Micro-doppler radar classification of human motions under various training scenarios

Dustin P. Fairchild, Ram Mohan Narayanan

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

16 Scopus citations

Abstract

The identification and classification of human motions has become a popular area of research due to its broad range of applications. Knowledge of a person's movements can be a useful tool in surveillance, security, military combat, search and rescue operations, and the medical fields. Classification of common stationary human movements has been performed under various scenarios for two different micro-Doppler radar systems: S-band radar and millimeter-wave (mm-wave) radar. Each radar system has been designed for a specific scenario. The S-band radar is intended for through-the-wall situations at close distances, whereas the mm-wave radar is designed for long distance applications and also for through light foliage. Here, the performance of these radars for different training scenarios is investigated. The S-band radar will be analyzed for classification without a wall barrier, through a brick wall, and also through a cinder block wall. The effect of a wall barrier on micro-Doppler signatures will be briefly discussed. The mm-wave radar will be analyzed for classification at distances of 30, 60, and 91 meters.

Original languageEnglish (US)
Title of host publicationActive and Passive Signatures IV
Volume8734
DOIs
StatePublished - 2013
EventActive and Passive Signatures IV - Baltimore, MD, United States
Duration: May 1 2013May 2 2013

Other

OtherActive and Passive Signatures IV
CountryUnited States
CityBaltimore, MD
Period5/1/135/2/13

All Science Journal Classification (ASJC) codes

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Fingerprint Dive into the research topics of 'Micro-doppler radar classification of human motions under various training scenarios'. Together they form a unique fingerprint.

Cite this