Real-time vision-based violent actions detection through CCTV cameras with pose estimation

Simple item page
dc.contributor.authorBenoit, Paul
dc.contributor.authorBresson, Marc
dc.contributor.authorXing, Yang
dc.contributor.authorGuo, Weisi
dc.contributor.authorTsourdos, Antonios
dc.date.accessioned2024-03-22T11:05:01Z
dc.date.available2024-03-22T11:05:01Z
dc.date.issued2024-03-01
dc.description.abstractIn large structures under video surveillance, or when a place is crowded, a CCTV operator cannot monitor hundreds of people on different video streams. This paper presents a proof of concept for a real-time vision-based system for detecting violent actions through CCTV cameras with pose estimation. The proposed system uses a combination of computer vision techniques, including pose estimation, object tracking, and a deep learning algorithm based on time-series features, to accurately identify violent actions in real-time. Our features are based on a fixed-size rolling window that computes the position of each person’s limb along with their velocity. The proposed pipeline achieves a high accuracy rate of 92% with an overall latency of around 0.07 seconds per frame using a RTX 3060 Mobile GPU, making it a powerful tool for enhancing public safety and security. This system can be deployed in a wide range of scenarios, including public places, transportation hubs, and other critical infrastructure, to provide real-time alerts and facilitate rapid response in case of violent incidentsen_UK
dc.identifier.citationBenoit P, Bresson M, Xing Y, et al., (2024) Real-time vision-based violent actions detection through CCTV cameras with pose estimation. In: 2023 IEEE Smart World Congress (SWC), 28-31 August 2023, Portsmouth, UK, pp. 844-849en_UK
dc.identifier.eisbn979-8-3503-1980-4
dc.identifier.isbn979-8-3503-1980-4
dc.identifier.urihttps://doi.org/10.1109/SWC57546.2023.10448959
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/21077
dc.language.isoen_UKen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectViolence detectionen_UK
dc.subjectpose estimationen_UK
dc.subjectnear-real timeen_UK
dc.subjectYOLOv8en_UK
dc.subjectdeep SORTen_UK
dc.titleReal-time vision-based violent actions detection through CCTV cameras with pose estimationen_UK
dc.typeConference paperen_UK
dcterms.dateAccepted2023-06-06

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Real-time_vision-based_violent_actions_detection-2024.pdf
Size:
2.53 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)