Motion recovery from image sequences using first-order optical flow information

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

Abstract

A closed-form solution for motion estimation from first-order flow in two `distinct' image regions is described. Uniqueness is guaranteed when these correspond to surface patches with different normal vectors. Given an image sequence, we show how the image may be segmented into regions with the necessary properties, optical flow is computed for these regions, and motion parameters are computed. The method can be applied to arbitrary scenes and camera motions. We will explain why it is more robust than other techniques that require the knowledge of the full flow or information up to the second-order terms of it. Experimental results are presented to support the theoretical derivations.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Workshop on Visual Motion
PublisherPubl by IEEE
Pages132-139
Number of pages8
ISBN (Print)0818621532
StatePublished - Dec 1 1991
EventProceedings of the IEEE Workshop on Visual Motion - Princeton, NJ, USA
Duration: Oct 7 1991Oct 9 1991

Publication series

NameProceedings of the IEEE Workshop on Visual Motion

Other

OtherProceedings of the IEEE Workshop on Visual Motion
CityPrinceton, NJ, USA
Period10/7/9110/9/91

    Fingerprint

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Negahdaripour, S., & Lee, S. (1991). Motion recovery from image sequences using first-order optical flow information. In Proceedings of the IEEE Workshop on Visual Motion (pp. 132-139). (Proceedings of the IEEE Workshop on Visual Motion). Publ by IEEE.