基于多视图几何的三维重建研究
|
摘要
在交通事故现场勘查中,应用计算机视觉测量系统通过图像之间对应点的关系可以恢复目标点的三维坐标,从而进行事故现场的事后测量和事故场景的重建。但是,大多数计算机视觉系统的三维重建只是度量重建。要想恢复出真正的欧氏重建,往往需要在现场放置尺度标杆或标定模板。而基于定焦相机构成的双目视觉系统虽然能够实现真正意义上的欧氏重建,但是由于焦距固定,使得拍摄场景范围受限。这在很大程度上降低了系统应用的灵活性,同时测量精度低或测量范围也都受到了很大的影响。
针对这一问题,本文对计算机视觉的多视图三维重建技术进行了研究。通过对摄像机自标定与三维重建技术的深入研究,将传统标定技术与自标定技术相结合,应用到变焦双目系统,从而解决现有计算机视觉测量系统中的测量精度与系统应用的灵活性问题。
首先,论文对固定内参数情况下的线性自标定技术进行了研究,针对现有自标定技术中绝对二次曲线的像(IAC)或二次曲线的对偶像(DIAC)矩阵必须正定这一问题,提出了新的分层自标定方法。算法利用摄像机内参数可以估计这一特点,直接对内参数矩阵进行了标定,避开了IAC或DIAC的正定问题。同时采用遗传算法进行参数求解,解决了一般算法中需要精确初值的问题。为了验证算法的性能,论文设计了大量的仿真实验和真实图像实验。实验结果表明,算法对参数标定的精度较高,在一定的噪声条件下,算法具有可行性。
大多数自标定算法中只考虑了摄像机的线性投影模型,但是镜头畸变带来的图像非线性失真常常是基于图像测量中不可忽略的因素。而对于非线性模型的标定目前都是采用网格模板通过离线标定的方法。但是对于变焦系统,畸变参数随着焦距的变化而改变,这就要求我们必须采用在线标定的方法。本文针对这种情况,利用Hough变换检测直线,将直线与Canny算子检测的边缘之间存在的误差作为畸变误差,从而实现了固定内参数下的摄像机非线性投影模型的在线标定。
为了获得系统应用的灵活性,本文进一步对变焦相机的自标定技术进行了研究。通过对Kruppa方程的推导,实现了两视图焦距的标定。在理论上证实了从两幅图像也可以实现焦距的标定。实验结果表明,两视图可以实现不同焦距的标定,但是其结果对噪声较为敏感,因此一般采用三幅以上视图标定摄像机焦距。
在单目视觉系统研究基础上,论文对双目视觉系统的三维重建技术和自标定技术也进行了研究,并提出了将传统标定方法与自标定方法相结合的变焦双目视觉系统,即采用传统标定方法进行主点等内外参数标定,而采用自标定技术进行焦距和畸变参数标定的双目视觉系统。在此过程中,为了提高系统的标定精度,论文提出了将立体对运动前后的变换矩阵引入到匹配过程作为匹配约束的方法,提高了变换矩阵的求解精度,同时也降低了误匹配概率。这一系统有效地结合了传统标定与自标定的优点,避免了测量过程中使用标定模板的问题,在确保系统精度的前提下提高了系统应用的灵活性,为交通事故现场勘查提供了更多的方便。
The computer vision measurement system can be used to investigate the traffic accident later and reconstruct the scence. The 3D structure of the objects can be recovered from the correspondences of image pairs. However, most of computer vision systems can only get metric reconstruction, and the Euclidean reconstruction is necessary for our application. So staff gauge or calibration temple are placed on locale to achieve it in these systems which will affect the accuracy and bring inconvience. And if we use stereo system with constant focal, the Euclidean reconstruct can be obtained, while the measurement scope is limited. This debases the flexibility of the system, and the measurement accuracy and scope are all affected.
In this paper, the 3D reconstruction from multiple views is researched to solve this problem. Based on the researching of 3D reconstruction and self-calibration, the technique which integrates the traditional calibration and self-calibration is applied to varying focal stereo rig.
Firstly, the linear self-calibration using constant intrinsic parameter is researched. A novel stratified self-calibration method is presented in this paper to solve the problem that the image of absolute conic (IAC) or dual image of absolute conic (DIAC) must be positive definite for self-calibration techniques. Because the intrinsic can be estimated, so it is possible to avoid the positive definite problem with optimizing the intrinsic parameters directly. The genetic algorithm is used to get the intrinsic parameters which need not initial values. The performance of method is confirmed by a lot of synthetic and real images. The results show that the algorithm has good accuracy and is practicable.
Common self-calibration use linear camera model, but the distortion from lens can not be ignored for high accuracy measurement. The grid template is used to calibrate the linear model generally. But this method is not usable if we use vary focal system. So a calibration method on line is presented in this paper. Hough transform is used to detect lines, and canny algorithm is applied to find edges and connect edges. Therefore, the difference between the edges and lines is the distortion which can help us rectify the distort image.
Because of the need of system, the self-calibration on varying focal is researched. The Kruppa equation is deduced to calibrate the focal lengths from two views. The method is verified by theory and real test result. But the method is sensitivity to image noise, so the three or more images are advised.
Based on the research of single camera system, the 3D reconstruction and self-calibration of stereo rig are also studied. A stereo rig system with varying focal cameras is presented which integrates traditional calibration and self-calibration. Principal points of the cameras and other parameters are calibrated by traditional method, and only focal length and distortion parameters are calibrated by self-calibration. And the transform matrix restriction is introduced to improve on images matching during this process. This method can depress the ratio of error match and get accurate transform matrix. This system combines the advantages of traditional calibration and self-calibration method and decrease the inconvenience for using template. Good accuracy and flexibleness can be acquired for traffic accident investigation.
针对这一问题,本文对计算机视觉的多视图三维重建技术进行了研究。通过对摄像机自标定与三维重建技术的深入研究,将传统标定技术与自标定技术相结合,应用到变焦双目系统,从而解决现有计算机视觉测量系统中的测量精度与系统应用的灵活性问题。
首先,论文对固定内参数情况下的线性自标定技术进行了研究,针对现有自标定技术中绝对二次曲线的像(IAC)或二次曲线的对偶像(DIAC)矩阵必须正定这一问题,提出了新的分层自标定方法。算法利用摄像机内参数可以估计这一特点,直接对内参数矩阵进行了标定,避开了IAC或DIAC的正定问题。同时采用遗传算法进行参数求解,解决了一般算法中需要精确初值的问题。为了验证算法的性能,论文设计了大量的仿真实验和真实图像实验。实验结果表明,算法对参数标定的精度较高,在一定的噪声条件下,算法具有可行性。
大多数自标定算法中只考虑了摄像机的线性投影模型,但是镜头畸变带来的图像非线性失真常常是基于图像测量中不可忽略的因素。而对于非线性模型的标定目前都是采用网格模板通过离线标定的方法。但是对于变焦系统,畸变参数随着焦距的变化而改变,这就要求我们必须采用在线标定的方法。本文针对这种情况,利用Hough变换检测直线,将直线与Canny算子检测的边缘之间存在的误差作为畸变误差,从而实现了固定内参数下的摄像机非线性投影模型的在线标定。
为了获得系统应用的灵活性,本文进一步对变焦相机的自标定技术进行了研究。通过对Kruppa方程的推导,实现了两视图焦距的标定。在理论上证实了从两幅图像也可以实现焦距的标定。实验结果表明,两视图可以实现不同焦距的标定,但是其结果对噪声较为敏感,因此一般采用三幅以上视图标定摄像机焦距。
在单目视觉系统研究基础上,论文对双目视觉系统的三维重建技术和自标定技术也进行了研究,并提出了将传统标定方法与自标定方法相结合的变焦双目视觉系统,即采用传统标定方法进行主点等内外参数标定,而采用自标定技术进行焦距和畸变参数标定的双目视觉系统。在此过程中,为了提高系统的标定精度,论文提出了将立体对运动前后的变换矩阵引入到匹配过程作为匹配约束的方法,提高了变换矩阵的求解精度,同时也降低了误匹配概率。这一系统有效地结合了传统标定与自标定的优点,避免了测量过程中使用标定模板的问题,在确保系统精度的前提下提高了系统应用的灵活性,为交通事故现场勘查提供了更多的方便。
The computer vision measurement system can be used to investigate the traffic accident later and reconstruct the scence. The 3D structure of the objects can be recovered from the correspondences of image pairs. However, most of computer vision systems can only get metric reconstruction, and the Euclidean reconstruction is necessary for our application. So staff gauge or calibration temple are placed on locale to achieve it in these systems which will affect the accuracy and bring inconvience. And if we use stereo system with constant focal, the Euclidean reconstruct can be obtained, while the measurement scope is limited. This debases the flexibility of the system, and the measurement accuracy and scope are all affected.
In this paper, the 3D reconstruction from multiple views is researched to solve this problem. Based on the researching of 3D reconstruction and self-calibration, the technique which integrates the traditional calibration and self-calibration is applied to varying focal stereo rig.
Firstly, the linear self-calibration using constant intrinsic parameter is researched. A novel stratified self-calibration method is presented in this paper to solve the problem that the image of absolute conic (IAC) or dual image of absolute conic (DIAC) must be positive definite for self-calibration techniques. Because the intrinsic can be estimated, so it is possible to avoid the positive definite problem with optimizing the intrinsic parameters directly. The genetic algorithm is used to get the intrinsic parameters which need not initial values. The performance of method is confirmed by a lot of synthetic and real images. The results show that the algorithm has good accuracy and is practicable.
Common self-calibration use linear camera model, but the distortion from lens can not be ignored for high accuracy measurement. The grid template is used to calibrate the linear model generally. But this method is not usable if we use vary focal system. So a calibration method on line is presented in this paper. Hough transform is used to detect lines, and canny algorithm is applied to find edges and connect edges. Therefore, the difference between the edges and lines is the distortion which can help us rectify the distort image.
Because of the need of system, the self-calibration on varying focal is researched. The Kruppa equation is deduced to calibrate the focal lengths from two views. The method is verified by theory and real test result. But the method is sensitivity to image noise, so the three or more images are advised.
Based on the research of single camera system, the 3D reconstruction and self-calibration of stereo rig are also studied. A stereo rig system with varying focal cameras is presented which integrates traditional calibration and self-calibration. Principal points of the cameras and other parameters are calibrated by traditional method, and only focal length and distortion parameters are calibrated by self-calibration. And the transform matrix restriction is introduced to improve on images matching during this process. This method can depress the ratio of error match and get accurate transform matrix. This system combines the advantages of traditional calibration and self-calibration method and decrease the inconvenience for using template. Good accuracy and flexibleness can be acquired for traffic accident investigation.
