基于序列图像的三维重建算法研究
|
摘要
计算机视觉主要研究如何利用计算机实现人的视觉功能，即利用二维投影图像实现对客观世界三维场景的感知、识别和理解。随着计算机技术的迅速发展，人们对三维模型的需求越来越多。基于序列图像的三维重建方法具有成本低廉、操作简单、真实感强等优点，已成为计算机视觉领域的研究热点之一。本文研究了基于序列图像的三维重建的相关算法，系统总结了作者在基于两幅图像的三维重建、基于多幅图像的三维重建、稠密重建以及三维重建的实际应用等方面所做的研究和取得的成果。
(1)提出了一种基于SIFT(Scale Invariant Feature Transform，尺度不变特征变换)特征和角点特征相结合的三维重建算法。本文算法的基本思想是：SIFT特征点匹配比较准确但是很多匹配点对并不是三维重建所需要的点，而角点更能表达物体的真实形状，在SIFT特征点的基础上加入物体的角点特征，二者取长补短，使得重建结果在细节上更加突出，同不利用角点特征计算出的结果相比，二者结合后的重建物体真实感更强，更接近真实物体。
(2)提出了一种基于射影深度求解及简化ICP(Iterative Closest Point，迭代最近点)算法的序列图像三维重建算法。本文从几何意义的角度进行考虑，根据重构的多义性原理，得出一个关于射影深度及重建三维点比例系数之间关系的推论并由推论的证明过程实现了基于序列图像的三维重建。同时，为了避免误差累积，提出用简化迭代最近点算法校正重建结果。同基于顺序方法的序列图像三维重建相比，由于本文算法相当于对基于两幅图像的重建结果进行叠加，每两幅图像的重建结果之间不受前面结果的影响，从而有效避免了误差累积问题；与传统的基于矩阵分解的序列图像三维重建算法的不同之处在于本文算法不要求重建点在所有图像中均可见，从而可以在保证有足够多匹配点的情况下重建出目标的完整形状。
(3)提出利用稠密点进行网格化所形成的三角形的平均周长剔除误匹配，在特征点数量比较多的情况下，避免了重复计算比较耗时的基础矩阵，在不影响重建质量的前提下，有效加快了重建结果优化速度。本文研究了基于区域增长的稠密匹配算法，利用优化后的SIFT匹配点作为区域增长的种子点，大大提高了稠密匹配的准确度。本文还推导了序列图像相对同一参考坐标系的投影矩阵求解公式，从而可以将本文算法与目前效果最好的多视图重建算法相结合，解决了拍摄过程中由于光照不一致而影响重建效果的问题。
(4)提出考虑相机安装误差情况下基于单目摄像机的车辆行进方向与道路之间夹角的检测方法，同时，为了便于对比，根据三维重建原理利用双目视觉方法完成了对车辆行进方向与道路之间的夹角检测。本文利用机器视觉知识运用几何方法计算出了实际偏离角度，在假设相机与地面成一定角度的情况下计算了车辆行进方向与道路的夹角，并在实际拍摄的场景中验证了算法的有效性。本文算法的突出优势是相机距地面的高度以及俯仰角和水平偏转角不需要实际测量，完全由计算得到，从而进一步减少了测量误差。
Computer vision mainly studies how to use computers to implement the humanvisual function, namely, by using the two-dimensional projective images to achieve theperception, recognition and understanding of the three-dimensional objective worldseene. With the rapid development of computer technologies，people has more and moredemand for3D models.3D reconstruction based on image sequences has become one ofthe hot research topics in the field of computer vision because it has the advantages ofbeing low cost, simple and realistic. This thesis studied the correlative algorithms of3Dreconstruction using image sequences and systematically summarized the studies andachievements of the author in3D reconstruction based on two images,3Dreconstruction based on image sequences, dense reconstruction and the practicalapplication of3D reconstruction.
(1) A3D reconstruction algorithm based on SIFT and corner detector is presentedin this paper. The basic idea of the proposed algorithm is: SIFT feature points areaccurate, but many of them are not what needed in reconstruction. Corners can betterexpress the basic shape of objects. By combining the SIFT feature points with the Harriscorners it is possible to obtain more vivid and detailed3D models. Compared with themethod without corners, reconstruction results of the proposed method is much closer tothe real object.
(2) A novel3D reconstruction method using image sequences based on projectivedepth and the simplified Iterative Closest Point (ICP) is proposed. This paper firstpresents a corollary about the relation between the projective depth and3Dreconstruction points based on the ambiguity of reconstruction and then gives thedetailed proof. It proposes a new algorithm for3D construction from a sequence ofimages. In order to avoid accumulation of errors, this algorithm modifies thereconstruction results based on a simplified ICP algorithm. Compared with existingsequential algorithms, our algorithm can reduce the impact of accumulated errorsbecause the reconstruction process is equal to the pileup of the reconstruction resultsbased on two images. Moreover, compared with methods using Measurement MatrixFactorization, our algorithm does not require the feature points to be visible in all theimages. Therefore it is possible to reconstruct the whole shape of the object withsufficient corresponding points by the proposed algorithm.
(3) For dense points reconstruction, we developed a new method that optimizes the3D points by using the average girth of the triangles obtained from triangulation. It iscomputationally expensive to eliminate false matches with the fundamental matrix whenthere are a large number of points. Our algorithm can effectively accelerate theoptimization speed of the reconstruction result without affecting the reconstruction quality. We also studied the dense matching algorithm based on region growing andused the sparse points obtained from the SIFT feature matching algorithm andoptimized by the fundamental matrix as the seed points of the dense matching algorithm.As a result, the accuracy of the dense matching has been greatly improved. Wecalculated the projective matrices of the image sequence relative to the same referencecoordinate system according to this paper’s algorithm, the projective matrices were usedas the input of the up to date multi-view stereo algorithm, and the influence of photoconsistency had been avoided.
(4) To cope with the installation error of the camera, we developed an algorithm tocalculate the angle between the moving orientation of the vehicle and the drivewaybased on monocular vision using geometrical method. In order to facilitate comparison,we also achieved the angle detection between the moving orientation of the vehicle andthe driveway based on binocular vision according to the theory of3D reconstruction.The angle between the moving orientation of the vehicle and the driveway wascalculated with a hypothesis that there was an angle between the optical axis of thecamera and the ground, the actual deviation angle was also computed. Images capturedfrom the real scene validated the accuracy of our method. The prominent advantage ofthe proposed algorithm is that we do not need to measure the camera height above theground and the pitch angle and also the deflection angle, all the value can be obtainedfrom calculation, which can further decrease the measure error.
(1)提出了一种基于SIFT(Scale Invariant Feature Transform，尺度不变特征变换)特征和角点特征相结合的三维重建算法。本文算法的基本思想是：SIFT特征点匹配比较准确但是很多匹配点对并不是三维重建所需要的点，而角点更能表达物体的真实形状，在SIFT特征点的基础上加入物体的角点特征，二者取长补短，使得重建结果在细节上更加突出，同不利用角点特征计算出的结果相比，二者结合后的重建物体真实感更强，更接近真实物体。
(2)提出了一种基于射影深度求解及简化ICP(Iterative Closest Point，迭代最近点)算法的序列图像三维重建算法。本文从几何意义的角度进行考虑，根据重构的多义性原理，得出一个关于射影深度及重建三维点比例系数之间关系的推论并由推论的证明过程实现了基于序列图像的三维重建。同时，为了避免误差累积，提出用简化迭代最近点算法校正重建结果。同基于顺序方法的序列图像三维重建相比，由于本文算法相当于对基于两幅图像的重建结果进行叠加，每两幅图像的重建结果之间不受前面结果的影响，从而有效避免了误差累积问题；与传统的基于矩阵分解的序列图像三维重建算法的不同之处在于本文算法不要求重建点在所有图像中均可见，从而可以在保证有足够多匹配点的情况下重建出目标的完整形状。
(3)提出利用稠密点进行网格化所形成的三角形的平均周长剔除误匹配，在特征点数量比较多的情况下，避免了重复计算比较耗时的基础矩阵，在不影响重建质量的前提下，有效加快了重建结果优化速度。本文研究了基于区域增长的稠密匹配算法，利用优化后的SIFT匹配点作为区域增长的种子点，大大提高了稠密匹配的准确度。本文还推导了序列图像相对同一参考坐标系的投影矩阵求解公式，从而可以将本文算法与目前效果最好的多视图重建算法相结合，解决了拍摄过程中由于光照不一致而影响重建效果的问题。
(4)提出考虑相机安装误差情况下基于单目摄像机的车辆行进方向与道路之间夹角的检测方法，同时，为了便于对比，根据三维重建原理利用双目视觉方法完成了对车辆行进方向与道路之间的夹角检测。本文利用机器视觉知识运用几何方法计算出了实际偏离角度，在假设相机与地面成一定角度的情况下计算了车辆行进方向与道路的夹角，并在实际拍摄的场景中验证了算法的有效性。本文算法的突出优势是相机距地面的高度以及俯仰角和水平偏转角不需要实际测量，完全由计算得到，从而进一步减少了测量误差。
Computer vision mainly studies how to use computers to implement the humanvisual function, namely, by using the two-dimensional projective images to achieve theperception, recognition and understanding of the three-dimensional objective worldseene. With the rapid development of computer technologies，people has more and moredemand for3D models.3D reconstruction based on image sequences has become one ofthe hot research topics in the field of computer vision because it has the advantages ofbeing low cost, simple and realistic. This thesis studied the correlative algorithms of3Dreconstruction using image sequences and systematically summarized the studies andachievements of the author in3D reconstruction based on two images,3Dreconstruction based on image sequences, dense reconstruction and the practicalapplication of3D reconstruction.
