This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Relative Affine Structure: Canonical Model for 3D From 2D Geometry and Applications
September 1996 (vol. 18 no. 9)
pp. 873-883

Abstract—We propose an affine framework for perspective views, captured by a single extremely simple equation based on a viewer-centered invariant we call relative affine structure. Via a number of corollaries of our main results we show that our framework unifies previous work—including Euclidean, projective and affine—in a natural and simple way, and introduces new, extremely simple, algorithms for the tasks of reconstruction from multiple views, recognition by alignment, and certain image coding applications.

[1] A. Azarbayejani and A. Pentland, "Recursive Estimation of Motion, Structure and Focal Length," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 6, pp. 562-575, June 1995.
[2] E. Barrett, P.M. Payton, and G. Gheen, "Robust Algebraic Invariant Methods with Applications in Geometry and Imaging," Proc. SPIE Symp. Remote Sensing,San Diego, July 1995.
[3] J.R. Bergen, P. Anandan, K.J. Hanna, and R. Hingorani, “Hiercharchical Model-Based Motion Estimation,” Proc. European Conf. Computer Vision, pp. 237-252, 1992.
[4] D. Beymer, A. Shashua, and T. Poggio, "Example Based Image Analysis and Synthesis," M.I.T. A.I. Memo No. 1431, 1993.
[5] S. Demey, A. Zisserman, and P. Beardsley, "Affine and Projective Structure from Motion," Proc. British Machine Vision Conf., Oct. 1992.
[6] R. Deriche, Z. Zhang, Q.-T. Luong, and O. Faugeras, “Robust Recovery of the Epipolar Geometry for an Uncalibrated Stereo Rig,” Proc. Third European Conf. Computer Vision, 1994.
[7] R. Dutta, R. Manmatha, L.R. Williams, and E.M. Riseman, “A Data Set for Quantitative Motion Analysis,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 159–164, 1989.
[8] O. Faugeras, "What can be seen in three dimensions with an uncalibrated stereo rig?" Second European Conf. Computer Vision, pp. 563-578, 1992.
[9] O.D. Faugeras, "Stratification of Three-Dimensional Vision: Projective, Affine and Metric Representations," J. Optical Soc. of Am., vol. 12, no. 3, pp. 465-484, 1995.
[10] O. Faugeras, T. Luong, and S. Maybank, “Camera Self-Calibration: Theory and Experiments,” Proc Second European Conf. Computer Vision, pp. 321-334, May 1992.
[11] O.D. Faugeras and F. Lustman, "Let Us Suppose that the World Is Piecewise Planar," Int'l Symp. Robotics Research, O.D. Faugeras and G. Giralt, eds., pp. 33-40.Cambridge, Mass.: MIT Press, 1986.
[12] O.D. Faugeras and L. Robert, "What Can Two Images Tell Us about a Third One?" Proc. European Conf. Computer Vision, pp. 485-492,Stockholm, Sweden, May 1994.
[13] R. Hartley, “Projective Reconstruction and Invariants from Multiple Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 10, pp. 1036-1041, Oct. 1994.
[14] R. Hartley and R. Gupta, "Computing Matched-Epipolar Projections," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1993, pp. 549-555.
[15] R. Hartley, R. Gupta, and T. Chang, “Stereo from Uncalibrated Cameras,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 761-764, June 1992.
[16] D.P. Huttenlocher and S. Ullman, “Recognizing Solid Objects by Alignment with an Image,” Int'l J. Computer Vision, vol. 5, no. 2, pp. 195-212, 1990.
[17] D. Jacobs, "Space efficient 3D model indexing," IEEE Conf. Computer Vision and Pattern Recognition, pp. 439-444, 1992.
[18] J.J. Koenderink and A.J. Van Doorn, "Affine Structure from Motion," J. Optical Soc. Am., vol. 8, pp. 377-385, 1991.
[19] R. Kumar, P. Anandan, and K. Hanna, “Direct Recovery of Shape from Multiple Views: A Parallax Based Approach,” Proc. Int'l Conf. Pattern Recognition, pp. 685-688, Oct. 1994.
[20] R. Kumar,H.S. Sawhney,, and A. R. Hanson,“3D model acquisition from monocular image sequences,” 1992 IEEE Conf. on Computer Vision and Pattern Recognition, pp. 209-215, June 1992.Los Alamitos, Calif., IEEE Computer Society Press.
[21] C.H. Lee, "Structure and Motion from Two Perspective Views via Planar Patch," Int'l Conf. Computer Vision, pp. 158-164, 1988.
[22] H.C. Longuet-Higgins, "A Computer Algorithm for Reconstructing a Scene from Two Projections," Nature, vol. 293, pp. 133-135, 1981.
[23] B.D. Lucas and T. Kanade, "An Iterative Image Registration Technique with an Application to Stereo Vision," Proc. IJCAI, pp. 674-679,Vancouver, Canada, 1981.
