Publication detail

Efficient Feature Set Developed for Acoustic Gunshot Detection in Open Space

SIGMUND, M. HRABINA, M.

Original Title

Efficient Feature Set Developed for Acoustic Gunshot Detection in Open Space

Type

journal article in Web of Science

Language

English

Original 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 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. In binary classification, the developed approach achieved an accuracy of 95.02 % in gunshot detection.

Keywords

Acoustic signal processing; gunshot detection; neural networks; parameter estimation

Authors

SIGMUND, M.; HRABINA, M.

Released

23. 8. 2021

Publisher

Kaunas University of Technology

Location

Kaunas

ISBN

1392-1215

Periodical

Elektronika Ir Elektrotechnika

Year of study

27

Number

4

State

Republic of Lithuania

Pages from

62

Pages to

68

Pages count

7

URL

https://eejournal.ktu.lt/index.php/elt/article/view/28877

Full text in the Digital Library

http://hdl.handle.net/11012/203054

BibTex

@article{BUT173150,
  author="Milan {Sigmund} and Martin {Hrabina}",
  title="Efficient Feature Set Developed for Acoustic Gunshot Detection in Open Space",
  journal="Elektronika Ir Elektrotechnika",
  year="2021",
  volume="27",
  number="4",
  pages="62--68",
  doi="10.5755/j02.eie.28877",
  issn="1392-1215",
  url="https://eejournal.ktu.lt/index.php/elt/article/view/28877"
}