前视目标图像匹配定位技术研究
|
摘要
前视图像匹配定位是一个具有挑战性的难题。由于图像中各点的深度变化很大,待定位两幅图像间的关系不能用简单的相似变换来表达,而是涉及到复杂的透视变换。同时考虑到两幅图像成像的视点未知,且成像时间不同,模板图像甚至是从下视图像生成的,损失了很多细节信息,场景图像与模板图像不会表现出完全相同的特征。
当目标的三维模型已知时,给出了三维点集和二维点集的匹配定位算法。利用目标的三维数据信息,手动选择特征点,从而建立起关于目标的三维特征点模型;在待定位的二维场景图像中,自动寻找特征点。根据计算机视觉成像原理,利用三维点到二维点的投影关系,可以计算出摄像机相对世界坐标系的平移和旋转参数。该算法可以同时得到目标三维点与场景二维点的变换参数和对应关系。
当目标的三维模型未知时,将目标及其周围的场景作为模板图像,给出了基于特征点相似度的匹配定位算法。首先分析了尺度变化和旋转变化对特征点的提取和描述带来的影响,然后在寻找特征点对应关系的过程中,定义了特征点匹配度量的准则,利用特征点相似度进行匹配,然后用极线约束去除错误的匹配点对,最后根据参数拟合的方式寻找图像间的变化参数并进行目标定位。实验表明该算法能够适应一定的尺度变化、旋转变化、部分遮挡,对于一定立体旋转角度变化具有一定的鲁棒性。
基于特征点相似度的匹配定位方法仅仅考虑了极线约束,对特征点间的位置信息的利用并不完全。为了保持特征点间的位置信息,分析了松弛标记算法的原理,将特征点的相似度信息融入到松弛过程中,提出了基于松弛标记与特征点相似度的匹配定位算法。该算法不仅利用了模板图像的局部信息,还保持了模板图像的结构信息,实验证明相对于仅利用极线约束的算法,该算法能够找到更多的匹配点对。
为了保持特征点间的位置信息,除了松弛标记算法以外,还可以应用信任度扩散算法。将特征点的相似度信息融入到消息传递过程中,提出了基于信任度扩散与特征点相似度的匹配定位算法。该算法在结合模板图像的局部信息的同时,还保持了模板图像的结构信息。实验表明相对于仅利用极线约束的算法,该算法能够找到更多的匹配点对。
前述算法都是先计算特征点的匹配对再进行目标定位,而前视图像匹配定位的特点是不需要准确地找到模板图像特征点与场景图像特征点之间的对应关系,仅仅关心场景图像中模板图像所在的位置、尺度大小和旋转角度。将特征点的匹配过程与目标定位过程融合到一起,提出了基于均值漂移与投票的匹配定位算法。利用特征点的尺度、朝向和描述向量,构成一个一对多的匹配集合。对每个可能的匹配对,计算场景中模板图像的位置、尺度变化因子和旋转角度,构成一个4维的投票密度图,则密度最大的地方就是最后的定位结果。实验表明该算法鲁棒性更强。
The forward-looking image matching and localization is one of challenging problems. For the depth of each point changes largely, the relationship of the template image and scene image can not be described by simple homography transformation but the complicated projective transformatioa The imaging viewpoint is unknown, the time may be different, and even the template image may be generated from the downward-looking image, so lots of information is lost.
When the 3d model of the object is known, the matching and localization algorithm is given for matching the 3d points in model and 2d points in image. The 3d points are maintained by hand, so the model of 3d points is formed. The 2d points are extracted automatically. Using the relationship of the projective transformation between 3d points and 2d points, the translation and the rotation angle can be computed. The algorithm can output the transformation parameters and the correspondence simultaneously.
When the 3d model of object is unknown, the template is described by the image around the object, and the image matching and localization algorithm based on the similarity of feature point is given. The procedures of extracting and describing the feature point are analyzed. The rule of determining the correspondence point is defined. The similarity of feature point is used to find correspondence points, and then the false correspondence points are eliminated through the epipolar constraint The transform parameters of images are computed and the localization of object is obtained. Experimental results show that the algorithm is robust in the case of scale factor, rotation angle, partial occlusion, and even 3d rotation angle change.
The above method only considers the epipolar constraint and does not make full of the location information of feature points. In order to maintain the location information of the feature points, the principle of relaxation labeling method is analyzed and the local invariant is incorporated into the relaxation procedure. The algorithm based on relaxation labeling method and the feature point similarity is proposed. Experimental results demonstrate that the algorithm can find more correspondence points relative to the methods based on the epipolar constraint
In order to maintain the location information of the feature points, the principle of belief propagation method is analyzed and the local invariant is incorporated into the message passing procedure. The algorithm based on belief propagation method and the feature point similarity is proposed. Experimental results demonstrate that the algorithm can find more correspondence points relative to the methods based on the epipolar constraint
The three above methods first determine the correspondence points and then locate the object, but the characteristic of forward-looking image matching and localization is mat it does not care the accurate correspondence points but the position, scale factor and rotation angle of the object in the scene image, the algorithm based on mean shift and vote is proposed. Using the position, orientation and the descriptor of feature point, the match set is formed in the way of one to many. For each match point, the position, scale factor and the rotation angle of the object in scene image can be computed, so the 4d vote space is formed. The densest point in the vote space is kept as the position, scale factor and rotation angle of the object Experimental results of the algorithm demonstrate both the robustness and efficacy of the overall approach on real images.
