Multi-scale stereo matching

Michael S. Lew, Kam W. Wong, Thomas S. Huang

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


Most work in pyramidal or hierarchical stereo matching has primarily used the direct coarse-to-fine or hill climbing search method. However, there are two significant problems in using the hill climbing method. First, the match at the initial scale level can be wrong. Second, the binary decision at any of the finer scale levels may be wrong. Our method, which is essentially a best-first or cost minimization search method, alleviates both of these problems. The results of our method applied to real world image pairs are presented as well as a direct comparision in terms of percentage of correct matches to the traditional hill climbing method.

Original languageEnglish (US)
Title of host publicationConference A
Subtitle of host publicationComputer Vision and Applications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages4
ISBN (Print)081862910X
StatePublished - 1992
Event11th IAPR International Conference on Pattern Recognition, IAPR 1992 - The Hague, Netherlands
Duration: Aug 30 1992Sep 3 1992

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Other11th IAPR International Conference on Pattern Recognition, IAPR 1992
CityThe Hague

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Multi-scale stereo matching'. Together they form a unique fingerprint.

Cite this