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

Author

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

Author_Institution

Holistic Electron. Res. Lab., Univ. of Cyprus, Nicosia, Cyprus

fYear

2011

fDate

10-12 Nov. 2011

Firstpage

444

Lastpage

447

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

Doppler measurement; biomedical ultrasonics; gait analysis; medical signal processing; signal classification; video signal processing; contactless systems; gait-based person; gender classification; gender recognition; micro-Doppler signatures; recognition accuracies; ultrasonic device; video-based processing; walking; Accuracy; Acoustics; Conferences; Humans; Prototypes; Sonar; Spectrogram; Micro-Doppler; gender classification; individual recognition; k-NN classifier; spectrogram; ultrasonic device;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Circuits and Systems Conference (BioCAS), 2011 IEEE

Conference_Location

San Diego, CA

Print_ISBN

978-1-4577-1469-6

Type

conf

DOI

10.1109/BioCAS.2011.6107823

Filename

6107823