Detecting violent behaviour on edge using Convolutional Neural Networks

Gelayol Golcarenarenji*, Rinat Khusainov, Alexander Gegov, Ignacio Martinez-Alpiste

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A new portable solution is proposed based on Convolutional Neural Networks (CNN) to increase the speed and accuracy of detecting violence behaviour on edge devices. This solution has numerous applications in public safety. A combination of surveillance using CCTV cameras and Unmanned Aerial Vehicles (UAVs) is used to demonstrate the real-world surveillance use cases to monitor abnormal behaviours in public. The proposed solution delivers 95.01\% accuracy while taking 13.2ms for inference on GeForce GTX 1660 Ti GPU and reaching 38 frames per second throughput on Jetson AGX Orin measured on a combination of Drone-action and chu-surveillance-violence-detection datasets. The results show the strong practical application potential of the proposed solution in terms of real-time performance, visual quality, and high accuracy.
Original languageEnglish
Title of host publicationProceedings of the 12th IEEE International Conference on Intelligent Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Publication statusAccepted for publication - 15 May 2024
Event12th IEEE International Conference on Intelligent Systems - Varna, Bulgaria
Duration: 29 Aug 202431 Aug 2024

Publication series

NameIntelligent Systems Conference Proceedings
PublisherIEEE
ISSN (Print)2832-4145
ISSN (Electronic)2767-9802

Conference

Conference12th IEEE International Conference on Intelligent Systems
Country/TerritoryBulgaria
CityVarna
Period29/08/2431/08/24

Keywords

  • YOLOV5
  • Edge Computing
  • violent behaviour
  • UAVs
  • CCTV Cameras

Fingerprint

Dive into the research topics of 'Detecting violent behaviour on edge using Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this