引文
1 2005 年全国道路交通事故情况. www.stats.gov.cn
2 Sanjab K Ghost. Photogrammetry for Police Use: Experience in Japan. Photogrammetric Engineering and Remote Sensing. 1980,(3):46~57
3 John F. Kerkhoff. Photographic Techniques for Accident Reconstruction. SAE Paper850248,1985:145~158
4 J. Rolly Kinney, Bill Magedanz. TRANS4 – A Traffic Accident Photogrammetric System, Description of the System and Its Inherent Errors. SAE Paper. 861417,1986:1~8
5 Wesley D. Grimes, Charles H. Culley, and J. Robert Cromack. Field Application of Photogrammetric Analysis Techniques: Applications of the FOTOGRAM Program. SAE Paper 861418,1986:1~7
6 鲁光泉,李一兵. 基于普通数码相机的交通事故摄影测量技术及其研究进展. 交通运输工程与信息学报. 2005,(9):63~67
7 马颂德,张正友.计算机视觉.北京:科学出版社,1998:7~10
8 Zhang Z. Flexible camera calibration by viewing a plane from unknown orientations. Proceedings of the 7th International Conference on Computer Vision. Greece: Corfu, 1999: 666~673
9 Meng X Q ,Li H ,Hu Z Y. A new camera calibration technique based on circular points. Proceedings of British Machine Vision Conference. UK: Bristol, 2001: 496~505
10 吴福朝,王光辉,胡占义. 由矩形确定摄像机内参数与位置的线性方法.软件学报. 2003,(03):703~712
11 Tsai R. An efficient and accurate camera calibration technique for 3D machine vision. Proceedings of Computer Vision and Pattern Recognition. USA: Miami Beach, Fl, 1986:364~374
12 Ma S D. A self-calibration technique for active vision system. IEEE Transactions on Robot Automation , 1996 , 12(1) :114~120
13 R.I.Hartley. Self-calibration from multiple views with a rotating camera. European Conference on Computer Vision.1994:471~478
14 W.Triggs. Autocalibration from planar scenes. 5th European Conference onComputer Vision,1999:278~284
15 Faugeras O , Luong Q T , Maybank S. Camera self-calibration: Theory and experiments. Proceedings of the 2nd European Conference on Computer Vision, Italy, 1992: 321~334
16 Maybank S , Faugeras O. A theory of self-calibration of a moving camera. International Journal of Computer Vision , 1992 , 8 (2) :123~151
17 Richard Hartley, Fredrik Kahl.Critical Configurations for Projective Reconstruction from Multiple Views.International Journal of Computer Vision. 2007, 71(1):5~47
18 Hartley R. Projective reconstruction from line correspondences. Proceedings of Computer Vision and Pattern Recognition. Seattle : WA , 1994: 103~109
19 Beardsley P , Zisserman A , Murray D. Sequential update of projective and affine structure from motion. International Journal of Computer Vision , 1997 , 23(3) :235~259
20 Hung, Y. Projective Reconstruction from Multiple Views with Minimization of 2D Reprojection Error. International Journal of Computer Vision, 2006(3):305~317
21 Anders Heyden, Fredrik Kahl. Direct Affine Reconstruction.Proc. International Conference on Pattern Recognition. Barcelona, Spain, 2000:885~888
22 ParHammarstedt, Fredrik Kahl, Anders Heyden.Affine Reconstruction from Translational Motion under Various Autocalibration Constraints. Journal of Mathematical Imaging and Vision, 2006, (2):245~257
23 P. Hammarstedt, F.Kahl, A.Heyden. Affine Structure from Translational Motion with Varying and Unknown Focal Length. Proc. International Conference on Pattern Recognition, Cambridge, UK, 2004:120~123
24 P.Hammarstedt, F.Kahl, A.Heyden. Affine Structure from Translational Motion in Image Sequences. Proc. Scandinavian Conference on Image Analysis, Goteborg, Sweden, 2003:387~394
25 Fredrik Kahl, Didier Henrion.Globally Optimal Estimates for Geometric Reconstruction Problems.International Journal of Computer Vision, 2007 (1):3~15
26 Sameer Agarwal, Manmohan Chandraker.Practical Global Optimization forMultiview Geometry. Proc. European Conference on Computer Vision, Graz, Austria, 2006:592~605
27 Fredrik Kahl, Didier Henrion.Globally Optimal Estimates for Geometric Reconstruction Problems. Proc. International Conference on Computer Vision, Beijing, China, 2005:978~985
28 Ma Y, Vidal B , Kosecka J , Sastry S. Kruppa equation revisited: Its renormalization and degeneracy , ECCV’00 , Springer-Verlag ,2000: 561~577
29 Hartley R. Euclidean reconstruction and invariants from multiple images. IEEE Transactions on Pattern Analysis and Machine Intel ligence, 1994, 16(10):1036~1041
30 Triggs B. Auto-calibration and the absolute quadric. Proceedings of Computer Vision and Pattern Recognition , 1997: 609~614
31 Pollefeys M, Van Gool L , Oosterlinck A. The modulus constraint: A new constraint for self-calibration. Proceedings of International Conference of Pattern Recognition , Vienna , 1996:349~353
32 Heyden A , Sturm K. Euclidean reconstruction from image sequences with varying and unknown focal length and principal point .Proceedings of Computer Vision and Pattern Recognition , 1997:438~443
33 Pollefeys M, Koch R , Van Gool L. Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters. Proceedings of the 6th International Conference on Computer Vision. India ,1998:90~95
34 Hartley R , Zisserman A. Multiple View Geometry in Computer Vision. Cambridge : Cambridge University Press , 2003:112~135
35 孟晓桥,胡占义. 摄相机自标定方法的研究与进展. 自动化学报, 2003, 29(1):110~124
36 孙凤梅,吴福朝. 由平行平面的投影确定无穷远平面的单应矩阵. 软件学报, 2003,14(5):936~946
37 雷成,胡占义. 一种新的基于 Kruppa 方程的摄像机自标定方法. 计算机学报, 2003,5: 1130~1139
38 Lei C , Wu F C ,Hu Z Y. Kruppa equations and camera self-calibration. Acta Automatica Sinica , 2001 , 27(5) :621~630
39 Wexler, Y. , Fitzgibbon, A. and Zisserman, A. Learning epipolar geometry from image sequences. Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition, 2003:209~225
40 Xu G, Zhang Z. Epipolar Geometry in Stereo, Motion and Object Recognition: A Unified Approach. Kluwer Acamdemic Publisher , 1996
41 Luong Q, Faugeras O. The fundamental matrix: Theory, algorithms , and stability analysis. International Journal of Computer Vision , 1996 , 17(1) :43~76
42 Zeller C, Faugeras O. Camera self-calibration from video sequences : The Kruppa equations revisited. Research Report 2793 , INRIA Sophia-Antipolis , France , 1996:1~35
43 Pollefeys M. Self-calibration and Metric 3D Reconstruction from Uncalibrated Image Sequences. Ph.D. thesisKatholieke Universiteit Leuven , 1999:45~58
44 Enciso R , Vieville T. Experimentally self2calibration fromfour views. In : Proceedings of 1995 International Conference on Image Analysis and Processing. Italy , San Remo , 1995
45 Hartley R. Extracting of focal lengths from the fundamental matrix. GE internal report , G. E. CRD , Schenectady , NY, 1993
46 Heyden A , Sturm K. Euclidean reconstruction from constant intrinsic parameters. Proceedings of International Conference of Pattern Recognition , Vienna , 1996: 339~343
47 Pollefeys M, Van Gool L. Self-calibration from the absolute conic on the plane at infinity. Proceedings of Computer Analysis of Images and Patterns , Lecture Notes in Computer Science , Spring-Verlag , 1997 ,1296: 175~182
48 Sturm P. Self-calibration of a moving camera by precalibration. Proceedings of British Machine Vision Conference. Scotland:Edinburgh, 1996: 675~684
49 R.I.Hartley. The cunbic rational polynomial camera model. Proc. DARPA Image Understanding Workshop.1997:649~653
50 Heyden A. Flexible calibration: Minimal cases for autocalibration. Proceedings of the 7th International Conference on Computer Vision, Greece , 1999. 350～355
51 李波,王祥凤,李本山. 基于单幅图像的三维重建技术. 信息与电子工程. 2006,4(2):129~133
52 A. Criminisi. Accurate visual metrology from single and multiple images.Springer Press. 2001:201~240
53 Luong Q, Faugeras O. The fundamental matrix: Theory, algorithms , and stability analysis. International Journal of Computer Vision, 1996, 17(1): 43~76
54 Hartley R. Self-calibration of stationary cameras. International Journal of Computer Vision , 1997 , 22 (1) :5~23
55 Ma S D. A self-calibration technique for active vision system. IEEE Transactions on Robot Automation , 1996 , 12(1) :114~120
56 Hartley R. A linear method for reconstruction from points and lines. Proceedings of the 5th International Conference on Computer Vision. Boston : MA ,1995:882~887
57 Werner, T. and Zisserman, A. New Techniques for Automated Architecture Reconstruction from Photographs. Proceedings of the 7th European Conference on Computer Vision, Copenhagen, Denmark, 2002:541~555
58 Hartley, R. I. and Schaffalitzky, F. Reconstruction from projections using Grassmann tensors. Proceedings of the 8th European Conference on Computer Vision, Prague, Czech Republic, 2004:363~375
59 于起峰. 基于图像的精密测量与运动测量.科学出版社.2002:35~37
60 D. E. Goldberg. Genetic Algorithms : in Search Optimization &Machine Learning. Addison-Weslev Publishing Company Inc, 1989:32~47
61 S. C. Ng, S. H. Leung, C. Y. Chung. The Genetic Search Approach : A New Learning Algorithm for Adaptive IIR Filtering . IEEE Signal Processing Magazine. 1996, 13(6):38~46
62 陈小平 , 于盛林 . 实数遗传算法交叉策略的改进 . 电子学报 . 2003, 31(1):71~74
63 Tomasi and T.Kanade. Shape and motion from image streams under orthography: a factorization approach. International Journal of Computer Vision. 1992(2):137~154
64 P. Sturm, W. Triggs. A Factorization Based Algorithm for Multi-image Projective Structure and Motion. In Proc. European Conference on Computer Vision, 1996:709~720.
65 L. Quan. Two-way ambiguity in 2d projective reconstruction from three uncalibrated 1d images. IEEE Transactions on Pattern Analysis and MachineIntelligence, 2001,23(2):212~216
66 王小平,曹立明. 遗传算法——理论、应用与软件实现. 西安交通大学出版社,2002:21~25
67 John Canny. Member. IEEE. A Computational Approach to Edge Detection. IEEE Trans. Pattern Analysis and Machine Intelligence. 1986,(11):679~697
68 贾云得. 机器视觉. 北京科学出版社,2000:97~100
69 杨绍清,贾传荧. 基于模糊判决的图像边缘连接. 光学技术, 2002, 28(2): 108~109.
70 Nevatia R, Babuk R. Linear Feature Extraction and Description .Computer Graphics and Image Processing, 1980, 13(2): 257-269.
71 L. Quan, R. Mohr. Determining perspective structures using hierarchical Hough transform. Pattern Recognition Letter. 1998, (9):279~286
72 L.Pires, P.De Smet, I.Bruyland. Line extraction with the use of an automatic gradient threshold technique and the Hough Transform. International Conference on Image Processing.Vancouver,IEEE,2000:909-912
73 C.Galambos, J. Kitter, J.Matas. Gradient based progressive probabilistic Hough Transform. Proceedings of Image and Signal Processing. IEEE, 2001, (3):158~165.