(1) A3D reconstruction algorithm based on SIFT and corner detector is presentedin this paper. The basic idea of the proposed algorithm is: SIFT feature points areaccurate, but many of them are not what needed in reconstruction. Corners can betterexpress the basic shape of objects. By combining the SIFT feature points with the Harriscorners it is possible to obtain more vivid and detailed3D models. Compared with themethod without corners, reconstruction results of the proposed method is much closer tothe real object.
(2) A novel3D reconstruction method using image sequences based on projectivedepth and the simplified Iterative Closest Point (ICP) is proposed. This paper firstpresents a corollary about the relation between the projective depth and3Dreconstruction points based on the ambiguity of reconstruction and then gives thedetailed proof. It proposes a new algorithm for3D construction from a sequence ofimages. In order to avoid accumulation of errors, this algorithm modifies thereconstruction results based on a simplified ICP algorithm. Compared with existingsequential algorithms, our algorithm can reduce the impact of accumulated errorsbecause the reconstruction process is equal to the pileup of the reconstruction resultsbased on two images. Moreover, compared with methods using Measurement MatrixFactorization, our algorithm does not require the feature points to be visible in all theimages. Therefore it is possible to reconstruct the whole shape of the object withsufficient corresponding points by the proposed algorithm.
(3) For dense points reconstruction, we developed a new method that optimizes the3D points by using the average girth of the triangles obtained from triangulation. It iscomputationally expensive to eliminate false matches with the fundamental matrix whenthere are a large number of points. Our algorithm can effectively accelerate theoptimization speed of the reconstruction result without affecting the reconstruction quality. We also studied the dense matching algorithm based on region growing andused the sparse points obtained from the SIFT feature matching algorithm andoptimized by the fundamental matrix as the seed points of the dense matching algorithm.As a result, the accuracy of the dense matching has been greatly improved. Wecalculated the projective matrices of the image sequence relative to the same referencecoordinate system according to this paper’s algorithm, the projective matrices were usedas the input of the up to date multi-view stereo algorithm, and the influence of photoconsistency had been avoided.
(4) To cope with the installation error of the camera, we developed an algorithm tocalculate the angle between the moving orientation of the vehicle and the drivewaybased on monocular vision using geometrical method. In order to facilitate comparison,we also achieved the angle detection between the moving orientation of the vehicle andthe driveway based on binocular vision according to the theory of3D reconstruction.The angle between the moving orientation of the vehicle and the driveway wascalculated with a hypothesis that there was an angle between the optical axis of thecamera and the ground, the actual deviation angle was also computed. Images capturedfrom the real scene validated the accuracy of our method. The prominent advantage ofthe proposed algorithm is that we do not need to measure the camera height above theground and the pitch angle and also the deflection angle, all the value can be obtainedfrom calculation, which can further decrease the measure error.
引文
[1]朱淼良.计算机视觉[Ｍ].杭州:浙江大学出版社,1997.
[2]王汝传,邹北骥.计算机图形学[Ｍ].北京:人民邮电出版社,2002.
[3]章毓晋.图像理解与计算机视觉[Ｍ].北京:清华大学出版社,2000.
[4] Fruh C, Zakhor A.3D Model Generation for Cities using Aerial Photographsand Ground Level Laser Scans [C]. In Preceedings of International Conference onComputer Vision and Pattern Recognition,2001:31~38.
[5] Stamos I, Alien P K. Automatic Registration of2D with3D Imagery in UrbanEnvironments [C]. In Preceedings of International Conference on Computer Vision,2001:731~736.
[6]马颂德,张正友.计算机视觉——计算理论与算法基础[Ｍ].北京:科学出版社,1998.
[7] Faugeraus O, Laveau S, Robert L etc.3D reconstruction of urban scenes fromsequences of images [R]. INRIA,1995:2572~2580.
[8] Barnard S, Fischler M. Computational stereo [J]. ACM Computer Suiveys,1982,(3):62~67.
[9] Jaumann R, Neukum G, Behnke T etc.. The highresolution stereo camera(HRSC) experiment on Mars Express: instrument aspects and experiment conduct frominterplanetary cruise through the nominal mission [J]. Planet Space Sci,2007,(55):7~8.
[10] Bell J F, Squyres S W, Herkenhoff K E etc.. Mars exploration rover Athenapanoramic camera (Pancam) investigation [J]. Journal of Geophysical Research,2003,108(12).
[11] Olson F, Rached H, Ye M, Hendrich P. Wide-baseline Stereo Vision for MarsRovers [C]. Proceedings of the2003IEEE/RSJ Intl. Conference on Intelligent Robotsand Systems,2003:1302~1307.
[12] Asada M, Tanaka T, Hosoda K. Visual Tracking of Unknown Moving Objectby Adaptive Binocular Visual Servoing [C]. Proceeding of the1999IEEE InternationalConference on Multisensor Fusion and Intelligent Systems,1999:249~254.
[13] Steve V， Masayuki K, Naokazu Y. Binocular Vision-based AugmentedReality System with an Increased Registration Depth using Dynamic Correction ofFeature Positions [C]. Proceedings of the2003IEEE Virtual Reality,2003:271~278.
[14]高庆吉,洪炳熔,阮玉峰.基于异构双目视觉的全自主足球机器人导航[J].哈尔滨工业大学学报,2003,35(9):1029~1030.
[15] Fang Y, Masaki I, Hom B. Depth-based Target Segmentation for IntelligentVehicles: Fusion of Radar and Binocular Stereo [J]. IEEE Transactions on IntelligentTransportation Systems,2002,3(3):196~202.
[16] Izumi T, Ueki Y. Improvement of Precision by Introducing Vitality Degree tothe Height Measurement System using Stereo Vision [C]. SICE Annual Conference inSappoor, Hokkaido Institude of technology, Japan.2004:4~8.
[17]阮晓东,李世伦,诸葛良等.用立体视觉测量多自由度机械装置姿态的研究[J].中国机械工程,200011(5):571~573.
[18] Okada K, Inada M. Integration of Real-Time Binocular Stereo Vision andWhole Body Information for Dynamic Walking Navigation of Humanoid Robot [C].IEEE Conference on Multisensor Fusion and Integration for Intelligent Systems,2003:131~136.
[19]朱永光,孙政顺,赵南元.拟人机器人视觉系统的硬件结构设计[J].计算机工程与应用,2002,(9):114~119.
[20] Longuet-Higgins H C. A Computer Algorithm for Reconstructing a Scenefrom Two Projections [J]. Nature,1981(293):133~135.
[21]罗仕鉴,朱上上,孙守迁.人体测量技术的现状与发展趋势[J].人类工效学,2002,8(2):31~34.
[22] Polleleys M. Self-calibration and Metric3D Reconstruction from UncalibratedImage Sequences [D]. Ph.D.Thesis, Heverlee: Katholiek Universiteit Leuven,1999.
[23] Faugeras O D, Mourrain B. On the Geometry and Algebra on the Point andLine Correspondences between N Images [C]. Proc. International Conference onComputer Vision,1995:951~956.
[24] Faugeras O D, Papadopoulo T. A Nonlinear Method for Estimating theProjective Geometry of Three Views [C]. Proc. International Conference on ComputerVision,1998:477~484.
[25] Bougnoux S, Robert L. TotalCalib: A Fast and Reliable System for Off-lineCalibration of Image Sequences [C]. Proc. Compute Vision and Pattern Recognition,Demo Session,1997.
