Time-domain classification of humans using seismic sensors

Sean Schumer

doi:10.1117/12.850092

7 May 2010 Time-domain classification of humans using seismic sensors

Sean Schumer

Proceedings Volume 7693, Unattended Ground, Sea, and Air Sensor Technologies and Applications XII; 769311 (2010) https://doi.org/10.1117/12.850092
Event: SPIE Defense, Security, and Sensing, 2010, Orlando, Florida, United States

Abstract

Methods of human classification and direction of travel are developed for the purpose of being embedded in low-power, low-cost microprocessors. Techniques are explored for classifying an impulsive set of events in a seismic field as being either human or non-human based on information extrapolated from time-domain data of geophones. Additionally, a method of time domain direction of travel determination is explored. As a target is traversing the field of detection, simple impulse detection techniques determine seismic activities that are of interest. By recreating the time-domain signal as an average energy over time, the frequency of footstep of the target can be determined after a human has left the field by using post processing techniques, even when multiple targets are present. An autocorrelation of the energy averaged signal will yield an output that can be used to easily determine the most dominant frequency of the observed series of impulsive events. This method is capable of classifying humans under certain conditions at a rate of up to 98% with a varying rate of rejection for different types of animals and environmental factors. The technique can be easily integrated to work in conjunction with other modalities for an increase in classifier confidence.

Citation Download Citation

Sean Schumer "Time-domain classification of humans using seismic sensors", Proc. SPIE 7693, Unattended Ground, Sea, and Air Sensor Technologies and Applications XII, 769311 (7 May 2010); https://doi.org/10.1117/12.850092

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available