Object Detection: Harmful Weapons Detection using YOLOv4

Afandi, Wan Emilya Izzety Binti Wan Noor; Isa, Naimah Mat

doi:10.1109/iswta52208.2021.9587423

Cited by 10 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paper described difference between YOLOv3 and YOLOv4 in terms of sensitivity and processing time [25]. The experimental part of following studies confirms the superiority of YOLOv4 over previous YOLOv3 [26]- [28]. Also, this model can be implemented for custom object detection on Jetson Nano GPU from Nvidia with a TensorRT network optimizer [29].…”

Section: Related Workmentioning

confidence: 54%

See 1 more Smart Citation

Weapons Detection System Based on Edge Computing and Computer Vision

Burnayev¹,

Toibazarov²,

Atanov³

et al. 2023

IJACSA

View full text Add to dashboard Cite

Early detection of armed threats is crucial in reducing accidents and deaths resulting from armed conflicts and terrorist attacks. The most significant application of weapon detection systems would be found in public areas such as airports, stadiums, central squares, and on the battlefield in urban or rural conditions. Modern surveillance and control systems of closed-circuit television cameras apply deep learning and machine learning algorithms for weapons detection on the base of cloud architecture. However, cloud computing is inefficient for network bandwidth, data privacy and slow decision-making. To address these issues, edge computing can be applied, using Raspberry Pi as an edge device with the EfficientDet model for developing the weapons detection system. The image processing results are transmitted as a text report to the cloud platform for further analysis by the operator. Soldiers can equip themselves with the suggested edge node and headphones for armed threat notifications, plugged into augmented reality glasses for visual data output. As a result, the application of edge computing makes it possible to ensure data safety, increase the network bandwidth and provide the device operation without the internet. Thus, an independent weapon detection system was developed that identifies weapons in 1.48 seconds without the Internet.

show abstract

Section: Related Workmentioning

confidence: 54%

“…Consequently, those models consume more disk space and computing resources. The highest accuracy of the knife detection case for EfficientDet-Lite0 model is an average result compared to 71.44 per cent for Faster R-CNN [17] and 77.78 per cent for YOLOv4 [26].…”

Section: Discussion Of Resultsmentioning

confidence: 93%