Přístupnostní navigace
E-application
Search Search Close
Publication detail
BAJZÍK, J. PŘINOSIL, J. KONIAR, D.
Original Title
Gunshot detection using convolutional neural networks
Type
conference paper
Language
English
Original Abstract
The main paper deals with the analysis of the methods of signal processing and events recognition in the audio signal and the implementation of the selected method in real use. Recognized events are gunshots mixed with a background sound such as traffic noise, human voice, animal sounds and other forms of environmental sounds. The proposed algorithm adapted for explosion detection can be used as part of a security system for monitoring depots or places dedicated to storing dangerous materials. For events classification and class recognition, the freely available machine learning frameworks TensorFlow and Keras are used.
Keywords
Acoustic signal processing, Gunshot detection systems, Image processing, Signal analysis.
Authors
BAJZÍK, J.; PŘINOSIL, J.; KONIAR, D.
Released
15. 6. 2020
Publisher
Institute of Electrical and Electronics Engineers Inc.
Location
Litva
ISBN
978-1-7281-5868-6
Book
24th International Conference Electronics, ELECTRONICS 2020
Pages from
1
Pages to
5
Pages count
URL
https://ieeexplore.ieee.org/document/9141621
BibTex
@inproceedings{BUT165911, author="Jakub {Bajzík} and Jiří {Přinosil} and Dušan {Koniar}", title="Gunshot detection using convolutional neural networks", booktitle="24th International Conference Electronics, ELECTRONICS 2020", year="2020", pages="1--5", publisher="Institute of Electrical and Electronics Engineers Inc.", address="Litva", doi="10.1109/IEEECONF49502.2020.9141621", isbn="978-1-7281-5868-6", url="https://ieeexplore.ieee.org/document/9141621" }