Multi-resolution template kernels

C. J. Needham*, R. D. Boyle

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

Abstract

Domains in which shapes of objects change rapidly and significantly are a challenge for existing representation techniques: sport is a good example of this. We present a texture-based approach that copes with these problems in addition to resolution variation. A set of exemplar poses are learned from subsampled example images of the target object, creating a set of multi-resolution template kernels which when convolved with the image respond suitably. This technique may then be used in established tracking algorithms (e.g. CONDENSATION). We demonstrate the technique in two domains, and suggest a Markov approach using it to model behaviour.

Original languageEnglish
Title of host publicationProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
EditorsJ. Kittler, M. Petrou, M. Nixon
Pages233-236
Number of pages4
DOIs
Publication statusPublished - 2004
Externally publishedYes
EventProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 - Cambridge, United Kingdom of Great Britain and Northern Ireland
Duration: 23 Aug 200426 Aug 2004

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2
ISSN (Print)1051-4651

Conference

ConferenceProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
Country/TerritoryUnited Kingdom of Great Britain and Northern Ireland
CityCambridge
Period23 Aug 200426 Aug 2004

Fingerprint

Dive into the research topics of 'Multi-resolution template kernels'. Together they form a unique fingerprint.

Cite this