Robust discrimination of human footsteps using seismic signals

Aram E. Faghfouri; Michael B. Frish

doi:10.1117/12.882726

23 May 2011 Robust discrimination of human footsteps using seismic signals

Aram E. Faghfouri, Michael B. Frish

Proceedings Volume 8046, Unattended Ground, Sea, and Air Sensor Technologies and Applications XIII; 80460D (2011) https://doi.org/10.1117/12.882726
Event: SPIE Defense, Security, and Sensing, 2011, Orlando, Florida, United States

Abstract

This paper provides a statistical analysis method for detecting and discriminating different seismic activity sources such as humans, animals, and vehicles using their seismic signals. A five-step process is employed for this purpose: (1) a set of signals with known seismic activities are utilized to verify the algorithms; (2) for each data file, the vibration signal is segmented by a sliding-window and its noise is reduced; (3) a set of features is extracted from each window of the signal which captures its statistical and spectral properties. This set is formed as an array and is called a feature array; (4) a portion of the labeled feature arrays are utilized to train a classifier for discriminating different types of signals; and (5) the rest of the labeled feature arrays are employed to test the performance of the developed classifier. The results indicate that the classifier achieves probability of detection (p_d) above 95% and false alarm rate (p_fa) less than 1%.

Citation Download Citation

Aram E. Faghfouri and Michael B. Frish "Robust discrimination of human footsteps using seismic signals", Proc. SPIE 8046, Unattended Ground, Sea, and Air Sensor Technologies and Applications XIII, 80460D (23 May 2011); https://doi.org/10.1117/12.882726

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