Publication detail

Independent Channel Residual Convolutional Network for Gunshot Detection

BAJZÍK, J. PŘINOSIL, J. JARINA, R. MEKYSKA, J.

Original Title

Independent Channel Residual Convolutional Network for Gunshot Detection

Type

journal article in Web of Science

Language

English

Original Abstract

The main purpose of this work is to propose a robust approach for dangerous sound events detection (e.g. gunshots) to improve recent surveillance systems. Despite the fact that the detection and classification of different sound events has a long history in signal processing, the analysis of environmental sounds is still challenging. The most recent works aim to prefer the time-frequency 2-D representation of sound as input to feed convolutional neural networks. This paper includes an analysis of known architectures as well as a newly proposed Independent Channel Residual Convolutional Network architecture based on standard residual blocks. Our approach consists of processing three different types of features in the individual channels. The UrbanSound8k and the Free Firearm Sound Library audio datasets are used for training and testing data generation, achieving a 98 % F1 score. The model was also evaluated in the wild using manually annotated movie audio track, achieving a 44 % F1 score, which is not too high but still better than other state-of-the-art techniques.

Keywords

Acoustic signal processing; gunshot detection systems; audio signal analysis; machine learning; deep learning; residual networks

Authors

BAJZÍK, J.; PŘINOSIL, J.; JARINA, R.; MEKYSKA, J.

Released

1. 5. 2022

Publisher

Science and Information Organization

ISBN

2156-5570

Periodical

International Journal of Advanced Computer Science and Applications

Year of study

13

Number

4

State

United Kingdom of Great Britain and Northern Ireland

Pages from

950

Pages to

958

Pages count

9

URL

https://thesai.org/Publications/ViewPaper?Volume=13&Issue=4&Code=IJACSA&SerialNo=108

Full text in the Digital Library

http://hdl.handle.net/11012/209174

BibTex

@article{BUT180622,
  author="Jakub {Bajzík} and Jiří {Přinosil} and Roman {Jarina} and Jiří {Mekyska}",
  title="Independent Channel Residual Convolutional Network for Gunshot Detection",
  journal="International Journal of Advanced Computer Science and Applications",
  year="2022",
  volume="13",
  number="4",
  pages="950--958",
  doi="10.14569/IJACSA.2022.01304108",
  issn="2156-5570",
  url="https://thesai.org/Publications/ViewPaper?Volume=13&Issue=4&Code=IJACSA&SerialNo=108"
}