4 June 2014 Feature extraction from time domain acoustic signatures of weapons systems fire
Author Affiliations +
Abstract
The U.S. Army is interested in developing algorithms to classify weapons systems fire based on their acoustic signatures. To support this effort, an algorithm was developed to extract features from acoustic signatures of weapons systems fire and applied to over 1300 signatures. The algorithm filtered the data using standard techniques then estimated the amplitude and time of the first five peaks and troughs and the location of the zero crossing in the waveform. The results were stored in Excel spreadsheets. The results are being used to develop and test acoustic classifier algorithms.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Christine Yang, Geoffrey H. Goldman, "Feature extraction from time domain acoustic signatures of weapons systems fire", Proc. SPIE 9082, Active and Passive Signatures V, 90820E (4 June 2014); doi: 10.1117/12.2070455; https://doi.org/10.1117/12.2070455
PROCEEDINGS
9 PAGES


SHARE
Back to Top