Clothes-invariant gait identification using part-based adaptive weight control

This paper describes a method of part-based gait identification under substantial clothes variations. When clothes types between a gallery and a probe are different, silhouettes fairly change for some parts and subject discrimination capability decrease for those parts. Therefore, we exploit the dis...

Full description

Saved in:
Bibliographic Details
Published in2008 19th International Conference on Pattern Recognition pp. 1 - 4
Main Authors Hossain, M.A., Makihara, Y., Wang Junqui, Yagi, Y.
Format Conference Proceeding
LanguageEnglish
Japanese
Published IEEE 01.12.2008
Subjects
Adaptive control
Feature extraction
Phase measurement
Probes
Programmable control
Rain
Testing
Weight control
Yagi-Uda antennas
Online AccessGet full text
ISBN9781424421749
1424421748
ISSN1051-4651
DOI10.1109/ICPR.2008.4761436

Cover

More Information
Summary:This paper describes a method of part-based gait identification under substantial clothes variations. When clothes types between a gallery and a probe are different, silhouettes fairly change for some parts and subject discrimination capability decrease for those parts. Therefore, we exploit the discrimination capability as a matching weight for each part and control the weights adaptively based on a distribution of distances between a probe and all the galleries. As a result of experiments with our clothes-variation gait dataset, the proposed method achieved much better performance than a whole-based approach.
ISBN:9781424421749
1424421748
ISSN:1051-4651
DOI:10.1109/ICPR.2008.4761436