An FMCW radar sensor for human gesture recognition in the presence of multiple targets

Zhengyu Peng, Changzhi Li, José María Muñoz-Ferreras, Roberto Gómez-García

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

48 Scopus citations

Abstract

Hand gesture recognition is an emerging application of portable radar sensors. Most of existing works rely on Doppler-radar sensors for non-contact detection of hand motions. However, Doppler-radar-based hand gesture recognition utilizes only the Doppler effect to extract motion features, which imposes a stringent requirement that only one motion is in the field of view of the sensor, leading to limitations in practical applications. In this paper, we investigate the feasibility of using an FMCW radar sensor with range-Doppler processing to recognize human gestures when multiple moving subjects are present in the sensor's field of view. A custom-designed portable 5.8-GHz FMCW radar is used. By using range-Doppler processing in the range-Doppler domain, experimental results enable to verify the effectiveness of the proposed radar sensor in hand gesture identification with the existence of interferences from surrounding moving targets.

Original languageEnglish
Title of host publication2017 1st IEEE MTT-S International Microwave Bio Conference, IMBioC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538617137
DOIs
StatePublished - Jun 30 2017
Event1st IEEE MTT-S International Microwave Bio Conference, IMBioC 2017 - Gothenburg, Sweden
Duration: May 15 2017May 17 2017

Publication series

Name2017 1st IEEE MTT-S International Microwave Bio Conference, IMBioC 2017

Conference

Conference1st IEEE MTT-S International Microwave Bio Conference, IMBioC 2017
Country/TerritorySweden
CityGothenburg
Period05/15/1705/17/17

Keywords

  • FMCW radar
  • Micro-Doppler
  • gesture recognition
  • micro-range
  • range-Doppler

Fingerprint

Dive into the research topics of 'An FMCW radar sensor for human gesture recognition in the presence of multiple targets'. Together they form a unique fingerprint.

Cite this