Acoustic classification of battlefield transient events using wavelet sub-band features

M. R. Azimi-Sadjadi; Y. Jiang; S. Srinivasan

doi:10.1117/12.722296

11 May 2007 Acoustic classification of battlefield transient events using wavelet sub-band features

M. R. Azimi-Sadjadi, Y. Jiang, S. Srinivasan

Proceedings Volume 6562, Unattended Ground, Sea, and Air Sensor Technologies and Applications IX; 656215 (2007) https://doi.org/10.1117/12.722296
Event: Defense and Security Symposium, 2007, Orlando, Florida, United States

Abstract

Detection, localization and classification of battlefield acoustic transient events are of great importance especially for military operations in urban terrain (MOUT). Generally, there can be a wide variety of battlefield acoustic transient events such as different caliber gunshots, artillery fires, and mortar fires. The discrimination of different types of transient sources is plagued by highly non-stationary nature of these signals, which makes the extraction of representative features a challenging task. This is compounded by the variations in the environmental and operating conditions and existence of a wide range of possible interference. This paper presents new approaches for transient signal estimation and feature extraction from acoustic signatures collected by several distributed sensor nodes. A maximum likelihood (ML)-based method is developed to remove noise/interference and fading effects and restore the acoustic transient signals. The estimated transient signals are then represented using wavelets. The multi-resolution property of the wavelets allows for capturing fine details in the transient signals that can be utilized to successfully classify them. Wavelet sub-band higher order moments and energy-based features are used to characterize the transient signals. The discrimination ability of the subband features for transient signal classification has been demonstrated on several different caliber gunshots. Important findings and observations on these results are also presented.

Citation Download Citation

M. R. Azimi-Sadjadi, Y. Jiang, and S. Srinivasan "Acoustic classification of battlefield transient events using wavelet sub-band features", Proc. SPIE 6562, Unattended Ground, Sea, and Air Sensor Technologies and Applications IX, 656215 (11 May 2007); https://doi.org/10.1117/12.722296

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