inverse visual problems involving discontinuities[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1986,8(4):413-424.
[179]傅洁,吴立德.计算机视觉中运动分析的连续处理方法综述[J].模式识别与人工智能,1991,4(1):91-100.
[180]Seferidis V.General approach to block matching motion estimation[J].Optical Engineering,1993,32(1):79-91.
[181]Tekalp A M.Digital video processing[M].New Jersey:Prentice-Hall inc,1996.
[182]Marzani E,Legrand L,Dusserre L.Fourier adaptive smoothness constraint for computing optical flow on sequences of angiographic images[A].In:Proceedings of the IEEE Symposium on Computer Based Medical Systems[C].Los Alamito s:1996:53-58.
[183]Convertino G,Stella E,Branca A et al.Optic flow estimation by a Hopfield neural network using geometrical constraints[J].Pattern Recognition,1997,10(3):114-122
[184]Papenberg N.Bruhn A.Brox T.Didas S and Weickert J.Highly accurate optic flow computation with theoretically justified warping[J].International Journal of Computer Vision 67(2),141 - 158,2006
[185]Brox T.Bruhn A.Papenberg N.And Weickert J.2004.High accuracy optic flow estimation based on a theory for warping[C].In T.Pajdla and J.Matas,editors,Computer Vision - ECCV 2004,25- 36.
[186]Briggs W.L.Henson V.E.and McCormick S.F.2000.A Multigri Tutorial [B].2edition,SIAM,Philadelphia.
[187]Boykov Y,Veksler O,Zabih R.Fast approximate energy minimization via graph cuts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(11):1222-1239.
[188]Veksler O.Stereo cOrreo pOndence by dynamic programming on a tree[A].In:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],San Diego,CA,USA,2005:384-390
[189]Kolmogorov V,Zabih R.Multi-camera scene reconstruction via graph cuts[A].In:Proceedings of Seventh European Conference on Computer Vision[C],Copenhagen,Denmark,2002:82-96.
[190]Kolmogorov V,Zabih R.Computing visual cOrre。 pOndence with occlusions using graph cuts[A].In:Proceedings of International Conference on Computer Vision[C],Vancouver,Canada,2001:508-515.
[191]Gong M L,Yang Y H.Near real-time reliable stereo matching using programmable graphics hardware[A].In:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],SanDiego,CA,USA,2005:924-931.
[192]钱刚,曾贵华.典型视频镜头分割方法的比较.计算机工程与应用.2004(32):51-55
[193]张庆利,张兆扬.一种基于运动背景的视频对象分割算法.上海大学学报.2005,11(2):111-115
[194]何斌等.Visual C++数字图像处理.第2版.北京:人民邮电出版社,2002
[195]Chai Douglas,Ngan King N.Locating facial region of a head-and-shouders color image[C].Proe 3rd IEEE International Conference on Automatic Face and Gesture Recognition.1998,124-129
[196]韩锦成,施鹏飞,莫玉龙.基于差值图像及子波变换的人脸检测方法.上海交通大学学报.1999,33(11):1381-1385
[197]周小高等.基于差值图像及肤色特征的人脸定位方法.上海大学学报.2003,9(1):5-8
[198]安平,张兆扬.立体图像分层交叠块视差估计与自适应补偿[J].通信学报,2003,24(3):1-7.
[2] Ichikawa Y., Okada K., Jeong G., Tanaka S, Matushita, Y.MAJIC "Videoeonferencing System: Experiments, Evaluation and Improvement"[J]. ECSCW'95,1995.
[3] Jefferson H ,Brian S. CU-SeeMe VR Immersive Desktop Teleconferencing [J], ACM Multimedia 1996
[4] Gonzalez, D, Arns, L. AG virtual reality. Presented at the Access Grid~(TM)[J]. San Francisco, 2005.
[5] Regenbrecht H, Ott C, Wagner M, Lum T, Kohler P, Wilke W, Mueller E, An Augmented Virtuality Approach to 3D Videoconferencing[C]. Proceedings of the Second IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR '03) 2003.
[6] Billinghurst M, Bowskill J, Jessop M, Morphett J. Real World Teleconferencing[J]. Proceedings ofISWC'98, IEEE Press, pp. 76-83
[7] Prince S,. Cheok AD, Farbiz F, Williamson T, Johnson N, Billinghurst M, Kato H. Real-Time 3D Interaction for Augmented and Virtual Reality[J]. SIGGRAPH'02 Sketches
[8] Ishii H, Kobayashi M, Arita K. ClearBoard: A Seamless Medium for Shared Drawing and Conversation with Eye Contact[J]. Communications of the ACM, Vol. 37, No.8, August 1994, 83-97
[9] Fumio K, Tsutomu M, Nobuyoshi T.Virtual Space Teleconferencing "Communication with Realistic Sensations"[J]. IEEE International Workshop on Robot and Human Communication 0-7803-2904-x/95 1995.