当目标的三维模型已知时,给出了三维点集和二维点集的匹配定位算法。利用目标的三维数据信息,手动选择特征点,从而建立起关于目标的三维特征点模型;在待定位的二维场景图像中,自动寻找特征点。根据计算机视觉成像原理,利用三维点到二维点的投影关系,可以计算出摄像机相对世界坐标系的平移和旋转参数。该算法可以同时得到目标三维点与场景二维点的变换参数和对应关系。
当目标的三维模型未知时,将目标及其周围的场景作为模板图像,给出了基于特征点相似度的匹配定位算法。首先分析了尺度变化和旋转变化对特征点的提取和描述带来的影响,然后在寻找特征点对应关系的过程中,定义了特征点匹配度量的准则,利用特征点相似度进行匹配,然后用极线约束去除错误的匹配点对,最后根据参数拟合的方式寻找图像间的变化参数并进行目标定位。实验表明该算法能够适应一定的尺度变化、旋转变化、部分遮挡,对于一定立体旋转角度变化具有一定的鲁棒性。
基于特征点相似度的匹配定位方法仅仅考虑了极线约束,对特征点间的位置信息的利用并不完全。为了保持特征点间的位置信息,分析了松弛标记算法的原理,将特征点的相似度信息融入到松弛过程中,提出了基于松弛标记与特征点相似度的匹配定位算法。该算法不仅利用了模板图像的局部信息,还保持了模板图像的结构信息,实验证明相对于仅利用极线约束的算法,该算法能够找到更多的匹配点对。
为了保持特征点间的位置信息,除了松弛标记算法以外,还可以应用信任度扩散算法。将特征点的相似度信息融入到消息传递过程中,提出了基于信任度扩散与特征点相似度的匹配定位算法。该算法在结合模板图像的局部信息的同时,还保持了模板图像的结构信息。实验表明相对于仅利用极线约束的算法,该算法能够找到更多的匹配点对。
前述算法都是先计算特征点的匹配对再进行目标定位,而前视图像匹配定位的特点是不需要准确地找到模板图像特征点与场景图像特征点之间的对应关系,仅仅关心场景图像中模板图像所在的位置、尺度大小和旋转角度。将特征点的匹配过程与目标定位过程融合到一起,提出了基于均值漂移与投票的匹配定位算法。利用特征点的尺度、朝向和描述向量,构成一个一对多的匹配集合。对每个可能的匹配对,计算场景中模板图像的位置、尺度变化因子和旋转角度,构成一个4维的投票密度图,则密度最大的地方就是最后的定位结果。实验表明该算法鲁棒性更强。
The forward-looking image matching and localization is one of challenging problems. For the depth of each point changes largely, the relationship of the template image and scene image can not be described by simple homography transformation but the complicated projective transformatioa The imaging viewpoint is unknown, the time may be different, and even the template image may be generated from the downward-looking image, so lots of information is lost.
When the 3d model of the object is known, the matching and localization algorithm is given for matching the 3d points in model and 2d points in image. The 3d points are maintained by hand, so the model of 3d points is formed. The 2d points are extracted automatically. Using the relationship of the projective transformation between 3d points and 2d points, the translation and the rotation angle can be computed. The algorithm can output the transformation parameters and the correspondence simultaneously.
When the 3d model of object is unknown, the template is described by the image around the object, and the image matching and localization algorithm based on the similarity of feature point is given. The procedures of extracting and describing the feature point are analyzed. The rule of determining the correspondence point is defined. The similarity of feature point is used to find correspondence points, and then the false correspondence points are eliminated through the epipolar constraint The transform parameters of images are computed and the localization of object is obtained. Experimental results show that the algorithm is robust in the case of scale factor, rotation angle, partial occlusion, and even 3d rotation angle change.
The above method only considers the epipolar constraint and does not make full of the location information of feature points. In order to maintain the location information of the feature points, the principle of relaxation labeling method is analyzed and the local invariant is incorporated into the relaxation procedure. The algorithm based on relaxation labeling method and the feature point similarity is proposed. Experimental results demonstrate that the algorithm can find more correspondence points relative to the methods based on the epipolar constraint
In order to maintain the location information of the feature points, the principle of belief propagation method is analyzed and the local invariant is incorporated into the message passing procedure. The algorithm based on belief propagation method and the feature point similarity is proposed. Experimental results demonstrate that the algorithm can find more correspondence points relative to the methods based on the epipolar constraint
The three above methods first determine the correspondence points and then locate the object, but the characteristic of forward-looking image matching and localization is mat it does not care the accurate correspondence points but the position, scale factor and rotation angle of the object in the scene image, the algorithm based on mean shift and vote is proposed. Using the position, orientation and the descriptor of feature point, the match set is formed in the way of one to many. For each match point, the position, scale factor and the rotation angle of the object in scene image can be computed, so the 4d vote space is formed. The densest point in the vote space is kept as the position, scale factor and rotation angle of the object Experimental results of the algorithm demonstrate both the robustness and efficacy of the overall approach on real images.
引文
[1].张天序。成像自动目标识别。湖北科学技术出版社,2005
[2].G.Bebis,M.Georgiopoulos,N.V.Lobo.Learning Geometric Hashing Functions for Model-based Object Recognition.In Proceedings of the International Conference on Computer Vision,1995,pp.543-548
[3].J.S.Beis,D.G.Lowe.Indexing without Invariants in 3d Object Recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(10):1000-1015
[4].D.G.Lowe.Fitting Parameterized Three-dimensional Models to Images.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(5):441-450
[5].I.Shimshoni,J.Ponce.Probabilistic 3d Object Recognition.In Proceedings of the International Conference on Computer Vision,1995,pp.488-493
[6].S.Belongie,J.Malik,J.Puchiza.Shape Matching and Object Recognition Using Shape Contexts,IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(24):509-522
[7].A.Jain,R.Duin,J.Mao.Statistical Pattern Recognition:A Review.IEEE Transactions on Pattern Analysis and Machine Intelligenve,2000,22(1):4-37
[8].A.Hyvarinen,E.Oja.Independent Component Analysis:Algorithms and Applications.Neural Networks,2000,13,pp.411-430
[9].H.Murase,S.Nayar.Visual Learning and Recognition of 3d Objects from Appearance.International Journal of Computer Vision,1995,14(1):5-24
[10].D.Conte,P.Foggia,C.Sansone,et al.Thirty Years of Graph Matching in Pattern Recognition.Special Edition of the International Journal of Pattern Recognition and Artificial Intelligence on Graph Theory in Vision,2004,18(3):265-298
