Accurate Computation of Optical Flow by Using Layered Motion Representations

Steve Hsu, P. Anandan, Shmuel Peleg

Research output: Contribution to journalConference articlepeer-review

31 Scopus citations

Abstract

This paper presents a framework combining two prevailing approaches to motion analysis: opticalflow which describes motion at each point, and methods that define global motions for [arger regions. Image motion is represented by layers, image regions whose coherent motion can be approximated by some parametric motion model. The motion at every point is obtained by the parametric motion estimate of the entire layer, corrected by a residualflow field which captures the diflerence between the real image motion and the layer's motion model. The new approach is able to construct accurate flow fields in the presence of multiple motions, motion boundaries, and transparent motions.

Original languageEnglish
Pages (from-to)743-746
Number of pages4
JournalProceedings - International Conference on Pattern Recognition
Volume1
DOIs
StatePublished - 1994
Externally publishedYes
EventProceedings of the 12th IAPR International Conference on Pattern Recognition. Part 1 (of 3) - Jerusalem, Isr
Duration: 9 Oct 199413 Oct 1994

Bibliographical note

Publisher Copyright:
© 2011 IEEE Computer Society. All rights reserved.

Fingerprint

Dive into the research topics of 'Accurate Computation of Optical Flow by Using Layered Motion Representations'. Together they form a unique fingerprint.

Cite this