Independent Channel Residual Convolutional Network for Gunshot Detection

Simple item page
dc.contributor.authorBajzík, Jakubcs
dc.contributor.authorPřinosil, Jiřícs
dc.contributor.authorJarina, Romancs
dc.contributor.authorMekyska, Jiřícs
dc.coverage.issue4cs
dc.coverage.volume13cs
dc.date.issued2022-05-01cs
dc.description.abstractThe 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.en
dc.formattextcs
dc.format.extent950-958cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationInternational Journal of Advanced Computer Science and Applications. 2022, vol. 13, issue 4, p. 950-958.en
dc.identifier.doi10.14569/IJACSA.2022.01304108cs
dc.identifier.issn2156-5570cs
dc.identifier.orcid0000-0003-3299-6204cs
dc.identifier.orcid0000-0002-6195-193Xcs
dc.identifier.other180622cs
dc.identifier.researcheridK-4001-2015cs
dc.identifier.scopus35746344400cs
dc.identifier.urihttp://hdl.handle.net/11012/209174
dc.language.isoencs
dc.publisherScience and Information Organizationcs
dc.relation.ispartofInternational Journal of Advanced Computer Science and Applicationscs
dc.relation.urihttps://thesai.org/Publications/ViewPaper?Volume=13&Issue=4&Code=IJACSA&SerialNo=108cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/2156-5570/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectAcoustic signal processingen
dc.subjectgunshot detection systemsen
dc.subjectaudio signal analysisen
dc.subjectmachine learningen
dc.subjectdeep learningen
dc.subjectresidual networksen
dc.titleIndependent Channel Residual Convolutional Network for Gunshot Detectionen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-180622en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:42:29en
sync.item.modts2025.01.17 18:34:24en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav telekomunikacícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Paper_108.pdf
Size:
3.77 MB
Format:
Adobe Portable Document Format
Description:
Paper_108.pdf
Download
Collections
Ústav telekomunikací