基于计算机视觉的特征检测技术研究
|
摘要
特征检测技术问题一直以来就是计算机视觉研究领域中的一个重要研究方向,而基于计算机视觉的特征检测技术中的特征匹配存在一个难题。因此研究一种精度高、鲁棒性强、性能稳定和适用性很强的特征匹配算法在计算机视觉中的任务依然艰巨,且具有很高的研究意义和实用价值。
论文的研究主要工作内容包括:
(1)本文深入研究了计算机视觉相关基础理论,研究并实现了目标被测物体特征的提取及匹配,实验证明并达到了良好的效果。
(2)特征点提取方面,对传统的SUSAN算法、Harris算法进行了详细深入的研究,通过实验并进行实验结果对比分析,在比较经典的Harris特征点检测算法的基础上。本文在图像增强技术条件下采用一种改进的多尺度Harris角点检测算法。该方法具有误差较小、伪角点较少,错误率较低,精度较明显提高等优点。
(3)摄像机标定方面,为确定摄像机的具体位置、属性参数并建立相机成像模型,以确定空间坐标系中图像点与空间点的之间对应关系而进行相机标定,本文在深入研究传统标定方法和自标定方法基础上采用两步法标定方式,避免了传统标定方法设备要求高、操作繁琐等缺点,又较自标定方法精度高,参数也更具有鲁棒性。
(4)特征匹配方面,在比较特征匹配的算法基础上,本文详细研究和分析传统匹配算法的优缺点,采模板匹配方法,减少图像计算的复杂度,提高模板匹配的精度,实验验证了该算法进行特征匹配在特征匹配速率、匹配精度和匹配鲁棒性方面得到良好效果。
Feature detection problem has always been in the field of computer vision research is an important research direction, while the characteristics of computer vision-based detection technology in the feature match there is a problem. Therefore studying a high accuracy, robustness, performance, stability and applicability of a strong feature matching algorithm in computer vision tasks are still difficult.
Thesis research work includes:
(1) This article studies the basic theory of computer vision-related research and to achieve the objectives of the measured object feature extraction and matching, and proved to achieve good results.
(2) Feature point extraction, the traditional SUSAN algorithm, Harris algorithm in-depth study , through experimental and comparative analysis of the experiment, comparing the classic Harris feature point detection algorithm based on the. In this paper, image enhancement technologies to the use of an improved multi-scale Harris corner detection algorithm. This method has smaller error, false corner less error rate low, improve the accuracy of the more obvious advantages.
(3) Camera calibration, in order to determine the specific location of the camera, property and the establishment of the camera imaging model,parameters to determine the spatial coordinates of image points and space points of correspondence between the camera calibration carried out, This in-depth study of traditional and self-calibration method based on the calibration method using two-step calibration, calibration equipment to avoid the traditional high requirements, easy to operate and other shortcomings, but also a more accurate self-calibration method, parameters has more robust.
(4) In the aspect of feature matching, comparing the feature matching algorithms, the paper comprehensively analysizes the strong and weak points of traditional matching algorithms; Template matching method adopted to reduce the complexity of the image calculated to improve the accuracy of template matching, experimental verification of the feature matching algorithm in feature matching rate, matching accuracy and robustness in terms of matching obtained good results.
论文的研究主要工作内容包括:
(1)本文深入研究了计算机视觉相关基础理论,研究并实现了目标被测物体特征的提取及匹配,实验证明并达到了良好的效果。
(2)特征点提取方面,对传统的SUSAN算法、Harris算法进行了详细深入的研究,通过实验并进行实验结果对比分析,在比较经典的Harris特征点检测算法的基础上。本文在图像增强技术条件下采用一种改进的多尺度Harris角点检测算法。该方法具有误差较小、伪角点较少,错误率较低,精度较明显提高等优点。
(3)摄像机标定方面,为确定摄像机的具体位置、属性参数并建立相机成像模型,以确定空间坐标系中图像点与空间点的之间对应关系而进行相机标定,本文在深入研究传统标定方法和自标定方法基础上采用两步法标定方式,避免了传统标定方法设备要求高、操作繁琐等缺点,又较自标定方法精度高,参数也更具有鲁棒性。
(4)特征匹配方面,在比较特征匹配的算法基础上,本文详细研究和分析传统匹配算法的优缺点,采模板匹配方法,减少图像计算的复杂度,提高模板匹配的精度,实验验证了该算法进行特征匹配在特征匹配速率、匹配精度和匹配鲁棒性方面得到良好效果。
Feature detection problem has always been in the field of computer vision research is an important research direction, while the characteristics of computer vision-based detection technology in the feature match there is a problem. Therefore studying a high accuracy, robustness, performance, stability and applicability of a strong feature matching algorithm in computer vision tasks are still difficult.
Thesis research work includes:
(1) This article studies the basic theory of computer vision-related research and to achieve the objectives of the measured object feature extraction and matching, and proved to achieve good results.
(2) Feature point extraction, the traditional SUSAN algorithm, Harris algorithm in-depth study , through experimental and comparative analysis of the experiment, comparing the classic Harris feature point detection algorithm based on the. In this paper, image enhancement technologies to the use of an improved multi-scale Harris corner detection algorithm. This method has smaller error, false corner less error rate low, improve the accuracy of the more obvious advantages.
(3) Camera calibration, in order to determine the specific location of the camera, property and the establishment of the camera imaging model,parameters to determine the spatial coordinates of image points and space points of correspondence between the camera calibration carried out, This in-depth study of traditional and self-calibration method based on the calibration method using two-step calibration, calibration equipment to avoid the traditional high requirements, easy to operate and other shortcomings, but also a more accurate self-calibration method, parameters has more robust.
(4) In the aspect of feature matching, comparing the feature matching algorithms, the paper comprehensively analysizes the strong and weak points of traditional matching algorithms; Template matching method adopted to reduce the complexity of the image calculated to improve the accuracy of template matching, experimental verification of the feature matching algorithm in feature matching rate, matching accuracy and robustness in terms of matching obtained good results.
引文
[1].孙龙样,程义民等.深度图像分析.电子工业出版社,1996.
[2].B.Zitova,J.Flusser.Image registration methods:a survey.Image and Vision Computing 2003,21:977-1000.
[3].Koschan,A., What is New in Computational Stereo Since 1989:A Survey of Current Stereo Papers[R],Technical Report93-22.Univ. of Berlin,1993.
[4].SclarofS and Pentland.A.P,"Modal matching for correspondence and recognition",IEEE Transon PAMI,Vol17(6),1995
[5].Brown L G,A survey registration techniques,ACM Comput.Survey,1992,24(4):25-37.
[6].Ventura A D,Pampini A,and Schetfini R.Image registration by recognition of corresponding structures.IEEE trans.On Geosci.Remote sensing,1990,28(3):305-313.
[7].Zheng.Q and Chellappa.R A computational vision approach to image registration,IEEE Trans.Image Processing,1993.2(3):311-326.
[8].Barnard ST,and Fishchler M A,Computational stereo,ACM Compute.Survey,1982,14(4): 553-572.
[9].Lee H J and Lei W L,Region matching and depth finding for 3-D objects stereo photographs,PaRem Recognition,1990,23(1/2):81-94.
[10].Haieh Y C,Mckeown DM et al,Performation evalution of scene registration and steromatching for cartographic feature extraction,IEEE Trans.On PAMI,1992,14(2):214-238.
[11].Zheng Q and Chellappa R Automatic feature point extraction and tracking in image sequence for arbitrary camera motion,I.J.Computer vision,1995,15:31-76.
[12].Arun KS,Huang T S,and Blostein S D,Least-square firing of two 3-D point sets,IEEE Trans.On PAMI-9(5),698-700.
[13].Rodrigguer J J and Aggarwal J R,matching aerial images to 3-D terrain maps,Image IEEE Trans.On PAMI-12(12):1138-1149.
[14].A.B.Abche,F.Yaacoub,A.Maalouf,et a1.Image registration based on neural network and fourier transform. 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society,2006:4803-4806.
[15].L.Luca,L.Simeon,C.G.M.Estimation of two-dimensional affine transformations through polar curve matching and its application to image mosaicking and remote-sensing dataregistration.IEEE Transactions on Image Processing,2006,15(10):3008-3019.
[16].C Harris and M Stephens.A Combined Corner and Edge Detector[C].Proc.Alvey Conf,1987:189-192.
[17].David G Lowe.Distinctive Image Features from Scale-Invariant Key points[J]. International Journal of Computer Vision,2004,60(2):91-110.
[18].D.Lowe.Object Recognition from Local Scale-Invariant Features[C].In Procs of the International Conference on Computer Vision, pages1150-1157,Corfu,Greece,September 1999.