[26]管业鹏,童林夙,陈娜.基于双目立体视觉的偏转线圈测量方法研究[J].电子学报,2003,31(9):1382~1385.
[27] Pollefeys M, Van G L. Stratified Self-calibration with the Modulus Constraint[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1999:707~724.
[28] Cipolla R, Robertson D P, Boyer E G. Photobuilder-3D Models ofArchitectural Scenes from Uncalibrated Images [C]. In Proc. IEEE InternationalConference on Multimedia Computing and Systems. Firenze,1999(1):25~31.
[29] Shum H Y, Szeliski R, Baker S, etc.. Interative3D modeling from multipleimages using scene regularities [C]. In Proceedings of Fourth IEEE Workshop onApplication of Computer Vision.1998:234~235.
[30]张宏伟,张国雄,秦鹏等.双目视觉检测技术在自由曲面测量中的应用[J].机械工程学报,2004,40(7):110~113.
[31] Horn B K P. Relative Orientation [J]. International Journal of ComputerVision,1990(4):59~78.
[32] Horn B K P. Relative Orientation Revisited [J]. Journal of the Optical Societyof America,1991,8(10):1630~1638.
[33] Hartley R I. Euclidean Reconstruction from Uncalibrated Views [J].Applications of Invariance in Computer Vision, volume825of Lecture Notes inComputer Science, Springer-Verlag,1993:237~256.
[34] Faugeras O. What can be Seen in Three Dimensions with an UncalibratedStereo Rig?[C]. In Proceedings of the European Conference on Computer Vision. SantaMargherita L,1992:563~578.
[35] Maybank S J, Faugeras O D. A Theory of Self-calibration of a MovingCamera [J]. International Journal of Computer Vision,1992,8(2):123~151.
[36] Faugeras O D, Luong Q T, Maybank S J. Camera Self-calibration: Theory andExperiments [C]. In Proceedings of the European Conference on Computer Vision.Santa Margherita L.,1999:3321~3342.
[37] Huang T S, Netravali A N. Motion and Structure from FeatureCorrespondences: A Review [C]. Proc. of the IEEE,1994,82(2):252-268.
[38] Hartley R I. Estimation of Relative Camera Position for Uncalibrated Cameras
[C]. In Proceedings of the European Conference on Computer Vision. Santa MargheritaL.,1992:579~587.
[39] Zhang Z, Deriche R, Faugeras O D etc.. A Robust Technique for MatchingTwo Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry[J]. Artificial Intelligence,1995,75(1-2):87~120.
[40] Schaffalitzky F, Zisserman A, Hartley R I etc.. A Six Point Solution forStructure and Motion [C]. In Proceedings of the European Conference on ComputerVision.2000,Vol (1):632~648.
[41] Pollefeys M, Van Gool L. A Stratified Approach to Metric Self-calibration [C].In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Puerto Rico,1997:407~412.
[42] Pollefeys M, Van Gool L, Oosterlinck A. The Modulus Constraint: A NewConstraint for Self-calibration [C]. In Proceedings of the International Conference onPattern Recognition. Vienna, l996:349~353.
[43] Heyden A, Astrom K. Euclidean Reconstruction from Constant IntrinsicParameters [C]. In Proceedings of the International Conference on Pattern Recognition.Vienna,1996:339~343.
[44] Triggs B. Autocalibration and the Absolute Quadric [C]. In Proceedings of theIEEE Conference on Computer Vision and Pattern Recognition. Puerto Rico,1997:609~614.
[45] Heyden A, Astrom K. Euclidean Reconstruction from Image Sequences withVarying and Unknown Focal Length and Principal Point [C]. In Proceedings of theIEEE Conference on Computer Vision and Pattern Recognition. Puerto Rico,1997:438~443.
[46] Pollefeys M, Koch R, Van Gool L. Self-calibration and Metric Reconstructionin Spite of Varying and Unknown Internal Camera Parameters [C]. In Proceedings ofthe IEEE International Conference on Computer Vision. Bombay,1998:90~95.
[47] Manning R and Dyer C. Affine Calibration from Moving Objects [C]. In Proc.International Journal of Computer Vision.2001,Vol(1):494~500.
[48]祝海江.三维重建和摄像机标定技术研究[D].北京:中国科学院自动化研究所博士学位论文,2004.
[49] Zheng J Y. Acquiring3-d Models from a Sequence of Contours [J]. IEEETrans. Pattern Anal. Machine Intell.,1994,(16):163~178.
[50] Kanade T, Okutomi M, Nakahara T. A Multiple-baseline Method [C]. in Proc.DARPA Image Understanding Workshop.1992:409~426.
[51] Kanade T, Kang S B, Webb J, etc.. A Multibaseline Stereo System withActive Illumination and Real-time Image Acquisition [C]. in Proc. Int. Cont. ComputerVision.1995:88~93.
[52] Debevec P E, Taylor C J, Malik J. Modeling and Rendering Architecture fromPhotographs: A Hybrid Geometry and Image-based Approach [C]. In Proc. ComputerGraphics.1996:11~20.
[53] Martin W N, Aggarwal J K. Volumetric Descriptions of Objects fromMultiple Views [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,1983,5(2):150~158.
[54] Kutulakos K N, Seitz S M. A Theory of Shape by Space Carving [J]. Int. J.Computer Vision,2000,38(3):1999~2187.
[55]王亚昕.基于序列图像的摄像机定标和三维重建的研究[D].北京:北京交通大学硕士学位论文,2004.
[56] Li R, Sclaroff S. Multi-scale3D Scene Flow from Binocular Stereo Sequences
[C]. In Preceedings of the IEEE Workshop on Moton and Video Computing.2005:147~153.
[57] Hom B K P. Shape from Shading: A Method for Obtaining the Shape of aSmooth Opaque Object from One View [D]. MIT: PhD thesis,1970.
[58] Bichsel M, Pentland A P. A Simple Algorithm for Shape from Shading [C].IEEE Proceedings of Computer Vision and Pattern Recognition.1992:459~465.
[59] Zhang R, Tsai P S, Cryer J. Shape from Shading: A Surrey [J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1999,21(8):690~706.
[60]张楠.基于图像序列重建三维物体的一种方法[D].大连:大连理工大学硕士学位论文,2005.
[61] Stone J V. Shape from Texture: a Computational Analysis [D]. University ofSussex:PhD thesis,1990.
[62] Brzakovic D, White B. Surface Orientation using Texture Gradient Derivedfrom Two Views of a Scene [C]. Proc.8th International Conference on PatternRecognition.1986:1045~1047.
[63] Wang S J, Zhuang Y, Zheng K Q, etc..3D Scene Reconstruction UsingPanoramic Laser Scanning and Monocular Vision [C]. In Proceedings of the8thWorldCongress on Intelligent Control and Automation. Jinan, China,2010,861~866.
[64] Yang R, Pollefeys M, Welch G. Dealing with Textureless Regions andSpecular Highlights: A Progressive Space Carving Scheme using a NovelPhoto-consistency Measure [C]. IEEE International Conference on Computer Vision.Piscataway, NJ, USA:2003:576~584.
[65]孟维亮.基于图像的多视图重建和纹理恢复[D].天津:天津大学硕士学位论文,2006.
[66] Shashua A. On Photometric Issues in3D Visual Recognition from a Single2D Image [J]. International Journal of Computer Vision,1997vol.21:99~122.
[67] Barnard S, Fischler M. Computational Stereo [J]. ACM Computer Suiveys,1982,14(4):553~572.
[68] Zhang Z Y. A Flexible Camera Calibration by Viewing a Plane fromUnknown Orientation [C]. The7thIEEE International Conference of Computer Vision.Corfu, Greece,1999:666~673.
[69] Maybank S J, Faugeras O. A Theory of Self-Calibration of a Moving Camera[J]. International Journal of Computer Vision,1992, vol.8:123~152.
[70]周彦.基于双目视觉的图像三维重建[D].中国海洋大学硕士学位论文,2008.
[71] Arnold R D. Local Context in Matching Edges for Stereo Vision.1978.
[72] Wei G Q, Gerd H. Intensity and Feature Based Stereo Matching by DisparityParameterization [C]. Sixth International Conference on Computer Vision,1998:1035~1040.
[73] Zhu Q, Wu B, Xu Z. Seed Point Selectiion Method for Triangle ConstrainedImage Matching Propagation [J]. IEEE Geoscience and Remote Sensing Letters,2006,3:207~211.
[74]李海超,张广军.一种基于角点引导的快速立体边缘匹配方法[J].北京航空航天大学学报,2007,33(5):557~560.
[75] Lowe D. Object Recognition from Local Scale-Invariant Features [C].Proceedings of the Seventh IEEE International Conference on Computer Vision.Kerkyra, Greece,1999:1150~1157.
[76] Bay H, Tuytelaars T, Van Gool L. SURF: Speeded Up Robust Features [C]. InProceedings of European Conference on Computer Vision.2006:404~417.
[77] Mikolajczyk K, String T T, Fp C S, etc.. A Comparison of Affine RegionDetectors [J]. International Journal of Computer Vision,2005,65(1-2):43~72.
[78]郑志刚.高精度摄像机标定和鲁棒立体匹配算法研究[D].中国科学技术大学博士学位论文,2008.
[79] Megyesi Z, Chetverikov D. Enhanced Surface Reconstruction from WideBaseline Images [C]. In Proceedings of the Second International Symposium on3DData Processing, Visualization and Transmission.2004:463~469.
[80] Radim S. Finding the Largest Unambiguous Component of Stereo Matching
[C]. In Proceedings of European Conference on Computer Vision.2002:900~914.
[81] Cech J, Sara R. Efficient Sampling of Disparity Space for Fast and AccurateMatching [C].2007International Conference on Computer Vision and PatternRecognition.2007:1~8.
[82] Hartley R, Zisserman A. Multiple View Geometry in Computer Vision [M].Cambridge University Press,2003.
[83]方德植,陈奕培.射影几何[M].北京:高等教育出版社,1983.
[84]章权兵.基于多视图的三维重构研究[D].安徽大学博士学位论文,2004.
[85]刘勇.基于非定标图象的三维重建方法研究[D].西安:西安电子科技大学大学博士学位论文,2001.
[86]于海雁.基于多视图几何的三维重建研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2007.
[87]李云翔.相机标定与三维重建技术研究[D].青岛:青岛大学硕士学位论文,2009.
[88] Rother C, Carlsson S. Linear Multi-view Reconstruction and CameraRecovery Using A Reference Plane [J]. International Journal of Computer Vision,2002,49(2/3):117~141.
[89] Peng K J, Chen X, Zhou D X, etc..3D Reconstruction Based on SIFT andHarris Feature Points [C].2009IEEE International Conference on Robotics andBiomimetics. Guilin, China,2009:960~964.
[90] Zhao J, Chang S, Men G.3D Reconstruction Based on the Matching Methodof GA [C]. Proceedings of the Ninth International Conference on Machine Learning andCybernetics. Qingdao, China,2010:1798~1801.
[91] Lowe D. Distinctive Image Features from Scale-Invariant Interest Points [J].International Journal of Computer Vision,2004,60(2):91~110.
[92] Harris C G, Stephens M. A Combined Corner and Edge Detector ［C］.Proceedings of the4th Alvey Vision Conference. Manchester, UK,1998:147~151.
[93] Fishler M A, Bolles R C. Random Sample Consensus, A Paradigm for ModelFitting with Applications to Image Analysis and Automated Cartography [J].Communications of ACM,1981,24(6):381~395.
[94]舒志龙,阮秋琦.快速对称多窗口正交三目立体匹配[J].计算机研究与发展,2001,38(10):1229~1235.
[95] Witkin A P. Scale-space Filtering [J]. International Joint Conference onArtificial Intelligence. Karlsruhe, Germany.1983:1019~1022.
[96] Koenderink J J. The Structure of Images [J]. Biological ybernetics,1984(50):363~396.
[97] Lindbeegr. Detecting Salient Blob-like Image Structures and Their Scaleswith a Cale-spaceprimal Sketch: A Method for Focus-of-attention [J]. InternationalJournal of Computer Vision,1993,11(3):283~318.
[98]王瑞.基于GPU的SIFT特征图像匹配算法研究与应用[D].长沙:国防科技大学硕士学位论文,2010.
[99] Luong Q T, Faugeras O. The Fundamental Matrix: Theory, Algorithms, andStability Analysis [J]. International Journal of Computer Vision,1996,17(1):43~75.
[100]唐丽.由手提相机获得的序列图像进行三维重建[D].西安:西安电子科技大学博士学位论文,2003:9~10.
[101] Mehrotra R, Nichani S. Corner Detection [J]. Pattern Recognition,1990,23(11):1223~1233.
[102] Wang H, Brady M. Realtime Corner Detection Algorithm for MotionEstimation [J]. Image and Vision Computing,1995,13(9):695~703.
[103] Sheu H T, Hu W C. A Rotationally Invariant Two Phase Scheme for CornerDetection [J]. Pattern Recognion,1996,29(5):819~828.
[104] Smith S M, Brady J M. SUSAN—A New Approach to Low Level ImageProcessing [J]. International Journal of Computer Vision,1997,23(1):45~78.
[105] Laganiere R. A Morphological Operator for Corner Detection [J]. PatternRecognition,1998,31(11):1643~1652.
[106] Zitova B, Flusser J. Image Registration Methods: A Survey [J]. Image andVision Computing,2003,21(11):977~1000.
[107] Tissainayagam D S. Assessing the Performance of Corner Detectors forPoint Feature Tracking Applications [J]. Image and Vision Computing.2004,22(8):663~679.
[108] Liu S, Zhao L, Li J, etc.. The Research of3D Reconstruction fromUncalibrated Image Sequences Combined with3D Models [C]. Proceedings of2008International conference on computer science and software engineering.2008:1117-1119.
[109] Micusik B, Kosecka J. Piecewise Planar City Modeling from Street ViewPanoramic Sequences [C]. In CVPR,2009:2906~2912.
[110] Pollefeys M et al. Detailed Real-time Urban3d Reconstruction from Video[J]. IJCV,2008,78(2-3):143~167.
[111] Tomasi C, Kanade T. Shape and Motion from Image Streams UnderOrthography: A Factorization Method[J]. International Journal of Computer Vision,1992,9(2):137~154.
[112] Poelman C, Kanade T. A Paraperspective Factorization Method for Shapeand Motion Recovery [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1997,19(3):580~593.
[113] Sturm P, Triggs B. A Factorization Based Algorithm for Multi-imageProjective Structure and Motion [C]. Proceedings of the4th European Conference onComputer Vision. Cambridge, England,1996:709~720.
[114]吴玲达,邓宝松,高宇,魏迎梅.基于长序列图像的三维重建技术研究[J].计算机应用研究.2007,24(5):314~317.
[115] Frahm J, Pollefeys M, Lazebnik S, et al.. Fast Robust Reconstruction ofLarge-Scale Environments [C].201044th Annual Conference on Information Scienceand Systems (CISS2010), USA,2010:1~6.
[116] Gallup D, Frahm J, Pollefeys M, et al.. Piecewise Planar and Non-planarStereo for Urban Scene Reconstruction [C].2010IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition(CVPR2010), USA,2010:1418~1425.
[117] Agarwal S, Snavely N, Simon I, et al.. Building Rome in a Day [C]. In ICCV,Japan,2009:72~79.
[118] Frahm J, Fite-Georgel P, Gallup D, et al.. Building Rome on a Cloudless Day
[C].11th European Conference on Computer Vision (ECCV2010), Greece,2010, v6314LNCS, n PART4, pp368~381.
[119] Wu T, Yeung S, Jia J, et al.. Quasi-Dense3D Reconstruction usingTensor-based Multiview Stereo [C]. Proceeding of the IEEE Computer SocietyConference on Computer Vision and Pattern Recognition (CVPR2010), USA,2010:1482~1489.
[120] Furekawa Y, Curless B, Steven M, et al.. Towards Internet-scale Multi-viewStereo [C]. Proceeding of the IEEE Computer Society Conference on Computer Visionand Pattern Recognition (CVPR2010), USA,2010:1434~1441.
[121] Avidan, Shuahua A. Novel View Synthesis by Cascading Trilinear Tensors[J]. IEEE Transaction on Visualization and Computer Graphics,1998,4(3):11~12.
[122] Besl P J, Mckay H D. A Method for Registration of3-D Shapes [J].Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239~256.
[123] Triggs B, McLauchlan P, Hartley R, et al.. Bundle Adjustment–A ModernSynthesis, Vision Algorithms: Theory and Practice [J]. Springer–Verlag,2000:298~372.
[124] Furukawa Y, Ponce J. Accurate, Dense, and Robust Multi-View Steriopsis[J]. In: PAMI09,2009:1~8.
[125] Hartley R, Zisserman A.计算机视觉中的多视图几何[M].韦穗,等译.合肥:安徽大学出版社:2002,8.
[126] Triggs B. Factorization Methods for Projective Sturcutre and Motion [C].Proceedings of Computer Vision and Pattern Recognition. San Francisco, Caliofornia，USA,1996:845~851.
[127] Heyden A, Berthilsson R, Sparr G. An Iterative Factorization Method forProjective Sturcutre and Motion from Image Sequences[J]. Image and VisionComputing,1999,17(13):981~991.
[128]陈付幸.基于非定标图像序列的三维重建关键技术研究[D].长沙:国防科技大学博士学位论文,2005.
[129]方磊.基于特征的图像序列三维场景重建技术研究[D].武汉:华中科技大学博士学位论文,2006.
[130]曹智清,石教英,张世明等.基于序列图像建模的多视图模型合并策略[J].计算机研究与发展,2005,42(9):1633~1639.
[131]李世飞,王平,沈振康.迭代最近点算法研究进展[J].信号处理,2009,25(10):1582~1588.
[132] Lhuillier M, Quan L. Match Propagation for Image-Based Modeling andRendering [J]. IEEE Transactions on Pattern Analysis and Machine Inteligence,2002,Vol.24. No.8:1140~1146.
[133] Falkenhagen L. Depth Estimation from Stereoscopic Image Pairs AssumingPiecewise Continuous Surfaces [C]. In European Workshopon Combined RealandSynhtetic Image Processing for Broadcast and Video Productions. Hamburg, Gemran,1994:115~127.
[134] Cox I, Hingorani S, Rao S. A Mxaimum Likelihood Stereo Algorithm [J].Computer Vision and Image Understanding,1996,63(3):542~567.
[135] Ohta Y, Kanade T, Stereo by Intra-and Inter-Scanline Search Using Dynamicprogramming [J]. EIEE Trans. Pattern Analysis and Machine Intelligence,1985,7(2):139~154.
[136] Okutomi M, Kanade T. A Locally Adaptive Window for Signal Processing[J]. International Journal of Computer Vision.1992,7:143~162.
[137] Roy S, Meunier J, Cox I. Cylindrical Rectification to Minimize EpipolarDistortion [C]. In IEEE Conference on Computer Vision and Pattern Recognition.1997:393~399.
[138] Lhuillier M, Quan L. Edge-Constrained Joint View Triangulation for ImageInterpolation [C]. In Proceedings of the Conference on Computer Vision and PatternRecognition. HiltonHead, South Carolina,2000:218~224.
[139] Scharstein D, Szeliski R. A Taxonomy and Evaluation of Dense Two-FrameStereo Correspondence Algorithms [J]. International Journal of Computer Vision,2002,47(1-3):7~42.
[140]葛亮.图像建模中立体匹配问题的研究[D].重庆:重庆大学博士学位论文,2009.
[141]王海彬.地面自主机器人视觉导航三维重建算法研究[D].长沙:国防科技大学硕士学位论文,2006.
[142]梁志敏.遥控焊接机器人任务空间的三维重建研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2008.
[143] Strecha C,“Multi-view evaluation.”[Online]. Available:http://cvlab.epfl.ch/~strecha/multiview.
[144]史利民,郭复胜,胡占义.利用空间几何信息的改进PMVS算法[J].自动化学报,2011,37(5):560~568.
[145] Bishop R. A Survey of Intelligent Vehicle Applications Worldwide [C]. In:Proceedings of the IEEE Intelligent Vehicles Symposium2000. Dearbom, MI, USA,2000:25~30.
[146] Tsuji M, Shirato R, Furusho H. Estimation of Road Configuration andVehicle Attitude by Lane Detection for a Lane-keeping System [C]. In: SAE2001World Congress Intelligent Vehicle Inititaive(IVI) Vehicle Navigation Systems (PartA&B)[C]. Detroit, Michigan, USA,2001:45~51.
[147] Rosito J C, Roberto K C. A Lane Departure Warning System Using LateralOffset with Uncalibrated Camera [C], IEEE Conference on Intelligent TransportationSystems. Vienna, Austria,2005:102~107.
[148]余厚云,张为公.基于动态感兴趣区域的车道线识别与跟踪[J].工业仪表与自动化装置,2009年第5期:103~106.
[149]叶庆,赵明辉,李菲等.夜间车道线检测与跟踪算法研究[J].现代电子技术,2009年第13期:155~158.
[150]于兵,张为公,龚宗洋.基于机器视觉的车道偏离报警系统[J].东南大学学报(自然科学版),2009,39(5):928~932.
[151]余厚云,张为公.基于摄像机模型的运动车辆车道偏离检测[J].东南大学学报(自然科学版),2009,39(5):933~936.
[152] Bertozzi M, Broggi A. Gold: A Parallel Real-Time Stereo Vision System forGeneric Obstacle and Lane Detection [J]. IEEE Transactions on Image Processing,1998,7(1):62~81.
[153]刘洁,黄斌.单目视觉车道偏离报警系统[J].电子产品世界,2007(03)：128~130.
[154]卢卫娜,史忠科.基于单目视觉的车道线和道路边界同步检测[J].传感技术学报,2007,20(5):1171~1175.
[155] Hough PVC. A Method and Means for Recognizing Complex Patterns [P].US Patent,1962.
[156]姜大志.计算机视觉中三维重构的研究与应用[D].南京:南京航空航天大学博士学位论文,2001.
[157]隋婧,金伟其.双目立体视觉技术的实现及其进展[J].电子技术应用,2004:4~6.
[158]刘钢,彭群生,鲍虎军.基于多幅图像的场景交互建模系统[J].计算机辅助设计与图形学学报,2004,16(10):1419~1424.
[159]山海涛,马淑宇,郝向阳等.一种基于Hough变换的对极几何稳健估计算法[J].测绘科学技术学报,2008,25(3):202~205.
[160]唐丽,吴成柯,刘侍刚等.基于区域增长的立体像对稠密匹配算法[J].计算机学报,2004,27(7):936~943.
[161]刘宇斌.一种分阶段的高精度亚像素特征点提取方法[J].南华大学学报,2006:54~57.
[162]彭科举,陈新,周东翔,刘云辉.基于单目视觉的车辆行驶方向检测及误差分析[J].信号处理,2010,26(10):1560-1566.
[2]王汝传,邹北骥.计算机图形学[Ｍ].北京:人民邮电出版社,2002.
[3]章毓晋.图像理解与计算机视觉[Ｍ].北京:清华大学出版社,2000.
[4] Fruh C, Zakhor A.3D Model Generation for Cities using Aerial Photographsand Ground Level Laser Scans [C]. In Preceedings of International Conference onComputer Vision and Pattern Recognition,2001:31~38.
[5] Stamos I, Alien P K. Automatic Registration of2D with3D Imagery in UrbanEnvironments [C]. In Preceedings of International Conference on Computer Vision,2001:731~736.
[6]马颂德,张正友.计算机视觉——计算理论与算法基础[Ｍ].北京:科学出版社,1998.
[7] Faugeraus O, Laveau S, Robert L etc.3D reconstruction of urban scenes fromsequences of images [R]. INRIA,1995:2572~2580.
[8] Barnard S, Fischler M. Computational stereo [J]. ACM Computer Suiveys,1982,(3):62~67.
[9] Jaumann R, Neukum G, Behnke T etc.. The highresolution stereo camera(HRSC) experiment on Mars Express: instrument aspects and experiment conduct frominterplanetary cruise through the nominal mission [J]. Planet Space Sci,2007,(55):7~8.
[10] Bell J F, Squyres S W, Herkenhoff K E etc.. Mars exploration rover Athenapanoramic camera (Pancam) investigation [J]. Journal of Geophysical Research,2003,108(12).
[11] Olson F, Rached H, Ye M, Hendrich P. Wide-baseline Stereo Vision for MarsRovers [C]. Proceedings of the2003IEEE/RSJ Intl. Conference on Intelligent Robotsand Systems,2003:1302~1307.
[12] Asada M, Tanaka T, Hosoda K. Visual Tracking of Unknown Moving Objectby Adaptive Binocular Visual Servoing [C]. Proceeding of the1999IEEE InternationalConference on Multisensor Fusion and Intelligent Systems,1999:249~254.
[13] Steve V， Masayuki K, Naokazu Y. Binocular Vision-based AugmentedReality System with an Increased Registration Depth using Dynamic Correction ofFeature Positions [C]. Proceedings of the2003IEEE Virtual Reality,2003:271~278.
