Efficient Feature Set Developed for Acoustic Gunshot Detection in Open Space

Authors

  • Milan Sigmund Faculty of Electrical Engineering and Communication, Brno University of Technology, Czech Republic
  • Martin Hrabina Faculty of Electrical Engineering and Communication, Brno University of Technology, Czech Republic

DOI:

https://doi.org/10.5755/j02.eie.28877

Keywords:

Acoustic signal processing, Gunshot detection, Neural networks, Parameter estimation

Abstract

This paper presents an efficient approach to automatic gunshot detection based on a combination of two feature sets: adapted standard sound features and hand-crafted novel features. The standard features are mel-frequency cepstral coefficients adapted for gunshot recognition in terms of uniform gamma-tone filters linearly spaced over the whole frequency range from 0 kHz to 16 kHz. The first 18 coefficients calculated from the 41 filters represent the best set of the optimized cepstral coefficients. The novel features were derived in the time domain from individual significant points of the raw waveform after amplitude normalization. Experiments were performed using single and ensemble neural networks to verify the effectiveness of the novel features for supplementing the standard features. The novelty of the work is the proposed feature combination, which allows to achieve very effective detection of gunshots from hunting weapons using 23 features and a simple neural network. In binary classification, the developed approach achieved an accuracy of 95.02 % in gunshot detection and 98.16 % in disregarding other sounds (i.e., non-gunshot).

Downloads

Published

2021-08-23

How to Cite

Sigmund, M., & Hrabina, M. (2021). Efficient Feature Set Developed for Acoustic Gunshot Detection in Open Space. Elektronika Ir Elektrotechnika, 27(4), 62-68. https://doi.org/10.5755/j02.eie.28877

Issue

Section

SIGNAL TECHNOLOGY

Funding data