Extraction of 3D shape from optic flow: a geometric approach

Several 3D shape measures are derived directly from the velocity field generated by a rigid curved surface patch under perspective projection. We use invariance under rotation of the image plane to decompose the velocity field into differential invariants. From a combination of these invariants, we construct an approximation to the absolute value of the shape index, to the curvature, and to the principal direction. We show the effect of these approximations to be small for a 6/spl deg/ field-of-view.<<ETX>>

[1]  P. R. Snoeren,et al.  EXTRACTION OF THREE-DIMENSIONAL SHAPE FROM OPTIC FLOW : A GEOMETRIC APPROACH , 1994 .

[2]  Andrea J. van Doorn,et al.  Surface shape and curvature scales , 1992, Image Vis. Comput..

[3]  J. Koenderink,et al.  Second-order optic flow , 1992 .

[4]  J J Koenderink,et al.  Affine structure from motion. , 1991, Journal of the Optical Society of America. A, Optics and image science.

[5]  Narendra Ahuja,et al.  Optimal motion and structure estimation , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  D. Knill,et al.  Extraction of 3d Shape from Optic Flow , 1994 .

[7]  金谷 健一.  Group-theoretical methods in image understanding , 1990 .

[8]  Andrea J. van Doorn,et al.  Invariant Properties of the Motion Parallax Field due to the Movement of Rigid Bodies Relative to an Observer , 1975 .