[10] Christian P, Kunz M.Construction of a Three-sided Immersive Telecollaboration System VR[R]. 2003,. 37-44.
[11] Simon J. Gibbs C A, Christian J. TELEPORT - Towards immersive copresence [J]. Multimedia Systems 1999, 7(3): 214-221.
[12] Stefan A, Alex W, Michael B. Reflection of Presence: Toward More Natural and Responsive Telecollaboration[J]. Proc. SPIE Multimedia Networks, 3228A, 1997.
[13] Kensaku H, Kentaro F, Hiroshi S, Kenichi O. e-MulCS : Multi-Party Conference System with Virtual Space and the Intuitive Input Interface [C]. the International Symposium on Applications and the(SAINT'04)2004
[14]Bruce C,Thomas M.The Coliseum Immersive Teleconferencing System[J].Published in and presented at the International Workshop on Immersive Telepresence,Juan Les Pins,France,6 2002
[15]Wen Lin,Yao-Jen Chang,Chi-MingWang,Yung-Chang Chen,Ming-Ting Sun.A Standard-Compliant Virtual Meeting System with Active Video Object Tracking[J].EURASIP Journal on Applied Signal Processing:2002,6,622-634.
[16]Kauff P,Schreer O.An immersive 3-D video-conferencing system using shared virtual team user environments[J].ACM Conf.Collaborative Virtual Environments,2002.
[17]Gemmell J,Zitnick C.L.,Kang T,Toyama K.,Seitz S.Gaze-awareness for Videoconferencing:A Software Approach[J].IEEE Multimedia,2000,7(4):26-35.
[18]Chris G,Steve B.Virtual Reality Tele-conferencing:Implementation and Experience[C]..Fourth European Conference on Computer Supported Cooperative Work(ECSCW'95),1995.
[19]Mortlock A N,Machin D,McConnell S,Sheppard P J.Virtual Conferencing[J].Telepresence,Kluwer Academic Publishers,Boston,1999,.209-225.
[20]Xin Wang,X-Conference:Reinventing a Teleconferencing System[J].Program in Media Arts and Sciences 2002
[21]H.Towles,W.-C Chen,R.Yang,S.-U Kum,H.Fuchs,N.Kelshikar,J.Mulligan,K.Daniilidis,L.Bolden,B.Zelesnik,A.Sadagic,and J.Lanier,3-D tele-collaboration over internet2[J],in Proc.Int.Workshop Immersive Telepresence,Juan-les-Pins,France,Dec.6,2002
[22]Chen W.C.Toward a compelling sensation of telepresence:Demonstrating a portal to a distant(static)office[C],in Proc.IEEE Conf.Visualization,Salt Lake City,UT,Oct.8-13,2000,.377-383.
[23]Jane M,Xenophon Z,Nikhil K,Kostas D.Stereo-Based Environment Scanning for Immersive Telepresence[J].IEEE Transactions on Circuits And Systems For Video Technology.2004,14(3).
[24]Celso S K,Ruigang Y,Anselmo L.Combining Approximate Geometry with View-Dependent Texture Mapping-A Hybrid Approach to 3D Video Teleconferencing[C].Proceedings of the XV Brazilian Symposium on Computer Graphics and Image Processing,2002.
[25]Hom B K P.Shape from Shading:A Method for Obtaining the Shape of a SmoothOpaque Object from one View[D].PhD thesis, MIT, 1970.
[26] Lkeuehi I K Horn B.K.P. .Numerical shape from shading and occluding boundaries[J]. Arti_cial Intelligence, 1981,17(3): 141 -184.
[27] Pentland A P. Local shading analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1984,6: 170-187
[28] Lee C.H, Rosenfeld A. Improved methods of estimating shape from shading using the light source coordinate system[J]. Arti_cial Intelligenee.1985.26:125-143.
[29] Tsai P S, Shah M.Shape from shading using linear approximation[J]. Image and Vision Computing Journal.1994,12(8):487-498.
[30] Akimoto T, Suenaga Y, Wallace R S. Automatic 3d facial models[J]. IEEE Computer Graphics and Applications, 1993.13(5): 16-22.
[31] Lee A W E, Sweldens W, Sehroder P, Cowsar L , Dobkin D. Maps:Multiresolution adaptive Parameterization of sufaces[J]. Proe.of SIGGRAPH'98,1998,95-104.