[14]高庆吉,洪炳熔,阮玉峰.基于异构双目视觉的全自主足球机器人导航[J].哈尔滨工业大学学报,2003,35(9):1029~1030.
[15] Fang Y, Masaki I, Hom B. Depth-based Target Segmentation for IntelligentVehicles: Fusion of Radar and Binocular Stereo [J]. IEEE Transactions on IntelligentTransportation Systems,2002,3(3):196~202.
[16] Izumi T, Ueki Y. Improvement of Precision by Introducing Vitality Degree tothe Height Measurement System using Stereo Vision [C]. SICE Annual Conference inSappoor, Hokkaido Institude of technology, Japan.2004:4~8.
[17]阮晓东,李世伦,诸葛良等.用立体视觉测量多自由度机械装置姿态的研究[J].中国机械工程,200011(5):571~573.
[18] Okada K, Inada M. Integration of Real-Time Binocular Stereo Vision andWhole Body Information for Dynamic Walking Navigation of Humanoid Robot [C].IEEE Conference on Multisensor Fusion and Integration for Intelligent Systems,2003:131~136.
[19]朱永光,孙政顺,赵南元.拟人机器人视觉系统的硬件结构设计[J].计算机工程与应用,2002,(9):114~119.
[20] Longuet-Higgins H C. A Computer Algorithm for Reconstructing a Scenefrom Two Projections [J]. Nature,1981(293):133~135.
[21]罗仕鉴,朱上上,孙守迁.人体测量技术的现状与发展趋势[J].人类工效学,2002,8(2):31~34.
[22] Polleleys M. Self-calibration and Metric3D Reconstruction from UncalibratedImage Sequences [D]. Ph.D.Thesis, Heverlee: Katholiek Universiteit Leuven,1999.
[23] Faugeras O D, Mourrain B. On the Geometry and Algebra on the Point andLine Correspondences between N Images [C]. Proc. International Conference onComputer Vision,1995:951~956.
[24] Faugeras O D, Papadopoulo T. A Nonlinear Method for Estimating theProjective Geometry of Three Views [C]. Proc. International Conference on ComputerVision,1998:477~484.
[25] Bougnoux S, Robert L. TotalCalib: A Fast and Reliable System for Off-lineCalibration of Image Sequences [C]. Proc. Compute Vision and Pattern Recognition,Demo Session,1997.
[26]管业鹏,童林夙,陈娜.基于双目立体视觉的偏转线圈测量方法研究[J].电子学报,2003,31(9):1382~1385.
[27] Pollefeys M, Van G L. Stratified Self-calibration with the Modulus Constraint[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1999:707~724.
[28] Cipolla R, Robertson D P, Boyer E G. Photobuilder-3D Models ofArchitectural Scenes from Uncalibrated Images [C]. In Proc. IEEE InternationalConference on Multimedia Computing and Systems. Firenze,1999(1):25~31.
[29] Shum H Y, Szeliski R, Baker S, etc.. Interative3D modeling from multipleimages using scene regularities [C]. In Proceedings of Fourth IEEE Workshop onApplication of Computer Vision.1998:234~235.
[30]张宏伟,张国雄,秦鹏等.双目视觉检测技术在自由曲面测量中的应用[J].机械工程学报,2004,40(7):110~113.
[31] Horn B K P. Relative Orientation [J]. International Journal of ComputerVision,1990(4):59~78.
[32] Horn B K P. Relative Orientation Revisited [J]. Journal of the Optical Societyof America,1991,8(10):1630~1638.
[33] Hartley R I. Euclidean Reconstruction from Uncalibrated Views [J].Applications of Invariance in Computer Vision, volume825of Lecture Notes inComputer Science, Springer-Verlag,1993:237~256.
[34] Faugeras O. What can be Seen in Three Dimensions with an UncalibratedStereo Rig?[C]. In Proceedings of the European Conference on Computer Vision. SantaMargherita L,1992:563~578.
[35] Maybank S J, Faugeras O D. A Theory of Self-calibration of a MovingCamera [J]. International Journal of Computer Vision,1992,8(2):123~151.
[36] Faugeras O D, Luong Q T, Maybank S J. Camera Self-calibration: Theory andExperiments [C]. In Proceedings of the European Conference on Computer Vision.Santa Margherita L.,1999:3321~3342.
[37] Huang T S, Netravali A N. Motion and Structure from FeatureCorrespondences: A Review [C]. Proc. of the IEEE,1994,82(2):252-268.
[38] Hartley R I. Estimation of Relative Camera Position for Uncalibrated Cameras
[C]. In Proceedings of the European Conference on Computer Vision. Santa MargheritaL.,1992:579~587.
[39] Zhang Z, Deriche R, Faugeras O D etc.. A Robust Technique for MatchingTwo Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry[J]. Artificial Intelligence,1995,75(1-2):87~120.
[40] Schaffalitzky F, Zisserman A, Hartley R I etc.. A Six Point Solution forStructure and Motion [C]. In Proceedings of the European Conference on ComputerVision.2000,Vol (1):632~648.
[41] Pollefeys M, Van Gool L. A Stratified Approach to Metric Self-calibration [C].In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Puerto Rico,1997:407~412.
[42] Pollefeys M, Van Gool L, Oosterlinck A. The Modulus Constraint: A NewConstraint for Self-calibration [C]. In Proceedings of the International Conference onPattern Recognition. Vienna, l996:349~353.
[43] Heyden A, Astrom K. Euclidean Reconstruction from Constant IntrinsicParameters [C]. In Proceedings of the International Conference on Pattern Recognition.Vienna,1996:339~343.
[44] Triggs B. Autocalibration and the Absolute Quadric [C]. In Proceedings of theIEEE Conference on Computer Vision and Pattern Recognition. Puerto Rico,1997:609~614.
[45] Heyden A, Astrom K. Euclidean Reconstruction from Image Sequences withVarying and Unknown Focal Length and Principal Point [C]. In Proceedings of theIEEE Conference on Computer Vision and Pattern Recognition. Puerto Rico,1997:438~443.
[46] Pollefeys M, Koch R, Van Gool L. Self-calibration and Metric Reconstructionin Spite of Varying and Unknown Internal Camera Parameters [C]. In Proceedings ofthe IEEE International Conference on Computer Vision. Bombay,1998:90~95.
[47] Manning R and Dyer C. Affine Calibration from Moving Objects [C]. In Proc.International Journal of Computer Vision.2001,Vol(1):494~500.
[48]祝海江.三维重建和摄像机标定技术研究[D].北京:中国科学院自动化研究所博士学位论文,2004.
[49] Zheng J Y. Acquiring3-d Models from a Sequence of Contours [J]. IEEETrans. Pattern Anal. Machine Intell.,1994,(16):163~178.
[50] Kanade T, Okutomi M, Nakahara T. A Multiple-baseline Method [C]. in Proc.DARPA Image Understanding Workshop.1992:409~426.
[51] Kanade T, Kang S B, Webb J, etc.. A Multibaseline Stereo System withActive Illumination and Real-time Image Acquisition [C]. in Proc. Int. Cont. ComputerVision.1995:88~93.
[52] Debevec P E, Taylor C J, Malik J. Modeling and Rendering Architecture fromPhotographs: A Hybrid Geometry and Image-based Approach [C]. In Proc. ComputerGraphics.1996:11~20.
[53] Martin W N, Aggarwal J K. Volumetric Descriptions of Objects fromMultiple Views [J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,1983,5(2):150~158.
[54] Kutulakos K N, Seitz S M. A Theory of Shape by Space Carving [J]. Int. J.Computer Vision,2000,38(3):1999~2187.
[55]王亚昕.基于序列图像的摄像机定标和三维重建的研究[D].北京:北京交通大学硕士学位论文,2004.
[56] Li R, Sclaroff S. Multi-scale3D Scene Flow from Binocular Stereo Sequences
[C]. In Preceedings of the IEEE Workshop on Moton and Video Computing.2005:147~153.
[57] Hom B K P. Shape from Shading: A Method for Obtaining the Shape of aSmooth Opaque Object from One View [D]. MIT: PhD thesis,1970.
[58] Bichsel M, Pentland A P. A Simple Algorithm for Shape from Shading [C].IEEE Proceedings of Computer Vision and Pattern Recognition.1992:459~465.
[59] Zhang R, Tsai P S, Cryer J. Shape from Shading: A Surrey [J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1999,21(8):690~706.
[60]张楠.基于图像序列重建三维物体的一种方法[D].大连:大连理工大学硕士学位论文,2005.
