Remote detection of humans and animals

Author

Tahmoush, Dave ; Silvious, Jerry

Author_Institution

US Army Res. Lab., Adelphi, MD, USA

fYear

2009

fDate

14-16 Oct. 2009

Firstpage

1

Lastpage

8

Abstract

Detecting humans and distinguishing them from natural fauna is an important issue in border security applications. In particular, it is important to detect and classify people who are walking in remote locations and transmit back detections over extended periods at a low cost and with minimal maintenance. Our simulation and measurement work has been relatively successful in providing a qualitative guide to improving our analysis, and has produced a reasonable model for studying signatures using radar micro-Doppler. This paper presents data on humans and animals at multiple angles and directions of motion, as well as features that can be extracted from radar data for the classification as animal versus human.

Keywords

Doppler radar; feature extraction; image classification; image motion analysis; animal remote detection; border security application; feature extraction; human remote detection; image classification; motion direction; multiple angle; radar microDoppler; Animals; Arm; Doppler radar; Frequency; Humans; Leg; Legged locomotion; Radar cross section; Radar measurements; Radar tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Applied Imagery Pattern Recognition Workshop (AIPRW), 2009 IEEE

Conference_Location

Washington, DC

ISSN

1550-5219

Print_ISBN

978-1-4244-5146-3

Electronic_ISBN

1550-5219

Type

conf

DOI

10.1109/AIPR.2009.5466303

Filename

5466303