Skip navigation
Skip navigation

Gait recognition under various viewing angles based on correlated motion regression

Kusakunniran, Worapan; Wu, Qiang; Zhang, Jian; Li, Hongdong

Description

It is well recognized that gait is an important biometric feature to identify a person at a distance, e.g., in video surveillance application. However, in reality, change of viewing angle causes significant challenge for gait recognition. A novel approach using regression-based view transformation model (VTM) is proposed to address this challenge. Gait features from across views can be normalized into a common view using learned VTM(s). In principle, a VTM is used to transform gait feature from...[Show more]

dc.contributor.authorKusakunniran, Worapan
dc.contributor.authorWu, Qiang
dc.contributor.authorZhang, Jian
dc.contributor.authorLi, Hongdong
dc.date.accessioned2015-12-10T23:15:40Z
dc.identifier.issn1051-8215
dc.identifier.urihttp://hdl.handle.net/1885/64743
dc.description.abstractIt is well recognized that gait is an important biometric feature to identify a person at a distance, e.g., in video surveillance application. However, in reality, change of viewing angle causes significant challenge for gait recognition. A novel approach using regression-based view transformation model (VTM) is proposed to address this challenge. Gait features from across views can be normalized into a common view using learned VTM(s). In principle, a VTM is used to transform gait feature from one viewing angle (source) into another viewing angle (target). It consists of multiple regression processes to explore correlated walking motions, which are encoded in gait features, between source and target views. In the learning processes, sparse regression based on the elastic net is adopted as the regression function, which is free from the problem of overfitting and results in more stable regression models for VTM construction. Based on widely adopted gait database, experimental results show that the proposed method significantly improves upon existing VTM-based methods and outperforms most other baseline methods reported in the literature. Several practical scenarios of applying the proposed method for gait recognition under various views are also discussed in this paper.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.sourceIEEE Transactions on Circuits and Systems for Video Technology
dc.subjectKeywords: Cross-view; Gait recognition; LDA; Multi-views; PCA; Sparse regression; View transformations; Biometrics; Gait analysis; Security systems; Regression analysis Cross-view; gait recognition; LDA; multiview; PCA; sparse regression; view transformation model (VTM)
dc.titleGait recognition under various viewing angles based on correlated motion regression
dc.typeJournal article
local.description.notesImported from ARIES
local.identifier.citationvolume22
dc.date.issued2012
local.identifier.absfor090601 - Circuits and Systems
local.identifier.absfor080104 - Computer Vision
local.identifier.ariespublicationf5625xPUB991
local.type.statusPublished Version
local.contributor.affiliationKusakunniran, Worapan, University of New South Wales
local.contributor.affiliationWu, Qiang, University of Technology Sydney
local.contributor.affiliationZhang, Jian, NICTA
local.contributor.affiliationLi, Hongdong, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.bibliographicCitation.issue6
local.bibliographicCitation.startpage966
local.bibliographicCitation.lastpage980
local.identifier.doi10.1109/TCSVT.2012.2186744
local.identifier.absseo970109 - Expanding Knowledge in Engineering
dc.date.updated2016-02-24T09:46:35Z
local.identifier.scopusID2-s2.0-84861965822
local.identifier.thomsonID000305180600013
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Kusakunniran_Gait_recognition_under_various_2012.pdf6.15 MBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator