Show simple item record

dc.contributor.authorTurtiainen, Hannu
dc.contributor.authorCostin, Andrei
dc.contributor.authorHämäläinen, Timo
dc.contributor.authorLahtinen, Tuomo
dc.contributor.authorSintonen, Lauri
dc.date.accessioned2023-03-22T10:05:35Z
dc.date.available2023-03-22T10:05:35Z
dc.date.issued2022
dc.identifier.citationTurtiainen, H., Costin, A., Hämäläinen, T., Lahtinen, T., & Sintonen, L. (2022). CCTVCV : Computer Vision model/dataset supporting CCTV forensics and privacy applications. In <i>TrustCom 2022 : Proceedings of the IEEE 21st International Conference on Trust, Security and Privacy in Computing and Communications </i> (pp. 1219-1226). IEEE. IEEE International Conference on Trust, Security and Privacy in Computing and Communications. <a href="https://doi.org/10.1109/trustcom56396.2022.00169" target="_blank">https://doi.org/10.1109/trustcom56396.2022.00169</a>
dc.identifier.otherCONVID_176934009
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/86088
dc.description.abstractThe increased, widespread, unwarranted, and unaccountable use of Closed-Circuit TeleVision (CCTV) cameras globally has raised concerns about privacy risks for the last several decades. Recent technological advances implemented in CCTV cameras, such as Artificial Intelligence (AI)-based facial recognition and Internet of Things (IoT) connectivity, fuel further concerns among privacy advocates. Machine learning and computer vision automated solutions may prove necessary and efficient to assist CCTV forensics of various types. In this paper, we introduce and release the first and only computer vision models are compatible with Microsoft common object in context (MS COCO) and capable of accurately detecting CCTV and video surveillance cameras in street view, generic images, and video frames. Our best detectors were built using 8,387 images, which were manually reviewed and annotated to contain 10,419 CCTV camera instances, and achieved an accuracy rate of up to 98.7%. This work proves fundamental to a handful of present and future applications that we discuss, such as CCTV forensics, pro-active detection of CCTV cameras, providing CCTV-aware routing, navigation, and geolocation services, and estimating their prevalence and density globally and on geographic boundaries.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofTrustCom 2022 : Proceedings of the IEEE 21st International Conference on Trust, Security and Privacy in Computing and Communications
dc.relation.ispartofseriesIEEE International Conference on Trust, Security and Privacy in Computing and Communications
dc.rightsIn Copyright
dc.subject.otherCCTV
dc.subject.othercameras
dc.subject.othercomputer vision
dc.subject.otherdatasets
dc.subject.othermachine learning
dc.subject.othermapping
dc.subject.otherobject detection
dc.subject.otherprivacy
dc.subject.othervideo surveillance
dc.titleCCTVCV : Computer Vision model/dataset supporting CCTV forensics and privacy applications
dc.typeconferenceObject
dc.identifier.urnURN:NBN:fi:jyu-202303222237
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineSecure Communications Engineering and Signal Processingfi
dc.contributor.oppiaineTekniikkafi
dc.contributor.oppiaineTietotekniikkafi
dc.contributor.oppiaineSecure Communications Engineering and Signal Processingen
dc.contributor.oppiaineEngineeringen
dc.contributor.oppiaineMathematical Information Technologyen
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
dc.relation.isbn978-1-6654-9426-7
dc.description.reviewstatuspeerReviewed
dc.format.pagerange1219-1226
dc.relation.issn2324-898X
dc.type.versionacceptedVersion
dc.rights.copyright© 2022 IEEE
dc.rights.accesslevelopenAccessfi
dc.relation.conferenceIEEE International Conference On Trust, Security And Privacy In Computing And Communications
dc.subject.ysotekninen rikostutkinta
dc.subject.ysotekoäly
dc.subject.ysotietosuoja
dc.subject.ysokasvontunnistus (tietotekniikka)
dc.subject.ysoyksityisyys
dc.subject.ysokameravalvonta
dc.subject.ysosovellukset (soveltaminen)
dc.subject.ysokamerat
dc.subject.ysokonenäkö
dc.subject.ysokoneoppiminen
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p28613
jyx.subject.urihttp://www.yso.fi/onto/yso/p2616
jyx.subject.urihttp://www.yso.fi/onto/yso/p3636
jyx.subject.urihttp://www.yso.fi/onto/yso/p26695
jyx.subject.urihttp://www.yso.fi/onto/yso/p10909
jyx.subject.urihttp://www.yso.fi/onto/yso/p4713
jyx.subject.urihttp://www.yso.fi/onto/yso/p28185
jyx.subject.urihttp://www.yso.fi/onto/yso/p6350
jyx.subject.urihttp://www.yso.fi/onto/yso/p2618
jyx.subject.urihttp://www.yso.fi/onto/yso/p21846
dc.rights.urlhttp://rightsstatements.org/page/InC/1.0/?language=en
dc.relation.doi10.1109/trustcom56396.2022.00169
jyx.fundinginformationThe authors acknowledge the grants of computer capacity from the Finnish Grid and Cloud Infrastructure (persistent identifier urn:nbn:fi:research-infras-2016072533). Part of this research was supported by a grant from the Decision of the Research Dean on research funding within the Faculty (17.06.2020), Decision of the Research Dean on research funding within the Faculty (07.04.2021), and Decision of the Research Dean on research funding within the Faculty (20.04.2022) of the Faculty of Information Technology of University of Jyväskylä (The authors thank Dr. Andrei Costin for facilitating and managing the grant). Hannu Turtiainen thanks the Finnish Cultural Foundation / Suomen Kulttuurirahasto (https://skr.fi/en) for supporting his Ph.D. dissertation work and research (under grant decision no.00221059) and the Faculty of Information Technology of the University of Jyväskylä (JYU), in particular, Prof. Timo Hämäläinen, for partly supporting and supervising his Ph.D. work at JYU in 2021–2023.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

In Copyright
Except where otherwise noted, this item's license is described as In Copyright