[32] Parke F I. Computer generated animation of faces[C]. In ACM National Conferenee,1972.
[33] Van Beek P J L,.Reinders M J T, Sankur B, Van Der Lubbe J C.A.Semantic segmentation of videophone image sequenees[C].in Proe.of SPIE Int.Conf. on Visual Communieations and Image processing, 1992,1182-1193.
[34] Ip H.S, Yin L.Constructing a 3d individualized head model from two orthogonal views[J]. The Visual Computer. 1996. (12):254-266.
[35]. Zheng J Y. Acquiring 3-d models from sequences of contours [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1994.16(2): 163-178.
[36] Liu Z, Zhang Z, Jacobs C, Cohen M. Rapid Modeling of Animated Faces From Video. Technical Report[R]. Microsoft Research. 2000,9-21
[37] Laurentini A. The visual hull concept for silhouette based image understanding[J]. IEEE PAMI. 1994.16(2): 150-162.
[38] Lee Y, Terzopoulos D, Waters K. Realistic modeling for facial animation[C]. In: SIGGRAPH Conference Proceedings, Los Angeles, USA, 1995, 55-62
[39] Martin W N, Aggarwal J K. Volumetric descriptions of objects from multiple views [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1983,5(2):150-158.
[40] Frisken S, Perly R, Rockwood A. Adaptively sampled distance fields:a general representation of shape for computer. In:Akeley K.ed.Proceedings of the SIGGRAPH 2000.NewYork:ACM Press, 2000.249-254.
[41]Peny R,Frisken S.Kizamu:A system for sculpting digital characters[R]In:Fiume,E.ed.Proeeedings of the SIGGRAPH2001 NewYork:ACM Press,2001.47-56.
[42]Matusik W,Buehler C,MeMillan L.Polyhedral visual hulls for real-time rendering[C].In:Myskowski K.,Gortler S,eds.Proceedings of the 12~(th)EurograPhics Workshop on Rendering.Wien:Springer-Verlag,2001.115-125.
[43]Blanz V,Vetter T.A morphable model for the synthesis of 3d faces.InComputer GraPhies[C].Annual Conference Series,SIGGRAPH99proeeedings,187-194
[44]Fua P,Miccio C..From regular images to animated heads:A least squares approach.In European conference on Computer Vision.1995,188-202.
[45]Fua P,Miccio C.Animated heads from ordinary images:A least-squares approach.Computer Vision and Image Understanding.1999,75(3):247-259.
[46]Fua P,Plaenkers R,Thalmann D..From synthesis to analysis:Fitting human animation models to image data.In Computer Graphics International,Albeta.Canada,1999.
[47]Zi cheng Liu,Ying Shan,Zheng you Zhang:Expressive expression mapping with ratio images[C].In siggraph'01 Conference Proceedings.271-276.
[48]Nagel.H Constraints for the estimation of displacement vector fields from image sequences[C].Proc.Eighth Int.Joint Conf.on Artificial Intelligence(IJCAI '83.Karlsruhe,August 1983,945-951.
[49]Chai Douglas,Ngan King N.Locating facial region of a head-and-shouders color image[C].Proc 3rd IEEE International Conference on Automatic Face and Gesture Recognition.1998,124-129.
[50]韩锦成,施鹏飞,莫玉龙.基于差值图像及子波变换的人脸检测方法.上海交通大学学报.1999,33(11):1381-1385.
[51]Agarwala A,Hertzmann A,Seitz S,et al,Keyframe-based tracking for rotoscoping and animation[C],Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,Los Angeles.2004:584-591.
[52]Chuang Y Y,Agarwala A,Curless B,et al.Video matting of complex scenes[C].Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,San Antonio,Texas.2002:243-248.
[53]Chuang Y Y.New models and methods for matting and compositing[D].Seattle:University of Washington,2004.
[54]Black M J,Anandan P.The robust estimation of multiple motions:parametric and piecewise-smooth flow fields[J].Computer Vision and Image Understanding,1996,63(1):75-104.
[55]ApostoloffN,Fitzgibbon A W.Bayesian video matting using learnt image priors[C].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,Washington D C.2004,407-414.
[56]McGurie M,Matusik W,Pfister H.Defocus video matting[C].Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,Los Angeles,2005:567-576
[57]Wang J,Bhat P,Colbum A.Interactive video cutout[C].Computer Graphics Proceedings.Annual Conference Series,ACM SIGGRAPH,Los Angeles.2005.585-594.
[58]Li Y,Sun J,Shum H Y.Video object cut and paste[C].Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH,Los Angeles.2005.595 -600.
