This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Estimating Motion and Structure from Correspondences of Line Segments between Two Perspective Images
December 1995 (vol. 17 no. 12)
pp. 1129-1139

Abstract—We present in this paper an algorithm for determining 3D motion and structure from correspondences of line segments between two perspective images. To our knowledge, this paper is the first investigation of use of line segments in motion and structure from motion. Classical methods use their geometric abstraction, namely straight lines, but then three images are necessary for the motion and structure determination process. In this paper we show that it is possible to recover motion from two views when using line segments. The assumption we use is that two matched line segments contain the projection of a common part of the corresponding line segment in space, i.e., they overlap. Indeed, this is what we use to match line segments between different views. This assumption constrains the possible motion between two views to an open set in motion parameter space. A heuristic, consisting of maximizing the overlap, leads to a unique solution. Both synthetic and real data have been used to test the proposed algorithm, and excellent results have been obtained with real data containing a relatively large set of line segments.

[1] J.K. Aggarwal and N. Nandhakumar, “On the Computation of Motion from Sequences of Images: A Review,” Proc. IEEE, vol. 76, no. 8, pp. 917-935, 1988.
[2] N. Ayache and F. Lustman,“Fast and reliable passive trinocular stereovision,” Proc. First Int’l Conf. Computer Vision, pp. 422-427,London, June 1987.
[3] D.H. Ballard and C.M. Brown, Computer Vision, Prentice Hall, Upper Saddle River, N.J., 1982.
[4] J.K. Cheng and T.S. Huang,“Image registration by matching relational structures,” Pattern Recognition, vol. 17, no. 1, pp. 149-159, 1984.
[5] R. Deriche and O. Faugeras,“Tracking line segments,” Proc. First European Conf. Computer Vision, O. Faugeras, ed., pp. 259-268,Antibes, France, Apr. 1990.
[6] O. Faugeras, "What can be seen in three dimensions with an uncalibrated stereo rig?" Second European Conf. Computer Vision, pp. 563-578, 1992.
[7] O.D. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint.Cambridge, Mass.: MIT Press, 1993.
[8] O.D. Faugeras and G. Toscani,“The calibration problem for stereo,” Proc. IEEE Conf. Computer Vision and Pattern Recog., pp. 15-20,Miami, June 1986.
[9] B. Giai-Checa,R. Deriche,T. Vieville,, and O. Faugeras,“Suivi de segments dans une séquence d’images monoculaire,” Technical Report 2113, INRIA Sophia-Antipolis, France, Dec. 1993.
[10] G. Giraudon,“Chaînage efficace contour,” Rapport de Recherche 605, INRIA, Sophia-Antipolis, France, Feb. 1987.
[11] R. Hartley, R. Gupta, and T. Chang, “Stereo from Uncalibrated Cameras,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 761-764, June 1992.
[12] T. Huang and A. Netravali,“Motion and structure from feature correspondences: A review,” Proc. IEEE, vol. 82, pp. 252-268, Feb. 1994.
[13] Y. Liu and T. Huang, “A Linear Algorithm for Determining Motion and Structure from Line Correspondences,” Computer Vision, Graphics, and Image Processing, vol. 44, no. 1, pp. 35-57, 1988.
[14] H.C. Longuet-Higgins,“A computer algorithm for reconstructing a scene from two projections,” Nature, vol. 293, pp. 133-135, 1981.
[15] Q.-T. Luong,“Matrice fondamentale et calibration visuelle sur l’environnement:Vers une plus grande autonomie des systèmes robotiques,” Dissertation, Univ. of Paris XI, Orsay, Paris, France, Dec. 1992.
[16] S. Maybank,Theory of Reconstruction from Image Motion.Berlin, Heidelberg: Springer-Verlag, 1993.
[17] J.A. Nelder and R. Mead,“A simplex method for function minimization,” Computer J., no. 7, pp. 308-313, 1965.
[18] J.W. Roach and J.K. Aggarwal,“Determining the movement of objects from a sequence of images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 2, no. 6, pp. 554-562, 1980.
[19] M. Spetsakis and J. Aloimonons,“A unified theory of structure from motion,” Technical Report CAR-TR-482, Computer Vision Laboratory, Univ. of Maryland, Dec. 1989.
[20] M.E. Spetsakis and J. Aloimonos, “Structure from Motion Using Line Correspondences,” Int'l J. Computer Vision, vol. 4, pp. 171-183, 1990.
[21] R.Y. Tsai and T.S. Huang,“Uniqueness and estimation of three-dimensional motion parameters ofrigid objects with curved surface,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol 6, no. 1, pp. 13-26, Jan. 1984.
[22] S. Ullman,The Interpretation of Visual Motion.Cambridge, Mass.: MIT Press, 1979.
[23] T. Viéville,Q.T. Luong,, and O.D. Faugeras,“Motion of points and lines in the uncalibrated case,” Int’l J. Computer Vision, to appear, vol. 17, no. 1.
[24] Z. Zhang,“Estimating motion and structure from correspondences of linesegments between two perspective images,” Research Report 2340, INRIA Sophia, 1994.
[25] Z. Zhang and O.D. Faugeras, 3D Dynamic Scene Analysis: A Stereo Based Approach. Berlin Heidelberg: Springer, 1992.

Index Terms:
Motion, structure from motion, line segments, epipolar geometry, perspective images, overlap, dynamic scene analysis.
Citation:
Zhengyou Zhang, "Estimating Motion and Structure from Correspondences of Line Segments between Two Perspective Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 12, pp. 1129-1139, Dec. 1995, doi:10.1109/34.476506
Usage of this product signifies your acceptance of the Terms of Use.