Gait-based person and gender recognition using micro-doppler signatures

Guillaume Garreau; Charalambos M. Andreou; Andreas G. Andreou; Julius Georgiou; Salvador Dura-Bernal; Thomas Wennekers; Sue Denham

doi:10.1109/BioCAS.2011.6107823

Gait-based person and gender recognition using micro-doppler signatures

Guillaume Garreau
, Charalambos M. Andreou
, Andreas G. Andreou
, Julius Georgiou
, Salvador Dura-Bernal
, Thomas Wennekers
, Sue Denham

Physiology / Pharmacology

SUNY Downstate Health Sciences University

University of Cyprus
University of Plymouth

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

29 Scopus citations

Abstract

The ability to identify an individual quickly and accurately is a critical parameter in surveillance. Conventional contactless systems are often complex and expensive to implement since video-based processing requires high computational resources. In this paper we present a micro-Doppler (mD) system and a computationally efficient classifier for the purpose of identifying individuals and gender. Walking subjects are successfully classified based on their mD time-frequency signatures. Recognition accuracies as high as 100% are obtained for some individuals and 92% for gender classification.

Original language	English
Title of host publication	2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011
Pages	444-447
Number of pages	4
DOIs	https://doi.org/10.1109/BioCAS.2011.6107823
State	Published - 2011
Event	2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011 - San Diego, CA, United States Duration: Nov 10 2011 → Nov 12 2011

Publication series

Name	2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011

Conference

Conference	2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011
Country/Territory	United States
City	San Diego, CA
Period	11/10/11 → 11/12/11

Keywords

Micro-Doppler
gender classification
individual recognition
k-NN classifier
spectrogram
ultrasonic device

Access to Document

10.1109/BioCAS.2011.6107823

Cite this

Garreau, G., Andreou, C. M., Andreou, A. G., Georgiou, J., Dura-Bernal, S., Wennekers, T., & Denham, S. (2011). Gait-based person and gender recognition using micro-doppler signatures. In 2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011 (pp. 444-447). Article 6107823 (2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011). https://doi.org/10.1109/BioCAS.2011.6107823

@inproceedings{6351570e7dc24c77918d765cf8b6fc9f,

title = "Gait-based person and gender recognition using micro-doppler signatures",

abstract = "The ability to identify an individual quickly and accurately is a critical parameter in surveillance. Conventional contactless systems are often complex and expensive to implement since video-based processing requires high computational resources. In this paper we present a micro-Doppler (mD) system and a computationally efficient classifier for the purpose of identifying individuals and gender. Walking subjects are successfully classified based on their mD time-frequency signatures. Recognition accuracies as high as 100\% are obtained for some individuals and 92\% for gender classification.",

keywords = "Micro-Doppler, gender classification, individual recognition, k-NN classifier, spectrogram, ultrasonic device",

author = "Guillaume Garreau and Andreou, \{Charalambos M.\} and Andreou, \{Andreas G.\} and Julius Georgiou and Salvador Dura-Bernal and Thomas Wennekers and Sue Denham",

year = "2011",

doi = "10.1109/BioCAS.2011.6107823",

language = "English",

isbn = "9781457714696",

series = "2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011",

pages = "444--447",

booktitle = "2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011",

note = "2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011 ; Conference date: 10-11-2011 Through 12-11-2011",

}

Garreau, G, Andreou, CM, Andreou, AG, Georgiou, J, Dura-Bernal, S, Wennekers, T & Denham, S 2011, Gait-based person and gender recognition using micro-doppler signatures. in 2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011., 6107823, 2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011, pp. 444-447, 2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011, San Diego, CA, United States, 11/10/11. https://doi.org/10.1109/BioCAS.2011.6107823

Gait-based person and gender recognition using micro-doppler signatures. / Garreau, Guillaume; Andreou, Charalambos M.; Andreou, Andreas G. et al.
2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011. 2011. p. 444-447 6107823 (2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011).

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

TY - GEN

T1 - Gait-based person and gender recognition using micro-doppler signatures

AU - Garreau, Guillaume

AU - Andreou, Charalambos M.

AU - Andreou, Andreas G.

AU - Georgiou, Julius

AU - Dura-Bernal, Salvador

AU - Wennekers, Thomas

AU - Denham, Sue

PY - 2011

Y1 - 2011

N2 - The ability to identify an individual quickly and accurately is a critical parameter in surveillance. Conventional contactless systems are often complex and expensive to implement since video-based processing requires high computational resources. In this paper we present a micro-Doppler (mD) system and a computationally efficient classifier for the purpose of identifying individuals and gender. Walking subjects are successfully classified based on their mD time-frequency signatures. Recognition accuracies as high as 100% are obtained for some individuals and 92% for gender classification.

AB - The ability to identify an individual quickly and accurately is a critical parameter in surveillance. Conventional contactless systems are often complex and expensive to implement since video-based processing requires high computational resources. In this paper we present a micro-Doppler (mD) system and a computationally efficient classifier for the purpose of identifying individuals and gender. Walking subjects are successfully classified based on their mD time-frequency signatures. Recognition accuracies as high as 100% are obtained for some individuals and 92% for gender classification.

KW - Micro-Doppler

KW - gender classification

KW - individual recognition

KW - k-NN classifier

KW - spectrogram

KW - ultrasonic device

UR - https://www.scopus.com/pages/publications/84855691037

U2 - 10.1109/BioCAS.2011.6107823

DO - 10.1109/BioCAS.2011.6107823

M3 - Conference contribution

SN - 9781457714696

T3 - 2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011

SP - 444

EP - 447

BT - 2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011

T2 - 2011 IEEE Biomedical Circuits and Systems Conference, BioCAS 2011

Y2 - 10 November 2011 through 12 November 2011

ER -

Gait-based person and gender recognition using micro-doppler signatures

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this