[19].马颂德,张正友.计算机视觉:计算理论与算法基础[M].科学出版社2004.
[20].Richard Hartley and Andrew Zisserman. Mutliple View Geometry[R].In CVRPJune 1999.
[21].Linda G.Shapiro and George C.Stockman, Computer Vision, Pearson Education,Inc. 2001.
[22].Abdel-Aziz Y.I.,Karara H.M.Direct 1inear transformation from comparator coordinates into object space coordinates inclose-range photo grammetry.In Proceedings Symposium on Close-Range Photogrammetry,1971-18.
[23].Richard Hartley,Multiple View Geometry in ComputerVision(Secondedition),Cambridge University Press,2004.
[24].朱俊樵,梁栋,程志友。一种多视图分层重构算法研究[J]。模式识别与人工智能,2003,16(4):408-411.
[25].H.Chen,P.K.Varshney.Mutual information based CT-MR brain image registration using generalized partial volume joint histogram estimation.IEEE Transactions on Medical Imaging,2003,22(9):1111-1119
[26].G.Cross,A.Fitzgibbon and A.Zisserman,Parallax Geometry of SmoothSurfaces in Multiple Views,In Proc.ICCV,pp:25-31,1998
[27].Smith SM,Brady M SUSAN-A New Approach to Low Level Image Processing[J].International Journal of Computer Vision,1997,23(1):45-78.
[28].Harris C,Stephens M A Combined Comer and Edge Detector[C].Manchester Proceedings of the 4th A lvey Vision Conference.1988:147-l52.
[29].Kitchen L,Rosenfeld A Gray Level Corner Detection [J]. Pattern Recognition Letters,1982,3(1):95-102.
[30].C. Harris, M. Stephens.A Combined Corner and Detector.Proceedings ofthe Alvey Vision Conference,1988,189-192.
[31].Z.Zhang.Flexible Camera Calibration by Viewing a Plane from Unknown Orientations.In Proceedings of the 7th International Conference on Computer Vision,Kerkyra ,Greece,1999,666-673.
[32].杨长江,汪威,胡占义。一种基于主动视觉的相机内参数自标定方法。计算机学报,1998.
[33].Schmid C,Mohr R,Bauckhage C. Evaluation of interest point detectors [J]. International Journal of Computer Vision,2000,37(2):151-172.
[34].陈白帆,蔡自兴.基于尺度空间理论的Harris角点检测[J].中南大学学报:自然科学版,2005,36(5): 751-754.
[35].吴立德.计算机视觉[M].上海:复旦大学出版社,1993.WU Li-de.Computer Vision [M].Shanghai:Fudan University Press,1993.
[36].Babaud J,Witkin A P,Baudin M ,et al .Uniqueness of the Gaussian kernel for scale-space filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(1):26-33.
[37].L.Luca,L.Simeon,C.G.M.Estimation of tw-dimensional affine transformations through polar curve matching and its application to image mosaicking and remote-sensing data registration.IEEE Transactions on Image Processing,2006,15(10):3008-3019.
[38].Lowe D G .Object recognition from local scale-invariant features[J].International Conference on Computer Vision,1999,3(1):1150-1157.
[39].LOWE D. Distinctive image features from scale-invariant keypoints [ J ] . International Journal of Computer Vision , 2004 , 60 (2) : 91-110.
[40].李玲玲,李印清.图像配准中角点检测算法的研究与比较[ J ].郑州航空工业管理学院学报:社会科学版, 2006, 25(2):190-192.
[41].菅云峰.频域图像匹配技术上海交通大学博士论文.2000.
[42].Christian Heipke.Overview of Image Matching Techniques.OEEPE Workshop on the Application of Digital Photogrammetric Workstations.1996,33:173-189
[43].邓志鹏,许丽敏,杨杰等基于直方图相关的图像灰度校正.红外与激光工程.2003,32(2):167-169
[44].Daniel I B,Harvery F S.A Class of Algorithm for Fast Digital Image Registration.IEEETranc on Computer,1972,C-21(2):179-185.
[45].徐奕,周军,周源华.立体视觉匹配技术.计算机工程与用.2003.15(6):1-5.
[46].Faugeras,0.Maybank,S.Motion from Point Matches:Multiplicity of Solutions. International Journal of Computer Vision,4,1990,225-246.
