Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385274311> ?p ?o ?g. }
- W4385274311 abstract "Abstract The early detection of handguns and knives from surveillance videos is crucial to enhance people’s safety. Despite the increasing development of Deep Learning (DL) methods for general object detection, weapon detection from surveillance videos still presents open challenges. Among these, the most significant are: (i) the very small size of the weapons with respect to the camera field of view and (ii) the need of a real-time feedback, even when using low-cost edge devices for computation. Complex and recently-developed DL architectures could mitigate the former challenge but do not satisfy the latter one. To tackle such limitation, the proposed work addresses the weapon-detection task from an edge perspective. A double-step DL approach was developed and evaluated against other state-of-the-art methods on a custom indoor surveillance dataset. The approach is based on a first Convolutional Neural Network (CNN) for people detection which guides a second CNN to identify handguns and knives. To evaluate the performance in a real-world indoor environment, the approach was deployed on a NVIDIA Jetson Nano edge device which was connected to an IP camera. The system achieved near real-time performance without relying on expensive hardware. The results in terms of both COCO Average Precision (AP = 79.30) and Frames per Second (FPS = 5.10) on the low-power NVIDIA Jetson Nano pointed out the goodness of the proposed approach compared with the others, encouraging the spread of automated video surveillance systems affordable to everyone." @default.
- W4385274311 created "2023-07-27" @default.
- W4385274311 creator A5000889718 @default.
- W4385274311 creator A5009204109 @default.
- W4385274311 creator A5066013158 @default.
- W4385274311 creator A5083358549 @default.
- W4385274311 creator A5083638676 @default.
- W4385274311 creator A5091783140 @default.
- W4385274311 date "2023-07-26" @default.
- W4385274311 modified "2023-09-23" @default.
- W4385274311 title "A deep-learning framework running on edge devices for handgun and knife detection from indoor video-surveillance cameras" @default.
- W4385274311 cites W2088049833 @default.
- W4385274311 cites W2168356304 @default.
- W4385274311 cites W2194775991 @default.
- W4385274311 cites W2213892522 @default.
- W4385274311 cites W2565639579 @default.
- W4385274311 cites W2570343428 @default.
- W4385274311 cites W2590001609 @default.
- W4385274311 cites W2778203997 @default.
- W4385274311 cites W2901412525 @default.
- W4385274311 cites W2915771847 @default.
- W4385274311 cites W2963037989 @default.
- W4385274311 cites W2963163009 @default.
- W4385274311 cites W2974320575 @default.
- W4385274311 cites W3010779341 @default.
- W4385274311 cites W3033765891 @default.
- W4385274311 cites W3038070101 @default.
- W4385274311 cites W3087567483 @default.
- W4385274311 cites W3095404142 @default.
- W4385274311 cites W3106250896 @default.
- W4385274311 cites W3107365388 @default.
- W4385274311 cites W3126631790 @default.
- W4385274311 cites W3157243312 @default.
- W4385274311 cites W3157386596 @default.
- W4385274311 cites W3175630421 @default.
- W4385274311 cites W3180134609 @default.
- W4385274311 cites W3188582951 @default.
- W4385274311 cites W3197089899 @default.
- W4385274311 cites W3212597799 @default.
- W4385274311 cites W4229453634 @default.
- W4385274311 cites W4293704627 @default.
- W4385274311 cites W4293721646 @default.
- W4385274311 cites W4312977443 @default.
- W4385274311 cites W4319600834 @default.
- W4385274311 doi "https://doi.org/10.1007/s11042-023-16231-x" @default.
- W4385274311 hasPublicationYear "2023" @default.
- W4385274311 type Work @default.
- W4385274311 citedByCount "0" @default.
- W4385274311 crossrefType "journal-article" @default.
- W4385274311 hasAuthorship W4385274311A5000889718 @default.
- W4385274311 hasAuthorship W4385274311A5009204109 @default.
- W4385274311 hasAuthorship W4385274311A5066013158 @default.
- W4385274311 hasAuthorship W4385274311A5083358549 @default.
- W4385274311 hasAuthorship W4385274311A5083638676 @default.
- W4385274311 hasAuthorship W4385274311A5091783140 @default.
- W4385274311 hasBestOaLocation W43852743111 @default.
- W4385274311 hasConcept C108583219 @default.
- W4385274311 hasConcept C12713177 @default.
- W4385274311 hasConcept C153180895 @default.
- W4385274311 hasConcept C154945302 @default.
- W4385274311 hasConcept C162307627 @default.
- W4385274311 hasConcept C162324750 @default.
- W4385274311 hasConcept C187736073 @default.
- W4385274311 hasConcept C2776151529 @default.
- W4385274311 hasConcept C2780451532 @default.
- W4385274311 hasConcept C31972630 @default.
- W4385274311 hasConcept C38652104 @default.
- W4385274311 hasConcept C41008148 @default.
- W4385274311 hasConcept C54355233 @default.
- W4385274311 hasConcept C59519942 @default.
- W4385274311 hasConcept C79403827 @default.
- W4385274311 hasConcept C81363708 @default.
- W4385274311 hasConcept C86803240 @default.
- W4385274311 hasConceptScore W4385274311C108583219 @default.
- W4385274311 hasConceptScore W4385274311C12713177 @default.
- W4385274311 hasConceptScore W4385274311C153180895 @default.
- W4385274311 hasConceptScore W4385274311C154945302 @default.
- W4385274311 hasConceptScore W4385274311C162307627 @default.
- W4385274311 hasConceptScore W4385274311C162324750 @default.
- W4385274311 hasConceptScore W4385274311C187736073 @default.
- W4385274311 hasConceptScore W4385274311C2776151529 @default.
- W4385274311 hasConceptScore W4385274311C2780451532 @default.
- W4385274311 hasConceptScore W4385274311C31972630 @default.
- W4385274311 hasConceptScore W4385274311C38652104 @default.
- W4385274311 hasConceptScore W4385274311C41008148 @default.
- W4385274311 hasConceptScore W4385274311C54355233 @default.
- W4385274311 hasConceptScore W4385274311C59519942 @default.
- W4385274311 hasConceptScore W4385274311C79403827 @default.
- W4385274311 hasConceptScore W4385274311C81363708 @default.
- W4385274311 hasConceptScore W4385274311C86803240 @default.
- W4385274311 hasFunder F4320323420 @default.
- W4385274311 hasLocation W43852743111 @default.
- W4385274311 hasOpenAccess W4385274311 @default.
- W4385274311 hasPrimaryLocation W43852743111 @default.
- W4385274311 hasRelatedWork W2731899572 @default.
- W4385274311 hasRelatedWork W2999805992 @default.
- W4385274311 hasRelatedWork W3015951701 @default.
- W4385274311 hasRelatedWork W3101676691 @default.
- W4385274311 hasRelatedWork W3116150086 @default.
- W4385274311 hasRelatedWork W3133861977 @default.