On the kinetic depth effect
- 1 April 1989
- journal article
- Published by Springer Nature in Biological Cybernetics
- Vol. 60 (6) , 445-455
- https://doi.org/10.1007/bf00204700
Abstract
The problem of the kinetic depth effect is revisited. We study how many points in how many views are necessary and sufficient to recover structure. The constraints in the cases where the velocities of the image points are known, and the positions of the image points are known with the correspondence between them established, are different and they have to be studied separately. In the case of two projections of any number of points there are infinitely many solutions, but if we regularize the problem we get a unique solution under some assumptions. Finally, an algorithm is discussed for learning this particular kind of regularization.Keywords
This publication has 22 references indexed in Scilit:
- Learning early-vision computationsJournal of the Optical Society of America A, 1989
- III-Posed problems early vision: from computational theory to analogue networksProceedings of the Royal Society of London. B. Biological Sciences, 1985
- Inferring the relative three-dimensional positions of two moving pointsJournal of the Optical Society of America A, 1985
- Equation Counting and the Interpretation of Sensory DataPerception, 1982
- Inferring local surface orientation from motion fieldsJournal of the Optical Society of America, 1982
- Recovery of the three-dimensional shape of an object from a single viewArtificial Intelligence, 1981
- The interpretation of a moving retinal imageProceedings of the Royal Society of London. B. Biological Sciences, 1980
- The interpretation of structure from motionProceedings of the Royal Society of London. B. Biological Sciences, 1979
- QCD predictions for processes involving real photonsPhysics Letters B, 1978
- Interpreting pictures of polyhedral scenesArtificial Intelligence, 1973