Gait based gender recognition using sparse spatio temporal features

Matthew Collins; Paul Miller; Jianguo Zhang

doi:10.1007/978-3-319-04117-9_8

Gait based gender recognition using sparse spatio temporal features

Matthew Collins
, Paul Miller
, Jianguo Zhang

Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

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.

Original language	English
Title of host publication	MultiMedia Modeling
Subtitle of host publication	20th Anniversary International Conference, MMM 2014, Dublin, Ireland, January 6-10, 2014, Proceedings, Part II
Editors	Cathal Gurrin, Frank Hopfgartner, Wolfgang Hurst, Håvard Johansen, Hyowon Lee, Noel O’Connor
Place of Publication	Berlin
Publisher	Springer
Pages	80-91
Number of pages	12
Volume	8326
ISBN (Electronic)	9783319041179
ISBN (Print)	9783319041162
DOIs	https://doi.org/10.1007/978-3-319-04117-9_8
Publication status	Published - 2014
Event	20th Anniversary International Conference on MultiMedia Modeling - Conference Centre inside the Guinness Storehouse, Dublin, United Kingdom Duration: 6 Jan 2014 → 10 Jan 2014 http://mmm2014.org/

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	8326
ISSN (Print)	0302-9743

Conference

Conference	20th Anniversary International Conference on MultiMedia Modeling
Abbreviated title	MMM 2014
Country/Territory	United Kingdom
City	Dublin
Period	6/01/14 → 10/01/14
Internet address	http://mmm2014.org/

Access to Document

10.1007/978-3-319-04117-9_8

http://library.dundee.ac.uk/F/HS7M3BJEB4NIVGYAGJ4Y9F6GUMD7UE2BHXTTHHPTN8KA82QXYA-23783?func=find-e&adjacent=N&request=9783319041179&find_scan_code=FIND_WRD&x=60&y=6

Gait based gender recognition using sparse spatio temporal features
Collins, M., Miller, P. & Zhang, J., 2014.
Research output: Contribution to conference › Paper

20th Anniversary International Conference on MultiMedia Modeling
Zhang, J. (Participant)
9 Jan 2014
Activity: Participating in or organising an event types › Participation in conference

Cite this

Collins, M., Miller, P., & Zhang, J. (2014). Gait based gender recognition using sparse spatio temporal features. In C. Gurrin, F. Hopfgartner, W. Hurst, H. Johansen, H. Lee, & N. O’Connor (Eds.), MultiMedia Modeling: 20th Anniversary International Conference, MMM 2014, Dublin, Ireland, January 6-10, 2014, Proceedings, Part II (Vol. 8326, pp. 80-91). (Lecture notes in computer science; Vol. 8326). Springer . https://doi.org/10.1007/978-3-319-04117-9_8

Collins, Matthew ; Miller, Paul ; Zhang, Jianguo. / Gait based gender recognition using sparse spatio temporal features. MultiMedia Modeling: 20th Anniversary International Conference, MMM 2014, Dublin, Ireland, January 6-10, 2014, Proceedings, Part II. editor / Cathal Gurrin ; Frank Hopfgartner ; Wolfgang Hurst ; Håvard Johansen ; Hyowon Lee ; Noel O’Connor. Vol. 8326 Berlin : Springer , 2014. pp. 80-91 (Lecture notes in computer science).

@inproceedings{8fd4de99e55244378703eb8a6139116b,

title = "Gait based gender recognition using sparse spatio temporal features",

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.",

author = "Matthew Collins and Paul Miller and Jianguo Zhang",

year = "2014",

doi = "10.1007/978-3-319-04117-9\_8",

language = "English",

isbn = "9783319041162",

volume = "8326",

series = "Lecture notes in computer science",

publisher = "Springer ",

pages = "80--91",

editor = "Gurrin, \{Cathal \} and Hopfgartner, \{Frank \} and Hurst, \{Wolfgang \} and Johansen, \{H{\aa}vard \} and Lee, \{Hyowon \} and O{\textquoteright}Connor, \{Noel \}",

booktitle = "MultiMedia Modeling",

note = "20th Anniversary International Conference on MultiMedia Modeling , MMM 2014 ; Conference date: 06-01-2014 Through 10-01-2014",

url = "http://mmm2014.org/",

}

Collins, M, Miller, P & Zhang, J 2014, Gait based gender recognition using sparse spatio temporal features. in C Gurrin, F Hopfgartner, W Hurst, H Johansen, H Lee & N O’Connor (eds), MultiMedia Modeling: 20th Anniversary International Conference, MMM 2014, Dublin, Ireland, January 6-10, 2014, Proceedings, Part II. vol. 8326, Lecture notes in computer science, vol. 8326, Springer , Berlin, pp. 80-91, 20th Anniversary International Conference on MultiMedia Modeling , Dublin, United Kingdom, 6/01/14. https://doi.org/10.1007/978-3-319-04117-9_8

Gait based gender recognition using sparse spatio temporal features. / Collins, Matthew; Miller, Paul; Zhang, Jianguo.
MultiMedia Modeling: 20th Anniversary International Conference, MMM 2014, Dublin, Ireland, January 6-10, 2014, Proceedings, Part II. ed. / Cathal Gurrin; Frank Hopfgartner; Wolfgang Hurst; Håvard Johansen; Hyowon Lee; Noel O’Connor. Vol. 8326 Berlin: Springer , 2014. p. 80-91 (Lecture notes in computer science; Vol. 8326).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Gait based gender recognition using sparse spatio temporal features

AU - Collins, Matthew

AU - Miller, Paul

AU - Zhang, Jianguo

PY - 2014

Y1 - 2014

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-319-04117-9_8

DO - 10.1007/978-3-319-04117-9_8

M3 - Conference contribution

SN - 9783319041162

VL - 8326

T3 - Lecture notes in computer science

SP - 80

EP - 91

BT - MultiMedia Modeling

A2 - Gurrin, Cathal

A2 - Hopfgartner, Frank

A2 - Hurst, Wolfgang

A2 - Johansen, Håvard

A2 - Lee, Hyowon

A2 - O’Connor, Noel

PB - Springer

CY - Berlin

T2 - 20th Anniversary International Conference on MultiMedia Modeling

Y2 - 6 January 2014 through 10 January 2014

ER -

Collins M, Miller P, Zhang J. Gait based gender recognition using sparse spatio temporal features. In Gurrin C, Hopfgartner F, Hurst W, Johansen H, Lee H, O’Connor N, editors, MultiMedia Modeling: 20th Anniversary International Conference, MMM 2014, Dublin, Ireland, January 6-10, 2014, Proceedings, Part II. Vol. 8326. Berlin: Springer . 2014. p. 80-91. (Lecture notes in computer science). doi: 10.1007/978-3-319-04117-9_8

Gait based gender recognition using sparse spatio temporal features

Abstract

Publication series

Conference

Access to Document

Fingerprint

Research output

Gait based gender recognition using sparse spatio temporal features

Activities

20th Anniversary International Conference on MultiMedia Modeling

Cite this