Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

This paper addresses the problem of 3D surface reconstruction using image sequences. It has been shown that shape recovery from three or more occluding contours of the surface is possible given a known camera motion. Several algorithms, which have been recently proposed, allow such a reconstruction under the assumption of a linear camera motion. A new approach is presented which deals with the reconstruction problem directly from a discrete point of view. First, a theoretical study of the epipolar correspondence between occluding contours is achieved. A correct depth formulation is then derived from a local approximation of the surface up to order two. This allows the local shape to be estimated, given three consecutive contours, without any constraints on the camera motion. Experimental results are presented for both synthetic and real data.

REFERENCES

• 1: Berger, M.-O. 1994. How to track efficiently piecewise curved contours with a view to reconstructing 3D objects. In Proceedings of the 12th International Conference on Pattern Recognition, Jerusalem (Israel), 1:32-36.
• 2: Bruce, J. and Giblin, P. 1984. Curves and Singularities. Cambridge University Press: Cambridge.
• 3: Cipolla, R. and Blake, A. 1990. The dynamic analysis of apparent contours. In Proceedings of 3rd International Conference on Computer Vision, IEEE (Ed.), Osaka (Japan), pp. 616-623.
• 4: R. Cipolla , K. E. Astrom , P. J. Giblin, Motion from the frontier of curved surfaces, Proceedings of the Fifth International Conference on Computer Vision, p.269, June 20-23, 1995
• 5: do Carmo, M. 1976. Differential Geometry of Curves and Surfaces. Prentice-Hall: Englewood Cliffs, New Jersey.
• 6: Olivier Faugeras, Three-dimensional computer vision: a geometric viewpoint, MIT Press, Cambridge, MA, 1993
• 7: David A. Forsyth , Joseph L. Mundy , Andrew Zisserman , Charlie Rothwell, Recognising rotationally symmetric surfaces from their outlines, Proceedings of the Second European Conference on Computer Vision, p.639-647, May 19-22, 1992
• 8: Giblin, P. and Weiss, R. 1987. Reconstruction of surfaces from profiles. In Proceedings of the First International Conference on Computer Vision, London, pp. 136-144.
• 9: Giblin, P. and Weiss, R. 1995. Epipolar curves on surfaces. Image and Vision Computing, 13(1):33-44.
• 10: R. Glachet , Michel Dhome , Jean-Thierry Lapresté, Finding the Pose of an Object of Revolution, Proceedings of the Second European Conference on Computer Vision, p.681-686, May 19-22, 1992
• 11: T. Joshi , N. Ahuja , J. Ponce, Structure and motion estimation from dynamic silhouettes under perspective projection, Proceedings of the Fifth International Conference on Computer Vision, p.290, June 20-23, 1995
• 12: Kass, M., Witkin, A., and Terzopoulos, D. 1988. Snakes: Active contour models. International Journal of Computer Vision, 1:321- 331.
• 13: Koenderink, J. 1984. What does the occluding contour tell us about solid shape? Perception, 13:321-330.
• 14: Jan J. Koenderink, An internal representation for solid shape based on the topological properties of the apparent contour, Image understanding 1985-86, Ablex Publishing Corp., Norwood, NJ, 1987
• 15: D. J. Kriegman , Jean Ponce, On Recognizing and Positioning Curved 3-D Objects from Image Contours, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.12 n.12, p.1127-1137, December 1990 [doi>10.1109/34.62602]
• 16: J. Ponce , D. Chelberg , W. B. Mann, Invariant Properties of Straight Homogeneous Generalized Cylinders and Their Contours, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.11 n.9, p.951-966, September 1989 [doi>10.1109/34.35498]
• 17: John Porrill , Stephen Pollard, Curve matching and stereo calibration, Image and Vision Computing, v.9 n.1, p.45-50, Feb. 1991 [doi>10.1016/0262-8856(91)90048-T]
• 18: Rieger, J. 1986. Three-dimensional motion from fixed points of a deforming profile curve. Optics Letters, 11:123-125.
• 19: W. Brent Seales , Olivier D. Faugeras, Building three-dimensional object models from image sequences, Computer Vision and Image Understanding, v.61 n.3, p.308-324, May 1995 [doi>10.1006/cviu.1995.1025]
• 20: Szeliski, R. and Weiss, R. 1993. Robust shape recovery from occluding contours using a linear smoother. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, New York (USA), pp. 666-667.
• 21: Régis Vaillant , Olivier D. Faugeras, Using Extremal Boundaries for 3-D Object Modeling, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.14 n.2, p.157-173, February 1992 [doi>10.1109/34.121787]
• 22: Zerroug, M. and Nevatia, R. 1993. Quasi-invariant properties and 3D shape recovery of non-straight, non-constant generalized cylinders. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, New York (USA), pp. 96-103.
• 23: ChangSheng Zhao , Roger Mohr, Relative 3D Regularized B-spline Surface Reconstruction Through Image Sequences, Proceedings of the Third European Conference-Volume II on Computer Vision, p.417-426, May 02-06, 1994

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION

Additional Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
  I.5 PATTERN RECOGNITION
      I.5.4 Applications
          Subjects: Computer vision

General Terms:
Design, Experimentation, Theory

Keywords:
epipolar correspondence, epipolar curve, occluding contours, rims, surface reconstruction