Computationally efficient classification of human transport mode using micro-Doppler signatures

Guillaume Garreau, Nicoletta Nicolaou, Charalambos Andreou, Cyrille D'Urbal, Guillermo Stuarts, Julius Georgiou

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

7 Citations (Scopus)

Abstract

In this paper we present a micro-Doppler (mD) system and a computationally efficient classifier for the purpose of distinguishing different means of transport for human beings (pedestrians, inline skaters and cyclists) based on their mD time-frequency signatures. Accuracies as high as 97% are obtained while keeping the overall computational cost low.

Original languageEnglish
Title of host publication2011 45th Annual Conference on Information Sciences and Systems, CISS 2011
DOIs
Publication statusPublished - 6 Jun 2011
Externally publishedYes
Event2011 45th Annual Conference on Information Sciences and Systems, CISS 2011 - Baltimore, MD, United States
Duration: 23 Mar 201125 Mar 2011

Conference

Conference2011 45th Annual Conference on Information Sciences and Systems, CISS 2011
CountryUnited States
CityBaltimore, MD
Period23/03/1125/03/11

Keywords

  • Micro-Doppler
  • spectrogram
  • standard deviation
  • transport mode
  • ultrasonic device

Fingerprint Dive into the research topics of 'Computationally efficient classification of human transport mode using micro-Doppler signatures'. Together they form a unique fingerprint.

  • Cite this

    Garreau, G., Nicolaou, N., Andreou, C., D'Urbal, C., Stuarts, G., & Georgiou, J. (2011). Computationally efficient classification of human transport mode using micro-Doppler signatures. In 2011 45th Annual Conference on Information Sciences and Systems, CISS 2011 [5766136] https://doi.org/10.1109/CISS.2011.5766136