[61] Stone J V. Shape from Texture: a Computational Analysis [D]. University ofSussex:PhD thesis,1990.
[62] Brzakovic D, White B. Surface Orientation using Texture Gradient Derivedfrom Two Views of a Scene [C]. Proc.8th International Conference on PatternRecognition.1986:1045~1047.
[63] Wang S J, Zhuang Y, Zheng K Q, etc..3D Scene Reconstruction UsingPanoramic Laser Scanning and Monocular Vision [C]. In Proceedings of the8thWorldCongress on Intelligent Control and Automation. Jinan, China,2010,861~866.
[64] Yang R, Pollefeys M, Welch G. Dealing with Textureless Regions andSpecular Highlights: A Progressive Space Carving Scheme using a NovelPhoto-consistency Measure [C]. IEEE International Conference on Computer Vision.Piscataway, NJ, USA:2003:576~584.
[65]孟维亮.基于图像的多视图重建和纹理恢复[D].天津:天津大学硕士学位论文,2006.
[66] Shashua A. On Photometric Issues in3D Visual Recognition from a Single2D Image [J]. International Journal of Computer Vision,1997vol.21:99~122.
[67] Barnard S, Fischler M. Computational Stereo [J]. ACM Computer Suiveys,1982,14(4):553~572.
[68] Zhang Z Y. A Flexible Camera Calibration by Viewing a Plane fromUnknown Orientation [C]. The7thIEEE International Conference of Computer Vision.Corfu, Greece,1999:666~673.
[69] Maybank S J, Faugeras O. A Theory of Self-Calibration of a Moving Camera[J]. International Journal of Computer Vision,1992, vol.8:123~152.
[70]周彦.基于双目视觉的图像三维重建[D].中国海洋大学硕士学位论文,2008.
[71] Arnold R D. Local Context in Matching Edges for Stereo Vision.1978.
[72] Wei G Q, Gerd H. Intensity and Feature Based Stereo Matching by DisparityParameterization [C]. Sixth International Conference on Computer Vision,1998:1035~1040.
[73] Zhu Q, Wu B, Xu Z. Seed Point Selectiion Method for Triangle ConstrainedImage Matching Propagation [J]. IEEE Geoscience and Remote Sensing Letters,2006,3:207~211.
[74]李海超,张广军.一种基于角点引导的快速立体边缘匹配方法[J].北京航空航天大学学报,2007,33(5):557~560.
[75] Lowe D. Object Recognition from Local Scale-Invariant Features [C].Proceedings of the Seventh IEEE International Conference on Computer Vision.Kerkyra, Greece,1999:1150~1157.
[76] Bay H, Tuytelaars T, Van Gool L. SURF: Speeded Up Robust Features [C]. InProceedings of European Conference on Computer Vision.2006:404~417.
[77] Mikolajczyk K, String T T, Fp C S, etc.. A Comparison of Affine RegionDetectors [J]. International Journal of Computer Vision,2005,65(1-2):43~72.
[78]郑志刚.高精度摄像机标定和鲁棒立体匹配算法研究[D].中国科学技术大学博士学位论文,2008.
[79] Megyesi Z, Chetverikov D. Enhanced Surface Reconstruction from WideBaseline Images [C]. In Proceedings of the Second International Symposium on3DData Processing, Visualization and Transmission.2004:463~469.
[80] Radim S. Finding the Largest Unambiguous Component of Stereo Matching
[C]. In Proceedings of European Conference on Computer Vision.2002:900~914.
[81] Cech J, Sara R. Efficient Sampling of Disparity Space for Fast and AccurateMatching [C].2007International Conference on Computer Vision and PatternRecognition.2007:1~8.
[82] Hartley R, Zisserman A. Multiple View Geometry in Computer Vision [M].Cambridge University Press,2003.
[83]方德植,陈奕培.射影几何[M].北京:高等教育出版社,1983.
[84]章权兵.基于多视图的三维重构研究[D].安徽大学博士学位论文,2004.
[85]刘勇.基于非定标图象的三维重建方法研究[D].西安:西安电子科技大学大学博士学位论文,2001.
[86]于海雁.基于多视图几何的三维重建研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2007.
[87]李云翔.相机标定与三维重建技术研究[D].青岛:青岛大学硕士学位论文,2009.
[88] Rother C, Carlsson S. Linear Multi-view Reconstruction and CameraRecovery Using A Reference Plane [J]. International Journal of Computer Vision,2002,49(2/3):117~141.
[89] Peng K J, Chen X, Zhou D X, etc..3D Reconstruction Based on SIFT andHarris Feature Points [C].2009IEEE International Conference on Robotics andBiomimetics. Guilin, China,2009:960~964.
[90] Zhao J, Chang S, Men G.3D Reconstruction Based on the Matching Methodof GA [C]. Proceedings of the Ninth International Conference on Machine Learning andCybernetics. Qingdao, China,2010:1798~1801.
[91] Lowe D. Distinctive Image Features from Scale-Invariant Interest Points [J].International Journal of Computer Vision,2004,60(2):91~110.
[92] Harris C G, Stephens M. A Combined Corner and Edge Detector ［C］.Proceedings of the4th Alvey Vision Conference. Manchester, UK,1998:147~151.
[93] Fishler M A, Bolles R C. Random Sample Consensus, A Paradigm for ModelFitting with Applications to Image Analysis and Automated Cartography [J].Communications of ACM,1981,24(6):381~395.
[94]舒志龙,阮秋琦.快速对称多窗口正交三目立体匹配[J].计算机研究与发展,2001,38(10):1229~1235.
[95] Witkin A P. Scale-space Filtering [J]. International Joint Conference onArtificial Intelligence. Karlsruhe, Germany.1983:1019~1022.
[96] Koenderink J J. The Structure of Images [J]. Biological ybernetics,1984(50):363~396.
[97] Lindbeegr. Detecting Salient Blob-like Image Structures and Their Scaleswith a Cale-spaceprimal Sketch: A Method for Focus-of-attention [J]. InternationalJournal of Computer Vision,1993,11(3):283~318.
[98]王瑞.基于GPU的SIFT特征图像匹配算法研究与应用[D].长沙:国防科技大学硕士学位论文,2010.
[99] Luong Q T, Faugeras O. The Fundamental Matrix: Theory, Algorithms, andStability Analysis [J]. International Journal of Computer Vision,1996,17(1):43~75.
[100]唐丽.由手提相机获得的序列图像进行三维重建[D].西安:西安电子科技大学博士学位论文,2003:9~10.
[101] Mehrotra R, Nichani S. Corner Detection [J]. Pattern Recognition,1990,23(11):1223~1233.
[102] Wang H, Brady M. Realtime Corner Detection Algorithm for MotionEstimation [J]. Image and Vision Computing,1995,13(9):695~703.
[103] Sheu H T, Hu W C. A Rotationally Invariant Two Phase Scheme for CornerDetection [J]. Pattern Recognion,1996,29(5):819~828.
[104] Smith S M, Brady J M. SUSAN—A New Approach to Low Level ImageProcessing [J]. International Journal of Computer Vision,1997,23(1):45~78.
[105] Laganiere R. A Morphological Operator for Corner Detection [J]. PatternRecognition,1998,31(11):1643~1652.
[106] Zitova B, Flusser J. Image Registration Methods: A Survey [J]. Image andVision Computing,2003,21(11):977~1000.
[107] Tissainayagam D S. Assessing the Performance of Corner Detectors forPoint Feature Tracking Applications [J]. Image and Vision Computing.2004,22(8):663~679.
[108] Liu S, Zhao L, Li J, etc.. The Research of3D Reconstruction fromUncalibrated Image Sequences Combined with3D Models [C]. Proceedings of2008International conference on computer science and software engineering.2008:1117-1119.
[109] Micusik B, Kosecka J. Piecewise Planar City Modeling from Street ViewPanoramic Sequences [C]. In CVPR,2009:2906~2912.
[110] Pollefeys M et al. Detailed Real-time Urban3d Reconstruction from Video[J]. IJCV,2008,78(2-3):143~167.
[111] Tomasi C, Kanade T. Shape and Motion from Image Streams UnderOrthography: A Factorization Method[J]. International Journal of Computer Vision,1992,9(2):137~154.
[112] Poelman C, Kanade T. A Paraperspective Factorization Method for Shapeand Motion Recovery [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1997,19(3):580~593.
[113] Sturm P, Triggs B. A Factorization Based Algorithm for Multi-imageProjective Structure and Motion [C]. Proceedings of the4th European Conference onComputer Vision. Cambridge, England,1996:709~720.