[59]隋婧,金伟其.双目立体视觉技术的实现及其进展.电子技术应用.2004,(10):4-6
[60]骆艳,张兆扬.一种基于立体视邻接帧时空相关性的最小代价函数帧估计算法.电子学报.2003,31(10):1513-1517.
[61]贾云得.机器视觉[M].北京:科学出版社,2001.
[62]Scharstein D,Szeliski R.A taxonimy and evaluation of dense two-frame stereo correspondence algorithms[J].IJCV,2002,47(1/2/3):7-42.
[63]陈棣湘,罗飞路,潘孟春.立体视觉测量中的图像匹配策略的研究[J].光学技术,2002,5:392-394.
[64]Kuijper A,I.M.J Florack.on the creations of critical points in scale space with applications to modical image analysis[J].UU-CS,2001,25:316-319.
[65]Moravec H P.Towards automatic visual obstacle avoidance[A].Proc.5th Int.Joint Conf.Aritifical Intell[C].Cambridge,MA,1977.
[66]Raymond Van Ee,Cliftom M Schor Unconstrainted stereoscopic matching of lines [J].Vision Research,2000.40:151-162.
[67]Lcaiza H,Triboulet J,Lelandais S,et al.Matching segments in stereoscopic vision [J].IEEE Instrumentation & Measurement.2001,03:37 - 42.
[68]Supa B J,Kiariquist W N.Patch- based stereo in general binocular viewing[J].Theory and Experiment,PAMI,1997,(19)3:247-252.
[69]Prince S J D.Eagle R D.Weighted directed energy model for human stereo correspondence[J].Vision Research,2000,40:151-162.
[70]Kisworo M,Venkatesh S.West modeling edges at subpixel accuracy using local energy approach[J].Theory and Experment,PAMI,1994,16(4):405-410
[71]He C,Dong J Y,Zheng Y F,et al.Object tracking using Gabor wavelet transform and the golden section algorithm[R].2002.
[72]Maitre H,etal.Using models to improve stereo reconstruction[J].IEEE Trans.on PAMI,1992,149(2):269-277.
[73]Jenkin M,etal,The measurement of binocular disparity in computational process in human vision[M].Ablex.NewJersey:Prentice -Hall,1988.
[74]Robson J G,Receptive fields:neural espresentation of the spatialand intensive attributes of the visual images[Z].Handbook of Preception,NewYork:Academic press,1985,5:81-116.
[75]Terzopoulos D.The computer of visible - surface representations[J].IEEE Trans.on PAMI,1988,10(40):417-438.
[76]Ohta Y,et al.Stereo by two - level dynamic programming[A].Proc.of 9th IJCAI [C].1985:1120-1124.
[77]Julesz T B.Stereoscopic vision[C].Vision Res.1986,26:1601-1612.
[78]Sanger T D.Stereo disparity computation using gabor filter[D].Nethedand:Delft University of Technology,1988.
[79]游素亚,柳健,万发贯.基于小波变换相位的立体匹配系统[J].信息与控制,1994,(5):28-31.
[80]贾波.视差图误差检测与校正的通用算法[J].清华大学学报,2000,40(1):28-31.
[81]Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window,theory and experiment[J].Proc IEEE PAMI,1994,16(9):920 -932.
[82]徐颜军,杜利民,候自强.基于相位的尺度自适应立体匹配方法[J].电子学报,1999.27:38-41.
[83]Scharstein D,Szeliski R.A texonomy and evaluation of dense two-frame stereo correspondence algorithms[J].IJCV,2002:47(1/2/3):551-554.
[84]Mumford David.M athematic theo ries of shape:Do they model percep tion[J].In:Proc.Geometric Methods in Computer Vision,SPIE,1991.1570:2-10
[85]Grimson W Eric,Huttenlcher Daniel P.On the sensitivity of Hough transform for object recognition[J].IEEE Trans.PAMI,1990,12(3):255- 274
[86]Derek CW Pao,Hon F L i,Jayakumar R.Shape recognition using the straight line Hough transform: Theory and generalization[J]. IEEE Trans. PAM I, 1992,14 (11): 1076-1089
[87] Gorman J W , Mirchell O R, Kuhl F P. Partial shape recognition using dynamic programming[J]. IEEE Trans. PAMI, 1988,10 (2): 257-266
[88] McConnell Ross, Kwok Ronald, Curlander John C, Kober W, Pang Shirley S. ψ -s correlation and dynamic time warping: Two methods for tracking ice floes in sar image[J]. IEEE Trans. Geoscience and Remote Sensing ,1991,29(6): 1004-1012
[89] Wolfson Haim J. On curve matching[J]. IEEE Trans. PAM I,1990,12(5): 483-489
[90] Ansari N, Delp E J. On the distribution of a deforming triangle[J]. Pattern Recognition, 1990,23 (12): 1333-1341
[91] Lamdan Y, Schwarz J T, Wolfson H J. Affine invariant model-based object recognition[J]. IEEE Trans. Robotics Automn, 1990, 6 (5): 578-589
[92] Jain A K, Zhong Y, Lak shmanan S. Objectmatching using deformable templates[J]. IEEE Trans. PAMI, 1996,18(3): 267-278
[93] Sclaroff Stan. Deformable prototypes for encoding shape categories in image database[J]. Pattern Recog nition, 1997,30 (4): 627-641
[94] Del Bimbo Alberto, Pala Pietro. Visual image retrieval by elesticmatching of user sketchs[J]. IE E E Trans. PAMI ,1997,19 (2) : 121-132.