[11].K.Rose,E.Gurewitz,G.C.Fox.Statistical Mechanics and Phase Transitions in Clustering.Physical review Letters,1990,pp.945-948
[12].孙冬梅,裘正定。基于确定性退火技术的鲁棒性的点匹配算法。计算机学报,2002,25(6):606-611
[13].孙冬梅,裘正定。利用薄板样条函数实现非刚性图像匹配算法。电子学报,2002,30(8):1104-1107
[14].张祥德,唐青松。确定性退火技术及其在点匹配中的应用。东北大学学报(自然科学版),2003,2401):1119-1122
[15].连玮,张洪才,潘泉。一种采用二次式作为阻尼项的点匹配算法。中国图像图形学报,2004,9(9):1080-1087
[16].Y.F.Zheng,D.Doermann.Robust Point Matching for Nonrigid Shapes by Preserving Local Neighborhood structures.IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):643-649
[17].H.Chui;A.Rangarajan.A New Point Matching Algorithm for Non-Rigid Registration.Computer Vision and Image Understanding,2003,89(2-3):114-141
[18].D.P.Huttenloeher,S.Ullman.Object Recognition Using Alignment.In Proceedings of the International Conference on Computer Vision,1987,pp.102-111
[19].L.Yehezkel,J.Wolfson.Geometric Hashing:A General and Efficient Model-based Reeonitiion Scheme.In Proceedings of the International Conference on Computer Vision,1988,pp.238-249
[20].A.Selinger,R.C.Nelson.A Perceptual Grouping Hierarchy for Appearance-based 3D Object Recognition.Computer Vision and Image Understanding,1999,76(1):83-92
[21].A.Baumberg.Reliable Feature Matching across Widely Separated Views.In Conference on Computer Vision and Pattern Recognition,2000,pp.774-781
[22].K.Mikolajczyk,C.Schmid.An Affine lnvariant Interest Point Detector.In Proceedings of European Conference on Computer Vision,2002,pp.128-142
[23].F.Schaffalitzky,A.Zisserman.Multi-view Matching for Unordered Image Sets,or "How Do I Organize My Holiday Snaps?".In Proceedings of European Conference on Computer Vision,2002,pp.414-431
[24].D.Tell,S.Carlsson.Wide Baseline Point Matching Using Affine Invariants Computed from Intensity Profiles.In Proceedings of European Conference on Computer Vision,2000,pp.814-828
[25].C.Schmid,R.Molar.Local Grayvalue Invariants for Image Retrieval.IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(5):530-535
[26].R.Pope,D.G.Lowe.Probabilistie Models of Appearance for 3-d Object Recognition.International Journal of Computer Vision,2000,40(2):149-167
[27].M.Weber,M.Welling,P.Perona.Unsupervised Learning of Models for Recognition.In Proceedings of European Conference on Computer Vision,2000,pp.18-32
[28].C.Harris,M.Stephens.A combined Edge and Corner Detector.In 4th Alvey Vision Conference,1988,pp.189-192
[29].C.Schmid,R.Mohr,C.Bauckhage.Evaluation of Interest Point Detectors.International Journal of Computer Vision,2000,37(2):151-172
[30].T.Lindeberg,J.Garding.Shape-adapted Smoothing in Estimation of 3-d Depth Cues from Affine Distortions of Local 2-d Brightness Structure.In Proceedings of European Conference on Computer Vision,1994,pp.389-400
[31].J.V.Stone.Shape from Texture:Textural Invariance and the Problem of Scale in Perspective Images of Surfaces.In British Machine Vision Conference,1990,pp.181-186
[32].D.G.Lowe.Object recognition from Local Seale-invariant Features.In Proceedings of the International Conference on Computer Vision,1999,pp.1150-1157
[33].T.Lindeberg.Feature Detection with Automatic Scale Selection.International Journal of Computer Vision,1998,30(2):77-116
[34].D.G.Lowe.Distinctive Image Features from Scale-invariant Keypoints.International Journal of Computer Vision,2004,60(2):91-110
[35].K.Mikolajczyk,Cordelia Schmid.Indexing Based on Scale hvariant Interest Points.In Proceedings of the International Conference on Computer Vision,2001,pp.525-531
[36].T.Tuytelaars,L.Van-Gool,L.Dhaene,et al.Matching Affinely Invariant Regions for Visual Scrvoing.In Proceedings of the IEEE Conference on Robotics and Automation,1999,pp.1601-1606
[37].T.Tuytelaars,Luc van gool.Matching Widely Separated Views Based on Affine Invariant Regions.International Journal of Computer Vision,2004,59(1),61-85
[38].J.Matas,O.Chum,M.Urban,et al.Robust Wide Baseline Stereo From Maximally Stable Extremal Regions.In British Machine Vision Conference,volume I,2002,pp.384-393
[39].T.Kadir,D.Boukerroui,M.Brady.An Analysis of the Scale Saliency Algorithm.Technical report,Robotics Research Laboratory,Department of Engineering Science,University of Oxford,2003
[40].T.Kadir,M.Brady.Saliency,Scale and Image Description.International Journal of Computer Vision,2001,45(2):83-105
[41].T.Kadir,M.Brady.Scale saliency:A Novel Approach to Salient Feature and Scale Selection.In International Conference on Visual Information Engineering 2003,pp.25-28
[42].T.Kadir,A.Zisserman,M.Brady.An Affine Invariant Salient Region Detector.In Proceedings of European Conference on Computer Vision,2004,pp.228-241
[43].丁险峰,吴洪,张宏江等。形状匹配综述。自动化学报,2001,27(5):678-694
[44].P.J.Besl,N.D.McKay.A Method for Registration of 3-D Shapes.IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256
[45].A.Yuille,D.Cohen,P.Hallinan.Feature Extraction from Faces Using Deformable Templates.International Journal of Computer Vision,1992,8(2):99-111
[46].S.Sclaroff.Deformable Prototypes for Encoding Shape Categories in Image Databases,Technical Report,1995
[47].M.Kass,A.Witkinm,D.Terzopoulos.Snakes:Active Contour Models.International Journal of Computer Vision,1988,1(4):321-331
[48].L.Cohen.Note on Active Contour Models and Balloons.CVGIP,Image Understanding,1991,53(2):211-21
[49].S.Belongie,J.Malik,J.Puchiza.Matching Shapes.In Proceedings of the International Conference on Computer Vision,2001,pp.454-461
[50].P.Felzenszwalb,D.Huttenlocher.Pictorial Structures for Object Recognition,International Journal of Computer Vision,2005,61(1):55-79
[51].T.B.Sebastian,P.N.Klein,B.B.Kimia.Recognition of Shapes by Editing Shock Graphs.IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(5):550-571
[52].K.Siddiqi,A.Shokoufandeh,S.J.Dickinson,et al.Shock Graphs and Shape Matching.In Proceedings of the International Conference on Computer Vision,1999,pp.222-229