[114]吴玲达,邓宝松,高宇,魏迎梅.基于长序列图像的三维重建技术研究[J].计算机应用研究.2007,24(5):314~317.
[115] Frahm J, Pollefeys M, Lazebnik S, et al.. Fast Robust Reconstruction ofLarge-Scale Environments [C].201044th Annual Conference on Information Scienceand Systems (CISS2010), USA,2010:1~6.
[116] Gallup D, Frahm J, Pollefeys M, et al.. Piecewise Planar and Non-planarStereo for Urban Scene Reconstruction [C].2010IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition(CVPR2010), USA,2010:1418~1425.
[117] Agarwal S, Snavely N, Simon I, et al.. Building Rome in a Day [C]. In ICCV,Japan,2009:72~79.
[118] Frahm J, Fite-Georgel P, Gallup D, et al.. Building Rome on a Cloudless Day
[C].11th European Conference on Computer Vision (ECCV2010), Greece,2010, v6314LNCS, n PART4, pp368~381.
[119] Wu T, Yeung S, Jia J, et al.. Quasi-Dense3D Reconstruction usingTensor-based Multiview Stereo [C]. Proceeding of the IEEE Computer SocietyConference on Computer Vision and Pattern Recognition (CVPR2010), USA,2010:1482~1489.
[120] Furekawa Y, Curless B, Steven M, et al.. Towards Internet-scale Multi-viewStereo [C]. Proceeding of the IEEE Computer Society Conference on Computer Visionand Pattern Recognition (CVPR2010), USA,2010:1434~1441.
[121] Avidan, Shuahua A. Novel View Synthesis by Cascading Trilinear Tensors[J]. IEEE Transaction on Visualization and Computer Graphics,1998,4(3):11~12.
[122] Besl P J, Mckay H D. A Method for Registration of3-D Shapes [J].Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239~256.
[123] Triggs B, McLauchlan P, Hartley R, et al.. Bundle Adjustment–A ModernSynthesis, Vision Algorithms: Theory and Practice [J]. Springer–Verlag,2000:298~372.
[124] Furukawa Y, Ponce J. Accurate, Dense, and Robust Multi-View Steriopsis[J]. In: PAMI09,2009:1~8.
[125] Hartley R, Zisserman A.计算机视觉中的多视图几何[M].韦穗,等译.合肥:安徽大学出版社:2002,8.
[126] Triggs B. Factorization Methods for Projective Sturcutre and Motion [C].Proceedings of Computer Vision and Pattern Recognition. San Francisco, Caliofornia，USA,1996:845~851.
[127] Heyden A, Berthilsson R, Sparr G. An Iterative Factorization Method forProjective Sturcutre and Motion from Image Sequences[J]. Image and VisionComputing,1999,17(13):981~991.
[128]陈付幸.基于非定标图像序列的三维重建关键技术研究[D].长沙:国防科技大学博士学位论文,2005.
[129]方磊.基于特征的图像序列三维场景重建技术研究[D].武汉:华中科技大学博士学位论文,2006.
[130]曹智清,石教英,张世明等.基于序列图像建模的多视图模型合并策略[J].计算机研究与发展,2005,42(9):1633~1639.
[131]李世飞,王平,沈振康.迭代最近点算法研究进展[J].信号处理,2009,25(10):1582~1588.
[132] Lhuillier M, Quan L. Match Propagation for Image-Based Modeling andRendering [J]. IEEE Transactions on Pattern Analysis and Machine Inteligence,2002,Vol.24. No.8:1140~1146.
[133] Falkenhagen L. Depth Estimation from Stereoscopic Image Pairs AssumingPiecewise Continuous Surfaces [C]. In European Workshopon Combined RealandSynhtetic Image Processing for Broadcast and Video Productions. Hamburg, Gemran,1994:115~127.
[134] Cox I, Hingorani S, Rao S. A Mxaimum Likelihood Stereo Algorithm [J].Computer Vision and Image Understanding,1996,63(3):542~567.
[135] Ohta Y, Kanade T, Stereo by Intra-and Inter-Scanline Search Using Dynamicprogramming [J]. EIEE Trans. Pattern Analysis and Machine Intelligence,1985,7(2):139~154.
[136] Okutomi M, Kanade T. A Locally Adaptive Window for Signal Processing[J]. International Journal of Computer Vision.1992,7:143~162.
[137] Roy S, Meunier J, Cox I. Cylindrical Rectification to Minimize EpipolarDistortion [C]. In IEEE Conference on Computer Vision and Pattern Recognition.1997:393~399.
[138] Lhuillier M, Quan L. Edge-Constrained Joint View Triangulation for ImageInterpolation [C]. In Proceedings of the Conference on Computer Vision and PatternRecognition. HiltonHead, South Carolina,2000:218~224.
[139] Scharstein D, Szeliski R. A Taxonomy and Evaluation of Dense Two-FrameStereo Correspondence Algorithms [J]. International Journal of Computer Vision,2002,47(1-3):7~42.
[140]葛亮.图像建模中立体匹配问题的研究[D].重庆:重庆大学博士学位论文,2009.
[141]王海彬.地面自主机器人视觉导航三维重建算法研究[D].长沙:国防科技大学硕士学位论文,2006.
[142]梁志敏.遥控焊接机器人任务空间的三维重建研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2008.
[143] Strecha C,“Multi-view evaluation.”[Online]. Available:http://cvlab.epfl.ch/~strecha/multiview.
[144]史利民,郭复胜,胡占义.利用空间几何信息的改进PMVS算法[J].自动化学报,2011,37(5):560~568.
[145] Bishop R. A Survey of Intelligent Vehicle Applications Worldwide [C]. In:Proceedings of the IEEE Intelligent Vehicles Symposium2000. Dearbom, MI, USA,2000:25~30.
[146] Tsuji M, Shirato R, Furusho H. Estimation of Road Configuration andVehicle Attitude by Lane Detection for a Lane-keeping System [C]. In: SAE2001World Congress Intelligent Vehicle Inititaive(IVI) Vehicle Navigation Systems (PartA&B)[C]. Detroit, Michigan, USA,2001:45~51.
[147] Rosito J C, Roberto K C. A Lane Departure Warning System Using LateralOffset with Uncalibrated Camera [C], IEEE Conference on Intelligent TransportationSystems. Vienna, Austria,2005:102~107.
[148]余厚云,张为公.基于动态感兴趣区域的车道线识别与跟踪[J].工业仪表与自动化装置,2009年第5期:103~106.
[149]叶庆,赵明辉,李菲等.夜间车道线检测与跟踪算法研究[J].现代电子技术,2009年第13期:155~158.
[150]于兵,张为公,龚宗洋.基于机器视觉的车道偏离报警系统[J].东南大学学报(自然科学版),2009,39(5):928~932.
[151]余厚云,张为公.基于摄像机模型的运动车辆车道偏离检测[J].东南大学学报(自然科学版),2009,39(5):933~936.
[152] Bertozzi M, Broggi A. Gold: A Parallel Real-Time Stereo Vision System forGeneric Obstacle and Lane Detection [J]. IEEE Transactions on Image Processing,1998,7(1):62~81.
[153]刘洁,黄斌.单目视觉车道偏离报警系统[J].电子产品世界,2007(03)：128~130.
[154]卢卫娜,史忠科.基于单目视觉的车道线和道路边界同步检测[J].传感技术学报,2007,20(5):1171~1175.
[155] Hough PVC. A Method and Means for Recognizing Complex Patterns [P].US Patent,1962.
[156]姜大志.计算机视觉中三维重构的研究与应用[D].南京:南京航空航天大学博士学位论文,2001.
[157]隋婧,金伟其.双目立体视觉技术的实现及其进展[J].电子技术应用,2004:4~6.
[158]刘钢,彭群生,鲍虎军.基于多幅图像的场景交互建模系统[J].计算机辅助设计与图形学学报,2004,16(10):1419~1424.
[159]山海涛,马淑宇,郝向阳等.一种基于Hough变换的对极几何稳健估计算法[J].测绘科学技术学报,2008,25(3):202~205.
[160]唐丽,吴成柯,刘侍刚等.基于区域增长的立体像对稠密匹配算法[J].计算机学报,2004,27(7):936~943.
[161]刘宇斌.一种分阶段的高精度亚像素特征点提取方法[J].南华大学学报,2006:54~57.
[162]彭科举,陈新,周东翔,刘云辉.基于单目视觉的车辆行驶方向检测及误差分析[J].信号处理,2010,26(10):1560-1566.