74 Faugeras O. What can be seen in the three dimensions with an uncalibrated stereo rig Proceedings of the 2nd European Conference on Computer Vision, Italy , 1992: 563~578
75 Zhang Z , Luong QT , Faugeras O. Motion of an uncalibrated stereo rig: Self-calibration and metric reconstruction , Research Report2079 , INRIA Sophia-Antipolis , France , 1993:103~113
76 R.Horaud. Selfcalibration and euclidean reconstruction using motions of a stereo rig. Proceedings of International Conference on Computer Vision, Bombay, India, 1998: 96～106
77 A. Zisserman, P. A. Beardsley, and I. D. Reid. Metric cali- bration of a stereo rig. In Proc. IEEE Workshop on Repre- sentations of Visual Scenes, Boston, 1995: 93~100.
78 Fadi Dornaika and Chi-kit Ronald Chung. Stereo Geometry From 3-D Ego-Motion Streams. IEEE Transaction on systems, man and cybernetics, 2003, (3): 308~323
79 P.Sturm. Critical motion sequences for monocular self-calibration and uncalibrated Euclidean reconstruction. Proceedings of Computer Vision and Pattern Recognition. USA: Puerto Rico , 2000:1100~1105
80 Faugeras O., Mourrain B. On the geometry and algebra of point and line correspondences between n images. Proceedings of the 5th International Conference on Computer Vision. Boston : MA , 1995:951~962
81 Oskarsson, M., Zisserman, A. and Astrom, K. Minimal projective reconstruction for combinations of points and lines in three views. Image and Vision Computing, 2004:777~785
82 H.C.Longuet-Higgins. A computer algorithm for reconstructing a scene from two projections. Nature,1981(9):133~135
83 R.Hartley. Camera calibration and the search for infinity. Proceedings of the 7th International Conference on Computer Vision ,Greece , 1999:510~517
84 Pollefeys M, Van Gool L , Proesmans M. Euclidean 3D reconstruction from image sequences with variable focal lengths. Proceedings of the 4th European Conference on Computer Vision , UK, Cambridge , 1996: 31~42
85 Hartley R. In defense of the eight-point algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence , 1997 , 19 (6): 580~593
86 Zhengyou Zhang. A new multistage approach to motion and structure estimation by gradually enforcing geometric constrains. Computer vision ACCV’98, 1998:567~574
87 Charlie Rothwell,Gabriella Csurka. Acomparison of projective reconstruction methods for pairs of views. Computer Vision and Image Understanding. 1997, 68(1):37~58
88 Hartley R, Gupta R , Chang T. Stereo from uncalibrated cameras. Proceedings of Computer Vision and Pattern Recognition ,1992:761~764
89 Torr P, Zisserman A. Robust computation and parameterization of multiple view relations. Proceedings of the 6th International Conference on Computer Vision , India , 2000:727~732
90 Ma Y, Kosecka J, Huang K. Rank deficiency condition of the multiple-view matrix for mixed point and line features.Proceedings of the 5th Asian Conference on Computer Vision. Australia : Melbourne , 2002: 338~341
91 Quan L. Uncalibrated 1D projective camera and 3D affine reconstruction oflines. Proceedings of Computer Vision and Pattern Recognition , USA , 1997: 60~65
92 Quan L. Self-calibration of an affine camera from multiple views. International Journal of Computer Vision , 1996 , 19(1):93~110
93 Luong Q.T., Vieville T. Canonic representation for the geometry of multiple projective views. Proceedings of the 3rd European Conference on Computer Vision, Sweden, 1994: 589~600
94 M. Pollefeys, R. Koch, M. Vergauwen, L. Van Gool. Automated reconstruction of 3D scenes from sequences of images, ISPRS Journal of Photogrammetry and Remote Sensing 2000 ,4 (55): 251~267
95 R. Koch, M. Pollefeys, L. Van Gool, Realistic surface reconstruction of 3D scenes from uncalibrated image sequences, Journal Visualization and Computer Animation, 2000,(11): 115~127
96 Beardsley P , Zisserman A , Murray D. Sequential update of projective and affine structure from motion. International Journal of Computer Vision, 1997 , 23(3) :235~259
97 Schaffalitzky, F. Grouping, Matching and Reconstruction in Multiple View Geometry, PhD thesis , 2002:79~87
98 Mundy J, Zisserman A. Geometric Invariance in Computer Vision. Massachusetts: Cambridge , MIT Press , 1992:105~119
99 Zhang Zhengyou. A Robust Technique for Matching Two Uncalibrated Images through the Recovery of the Unknown Epipolar Geometry. INRIA.1994:18~33
100 Sun D. M, A Robust Point Matching Algorithm Based on Deterministic Annealing. Journal of Computers, 2002,(6):606~611
101 Schimid. Matching by Local Invariants.INRIA.1995:8~22
102 Yuan C. Hsieh, David M. Mckeown. Performance Evaluation of Scene Registration and Stereo Matching for Cartographic Feature Extraction. IEEE Trans.1992, (l14):21~28
103 M. A. Fischler, R. C. Bolles. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Comm. of the ACM, 1981,(24): 381~395
104 Ma Y, Soatto S, Kosecka J, Sastry S. Euclidean reconstruction andreprojection up to subgroups. Proceedings of the 7th International Conference on Computer Vision , Greece , 2000: 773~780
105 M. Pollefeys and L. Van Gool. Virtualising the 3D Real World: Automatic Method for the Acquisition of Detailed 3D Models from Image Sequences, GIM International, 2000, 4(14): 12~15