[95] Wang Yong-Mei. Boundary finding with correspondence using statistical shape models[J]. In: Proc. IEEE CVPR,1998.338-345.
[96] Lai K, Chin R. Deformable Contours: Modeling and extraction[J].IEEE Trans. PAMI, 1995,17 (11): 1084-1090
[97] Ding Xian-Feng, Kong Wei-Xing, Lu Han-Qing, Ma Song-De. Genetic algorithm for partial shape recognition[J]. Beijing Mathmatics, 1998,4 (2): 182-188
[98] Yang Q , Ma S-D. Shape matching using Schwarz representation[J]. Pattern Recognition, 1999,32(6): 1039-1047
[99] EI Ansari M,Masmoudi L,Radouane L.A new region matching method for stereoscopic images[J].Pattern Recognition Letters, 2000,21(4):283-294.
[100] Vinet L, Gagalowicz Al. Region matching using neighborhood consistency[C]. In: Proceedings of the 8th Congress of Form Recognition and Artificial Intelligence, Lyon Villeurbanne, 1991, 2:821-826.
[101] Zagrouba E , Krey C. Region matching by adjacency propagation in stereo vision [C]. In : Proceedings of the 2nd International Conference on Automation, Robotics and Computer Vision, Hyatt Regency, Singapore, 1992.851-855.
[102]夏永泉,刘正东,杨静宇.不变矩方法在区域匹配中的应用[J].计算机辅助设与图形学学报,2005,17(10):2152-2156.
[103]S B Pollard,J E W Mayhew,and J P Frisby.A stereo correspondence algorithm using a disparity gradient limit[J].Perception,1985,14:449-470.
[104]Hu MK.Pattern recognition by moment invariants[C].Proc.IRE,1961;49(9):14-28.
[105]Teague MR.Image analysis via the general theory of moments[3].Opt.Soc.Amer,1980;70(8):920-930.
[106]Boyce JF,Hossack WJ.Moment invariants for pattern recognition[J].Pattern Recognition Lett.1983;1(5-6):451-455.
[107]Abu-Mostafa YS,Psaltis D.Recognitive aspects of moment invariants[J].IEEE Trans.Pattern Anal.Machine Intell,1984;PAMI - 6(11):698-706.
[108]Yoshida Y,Wu Y.Classification of rotated and scaled texture images using invariants based on spectral moments[J]IEICE Trans.Fundamentals,1998;E81A (8):1661-1666.
[109]Shen DG;Horace HS.Discriminative wavelet shape descriptors for recognition of Depattems[J].Pattern recognition,1999;32:151-165.
[110]Yang Z,Cohen F.Cross - weighted moments and affine invariants for image registration and matching[3].IEEE Trans.PAMI,1999;21(8):804-814.
[111]Wong RY.Scene matching with invariant moments[J].Computer Graphics and Image Processing,1978;8(1):16-24.
[112]Wang WH,Chen YC.Histogram matching by moment normalization[J].IEICE Trans.Inf.&Syst,1997;E80 - D(7):746-750.
[113]Dudani AS,Breeding KJ,Mcghee RB.Aircraft identification by moment invafiants[J].IEEE Transactions on Computers,1977;26(1):39-46.
[114]Mertzios BG,Tsirikolias K.Statistical shape discrimination and clustering using an efficient set of moments[J].Pattem Recognition Letters,1993;14:517 - 522.
[115]Trier OD,Jain AK,Taxt T.Feature extraction methods for character ecognition a survey[J].Pattern Recognition,1996;29(4):641- 662.
[116]Chim YC,Kassim AA,Ibrahim Y.Character recognition using statistical moments[J].Image and Vision Computing,1999;17:299-307.
[117]Sluzek A.Identification and inspection of 2 - D objects using new moment-based shape descriptors[J].Pattern Recognition Letters,1995;16:687-697.
[118]Mandal MK,Aboulnasr T,Panehanathan S.Image indexing using moments and wavelets[J].IEEE Trans.on Consumer Electronics,1996;42(3):557- 565
[119]Kim YS,Kim WY.Content - based trademark retrieval system using a visually salient feature[J].Image and Vision Computing,1998;16:931-939
[120]Teague M.Image analysis via the general theory of moments[J].Opt Soc Amer,1980,70(8):920-930.
[121]Yuan Y.Tang,Bing F.Li,nong Ma,and JimingLiu.Ring-projection-wavelet -fractal signatures:a novel approach to feature exraction[J].IEEE transactions on circuits and systems-Ⅱ:1998,45(8):1130-1134.
[122]Rittscher C,Kato J,Joga S.A probabilistic background model for tracking[Z].ECCV,Dublin Ireland,2000.
[123]Ridder A,Munkelt O,Kirchner H.A daptive Kalman-filtering[Z].ICRAM' 95,Istanbul,1995.
[124]Weng J.Image match ing using the windowed Fourier hase[J].Int J Computer Vision,1993,11(3):211-236.
[125]Fleet D,Jepson A.Stability of phase information[J].IEEE Trans PAMI,1993,15(12):1253-1268.
[126]Geman Stuart,Geman Donald.Stochastic relaxation,gibbs distributions,and the Bayesian restoration of images[J].IEEE Transactions on Pattern Analysis and Machine Intelligenc PAMI,1984,6:721-741
[127]王勇,吴立德.图像恢复和边缘提取的后验均值方法[J].电子学报,1994,22(2):70-76.
[128]Woontack Woo,Antonio Ortega.Stereo image compression with disparity compensation using the MRF model[A].Proc.SPIE VCIP[C].Orlando,FL;SPIE,1996,28-41.
[129]安平,张兆扬.基于立体摄像几何特性的视差匹配快速算法[J].上海大学学报,2000,6(5):399-403.
[130]李峰.关于立体匹配技术的研究[D].上海:上海交通大学,1999,6:1-5.
[131]Ahmed Y A,et al.New stereo matching algorithm[A].SPIE 3639[C].San Jose,California,1999.170-177.
[132]Redert A,et al.Correspondence estimation in image pairs[J].IEEE Signal Processing Magazine,1999,16(3):47-54.
[133]Qin J,Hayes M H.Stereo image coding[A].A projection approach,SPIE 3309[C].San Jose CA:1998.894-901.
[134]Sethuraman S,et al.A Multiresolution region based segmentation scheme for stereoscopic image sequence compression[A].Proc SPIE EI-Digital Video Compression:Algorithms and Technologies[C].1995.2419(2):265-274.
[135]LIN C W,et al.Hierarchical disparity estimation using spatial correlation[J].IEEE Trans on Consumer Electronics,1998,44(3):630-637.
[136]Su J K,Mersereau R i.Non-iterative rate-constrained motion estimation for OBMC[A].Proc IEEE ICIP[C].1997.33-36.
[137]Orchard M,SULLIVAN G.Overlapped block motion compensation:an estimation-theoretic approach[J].IEEE Trans on IP,1994,5(3):693-699.
[138]Marr D,Poggio T,Cooperative Computation of Stereo Disparity[J].Science,1976,194(4):209-236.
[139]Orchard M,SULLIVAN G.Overlapped block motion compensation:an estimation-theoretic approach[J].IEEE Trans on IP,1994,5(3):693-699.
[140]陈君,戚飞虎.一种新的基于特征点的立体匹配算法[J].中国图像图形学报,2005.10(11):1411-1414.
[141]Burr P,Julesz B.A Gradient Limit for Binocular Fusion[J].Science,1980,208(9):615-617.
[142]Pollard S,Porrill J,Mayhew J,et al.Disparity Gradient,Lipschitz Continuity,and Computing Binocular Correspondence[C].The Third International Symposium.Massachusetts:MIT Press,1986:19-26.
[143]Zhang Z,Shan Y,A Progressive Scheme for Stereo Matching[C],Springer LNCS 2018:3D Structure from Images-SMILE 2000.Berlin:Springer Yerlag,2001:68-85.
[144]Candes E J,Donoho D L.Curvelet A surprisingly ective nonadaptive representation for objects with edges,in Curve and Surface Fitting:SaintMalo[C]A.Cohen,C.Rabut,and L.L.Schumaker,Eds.Nashville,TN:Van2derbilt Univ.Press,1999
[145]Besag J.Spatial Interactions and the Statistical Analysis of Lattice Systems.Journal ofthe Royal Statistical Society(Series B),1974。 36(2):192-236
[146]刘伟强.陈鸿,夏德深.基于马尔可夫随机场的快速图像分割.中国图像图形 学报,.2001,6(3):228 233
[147]Geman S,Geman D.Stochastic Relaxation,Gibbs Distributions,and the Bayesian Restoration of Images.IEEE Trans on Pattern Analysis and Machine Intelligence,1984,6(6):721-741
[148]Bouman C,Sauer K.A Generalized Gaussian Image Model for Edge Preserving MAP Estimation.IEEE Trans on Image Processing,1993,2(3):296-310
[149]Derin H.Elliott H.Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields.IEEE Trans on Pattem Analysis and Machine Intelligence,1987,9(1):3955
[150]EI Baz A,Farag A A.Parameter Estimation in Gibbs-Markov Image Models.In z Proe of the 6th International Conference on Information Fusion.Queensland,Australia,2003,934-942
[151]Moiler J.Aspects of Spatial Statistics Stochastic Geometry and Markov Chain Monte Carlo Methods.Ph.D Dissertation.Faculty of Engineering and Science,Aalborg University,Aalborg,Denmark.1998
[152]Deseombes X,Morris R,Zerubia J,Berthod M.Estimation of Markov Random Field Prior Parameters Using Markov Chain Monte Carlo Maximum likelihood.IEEE Trans on Image Processing,1999,8(7):954-963
[153]章毓晋.图像分割[M].北京:科学出版社,2001.9-19.
[154]黄宁,朱慧敏,张守融.一种采用高斯隐马尔可夫随机场模型的遥感图像分类算法[J].电子信息学报.2003,1(25):50-53.
[155]Wang Z,Boy ik AC,SIMONCELLIEP.Structural approaches toimage quality assessment[A].Handbook of Image and Video Processing(A1 Bovik,eds.)[C],second edition,Academic Press,May 2005.
[156]邱茂林,马颂德,李毅.计算机视觉中摄象机定标[J].综述自动化学报.2000,26(1):43—45.[157]吴剑,王广志,丁海曙,骆文博.三维测量系统中线性CCD相机的直接线性变换[J].清华大学学报(自然科学版).2004.[158]Weng J,Cohen P,Herniou M.Camera calibration with distortion models and accuracy evaluation.IEEE Trans.PAMI.1992,14(10):965-980.[159]Martins H A,Birk J R,Kelley R B.Camera models based on data from two calibration planes[J].Computer Graphics Image Processing.1981.17(2):173-180.[160]Tikhonov A N,Arsenin V Y,Solutions of Ill-Posed Problems[J].John Wiley Sons,Washington,D.C.,1977.
[161]Perona P,Malik J,Scale space and edge detection using anisotropic diffusion[J].IEEE Trans.Pattern Anal.Intell.1990 12,629-639.
[162]Geman D,Reynolds G,Constrained restoration and the recovery of discontinuities[J].IEEE Trans.Pattern Anal.Mach.Intell.1992,14,367-383.
[163]Rudin L I,Osher S,Fatemi E,Nonlinear total variation based noise removal algorithms[D].Physica D,1992 60,259-268.
[164]Charbonnier P,Blanc_Feraud L,Aubert G,Barlaud M,Two deterministic half-quadratic regularization algorithms for computed imaging[J].Proc.IEEE Int.Conf.Image Processing(ICIP_94,Austin,1994(2),13-16),IEEE Computer Society Press,Los Alamitos,168-172.
[165]Nagel H H,Enkelmann W,An investigation of smoothness constraints for the estimation of displacement vector fields from images sequences[J].IEEE Trans.Pattern Anal Intell.1986 8,565-593.
[166]Alvarez L,Deriche R,S'anchez J,and Weickert J.Dense disparity map estimation respecting image derivatives:a PDE and scale-space based approach[J].Journal of Visual Communication and Image Representation,2002,13(1/2):3-21.
[167]Perona P,Malik J.Scale-space and edge detection using anisotropic diffusion[J].IEEETrans.PatternAnal.MachineIntell,1990,12(7):629-639
[168]杜啸晓,施鹏飞,杨新,严京旗.一种改进的偏微分方程图像平滑方法.上海交通大学学报2001,35(2):201-204.
[169]Anderson GL,Netravali AN.Image restoration based on a subjective riterion[J].IEEE Trans.Syst,Man,Cybern,SMC,1976,6(12).
[170]HORN B,SCHUNCK B.Determining optical flow[J].Artificial Intelligence,1981,17(4):1852203.
[171]Nagel H H,En Kelmann W.An investigation of smoothness constraint s for the estimation of displacement vector fields from image sequences[J]IEEE Trans on Pattern Analysis and Machine Intelligence,1986,8(5):5652593.
[172]En Kelmann W.investigations of multigrid algorithms for the estimation of optical flow fields in image sequences[J].Comp.Vis.Graph Image Proc.1988,43:1502177.
[173]Fogel S V.Estimation of velocity vector fields from Time-varying image sequences[J].CVGIP:Image Understanding,1991,53:2532287.
[174]Nagel H H.Constrains for the estimation of displacement vector fields from image sequences[AS.In:Proceeding IJCAI' 283[C],Karlsruhe,Germany,1983:945-951.
[175]Tretiak O,Pastor L.Velocity estimation from image sequences with second order differential operators[A].In:Proceedings Internation Conference on Pattern Recognition[C].Montreal,Canada,1984:16-19.
[176]Otte M,Nagel H H.Estimation of optical flow based on higher order spatio temporal derivatives in interlaced and non-interlaced image sequences[J].Artificial Intelligence,1995,78(2):5-43.
[177]Wohn K,Divis L S,Thrift P.Motion estimation based on multiple local constraints and nonlinear smoothing[J].Pattern Recognition,1983,16(6):563-570.
[178]Terzopoulos D.Regularization of inverse visual problems involving discontinuities[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1986,8(4):413-424.
[179]傅洁,吴立德.计算机视觉中运动分析的连续处理方法综述[J].模式识别与人工智能,1991,4(1):91-100.
[180]Seferidis V.General approach to block matching motion estimation[J].Optical Engineering,1993,32(1):79-91.
[181]Tekalp A M.Digital video processing[M].New Jersey:Prentice-Hall inc,1996.
[182]Marzani E,Legrand L,Dusserre L.Fourier adaptive smoothness constraint for computing optical flow on sequences of angiographic images[A].In:Proceedings of the IEEE Symposium on Computer Based Medical Systems[C].Los Alamito s:1996:53-58.
[183]Convertino G,Stella E,Branca A et al.Optic flow estimation by a Hopfield neural network using geometrical constraints[J].Pattern Recognition,1997,10(3):114-122
[184]Papenberg N.Bruhn A.Brox T.Didas S and Weickert J.Highly accurate optic flow computation with theoretically justified warping[J].International Journal of Computer Vision 67(2),141 - 158,2006
[185]Brox T.Bruhn A.Papenberg N.And Weickert J.2004.High accuracy optic flow estimation based on a theory for warping[C].In T.Pajdla and J.Matas,editors,Computer Vision - ECCV 2004,25- 36.
[186]Briggs W.L.Henson V.E.and McCormick S.F.2000.A Multigri Tutorial [B].2edition,SIAM,Philadelphia.
[187]Boykov Y,Veksler O,Zabih R.Fast approximate energy minimization via graph cuts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(11):1222-1239.
[188]Veksler O.Stereo cOrreo pOndence by dynamic programming on a tree[A].In:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],San Diego,CA,USA,2005:384-390
[189]Kolmogorov V,Zabih R.Multi-camera scene reconstruction via graph cuts[A].In:Proceedings of Seventh European Conference on Computer Vision[C],Copenhagen,Denmark,2002:82-96.
[190]Kolmogorov V,Zabih R.Computing visual cOrre。 pOndence with occlusions using graph cuts[A].In:Proceedings of International Conference on Computer Vision[C],Vancouver,Canada,2001:508-515.
[191]Gong M L,Yang Y H.Near real-time reliable stereo matching using programmable graphics hardware[A].In:Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C],SanDiego,CA,USA,2005:924-931.
[192]钱刚,曾贵华.典型视频镜头分割方法的比较.计算机工程与应用.2004(32):51-55
[193]张庆利,张兆扬.一种基于运动背景的视频对象分割算法.上海大学学报.2005,11(2):111-115
[194]何斌等.Visual C++数字图像处理.第2版.北京:人民邮电出版社,2002
[195]Chai Douglas,Ngan King N.Locating facial region of a head-and-shouders color image[C].Proe 3rd IEEE International Conference on Automatic Face and Gesture Recognition.1998,124-129
[196]韩锦成,施鹏飞,莫玉龙.基于差值图像及子波变换的人脸检测方法.上海交通大学学报.1999,33(11):1381-1385
[197]周小高等.基于差值图像及肤色特征的人脸定位方法.上海大学学报.2003,9(1):5-8
[198]安平,张兆扬.立体图像分层交叠块视差估计与自适应补偿[J].通信学报,2003,24(3):1-7.