[24] Q.-T. Luong and T. Vieville, “Canonic Representation for the Geometry of Multiple Projective Views,” Proc. European Conf. Computer Vision ECCV'94, pp. 589-600, 1994.
[25] R. Mohr, F. Veillon, and L. Quan, “Relative 3D Reconstruction Using Multiple Uncalibrated Images,” Proc. IEEE Fifth Int'l Conf. Computer Vision, pp. 543-548, 1993.
[26] T. Moons, L.J. Van Gool, M.V. Diest, and E.J. Pauwels, “Affine Reconstruction from Perspective Image Pairs Obtained by a Translating Camera,” Applications of Invariance in Computer Vision, J.L. Mundy, A. Zisserman, and D.A. Forsyth, eds., pp. 297-316, Springer-Verlag, 1994.
[27] J.L. Mundy, R.P. Welty, M.H. Brill, P.M. Payton, and E.B. Barrett, "3-D Model Alignment Without Computing Pose," Proc. ARPA Image Understanding Workshop, pp. 727-735.San Mateo, Calif.: Morgan Kaufmann, Jan. 1992.
[28] N. Navab and A. Shashua, "Algebraic Description of Relative Affine Structure: Connections to Euclidean, Affine and Projective Structure," Technical Report 270, Media Laboratory, Massachusetts Inst. of Tech nology, 1994.
[29] J. Oliensis and J.I. Thomas, "Incorporating Motion Error in Multi-Frame Structure From Motion, IEEE Workshop on Visual Motion, pp. 8-13, Princeton, N.J., Los Alamitos, Calif.: CS Press, Oct. 1991.
[30] L. Quan, "Affine Stereo Calibration for Relative Affine Shape Reconstruction," Proc. British Machine Vision Conf., pp. 659-668, 1993.
[31] L. Robert and O. Faugeras, "Relative 3D positionning and 3D convex hull computation from a weakly calibrated stereo pair," Proc. Fourth Int'l Conf. Computer Vision, pp. 540-544,Berlin, May 1993.
[32] H.S. Sawhney, "3D Geometry From Planar Parallax," Proc. CVPR '94, pp. 929-934, 1994.
[33] L.S. Shapiro, A. Zisserman, and M. Brady, "Motion from Point Matches Using Affine Epipolar Geometry," Proc. European Conf. Computer Vision, pp. 73-84,Stockholm, Sweden, May 1994.
[34] A. Shashua,“Correspondence and affine shape from two orthographic views: Motion and Recognition,” A.I. Memo No. 1327, Artificial Intelligence Laboratory, Massachusetts Inst. of Tech nology, Dec. 1991.
[35] A. Shashua, "On geometric and algebraic aspects of 3D affine and projective structures from perspective 2D views," Proc. Second Workshop on Applications of Invariance in Computer Vision, pp. 87-112, 1993.
[36] A. Shashua, "Projective Structure From Uncalibrated Images: Structure-From-Motion and Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 8, pp. 778-790, Aug. 1994.
[37] A. Shashua, “Algebraic Functions for Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 8, pp. 779-789, 1995.
[38] A. Shashua and N. Navab, "Relative Affine Structure: Theory and Application to 3D Reconstruction From Perspective Views," Proc. CVPR '94, pp. 483-489, 1994.
[39] G. Sparr, "An Algebraic-Analytic Method for Reconstruction from Image Correspondences," Seventh Scandinavian Conf. Image Analysis,Aalborg, Denmark, 1991.
[40] G. Sparr, "A Common Framework for Kinetic Depth, Reconstruction and Motion for Deformable Objects," Proc. European Conf. Computer Vision, pp. 471-482,Stockholm, Sweden, May 1994.
[41] R. Szeliski and S.B. Kang, "Recovering 3D Shape and Motion from Image Streams Using Non-Linear Least Squares," Technical Report D.E.C., Dec. 1992.
[42] R. Tsai,T. Huang,, and W. Zhu,“Estimating three-dimensional motion parameters of a rigid planar patch, ii: Singular value decomposition,” IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 30, no. 4, pp. 525-534, 1982.
[43] S. Ullman,“Aligning pictorial descriptions: An approach to object recognition,” Cognition, vol. 32, pp. 193-254, 1989. Also: in MIT AI Memo 931, Dec. 1986.
[44] D. Weinshall,“Model based invariants for 3D vision,” Int’l J. Computer Vision, vol. 10, no. 1, pp. 27-42, 1993.
[45] D. Weinshall and C. Tomasi, “Linear and Incremental Acquisition of Invariant Shape Models from Image Sequences,” Proc. Fourth Int'l Conf. Computer Vision, pp. 675-682, May 1993.

Index Terms:
Structure from motion, visual recognition, alignment, reprojection, projective reometry, algebraic and geometric invariants.
Citation:
Amnon Shashua, Nassir Navab, "Relative Affine Structure: Canonical Model for 3D From 2D Geometry and Applications," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 9, pp. 873-883, Sept. 1996, doi:10.1109/34.537342
Usage of this product signifies your acceptance of the Terms of Use.