106 Moons T, Van Gool L, Proesmans M, Pauwels E. Affine reconstruction from perspective image pairs with a relative object-camera translation in between. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(1):77～83
2 Sanjab K Ghost. Photogrammetry for Police Use: Experience in Japan. Photogrammetric Engineering and Remote Sensing. 1980,(3):46~57
3 John F. Kerkhoff. Photographic Techniques for Accident Reconstruction. SAE Paper850248,1985:145~158
4 J. Rolly Kinney, Bill Magedanz. TRANS4 – A Traffic Accident Photogrammetric System, Description of the System and Its Inherent Errors. SAE Paper. 861417,1986:1~8
5 Wesley D. Grimes, Charles H. Culley, and J. Robert Cromack. Field Application of Photogrammetric Analysis Techniques: Applications of the FOTOGRAM Program. SAE Paper 861418,1986:1~7
6 鲁光泉,李一兵. 基于普通数码相机的交通事故摄影测量技术及其研究进展. 交通运输工程与信息学报. 2005,(9):63~67
7 马颂德,张正友.计算机视觉.北京:科学出版社,1998:7~10
8 Zhang Z. Flexible camera calibration by viewing a plane from unknown orientations. Proceedings of the 7th International Conference on Computer Vision. Greece: Corfu, 1999: 666~673
9 Meng X Q ,Li H ,Hu Z Y. A new camera calibration technique based on circular points. Proceedings of British Machine Vision Conference. UK: Bristol, 2001: 496~505
10 吴福朝,王光辉,胡占义. 由矩形确定摄像机内参数与位置的线性方法.软件学报. 2003,(03):703~712
11 Tsai R. An efficient and accurate camera calibration technique for 3D machine vision. Proceedings of Computer Vision and Pattern Recognition. USA: Miami Beach, Fl, 1986:364~374
12 Ma S D. A self-calibration technique for active vision system. IEEE Transactions on Robot Automation , 1996 , 12(1) :114~120
13 R.I.Hartley. Self-calibration from multiple views with a rotating camera. European Conference on Computer Vision.1994:471~478
14 W.Triggs. Autocalibration from planar scenes. 5th European Conference onComputer Vision,1999:278~284
15 Faugeras O , Luong Q T , Maybank S. Camera self-calibration: Theory and experiments. Proceedings of the 2nd European Conference on Computer Vision, Italy, 1992: 321~334
16 Maybank S , Faugeras O. A theory of self-calibration of a moving camera. International Journal of Computer Vision , 1992 , 8 (2) :123~151
17 Richard Hartley, Fredrik Kahl.Critical Configurations for Projective Reconstruction from Multiple Views.International Journal of Computer Vision. 2007, 71(1):5~47
18 Hartley R. Projective reconstruction from line correspondences. Proceedings of Computer Vision and Pattern Recognition. Seattle : WA , 1994: 103~109
19 Beardsley P , Zisserman A , Murray D. Sequential update of projective and affine structure from motion. International Journal of Computer Vision , 1997 , 23(3) :235~259
20 Hung, Y. Projective Reconstruction from Multiple Views with Minimization of 2D Reprojection Error. International Journal of Computer Vision, 2006(3):305~317
21 Anders Heyden, Fredrik Kahl. Direct Affine Reconstruction.Proc. International Conference on Pattern Recognition. Barcelona, Spain, 2000:885~888
22 ParHammarstedt, Fredrik Kahl, Anders Heyden.Affine Reconstruction from Translational Motion under Various Autocalibration Constraints. Journal of Mathematical Imaging and Vision, 2006, (2):245~257
23 P. Hammarstedt, F.Kahl, A.Heyden. Affine Structure from Translational Motion with Varying and Unknown Focal Length. Proc. International Conference on Pattern Recognition, Cambridge, UK, 2004:120~123
24 P.Hammarstedt, F.Kahl, A.Heyden. Affine Structure from Translational Motion in Image Sequences. Proc. Scandinavian Conference on Image Analysis, Goteborg, Sweden, 2003:387~394
25 Fredrik Kahl, Didier Henrion.Globally Optimal Estimates for Geometric Reconstruction Problems.International Journal of Computer Vision, 2007 (1):3~15
26 Sameer Agarwal, Manmohan Chandraker.Practical Global Optimization forMultiview Geometry. Proc. European Conference on Computer Vision, Graz, Austria, 2006:592~605
27 Fredrik Kahl, Didier Henrion.Globally Optimal Estimates for Geometric Reconstruction Problems. Proc. International Conference on Computer Vision, Beijing, China, 2005:978~985
28 Ma Y, Vidal B , Kosecka J , Sastry S. Kruppa equation revisited: Its renormalization and degeneracy , ECCV’00 , Springer-Verlag ,2000: 561~577
29 Hartley R. Euclidean reconstruction and invariants from multiple images. IEEE Transactions on Pattern Analysis and Machine Intel ligence, 1994, 16(10):1036~1041
30 Triggs B. Auto-calibration and the absolute quadric. Proceedings of Computer Vision and Pattern Recognition , 1997: 609~614
31 Pollefeys M, Van Gool L , Oosterlinck A. The modulus constraint: A new constraint for self-calibration. Proceedings of International Conference of Pattern Recognition , Vienna , 1996:349~353
32 Heyden A , Sturm K. Euclidean reconstruction from image sequences with varying and unknown focal length and principal point .Proceedings of Computer Vision and Pattern Recognition , 1997:438~443
33 Pollefeys M, Koch R , Van Gool L. Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters. Proceedings of the 6th International Conference on Computer Vision. India ,1998:90~95
34 Hartley R , Zisserman A. Multiple View Geometry in Computer Vision. Cambridge : Cambridge University Press , 2003:112~135
35 孟晓桥,胡占义. 摄相机自标定方法的研究与进展. 自动化学报, 2003, 29(1):110~124
36 孙凤梅,吴福朝. 由平行平面的投影确定无穷远平面的单应矩阵. 软件学报, 2003,14(5):936~946
37 雷成,胡占义. 一种新的基于 Kruppa 方程的摄像机自标定方法. 计算机学报, 2003,5: 1130~1139
38 Lei C , Wu F C ,Hu Z Y. Kruppa equations and camera self-calibration. Acta Automatica Sinica , 2001 , 27(5) :621~630
39 Wexler, Y. , Fitzgibbon, A. and Zisserman, A. Learning epipolar geometry from image sequences. Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition, 2003:209~225
40 Xu G, Zhang Z. Epipolar Geometry in Stereo, Motion and Object Recognition: A Unified Approach. Kluwer Acamdemic Publisher , 1996
41 Luong Q, Faugeras O. The fundamental matrix: Theory, algorithms , and stability analysis. International Journal of Computer Vision , 1996 , 17(1) :43~76
42 Zeller C, Faugeras O. Camera self-calibration from video sequences : The Kruppa equations revisited. Research Report 2793 , INRIA Sophia-Antipolis , France , 1996:1~35
43 Pollefeys M. Self-calibration and Metric 3D Reconstruction from Uncalibrated Image Sequences. Ph.D. thesisKatholieke Universiteit Leuven , 1999:45~58
44 Enciso R , Vieville T. Experimentally self2calibration fromfour views. In : Proceedings of 1995 International Conference on Image Analysis and Processing. Italy , San Remo , 1995
45 Hartley R. Extracting of focal lengths from the fundamental matrix. GE internal report , G. E. CRD , Schenectady , NY, 1993
46 Heyden A , Sturm K. Euclidean reconstruction from constant intrinsic parameters. Proceedings of International Conference of Pattern Recognition , Vienna , 1996: 339~343
47 Pollefeys M, Van Gool L. Self-calibration from the absolute conic on the plane at infinity. Proceedings of Computer Analysis of Images and Patterns , Lecture Notes in Computer Science , Spring-Verlag , 1997 ,1296: 175~182
48 Sturm P. Self-calibration of a moving camera by precalibration. Proceedings of British Machine Vision Conference. Scotland:Edinburgh, 1996: 675~684
49 R.I.Hartley. The cunbic rational polynomial camera model. Proc. DARPA Image Understanding Workshop.1997:649~653
50 Heyden A. Flexible calibration: Minimal cases for autocalibration. Proceedings of the 7th International Conference on Computer Vision, Greece , 1999. 350～355
51 李波,王祥凤,李本山. 基于单幅图像的三维重建技术. 信息与电子工程. 2006,4(2):129~133
52 A. Criminisi. Accurate visual metrology from single and multiple images.Springer Press. 2001:201~240
53 Luong Q, Faugeras O. The fundamental matrix: Theory, algorithms , and stability analysis. International Journal of Computer Vision, 1996, 17(1): 43~76
54 Hartley R. Self-calibration of stationary cameras. International Journal of Computer Vision , 1997 , 22 (1) :5~23
55 Ma S D. A self-calibration technique for active vision system. IEEE Transactions on Robot Automation , 1996 , 12(1) :114~120
56 Hartley R. A linear method for reconstruction from points and lines. Proceedings of the 5th International Conference on Computer Vision. Boston : MA ,1995:882~887
57 Werner, T. and Zisserman, A. New Techniques for Automated Architecture Reconstruction from Photographs. Proceedings of the 7th European Conference on Computer Vision, Copenhagen, Denmark, 2002:541~555
58 Hartley, R. I. and Schaffalitzky, F. Reconstruction from projections using Grassmann tensors. Proceedings of the 8th European Conference on Computer Vision, Prague, Czech Republic, 2004:363~375
59 于起峰. 基于图像的精密测量与运动测量.科学出版社.2002:35~37
60 D. E. Goldberg. Genetic Algorithms : in Search Optimization &Machine Learning. Addison-Weslev Publishing Company Inc, 1989:32~47
61 S. C. Ng, S. H. Leung, C. Y. Chung. The Genetic Search Approach : A New Learning Algorithm for Adaptive IIR Filtering . IEEE Signal Processing Magazine. 1996, 13(6):38~46
62 陈小平 , 于盛林 . 实数遗传算法交叉策略的改进 . 电子学报 . 2003, 31(1):71~74
63 Tomasi and T.Kanade. Shape and motion from image streams under orthography: a factorization approach. International Journal of Computer Vision. 1992(2):137~154
64 P. Sturm, W. Triggs. A Factorization Based Algorithm for Multi-image Projective Structure and Motion. In Proc. European Conference on Computer Vision, 1996:709~720.
65 L. Quan. Two-way ambiguity in 2d projective reconstruction from three uncalibrated 1d images. IEEE Transactions on Pattern Analysis and MachineIntelligence, 2001,23(2):212~216
66 王小平,曹立明. 遗传算法——理论、应用与软件实现. 西安交通大学出版社,2002:21~25
67 John Canny. Member. IEEE. A Computational Approach to Edge Detection. IEEE Trans. Pattern Analysis and Machine Intelligence. 1986,(11):679~697
68 贾云得. 机器视觉. 北京科学出版社,2000:97~100
69 杨绍清,贾传荧. 基于模糊判决的图像边缘连接. 光学技术, 2002, 28(2): 108~109.
70 Nevatia R, Babuk R. Linear Feature Extraction and Description .Computer Graphics and Image Processing, 1980, 13(2): 257-269.
71 L. Quan, R. Mohr. Determining perspective structures using hierarchical Hough transform. Pattern Recognition Letter. 1998, (9):279~286
72 L.Pires, P.De Smet, I.Bruyland. Line extraction with the use of an automatic gradient threshold technique and the Hough Transform. International Conference on Image Processing.Vancouver,IEEE,2000:909-912
73 C.Galambos, J. Kitter, J.Matas. Gradient based progressive probabilistic Hough Transform. Proceedings of Image and Signal Processing. IEEE, 2001, (3):158~165.