[47].Y.Ohta and T.Kanade.Stereo by intra-and inter-scanl ine search using dynamic programming,IEEE.Trans.Pattern AnalysiS and Machine Intel 1 igence,v01.PAMI-7,no.2,PP. 139-154,1985
[48].Mayhew J E,Ffisby J P.Phychophysical computational studies toward a theory of human stereopsis.Artificial Intelligence,1981,17(3):349-385.
[49].周凌翔,顾伟康.立体视觉的微分几何约束与特征匹配.计算机学报,1997,20(7):608-615.
[50].Richard Hartley Andrew Zisserman著,韦穗杨尚骏章权兵胡茂林。计算机视觉中的多视图几何。安徽大学出版社,2002.
[51].D V Papadimitriou,T J Dennis.Epipolar line estimation and rectification for stereo image pairs[J].IEEE Transactions on Image Processing,1996,5(4).
[52].R Hartley.In defence of the 8point algorithmiC].In Proceedings of the 5th International Conference on Computer Vision,Boston,MR:IEEE Computer Society Press,1995:1064-1070.
[53].倪国强,刘琼.多源图像匹配技术分析与展望.光电工程,2004,31(9):1-6
[54].J.Flusser,T.Suk.A moment·based approach to registration of images with affine geometric distortion.IEEE Transactions on Geo-science and Remote Sensing,l 994,32(2):382-387.
[55].H.Li,B.S.Manjunath,S.K.Mitra.A contour-based approach to multisensor image registration.IEEE Transactions on Image Processing,1995,4(3):320-334.
[56].E.Coiras,J.Santamaria,C.Miravet.Segment.based registration techniques for visual-infrared images.Optical Engineering,2000,39(1):282-289
[57].高征兵,晏磊,赵红颖,张罡.基于特征匹配的地图图像自动配准技术研究.影像技术,2004年第2期:pp47-50.
[58].王新宇.基于计算机立体视觉的三维重建:硕士学位论文.中南大学.2004:3-5,35-36
[59].Zhang Z.Image Based Modeling of Objects and Human Faces.SPIE Conference Videometrics and Optical Methods for 3D Shape Measurement.Proceeding ofSPIE San Jose,CA,USA,2001(4309):21-26.
[60].PdtcheR P,Zisserman A.Matching and reconstruction from widely separated views.In 3D Structurefrom Multiple Images of Large·Scale Environments.LNCS 1506.Springer-Verlag.1998
[61].Lhuillier M,Quan L.Robust dense matching using local and global geometric constrains.Proceedings ofthe IAPR International Conference on Pattern Recognition,Barcelone,Spain,2000 9(2):968-972
[62].Cordelia Schmid,Roger Mohr,Local Grayvalue Invariants for Image Retrieval.IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,1 9(5),530-535.
[63].宰小涛,赵宇明.基于SIFT特征描述子的立体匹配算法[J].微计算机信息,2007,23(83):285—287.
[64].侯舒维,郭宝龙.一种图像自动拼接的快速算法.计算机工程,第3 1卷第15期,2005年.
[65].H Hirschmuller,P R Innocent,and J M Garibaldi.Real-Time Correlation-Based Stereo Vision with Reduced Border Errors[J].IJCv,2002,47(1/2/3):229-246.
[2].B.Zitova,J.Flusser.Image registration methods:a survey.Image and Vision Computing 2003,21:977-1000.
[3].Koschan,A., What is New in Computational Stereo Since 1989:A Survey of Current Stereo Papers[R],Technical Report93-22.Univ. of Berlin,1993.
[4].SclarofS and Pentland.A.P,"Modal matching for correspondence and recognition",IEEE Transon PAMI,Vol17(6),1995
[5].Brown L G,A survey registration techniques,ACM Comput.Survey,1992,24(4):25-37.
[6].Ventura A D,Pampini A,and Schetfini R.Image registration by recognition of corresponding structures.IEEE trans.On Geosci.Remote sensing,1990,28(3):305-313.
[7].Zheng.Q and Chellappa.R A computational vision approach to image registration,IEEE Trans.Image Processing,1993.2(3):311-326.
[8].Barnard ST,and Fishchler M A,Computational stereo,ACM Compute.Survey,1982,14(4): 553-572.
[9].Lee H J and Lei W L,Region matching and depth finding for 3-D objects stereo photographs,PaRem Recognition,1990,23(1/2):81-94.
[10].Haieh Y C,Mckeown DM et al,Performation evalution of scene registration and steromatching for cartographic feature extraction,IEEE Trans.On PAMI,1992,14(2):214-238.