[53].D.P.Huttenlocher,G.A.Klanderman,W.J.Rueklidge.Comparing Images Using the Hausdorff Distance.IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(9):850-863
[54].陈莹,韩崇昭。基于Hausdorff距离的3维模型匹配的改进方法。中国图象图形学报,2005,10(3):326-331
[55].T.B.Sebastian,P.N.Klein,B.B.Kimia.On Aligning Curves.IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(1):116-124
[56].M.K.Hu.Visual Pattern Recognition by Moment Invariants.IEEE Trans on information Theory,1962,8(2):179-187
[57].S.A.Dudan,K.J.Breeding,R.B.Ghee.Aircraft Identification by Moment Invariant.IEEE Transactions on Computer,1983,26(1):39-45
[58].Pasaltis.Image Normalization by Compels Moments.IEEE Transactions on Pattern Analysis and Machine Intelligence,1985,26:46-55
[59].A.P.Reeves,R.J.Prokop,S.E.Andrew,et al.Three-dimentional Shape Analysis Using Moments and Fourier Descriptor.IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(6):937-943
[60].C.Zahn,R.Poskies.Fourier Description for Plane Closed Curves.IEEE Transactions on Computer,1972,pp.269-281
[61].C.Richard,H.Hemani.Identification or Three-dimension Object Using Fourier Description of the Boundary Curve.IEEE Trans.Syst Man,Cybem,1984,(4):371-378
[62].E.Persoom,K.S.Fu.Shape Description Using Fourier Descriptor.IEEE Trans.On Syst Man,cybem,1987,(7):388-397
[63].K.Arbert,W.Snyder.Application of Affine Invariant Fourier Descriptions to Recognition of 3D object.IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,(12):640-647
[64].M.F.Wu,H.T.Sheu.Contour-based Correspondence Using Fourier Descriptions.In IEEE Proceedings of Vision Image Signal Process,1997,144(3):155-160
[65].D.A.Forsyth,J.L.Mundy,A.Zisserman,et al.Invariant Descriptors for 3-D Object Recognition and Pose.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(10):971-991
[66].S.Carlsson.Projectively Invariant Decomposition and Recognition of Planar Shapes. International Joumel of Computer Vision,1996,17(2):1993-209
[67].I.Weiss.Noise-Resistant Invariants of Curves.IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(9):943-948
[68].I.Weiss.Geometric Invariant and Object Recognition.Internatinal Journel of Computer Vision,1993,10(3):207-231
[69].边肇其,模式识别。清华大学出版社,1998
[70].傅京逊,模式识别及其应用。科学出版社,1993
[71].C.Yuan,H.Niemann.Neural Networks for Appearance-based 3-D Object Recognition.Neuro computing,2003,51:249-264
[72].M.I.Miller.Conditional-mean Estimation via Jump-diffusion Processes in Multiple Target Tracking/Recognition.IEEE transactions on Signal Processing,1995,43(11):2678-2690
[73].K.Aizaka,A.Nakamura.Parsing of Two-Dimensional Images Represented by Quadtree Adjoining Grammars.Pattern Recognition,1999,32(2):277-294
[74].A Vailaya,A Jain,H.J Zhang.On Image Classification:City Images vs.Landscapes.Pattern Recognition,1998,31(12):1921-1935
[75].D.Filliat.A Visual Bag of Words Method for Interactive Qualitative Localization and Mapping.In IEEE International Conference on Robotics and Automation,2007,pp.3921-3926
[76].Hotta,Kazuhiro.Object Categorization Based on Kernel Principal Component Analysis of Visual Words.In IEEE Workshop of Applications of Computer Vision,2008,pp.1-8
[77].T.Hofmann.Unsupervised Learning by Probabilistic Latent Semantic Analysis.Machine Learning,2001,42:177-196
[78].P.Viola,M.Jones.Rapid Object Detection Using a Boosted Cascade of Simple Features.In IEEE Conference on Computer Vision and Pattern Recognition,2001,pp.511-518
[79].P.Viola,M.Jones.Robust Real-Time Face Detection.International Journal of Computer Vision,2004,57(2):137-154
[80].M.Riesenhuber and T.Poggio.Models of Object Recognition.Nature.Neuro science,2000,pp.1199-1204
[81].T.Serre,J.Louie,M.Riesenhuber,et al.On the Role of Object-specific Features for Real World Recognition in Biological Vision.In BMCV,2002,pp.387-397
[82].K.W.Chia,A.D.Cheok,and S.J.D.Prince.Online 6 DOF Augmented Reality Registration from Natural Features.In Proceedings of the International Symposium on Mixed and Augmented Reality,2002,pp.305-313
[83].K.Cornelis,M.Pollefeys,M.Vergauwen,et al.Augmented Reality Using Uncalibrated Video Sequences.Lecture Notes in Computer Science,2001,pp.144-160
[84].M.Stephen,J.Smith,B.Michael.SUSAN-A New Approach to Low Level Image Processing.International Journal of Computer Vision,1997,23(1):45-78
[85].M.Trajkovic,M.Hedley.Fast Corner Detection,Image and Vision Computing,1998,16(1):75-87
[86].B.Frey,N.Jojic.A Comparison of Algorithms for Inference and Learning in Probabilistic Graphical Models.IEEE Transaetions on Pattern Analysis and Machine Intelligence,2005,27(9):1392-1416
[87].P.David,D.F.DeMenthon,R.Duraiswami,et al.SoftPOSIT:Simultaneous Pose and Correspondence Determination.In Proceedings of European Conference on Computer Vision,2002,pp.698-714
[88].Z.Zhang,R.Deriche,O.Faugeras,et al.A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry. Artificial Intelligence,1995,78:87-119
[89].C.Schmid and R.Mohr.Comparing and Evaluating Interest Points.In Proceedings of the International Conference on Computer Vision,1998,pp.230-235
[90].J.Matas,D.Koubaroulis,and J.Kittler.Colour Image Retrieval and Object Recognition Using the Multimodal Neighborhood Signature.In Proceedings of the European Conference on Computer Vision 2000,pp.48-64
[91].T.Tuytelaars,L.Van-Gool.Wide Baseline Stereo Based on Local,Affinely Invariant Regions.In Proceedings of the British Machine Vision Conference,2000,pp.121-130
[92].Y.Ke,R Sukthankar.PCA-SIFT:A More Distinctive Representation for Local Image Descriptors.Technical Report IRP-TR-03-15,School of Computer Science,Carnegie Mellon University and IntelResearch Pittsburgh,2003
[93].E Andrew,Johnson,M.Hebert.Using Spin-images for Efficient Multiple Model Recognition in cluttered 3-d scenes.IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(5):433-449
[94].S.Lazebnik,C.Schmid,and J.Ponce.A Sparse Texture Representation Using Affine Invariant Regions.In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2003,volume 2,pp.319-324