74 Faugeras O. What can be seen in the three dimensions with an uncalibrated stereo rig Proceedings of the 2nd European Conference on Computer Vision, Italy , 1992: 563~578
75 Zhang Z , Luong QT , Faugeras O. Motion of an uncalibrated stereo rig: Self-calibration and metric reconstruction , Research Report2079 , INRIA Sophia-Antipolis , France , 1993:103~113
76 R.Horaud. Selfcalibration and euclidean reconstruction using motions of a stereo rig. Proceedings of International Conference on Computer Vision, Bombay, India, 1998: 96～106
77 A. Zisserman, P. A. Beardsley, and I. D. Reid. Metric cali- bration of a stereo rig. In Proc. IEEE Workshop on Repre- sentations of Visual Scenes, Boston, 1995: 93~100.
78 Fadi Dornaika and Chi-kit Ronald Chung. Stereo Geometry From 3-D Ego-Motion Streams. IEEE Transaction on systems, man and cybernetics, 2003, (3): 308~323
79 P.Sturm. Critical motion sequences for monocular self-calibration and uncalibrated Euclidean reconstruction. Proceedings of Computer Vision and Pattern Recognition. USA: Puerto Rico , 2000:1100~1105
80 Faugeras O., Mourrain B. On the geometry and algebra of point and line correspondences between n images. Proceedings of the 5th International Conference on Computer Vision. Boston : MA , 1995:951~962
81 Oskarsson, M., Zisserman, A. and Astrom, K. Minimal projective reconstruction for combinations of points and lines in three views. Image and Vision Computing, 2004:777~785
82 H.C.Longuet-Higgins. A computer algorithm for reconstructing a scene from two projections. Nature,1981(9):133~135
83 R.Hartley. Camera calibration and the search for infinity. Proceedings of the 7th International Conference on Computer Vision ,Greece , 1999:510~517
84 Pollefeys M, Van Gool L , Proesmans M. Euclidean 3D reconstruction from image sequences with variable focal lengths. Proceedings of the 4th European Conference on Computer Vision , UK, Cambridge , 1996: 31~42
85 Hartley R. In defense of the eight-point algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence , 1997 , 19 (6): 580~593
86 Zhengyou Zhang. A new multistage approach to motion and structure estimation by gradually enforcing geometric constrains. Computer vision ACCV’98, 1998:567~574
87 Charlie Rothwell,Gabriella Csurka. Acomparison of projective reconstruction methods for pairs of views. Computer Vision and Image Understanding. 1997, 68(1):37~58
88 Hartley R, Gupta R , Chang T. Stereo from uncalibrated cameras. Proceedings of Computer Vision and Pattern Recognition ,1992:761~764
89 Torr P, Zisserman A. Robust computation and parameterization of multiple view relations. Proceedings of the 6th International Conference on Computer Vision , India , 2000:727~732
90 Ma Y, Kosecka J, Huang K. Rank deficiency condition of the multiple-view matrix for mixed point and line features.Proceedings of the 5th Asian Conference on Computer Vision. Australia : Melbourne , 2002: 338~341
91 Quan L. Uncalibrated 1D projective camera and 3D affine reconstruction oflines. Proceedings of Computer Vision and Pattern Recognition , USA , 1997: 60~65
92 Quan L. Self-calibration of an affine camera from multiple views. International Journal of Computer Vision , 1996 , 19(1):93~110
93 Luong Q.T., Vieville T. Canonic representation for the geometry of multiple projective views. Proceedings of the 3rd European Conference on Computer Vision, Sweden, 1994: 589~600
94 M. Pollefeys, R. Koch, M. Vergauwen, L. Van Gool. Automated reconstruction of 3D scenes from sequences of images, ISPRS Journal of Photogrammetry and Remote Sensing 2000 ,4 (55): 251~267
95 R. Koch, M. Pollefeys, L. Van Gool, Realistic surface reconstruction of 3D scenes from uncalibrated image sequences, Journal Visualization and Computer Animation, 2000,(11): 115~127
96 Beardsley P , Zisserman A , Murray D. Sequential update of projective and affine structure from motion. International Journal of Computer Vision, 1997 , 23(3) :235~259
97 Schaffalitzky, F. Grouping, Matching and Reconstruction in Multiple View Geometry, PhD thesis , 2002:79~87
98 Mundy J, Zisserman A. Geometric Invariance in Computer Vision. Massachusetts: Cambridge , MIT Press , 1992:105~119
99 Zhang Zhengyou. A Robust Technique for Matching Two Uncalibrated Images through the Recovery of the Unknown Epipolar Geometry. INRIA.1994:18~33
100 Sun D. M, A Robust Point Matching Algorithm Based on Deterministic Annealing. Journal of Computers, 2002,(6):606~611
101 Schimid. Matching by Local Invariants.INRIA.1995:8~22
102 Yuan C. Hsieh, David M. Mckeown. Performance Evaluation of Scene Registration and Stereo Matching for Cartographic Feature Extraction. IEEE Trans.1992, (l14):21~28
103 M. A. Fischler, R. C. Bolles. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Comm. of the ACM, 1981,(24): 381~395
104 Ma Y, Soatto S, Kosecka J, Sastry S. Euclidean reconstruction andreprojection up to subgroups. Proceedings of the 7th International Conference on Computer Vision , Greece , 2000: 773~780
105 M. Pollefeys and L. Van Gool. Virtualising the 3D Real World: Automatic Method for the Acquisition of Detailed 3D Models from Image Sequences, GIM International, 2000, 4(14): 12~15
106 Moons T, Van Gool L, Proesmans M, Pauwels E. Affine reconstruction from perspective image pairs with a relative object-camera translation in between. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(1):77～83