[11].Zheng Q and Chellappa R Automatic feature point extraction and tracking in image sequence for arbitrary camera motion,I.J.Computer vision,1995,15:31-76.
[12].Arun KS,Huang T S,and Blostein S D,Least-square firing of two 3-D point sets,IEEE Trans.On PAMI-9(5),698-700.
[13].Rodrigguer J J and Aggarwal J R,matching aerial images to 3-D terrain maps,Image IEEE Trans.On PAMI-12(12):1138-1149.
[14].A.B.Abche,F.Yaacoub,A.Maalouf,et a1.Image registration based on neural network and fourier transform. 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society,2006:4803-4806.
[15].L.Luca,L.Simeon,C.G.M.Estimation of two-dimensional affine transformations through polar curve matching and its application to image mosaicking and remote-sensing dataregistration.IEEE Transactions on Image Processing,2006,15(10):3008-3019.
[16].C Harris and M Stephens.A Combined Corner and Edge Detector[C].Proc.Alvey Conf,1987:189-192.
[17].David G Lowe.Distinctive Image Features from Scale-Invariant Key points[J]. International Journal of Computer Vision,2004,60(2):91-110.
[18].D.Lowe.Object Recognition from Local Scale-Invariant Features[C].In Procs of the International Conference on Computer Vision, pages1150-1157,Corfu,Greece,September 1999.
[19].马颂德,张正友.计算机视觉:计算理论与算法基础[M].科学出版社2004.
[20].Richard Hartley and Andrew Zisserman. Mutliple View Geometry[R].In CVRPJune 1999.
[21].Linda G.Shapiro and George C.Stockman, Computer Vision, Pearson Education,Inc. 2001.
[22].Abdel-Aziz Y.I.,Karara H.M.Direct 1inear transformation from comparator coordinates into object space coordinates inclose-range photo grammetry.In Proceedings Symposium on Close-Range Photogrammetry,1971-18.
[23].Richard Hartley,Multiple View Geometry in ComputerVision(Secondedition),Cambridge University Press,2004.
[24].朱俊樵,梁栋,程志友。一种多视图分层重构算法研究[J]。模式识别与人工智能,2003,16(4):408-411.
[25].H.Chen,P.K.Varshney.Mutual information based CT-MR brain image registration using generalized partial volume joint histogram estimation.IEEE Transactions on Medical Imaging,2003,22(9):1111-1119
[26].G.Cross,A.Fitzgibbon and A.Zisserman,Parallax Geometry of SmoothSurfaces in Multiple Views,In Proc.ICCV,pp:25-31,1998
[27].Smith SM,Brady M SUSAN-A New Approach to Low Level Image Processing[J].International Journal of Computer Vision,1997,23(1):45-78.
[28].Harris C,Stephens M A Combined Comer and Edge Detector[C].Manchester Proceedings of the 4th A lvey Vision Conference.1988:147-l52.
[29].Kitchen L,Rosenfeld A Gray Level Corner Detection [J]. Pattern Recognition Letters,1982,3(1):95-102.
[30].C. Harris, M. Stephens.A Combined Corner and Detector.Proceedings ofthe Alvey Vision Conference,1988,189-192.
[31].Z.Zhang.Flexible Camera Calibration by Viewing a Plane from Unknown Orientations.In Proceedings of the 7th International Conference on Computer Vision,Kerkyra ,Greece,1999,666-673.
[32].杨长江,汪威,胡占义。一种基于主动视觉的相机内参数自标定方法。计算机学报,1998.
[33].Schmid C,Mohr R,Bauckhage C. Evaluation of interest point detectors [J]. International Journal of Computer Vision,2000,37(2):151-172.
[34].陈白帆,蔡自兴.基于尺度空间理论的Harris角点检测[J].中南大学学报:自然科学版,2005,36(5): 751-754.
[35].吴立德.计算机视觉[M].上海:复旦大学出版社,1993.WU Li-de.Computer Vision [M].Shanghai:Fudan University Press,1993.
[36].Babaud J,Witkin A P,Baudin M ,et al .Uniqueness of the Gaussian kernel for scale-space filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(1):26-33.
[37].L.Luca,L.Simeon,C.G.M.Estimation of tw-dimensional affine transformations through polar curve matching and its application to image mosaicking and remote-sensing data registration.IEEE Transactions on Image Processing,2006,15(10):3008-3019.
[38].Lowe D G .Object recognition from local scale-invariant features[J].International Conference on Computer Vision,1999,3(1):1150-1157.
