Sound of guns: digital forensics of gun audio samples meets artificial intelligence
<p>Classifying a weapon based on its muzzle blast is a challenging task that has significant applications in various security and military fields. Most of the existing works rely on ad-hoc deployment of spatially diverse microphone sensors to capture multiple replicas of the same gunshot, whic...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , |
| Published: |
2022
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513567560040448 |
|---|---|
| author | Simone Raponi (14158911) |
| author2 | Gabriele Oligeri (14151426) Isra Mohamed Ali (14151429) |
| author2_role | author author |
| author_facet | Simone Raponi (14158911) Gabriele Oligeri (14151426) Isra Mohamed Ali (14151429) |
| author_role | author |
| dc.creator.none.fl_str_mv | Simone Raponi (14158911) Gabriele Oligeri (14151426) Isra Mohamed Ali (14151429) |
| dc.date.none.fl_str_mv | 2022-04-06T06:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1007/s11042-022-12612-w |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Sound_of_guns_digital_forensics_of_gun_audio_samples_meets_artificial_intelligence/21597417 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Information and computing sciences Artificial intelligence Computer vision and multimedia computation Cybersecurity and privacy Distributed computing and systems software Machine learning Multimedia Forensics AI-driven Forensics Gun Audio Sample Classification Convolutional Neural Network |
| dc.title.none.fl_str_mv | Sound of guns: digital forensics of gun audio samples meets artificial intelligence |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p>Classifying a weapon based on its muzzle blast is a challenging task that has significant applications in various security and military fields. Most of the existing works rely on ad-hoc deployment of spatially diverse microphone sensors to capture multiple replicas of the same gunshot, which enables accurate detection and identification of the acoustic source. However, carefully controlled setups are difficult to obtain in scenarios such as crime scene forensics, making the aforementioned techniques inapplicable and impractical. We introduce a novel technique that requires zero knowledge about the recording setup and is completely agnostic to the relative positions of both the microphone and shooter. Our solution can identify the category, caliber, and model of the gun, reaching over 90% accuracy on a dataset composed of 3655 samples that are extracted from YouTube videos. Our results demonstrate the effectiveness and efficiency of applying Convolutional Neural Network (CNN) in gunshot classification eliminating the need for an ad-hoc setup while significantly improving the classification performance.</p><h2>Other Information</h2> <p> Published in: Multimedia Tools and Applications<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1007/s11042-022-12612-w" target="_blank">http://dx.doi.org/10.1007/s11042-022-12612-w</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_2eeeb73155469e4fc5f1dbd8508dc9fb |
| identifier_str_mv | 10.1007/s11042-022-12612-w |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/21597417 |
| publishDate | 2022 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Sound of guns: digital forensics of gun audio samples meets artificial intelligenceSimone Raponi (14158911)Gabriele Oligeri (14151426)Isra Mohamed Ali (14151429)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationCybersecurity and privacyDistributed computing and systems softwareMachine learningMultimedia ForensicsAI-driven ForensicsGun Audio Sample ClassificationConvolutional Neural Network<p>Classifying a weapon based on its muzzle blast is a challenging task that has significant applications in various security and military fields. Most of the existing works rely on ad-hoc deployment of spatially diverse microphone sensors to capture multiple replicas of the same gunshot, which enables accurate detection and identification of the acoustic source. However, carefully controlled setups are difficult to obtain in scenarios such as crime scene forensics, making the aforementioned techniques inapplicable and impractical. We introduce a novel technique that requires zero knowledge about the recording setup and is completely agnostic to the relative positions of both the microphone and shooter. Our solution can identify the category, caliber, and model of the gun, reaching over 90% accuracy on a dataset composed of 3655 samples that are extracted from YouTube videos. Our results demonstrate the effectiveness and efficiency of applying Convolutional Neural Network (CNN) in gunshot classification eliminating the need for an ad-hoc setup while significantly improving the classification performance.</p><h2>Other Information</h2> <p> Published in: Multimedia Tools and Applications<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1007/s11042-022-12612-w" target="_blank">http://dx.doi.org/10.1007/s11042-022-12612-w</a></p>2022-04-06T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s11042-022-12612-whttps://figshare.com/articles/journal_contribution/Sound_of_guns_digital_forensics_of_gun_audio_samples_meets_artificial_intelligence/21597417CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/215974172022-04-06T06:00:00Z |
| spellingShingle | Sound of guns: digital forensics of gun audio samples meets artificial intelligence Simone Raponi (14158911) Information and computing sciences Artificial intelligence Computer vision and multimedia computation Cybersecurity and privacy Distributed computing and systems software Machine learning Multimedia Forensics AI-driven Forensics Gun Audio Sample Classification Convolutional Neural Network |
| status_str | publishedVersion |
| title | Sound of guns: digital forensics of gun audio samples meets artificial intelligence |
| title_full | Sound of guns: digital forensics of gun audio samples meets artificial intelligence |
| title_fullStr | Sound of guns: digital forensics of gun audio samples meets artificial intelligence |
| title_full_unstemmed | Sound of guns: digital forensics of gun audio samples meets artificial intelligence |
| title_short | Sound of guns: digital forensics of gun audio samples meets artificial intelligence |
| title_sort | Sound of guns: digital forensics of gun audio samples meets artificial intelligence |
| topic | Information and computing sciences Artificial intelligence Computer vision and multimedia computation Cybersecurity and privacy Distributed computing and systems software Machine learning Multimedia Forensics AI-driven Forensics Gun Audio Sample Classification Convolutional Neural Network |