Optical flow using spatiotemporal filters

Research output: Contribution to journalArticle

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 estimate image velocity. A parallel implementation computes a distributed representation of image velocity. A measure of image-flow uncertainty is formulated; preliminary results indicate that this uncertainty measure may be used to recognize ambiguity due to the aperture problem. The model appears to deal with the aperture problem as well as the human visual system since it extracts the correct velocity for some patterns that have large differences in contrast at different spatial orientations.

Original languageEnglish (US)
Pages (from-to)279-302
Number of pages24
JournalInternational Journal of Computer Vision
Volume1
Issue number4
DOIs
StatePublished - Jan 1988

Fingerprint

Optical flows
Neurophysiology
Uncertainty

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Optical flow using spatiotemporal filters. / Heeger, David J.

In: International Journal of Computer Vision, Vol. 1, No. 4, 01.1988, p. 279-302.

Research output: Contribution to journalArticle

@article{5ca2e9aa081044deb35208797f238bfd,
title = "Optical flow using spatiotemporal filters",
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 estimate image velocity. A parallel implementation computes a distributed representation of image velocity. A measure of image-flow uncertainty is formulated; preliminary results indicate that this uncertainty measure may be used to recognize ambiguity due to the aperture problem. The model appears to deal with the aperture problem as well as the human visual system since it extracts the correct velocity for some patterns that have large differences in contrast at different spatial orientations.",
author = "Heeger, {David J.}",
year = "1988",
month = "1",
doi = "10.1007/BF00133568",
language = "English (US)",
volume = "1",
pages = "279--302",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "4",

}

TY - JOUR

T1 - Optical flow using spatiotemporal filters

AU - Heeger, David J.

PY - 1988/1

Y1 - 1988/1

N2 - 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 estimate image velocity. A parallel implementation computes a distributed representation of image velocity. A measure of image-flow uncertainty is formulated; preliminary results indicate that this uncertainty measure may be used to recognize ambiguity due to the aperture problem. The model appears to deal with the aperture problem as well as the human visual system since it extracts the correct velocity for some patterns that have large differences in contrast at different spatial orientations.

AB - 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 estimate image velocity. A parallel implementation computes a distributed representation of image velocity. A measure of image-flow uncertainty is formulated; preliminary results indicate that this uncertainty measure may be used to recognize ambiguity due to the aperture problem. The model appears to deal with the aperture problem as well as the human visual system since it extracts the correct velocity for some patterns that have large differences in contrast at different spatial orientations.

UR - http://www.scopus.com/inward/record.url?scp=34250091331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250091331&partnerID=8YFLogxK

U2 - 10.1007/BF00133568

DO - 10.1007/BF00133568

M3 - Article

VL - 1

SP - 279

EP - 302

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 4

ER -