| publication name | Automatic Gun Detection Approach for Video Surveillance |
|---|---|
| Authors | Mai K. Galab; Ahmed Taha; Hala H. Zayed |
| year | 2020 |
| keywords | Closed Circuit Television, Convolutional Neural Network, Deep Neural Network, Transfer Learning, Video Surveillance Systems |
| journal | International Journal of Sociotechnology and Knowledge Development |
| volume | Not Available |
| issue | Not Available |
| pages | Not Available |
| publisher | IGI Global |
| Local/International | International |
| Paper Link | Not Available |
| Full paper | download |
| Supplementary materials | Not Available |
Abstract
Theimmensecrimeratesresultingfromusingpistolshaveledgovernmentstoseeksolutionstodeal withsuchterroristincidents.Theseincidentshaveanegativeimpactonpublicsecurityandcause panicamongcitizens.Fromthispoint,facingapandemicofweaponviolencehasbecomeanimportant researchtopic.Onewaytoreducethiskindofviolenceistopreventitviaremotedetectionandtogive anappropriateresponseinashorttime.Videosurveillanceistheprocessofmonitoringthebehavior ofpeopleandobjects.Surveillancesystemscanbeemployedinsecurityapplicationsaslegalevidence. Moreover,itisusedwidelyinsuspiciousactivitydetectionapplications.Intelligentvideosurveillance systems(IVSSs)aretheuseofautomaticvideoanalyticstoenhancetheeffectivenessoftraditional surveillancesystems.WiththerapiddevelopmentinDeepLearning(DL),itisnowwidelyusedto addresstheproblemsexistingintraditionaldetectiontechniques.Inthisarticle,anapproachtodetect pistolsandgunsinvideosurveillancesystemsisproposed.Thepresentedapproachdoesnotneed anyinvasivetoolsintheweapondetectionprocess.ItusesDLintheclassificationandthedetection processes.TheproposedapproachenhancestheobtainedresultsbyapplyingTransferLearning(TL). ItemploystwodifferentDLtechniques:AlexNetandGoogLeNet.Experimentalresultsverifythe adaptabilityofdetectingdifferenttypesofpistolsandguns.Theexperimentswereconductedona benchmarkgundatabasecalledInternetMovieFirearmsDatabase(IMFDB).Theresultsobtained suggestthattheproposedapproachispromisingandoutperformsitscounterparts.