Relative depth from motion using normal flow: an active and purposive solution

The authors show how an active observer can compute the relative depth of (stationary or moving) objects in the field of view using only the spatiotemporal derivatives of the time varying image intensity function. The solution they propose is purposive in the sense that it solves only the relative depth from motion problem and cannot be used for other problems related to motion; active in the sense that the activity of the observer is essential for the solution of the problem. Results indicate that exact computation of retinal motion does not appear to be a necessary first step for some problems related to visual motion. In addition, optic flow, whose computation is an ill-posed problem, is related to the motion of the scene only under very restrictive assumptions. As a result, the use of optic flow in some quantitative motion analysis studies is questionable.<<ETX>>

[1]  S. Ullman The Interpretation of Visual Motion , 1979 .

[2]  H. C. Longuet-Higgins,et al.  The interpretation of a moving retinal image , 1980, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[3]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[4]  H. C. Longuet-Higgins,et al.  A computer algorithm for reconstructing a scene from two projections , 1981, Nature.

[5]  Thomas S. Huang,et al.  Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Gilad Adiv,et al.  Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Berthold K. P. Horn Robot vision , 1986, MIT electrical engineering and computer science series.

[8]  G.-S. Young,et al.  3-D motion estimation using a sequence of noisy stereo images , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  Minas E. Spetsakis,et al.  Optimal Computing Of Structure From Motion Using Point Correspondences In Two Frames , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[10]  Gilad Adiv,et al.  Inherent Ambiguities in Recovering 3-D Motion and Structure from a Noisy Flow Field , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Yiannis Aloimonos,et al.  Purposive and qualitative active vision , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.