Abstract
A model is presented, consonant with current views regarding the neurophysiology and psychophysics of motion perception, that combines the outputs of a set of spatiotemporal motion-energy filters to extract optical flow. The model gives accurate estimates of two-dimensional velocity for a wide variety of test cases including realistic images, sequences generated from images of natural textures, and some sine-grating plaid patterns. The model is seen to perform as well as the human visual system in dealing with the aperture problem since extracts the correct velocity for patterns that have large differences in contrast at different spatial orientations.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the International Conference on Computer Vision |
| Publisher | IEEE |
| Pages | 181-190 |
| Number of pages | 10 |
| ISBN (Print) | 081860777X |
| State | Published - 1987 |
ASJC Scopus subject areas
- General Engineering