[39].LOWE D. Distinctive image features from scale-invariant keypoints [ J ] . International Journal of Computer Vision , 2004 , 60 (2) : 91-110.
[40].李玲玲,李印清.图像配准中角点检测算法的研究与比较[ J ].郑州航空工业管理学院学报:社会科学版, 2006, 25(2):190-192.
[41].菅云峰.频域图像匹配技术上海交通大学博士论文.2000.
[42].Christian Heipke.Overview of Image Matching Techniques.OEEPE Workshop on the Application of Digital Photogrammetric Workstations.1996,33:173-189
[43].邓志鹏,许丽敏,杨杰等基于直方图相关的图像灰度校正.红外与激光工程.2003,32(2):167-169
[44].Daniel I B,Harvery F S.A Class of Algorithm for Fast Digital Image Registration.IEEETranc on Computer,1972,C-21(2):179-185.
[45].徐奕,周军,周源华.立体视觉匹配技术.计算机工程与用.2003.15(6):1-5.
[46].Faugeras,0.Maybank,S.Motion from Point Matches:Multiplicity of Solutions. International Journal of Computer Vision,4,1990,225-246.
[47].Y.Ohta and T.Kanade.Stereo by intra-and inter-scanl ine search using dynamic programming,IEEE.Trans.Pattern AnalysiS and Machine Intel 1 igence,v01.PAMI-7,no.2,PP. 139-154,1985
[48].Mayhew J E,Ffisby J P.Phychophysical computational studies toward a theory of human stereopsis.Artificial Intelligence,1981,17(3):349-385.
[49].周凌翔,顾伟康.立体视觉的微分几何约束与特征匹配.计算机学报,1997,20(7):608-615.
[50].Richard Hartley Andrew Zisserman著,韦穗杨尚骏章权兵胡茂林。计算机视觉中的多视图几何。安徽大学出版社,2002.
[51].D V Papadimitriou,T J Dennis.Epipolar line estimation and rectification for stereo image pairs[J].IEEE Transactions on Image Processing,1996,5(4).
[52].R Hartley.In defence of the 8point algorithmiC].In Proceedings of the 5th International Conference on Computer Vision,Boston,MR:IEEE Computer Society Press,1995:1064-1070.
[53].倪国强,刘琼.多源图像匹配技术分析与展望.光电工程,2004,31(9):1-6
[54].J.Flusser,T.Suk.A moment·based approach to registration of images with affine geometric distortion.IEEE Transactions on Geo-science and Remote Sensing,l 994,32(2):382-387.
[55].H.Li,B.S.Manjunath,S.K.Mitra.A contour-based approach to multisensor image registration.IEEE Transactions on Image Processing,1995,4(3):320-334.
[56].E.Coiras,J.Santamaria,C.Miravet.Segment.based registration techniques for visual-infrared images.Optical Engineering,2000,39(1):282-289
[57].高征兵,晏磊,赵红颖,张罡.基于特征匹配的地图图像自动配准技术研究.影像技术,2004年第2期:pp47-50.
[58].王新宇.基于计算机立体视觉的三维重建:硕士学位论文.中南大学.2004:3-5,35-36
[59].Zhang Z.Image Based Modeling of Objects and Human Faces.SPIE Conference Videometrics and Optical Methods for 3D Shape Measurement.Proceeding ofSPIE San Jose,CA,USA,2001(4309):21-26.
[60].PdtcheR P,Zisserman A.Matching and reconstruction from widely separated views.In 3D Structurefrom Multiple Images of Large·Scale Environments.LNCS 1506.Springer-Verlag.1998
[61].Lhuillier M,Quan L.Robust dense matching using local and global geometric constrains.Proceedings ofthe IAPR International Conference on Pattern Recognition,Barcelone,Spain,2000 9(2):968-972
[62].Cordelia Schmid,Roger Mohr,Local Grayvalue Invariants for Image Retrieval.IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,1 9(5),530-535.
[63].宰小涛,赵宇明.基于SIFT特征描述子的立体匹配算法[J].微计算机信息,2007,23(83):285—287.
[64].侯舒维,郭宝龙.一种图像自动拼接的快速算法.计算机工程,第3 1卷第15期,2005年.
[65].H Hirschmuller,P R Innocent,and J M Garibaldi.Real-Time Correlation-Based Stereo Vision with Reduced Border Errors[J].IJCv,2002,47(1/2/3):229-246.