[95].K.Mikolajczyk and C.Schmid.A Performance Evaluation of Local Descriptors.In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2003,volume 2,pp.257-263
[96].M.Perdoch,J.Matas,and O.Chum.Epipolar Geometry from Two Correspondences.In International Conference on Pattern Recognition,Volume 4,2006,pp.215-219
[97].陈泽志,吴成柯,一种高精度估计的基础矩阵的线性算法。软件学报,2002,13(4):840-845
[98].A.M.Fischler and R.C.Bolles.Random Sample Consensus:A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography.Communications ACM,1981,24(6):381-395
[99].P.Torr,A.Zisserman.Mlesac:ANew Robust Estimator with Application to Estimating Image Geometry.Computer Vision and Image Understanding,2000,78(1):138-156
[100].王晓军,傅洁,吴立德。基于层次基元结构的优化匹配算法。计算机学报,1991,11:828-837
[101].E.R Hancock;J.Kittler.Edge-labeling Using Dictionary Based Relaxation.IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(2):165-181
[102].M Pelillo,M.Refice.Learning Compatibility Coefficients for Relaxation Labeling Processes.IEEE Transaetions on Pattern Analysis and Machine Intelligence,1994,16(9):933-945
[103].Y.Zheng,D.Doennann.Robust Point Matching for Two-dimensional Nonrigid Shapes.In Proceedings IEEE Conference on Computer Vision,2005,pp.1561-1566
[104].D.L.Waltz.Generating Semantic Deseriptions from Drawings of Scenes with Shadows.Technical Report 271,1972,MITAI Lab
[105].A.Rosenfeld,R.Hummel,and S.Zucker.Scene Labeling by Relaxation Operations.IEEE Trans.System.Man and Cybernetics,1976,6:420-433
[106].N.Sang,T.Zhang.Rotation and Scale Change Invariant Point Pattern Relaxation Matching by the Hopfield Neural Network.Optical Engineering,1997,36(12):3378-3385
[107].桑农,张天序。旋转与比例不变的点特征松弛匹配算法。电子学报,1998,26(6):74-77
[108].桑农,张天序。旋转与比例不变点特征松弛匹配算法的Hopfield神经网络实现。宇航学报,1999,20(3):31-37
[109].E.B.Sudderth,A.T.Ihler,W.T.Freeman et al.Nonparametric Belief Propagation.In IEEE Conference on Computer Vision and Pattern Recognition,2003,pp.605-612
[110].Y.Weiss.Interpreting Images by Propagating Baysian Beliefs.In Advances in Neural Information Processing Systems,1997,pp.908-914
[111].Y.Weiss,W.T.Freeman.On the Optimality of Solutions of the Max-product Belief Propagation Algorithm in Arbitrary Graphs.IEEE Transactions on Information Theory,2001,47(2):723-735
[112].J.Sun,N.N.Zheng,H.Y.Shum.Stereo Matching Using Belief Propagation- IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):787-800
[113].P.E Felzenszwalb,D.P.Huttenlocher.Efficient Belief Propagation for Early Vision.In IEEE Conference on Computer Vision and Pattern Recognition,Washington DC,2004,pp.261-268
[114].S.Xiang,F.Nie,and C.Zhang,Contour Matching Based on Belief Propagation,In Asian Conference of Computer Vision,2006,pp.489-498
[115].P.Tipwail,S.Madarasmi.A Coarse-and-Fine Bayesian Belief Propagation for Correspondence Problems in Computer Vision.In Mexican International Conference on Artificial Intelligence,2007,pp.683-693
[116].J.Coughlan,H.Shen.Shape Matching with Belief Propagation:Using Dynamic Quantization to Accomodate Occlusion and Clutter.In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops,2004,pp.180-189
[117].R.Subbarao,P.Meer.Nonlinear Mean Shift for Clustering over Analytic Manifolds.In IEEE Conference on Computer Vision and Pattern Recognition,2006,volume 1,pp.1168-1175
[118].O.Tuzel,R.Subbarao,and P.Meer.Simultaneous Multiple 3D Motion Estimation via Mode Finding on Lie Groups.In Proceedings of the International Conference on Computer Vision,volume 1,2005,pp.18-25
[119].R.Collins.Mean Shift Blob Tracking Through Scale Space.In IEEE Conference on Computer Vision and Pattern Recognition,Madison,Wisconsin,vol.2,2003,pp.234-240
[120].D.Comaniciu,V.Ramesh,and P.Meer.Kernel-based Object Tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577
[121].D.Comaniciu,P.Meet.Mean shift:A Robust Approach toward Feature Space Analysis.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619
[122].S.Birchfield,S.Rangarajan.Spatiograms vs Histograms for Region-based Tracking.In IEEE Conference on Computer Vision and Pattern Recognition,San Diego,CA,vol.2,2005,pp.1158-1163
[123].Z.Zivkovic,B.Krose.An EM-like Algorithm For Color Histogram Based Object Tracking.In IEEE Conference on Computer Vision and Pattern Recognition,Washington,DC,vol.1,2004,pp.798-803
[124].A.Elgammal,R.Dumiswami,and L.S.Davis.Efficient Kernel Density Estimation Using the Color Modeling and Tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(11):1499-1504
[125].H.Chen,P.Meet.Robust Fusion of Uncertain Information.IEEE Trans.Systems,Man,Cybernetics,Part B,2005,350):578-586
[126].D.Comaniciu.Variable Bandwidth Density-based Fusion.In IEEE Conference on Computer Vision and Pattern Recognition,Madison,Wisconsin,vol.1,2003,pp.59-66
[127].K.Fukunaga,L.D.Hostetler.The Estimation of The Gradient of A Density Function,with Applications in Pattern Recognition.IEEE Transactions on Information Theory,1975,21(1):32-40
[128].Y.Cheng.Mean Shift,Mode Seeking,and Clustering.IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799
[129].李乡儒,吴福朝,胡占义。均值漂移算法的收敛性。软件学报,2005,16(3):365-374
[130].D.Skea,R.Kuwahara,R.Poecker.A Control Point Matching Algorithm.Pattern Recognition,1993,26(2):269-276
[131].A.Teynor,H.Burkhardt.Patch Based Localization of Visual Object Class Instances.In Proceedings of Conference on Machine Vision Applications,2007,pp.211-214
[2].G.Bebis,M.Georgiopoulos,N.V.Lobo.Learning Geometric Hashing Functions for Model-based Object Recognition.In Proceedings of the International Conference on Computer Vision,1995,pp.543-548
[3].J.S.Beis,D.G.Lowe.Indexing without Invariants in 3d Object Recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(10):1000-1015
[4].D.G.Lowe.Fitting Parameterized Three-dimensional Models to Images.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(5):441-450
[5].I.Shimshoni,J.Ponce.Probabilistic 3d Object Recognition.In Proceedings of the International Conference on Computer Vision,1995,pp.488-493
[6].S.Belongie,J.Malik,J.Puchiza.Shape Matching and Object Recognition Using Shape Contexts,IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(24):509-522
