Towards robust gait recognition

Tenika Whytock, Alexander Belyaev, Neil Robertson

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

5 Citations (Scopus)

Abstract

Covariate factors, such as persons carrying a bag and wearing a jacket, continue to cause significant misclassification in gait recognition. A novel and efficient approach learns a “typical” Gait Energy Image representation free from covariate factors which aids their mitigation in test and training data. Combating the influence of covariate factors yields a significant improvement of 11% over existing state of the art performance for sequences capturing persons wearing a jacket.
Original languageEnglish
Title of host publicationAdvances in Visual Computing
Subtitle of host publication9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings, Part II
EditorsGeorge Bebis , Richard Boyle , Bahram Parvin, Darko Koracin, Baoxin Li, Fatih Porikli, Victor Zordan, James Klosowski , Sabine Coquillart , Xun Luo, Min Chen, David Gotz
Pages523-531
Number of pages9
ISBN (Electronic)978-3-642-41939-3
DOIs
Publication statusPublished - 2013

Publication series

NameLecture Notes in Computer Science
Volume8034
ISSN (Electronic)0302-9743

Fingerprint

Dive into the research topics of 'Towards robust gait recognition'. Together they form a unique fingerprint.

Cite this