Discovery - University of Dundee - Online Publications

Library & Learning Centre

Gait based gender recognition using sparse spatio temporal features

Gait based gender recognition using sparse spatio temporal features

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

View graph of relations

Authors

Research units

Info

Original languageEnglish
Title of host publicationMultiMedia Modeling
Subtitle of host publication20th Anniversary International Conference, MMM 2014, Dublin, Ireland, January 6-10, 2014, Proceedings, Part II
EditorsCathal Gurrin, Frank Hopfgartner, Wolfgang Hurst, Håvard Johansen, Hyowon Lee, Noel O’Connor
Place of PublicationBerlin
PublisherSpringer
Pages80-91
Number of pages12
Volume8326
ISBN (Electronic)9783319041179
ISBN (Print)9783319041162
DOIs
StatePublished - 2014
Event20th Anniversary International Conference on MultiMedia Modeling - Dublin, United Kingdom

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume8326
ISSN (Print)0302-9743

Conference

Conference20th Anniversary International Conference on MultiMedia Modeling
Abbreviated titleMMM 2014
CountryUnited Kingdom
CityDublin
Period6/01/1410/01/14
Internet address

Abstract

A gender balanced dataset of 101 pedestrians on a treadmill is presented. Gait is analysed for gender classification using a modification of a framework which has previously proven effective when used in behaviour recognition experiments. Sparse spatio temporal features from the video clips are classified using Support Vector Machines. Tuning parameters are investigated to find an effective feature descriptor for gender separation and an accuracy of 87% is achieved.

Research outputs

Activities

Documents

Library & Learning Centre

Contact | Accessibility | Policy