[7].A.Jain,R.Duin,J.Mao.Statistical Pattern Recognition:A Review.IEEE Transactions on Pattern Analysis and Machine Intelligenve,2000,22(1):4-37
[8].A.Hyvarinen,E.Oja.Independent Component Analysis:Algorithms and Applications.Neural Networks,2000,13,pp.411-430
[9].H.Murase,S.Nayar.Visual Learning and Recognition of 3d Objects from Appearance.International Journal of Computer Vision,1995,14(1):5-24
[10].D.Conte,P.Foggia,C.Sansone,et al.Thirty Years of Graph Matching in Pattern Recognition.Special Edition of the International Journal of Pattern Recognition and Artificial Intelligence on Graph Theory in Vision,2004,18(3):265-298
[11].K.Rose,E.Gurewitz,G.C.Fox.Statistical Mechanics and Phase Transitions in Clustering.Physical review Letters,1990,pp.945-948
[12].孙冬梅,裘正定。基于确定性退火技术的鲁棒性的点匹配算法。计算机学报,2002,25(6):606-611
[13].孙冬梅,裘正定。利用薄板样条函数实现非刚性图像匹配算法。电子学报,2002,30(8):1104-1107
[14].张祥德,唐青松。确定性退火技术及其在点匹配中的应用。东北大学学报(自然科学版),2003,2401):1119-1122
[15].连玮,张洪才,潘泉。一种采用二次式作为阻尼项的点匹配算法。中国图像图形学报,2004,9(9):1080-1087
[16].Y.F.Zheng,D.Doermann.Robust Point Matching for Nonrigid Shapes by Preserving Local Neighborhood structures.IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):643-649
[17].H.Chui;A.Rangarajan.A New Point Matching Algorithm for Non-Rigid Registration.Computer Vision and Image Understanding,2003,89(2-3):114-141
[18].D.P.Huttenloeher,S.Ullman.Object Recognition Using Alignment.In Proceedings of the International Conference on Computer Vision,1987,pp.102-111
[19].L.Yehezkel,J.Wolfson.Geometric Hashing:A General and Efficient Model-based Reeonitiion Scheme.In Proceedings of the International Conference on Computer Vision,1988,pp.238-249
[20].A.Selinger,R.C.Nelson.A Perceptual Grouping Hierarchy for Appearance-based 3D Object Recognition.Computer Vision and Image Understanding,1999,76(1):83-92
[21].A.Baumberg.Reliable Feature Matching across Widely Separated Views.In Conference on Computer Vision and Pattern Recognition,2000,pp.774-781
[22].K.Mikolajczyk,C.Schmid.An Affine lnvariant Interest Point Detector.In Proceedings of European Conference on Computer Vision,2002,pp.128-142
[23].F.Schaffalitzky,A.Zisserman.Multi-view Matching for Unordered Image Sets,or "How Do I Organize My Holiday Snaps?".In Proceedings of European Conference on Computer Vision,2002,pp.414-431
[24].D.Tell,S.Carlsson.Wide Baseline Point Matching Using Affine Invariants Computed from Intensity Profiles.In Proceedings of European Conference on Computer Vision,2000,pp.814-828
[25].C.Schmid,R.Molar.Local Grayvalue Invariants for Image Retrieval.IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(5):530-535
[26].R.Pope,D.G.Lowe.Probabilistie Models of Appearance for 3-d Object Recognition.International Journal of Computer Vision,2000,40(2):149-167
[27].M.Weber,M.Welling,P.Perona.Unsupervised Learning of Models for Recognition.In Proceedings of European Conference on Computer Vision,2000,pp.18-32
[28].C.Harris,M.Stephens.A combined Edge and Corner Detector.In 4th Alvey Vision Conference,1988,pp.189-192
[29].C.Schmid,R.Mohr,C.Bauckhage.Evaluation of Interest Point Detectors.International Journal of Computer Vision,2000,37(2):151-172
[30].T.Lindeberg,J.Garding.Shape-adapted Smoothing in Estimation of 3-d Depth Cues from Affine Distortions of Local 2-d Brightness Structure.In Proceedings of European Conference on Computer Vision,1994,pp.389-400
[31].J.V.Stone.Shape from Texture:Textural Invariance and the Problem of Scale in Perspective Images of Surfaces.In British Machine Vision Conference,1990,pp.181-186
[32].D.G.Lowe.Object recognition from Local Seale-invariant Features.In Proceedings of the International Conference on Computer Vision,1999,pp.1150-1157
[33].T.Lindeberg.Feature Detection with Automatic Scale Selection.International Journal of Computer Vision,1998,30(2):77-116
[34].D.G.Lowe.Distinctive Image Features from Scale-invariant Keypoints.International Journal of Computer Vision,2004,60(2):91-110
[35].K.Mikolajczyk,Cordelia Schmid.Indexing Based on Scale hvariant Interest Points.In Proceedings of the International Conference on Computer Vision,2001,pp.525-531
[36].T.Tuytelaars,L.Van-Gool,L.Dhaene,et al.Matching Affinely Invariant Regions for Visual Scrvoing.In Proceedings of the IEEE Conference on Robotics and Automation,1999,pp.1601-1606
[37].T.Tuytelaars,Luc van gool.Matching Widely Separated Views Based on Affine Invariant Regions.International Journal of Computer Vision,2004,59(1),61-85
[38].J.Matas,O.Chum,M.Urban,et al.Robust Wide Baseline Stereo From Maximally Stable Extremal Regions.In British Machine Vision Conference,volume I,2002,pp.384-393
[39].T.Kadir,D.Boukerroui,M.Brady.An Analysis of the Scale Saliency Algorithm.Technical report,Robotics Research Laboratory,Department of Engineering Science,University of Oxford,2003
[40].T.Kadir,M.Brady.Saliency,Scale and Image Description.International Journal of Computer Vision,2001,45(2):83-105
[41].T.Kadir,M.Brady.Scale saliency:A Novel Approach to Salient Feature and Scale Selection.In International Conference on Visual Information Engineering 2003,pp.25-28
[42].T.Kadir,A.Zisserman,M.Brady.An Affine Invariant Salient Region Detector.In Proceedings of European Conference on Computer Vision,2004,pp.228-241
[43].丁险峰,吴洪,张宏江等。形状匹配综述。自动化学报,2001,27(5):678-694
[44].P.J.Besl,N.D.McKay.A Method for Registration of 3-D Shapes.IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256
[45].A.Yuille,D.Cohen,P.Hallinan.Feature Extraction from Faces Using Deformable Templates.International Journal of Computer Vision,1992,8(2):99-111
[46].S.Sclaroff.Deformable Prototypes for Encoding Shape Categories in Image Databases,Technical Report,1995
[47].M.Kass,A.Witkinm,D.Terzopoulos.Snakes:Active Contour Models.International Journal of Computer Vision,1988,1(4):321-331
[48].L.Cohen.Note on Active Contour Models and Balloons.CVGIP,Image Understanding,1991,53(2):211-21
[49].S.Belongie,J.Malik,J.Puchiza.Matching Shapes.In Proceedings of the International Conference on Computer Vision,2001,pp.454-461
[50].P.Felzenszwalb,D.Huttenlocher.Pictorial Structures for Object Recognition,International Journal of Computer Vision,2005,61(1):55-79
[51].T.B.Sebastian,P.N.Klein,B.B.Kimia.Recognition of Shapes by Editing Shock Graphs.IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(5):550-571
[52].K.Siddiqi,A.Shokoufandeh,S.J.Dickinson,et al.Shock Graphs and Shape Matching.In Proceedings of the International Conference on Computer Vision,1999,pp.222-229
[53].D.P.Huttenlocher,G.A.Klanderman,W.J.Rueklidge.Comparing Images Using the Hausdorff Distance.IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(9):850-863
[54].陈莹,韩崇昭。基于Hausdorff距离的3维模型匹配的改进方法。中国图象图形学报,2005,10(3):326-331
[55].T.B.Sebastian,P.N.Klein,B.B.Kimia.On Aligning Curves.IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(1):116-124
[56].M.K.Hu.Visual Pattern Recognition by Moment Invariants.IEEE Trans on information Theory,1962,8(2):179-187
[57].S.A.Dudan,K.J.Breeding,R.B.Ghee.Aircraft Identification by Moment Invariant.IEEE Transactions on Computer,1983,26(1):39-45
[58].Pasaltis.Image Normalization by Compels Moments.IEEE Transactions on Pattern Analysis and Machine Intelligence,1985,26:46-55
[59].A.P.Reeves,R.J.Prokop,S.E.Andrew,et al.Three-dimentional Shape Analysis Using Moments and Fourier Descriptor.IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(6):937-943
[60].C.Zahn,R.Poskies.Fourier Description for Plane Closed Curves.IEEE Transactions on Computer,1972,pp.269-281
[61].C.Richard,H.Hemani.Identification or Three-dimension Object Using Fourier Description of the Boundary Curve.IEEE Trans.Syst Man,Cybem,1984,(4):371-378
[62].E.Persoom,K.S.Fu.Shape Description Using Fourier Descriptor.IEEE Trans.On Syst Man,cybem,1987,(7):388-397
[63].K.Arbert,W.Snyder.Application of Affine Invariant Fourier Descriptions to Recognition of 3D object.IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,(12):640-647
[64].M.F.Wu,H.T.Sheu.Contour-based Correspondence Using Fourier Descriptions.In IEEE Proceedings of Vision Image Signal Process,1997,144(3):155-160
[65].D.A.Forsyth,J.L.Mundy,A.Zisserman,et al.Invariant Descriptors for 3-D Object Recognition and Pose.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(10):971-991
[66].S.Carlsson.Projectively Invariant Decomposition and Recognition of Planar Shapes. International Joumel of Computer Vision,1996,17(2):1993-209
[67].I.Weiss.Noise-Resistant Invariants of Curves.IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(9):943-948
[68].I.Weiss.Geometric Invariant and Object Recognition.Internatinal Journel of Computer Vision,1993,10(3):207-231
[69].边肇其,模式识别。清华大学出版社,1998
[70].傅京逊,模式识别及其应用。科学出版社,1993
[71].C.Yuan,H.Niemann.Neural Networks for Appearance-based 3-D Object Recognition.Neuro computing,2003,51:249-264
[72].M.I.Miller.Conditional-mean Estimation via Jump-diffusion Processes in Multiple Target Tracking/Recognition.IEEE transactions on Signal Processing,1995,43(11):2678-2690
[73].K.Aizaka,A.Nakamura.Parsing of Two-Dimensional Images Represented by Quadtree Adjoining Grammars.Pattern Recognition,1999,32(2):277-294
[74].A Vailaya,A Jain,H.J Zhang.On Image Classification:City Images vs.Landscapes.Pattern Recognition,1998,31(12):1921-1935
[75].D.Filliat.A Visual Bag of Words Method for Interactive Qualitative Localization and Mapping.In IEEE International Conference on Robotics and Automation,2007,pp.3921-3926
[76].Hotta,Kazuhiro.Object Categorization Based on Kernel Principal Component Analysis of Visual Words.In IEEE Workshop of Applications of Computer Vision,2008,pp.1-8
[77].T.Hofmann.Unsupervised Learning by Probabilistic Latent Semantic Analysis.Machine Learning,2001,42:177-196
[78].P.Viola,M.Jones.Rapid Object Detection Using a Boosted Cascade of Simple Features.In IEEE Conference on Computer Vision and Pattern Recognition,2001,pp.511-518
[79].P.Viola,M.Jones.Robust Real-Time Face Detection.International Journal of Computer Vision,2004,57(2):137-154
[80].M.Riesenhuber and T.Poggio.Models of Object Recognition.Nature.Neuro science,2000,pp.1199-1204
[81].T.Serre,J.Louie,M.Riesenhuber,et al.On the Role of Object-specific Features for Real World Recognition in Biological Vision.In BMCV,2002,pp.387-397
[82].K.W.Chia,A.D.Cheok,and S.J.D.Prince.Online 6 DOF Augmented Reality Registration from Natural Features.In Proceedings of the International Symposium on Mixed and Augmented Reality,2002,pp.305-313
[83].K.Cornelis,M.Pollefeys,M.Vergauwen,et al.Augmented Reality Using Uncalibrated Video Sequences.Lecture Notes in Computer Science,2001,pp.144-160
[84].M.Stephen,J.Smith,B.Michael.SUSAN-A New Approach to Low Level Image Processing.International Journal of Computer Vision,1997,23(1):45-78
[85].M.Trajkovic,M.Hedley.Fast Corner Detection,Image and Vision Computing,1998,16(1):75-87
[86].B.Frey,N.Jojic.A Comparison of Algorithms for Inference and Learning in Probabilistic Graphical Models.IEEE Transaetions on Pattern Analysis and Machine Intelligence,2005,27(9):1392-1416
[87].P.David,D.F.DeMenthon,R.Duraiswami,et al.SoftPOSIT:Simultaneous Pose and Correspondence Determination.In Proceedings of European Conference on Computer Vision,2002,pp.698-714
[88].Z.Zhang,R.Deriche,O.Faugeras,et al.A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry. Artificial Intelligence,1995,78:87-119
[89].C.Schmid and R.Mohr.Comparing and Evaluating Interest Points.In Proceedings of the International Conference on Computer Vision,1998,pp.230-235
[90].J.Matas,D.Koubaroulis,and J.Kittler.Colour Image Retrieval and Object Recognition Using the Multimodal Neighborhood Signature.In Proceedings of the European Conference on Computer Vision 2000,pp.48-64
[91].T.Tuytelaars,L.Van-Gool.Wide Baseline Stereo Based on Local,Affinely Invariant Regions.In Proceedings of the British Machine Vision Conference,2000,pp.121-130
[92].Y.Ke,R Sukthankar.PCA-SIFT:A More Distinctive Representation for Local Image Descriptors.Technical Report IRP-TR-03-15,School of Computer Science,Carnegie Mellon University and IntelResearch Pittsburgh,2003
[93].E Andrew,Johnson,M.Hebert.Using Spin-images for Efficient Multiple Model Recognition in cluttered 3-d scenes.IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(5):433-449
[94].S.Lazebnik,C.Schmid,and J.Ponce.A Sparse Texture Representation Using Affine Invariant Regions.In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2003,volume 2,pp.319-324
[95].K.Mikolajczyk and C.Schmid.A Performance Evaluation of Local Descriptors.In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2003,volume 2,pp.257-263
[96].M.Perdoch,J.Matas,and O.Chum.Epipolar Geometry from Two Correspondences.In International Conference on Pattern Recognition,Volume 4,2006,pp.215-219
[97].陈泽志,吴成柯,一种高精度估计的基础矩阵的线性算法。软件学报,2002,13(4):840-845
[98].A.M.Fischler and R.C.Bolles.Random Sample Consensus:A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography.Communications ACM,1981,24(6):381-395
[99].P.Torr,A.Zisserman.Mlesac:ANew Robust Estimator with Application to Estimating Image Geometry.Computer Vision and Image Understanding,2000,78(1):138-156
[100].王晓军,傅洁,吴立德。基于层次基元结构的优化匹配算法。计算机学报,1991,11:828-837
[101].E.R Hancock;J.Kittler.Edge-labeling Using Dictionary Based Relaxation.IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(2):165-181
[102].M Pelillo,M.Refice.Learning Compatibility Coefficients for Relaxation Labeling Processes.IEEE Transaetions on Pattern Analysis and Machine Intelligence,1994,16(9):933-945
[103].Y.Zheng,D.Doennann.Robust Point Matching for Two-dimensional Nonrigid Shapes.In Proceedings IEEE Conference on Computer Vision,2005,pp.1561-1566
[104].D.L.Waltz.Generating Semantic Deseriptions from Drawings of Scenes with Shadows.Technical Report 271,1972,MITAI Lab
[105].A.Rosenfeld,R.Hummel,and S.Zucker.Scene Labeling by Relaxation Operations.IEEE Trans.System.Man and Cybernetics,1976,6:420-433
[106].N.Sang,T.Zhang.Rotation and Scale Change Invariant Point Pattern Relaxation Matching by the Hopfield Neural Network.Optical Engineering,1997,36(12):3378-3385
[107].桑农,张天序。旋转与比例不变的点特征松弛匹配算法。电子学报,1998,26(6):74-77
[108].桑农,张天序。旋转与比例不变点特征松弛匹配算法的Hopfield神经网络实现。宇航学报,1999,20(3):31-37
[109].E.B.Sudderth,A.T.Ihler,W.T.Freeman et al.Nonparametric Belief Propagation.In IEEE Conference on Computer Vision and Pattern Recognition,2003,pp.605-612
[110].Y.Weiss.Interpreting Images by Propagating Baysian Beliefs.In Advances in Neural Information Processing Systems,1997,pp.908-914
[111].Y.Weiss,W.T.Freeman.On the Optimality of Solutions of the Max-product Belief Propagation Algorithm in Arbitrary Graphs.IEEE Transactions on Information Theory,2001,47(2):723-735
[112].J.Sun,N.N.Zheng,H.Y.Shum.Stereo Matching Using Belief Propagation- IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):787-800
[113].P.E Felzenszwalb,D.P.Huttenlocher.Efficient Belief Propagation for Early Vision.In IEEE Conference on Computer Vision and Pattern Recognition,Washington DC,2004,pp.261-268
[114].S.Xiang,F.Nie,and C.Zhang,Contour Matching Based on Belief Propagation,In Asian Conference of Computer Vision,2006,pp.489-498
[115].P.Tipwail,S.Madarasmi.A Coarse-and-Fine Bayesian Belief Propagation for Correspondence Problems in Computer Vision.In Mexican International Conference on Artificial Intelligence,2007,pp.683-693
[116].J.Coughlan,H.Shen.Shape Matching with Belief Propagation:Using Dynamic Quantization to Accomodate Occlusion and Clutter.In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops,2004,pp.180-189
[117].R.Subbarao,P.Meer.Nonlinear Mean Shift for Clustering over Analytic Manifolds.In IEEE Conference on Computer Vision and Pattern Recognition,2006,volume 1,pp.1168-1175
[118].O.Tuzel,R.Subbarao,and P.Meer.Simultaneous Multiple 3D Motion Estimation via Mode Finding on Lie Groups.In Proceedings of the International Conference on Computer Vision,volume 1,2005,pp.18-25
[119].R.Collins.Mean Shift Blob Tracking Through Scale Space.In IEEE Conference on Computer Vision and Pattern Recognition,Madison,Wisconsin,vol.2,2003,pp.234-240
[120].D.Comaniciu,V.Ramesh,and P.Meer.Kernel-based Object Tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577
[121].D.Comaniciu,P.Meet.Mean shift:A Robust Approach toward Feature Space Analysis.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619
[122].S.Birchfield,S.Rangarajan.Spatiograms vs Histograms for Region-based Tracking.In IEEE Conference on Computer Vision and Pattern Recognition,San Diego,CA,vol.2,2005,pp.1158-1163
[123].Z.Zivkovic,B.Krose.An EM-like Algorithm For Color Histogram Based Object Tracking.In IEEE Conference on Computer Vision and Pattern Recognition,Washington,DC,vol.1,2004,pp.798-803
[124].A.Elgammal,R.Dumiswami,and L.S.Davis.Efficient Kernel Density Estimation Using the Color Modeling and Tracking.IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(11):1499-1504
[125].H.Chen,P.Meet.Robust Fusion of Uncertain Information.IEEE Trans.Systems,Man,Cybernetics,Part B,2005,350):578-586
[126].D.Comaniciu.Variable Bandwidth Density-based Fusion.In IEEE Conference on Computer Vision and Pattern Recognition,Madison,Wisconsin,vol.1,2003,pp.59-66
[127].K.Fukunaga,L.D.Hostetler.The Estimation of The Gradient of A Density Function,with Applications in Pattern Recognition.IEEE Transactions on Information Theory,1975,21(1):32-40
[128].Y.Cheng.Mean Shift,Mode Seeking,and Clustering.IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799
[129].李乡儒,吴福朝,胡占义。均值漂移算法的收敛性。软件学报,2005,16(3):365-374
[130].D.Skea,R.Kuwahara,R.Poecker.A Control Point Matching Algorithm.Pattern Recognition,1993,26(2):269-276
[131].A.Teynor,H.Burkhardt.Patch Based Localization of Visual Object Class Instances.In Proceedings of Conference on Machine Vision Applications,2007,pp.211-214
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |