Detection of armed people in a video stream using convolutional neural networks

Authors

  • O. K. Kolesnytsky Vinnytsia National Technical University
  • E. V. Yankovsky Vinnytsia National Technical University
  • I. K. Denisov Vinnytsia National Technical University
  • I. R. Arsenyuk Vinnytsia National Technical University

DOI:

https://doi.org/10.31649/1681-7893-2023-46-2-76-83

Keywords:

detection, video stream, weapon, convolution neural network

Abstract

Information technology for detecting armed people is proposed and its software implementation is investigated. The YOLO convolution neural network was used to detect objects in real time. The Python programming language and the PyTorch library were used to develop the neural network. A program designed to detect armed people in a video stream has been created, the functionality of which allows classifying the type of recognized weapon.

Author Biographies

O. K. Kolesnytsky, Vinnytsia National Technical University

доцент, канд. техн. наук, професор кафедри комп’ютерних наук

E. V. Yankovsky, Vinnytsia National Technical University

магістрант кафедри комп’ютерних наук

I. K. Denisov, Vinnytsia National Technical University

викладач кафедри комп’ютерних наук

I. R. Arsenyuk, Vinnytsia National Technical University

доцент, канд. техн. наук, доцент кафедри комп’ютерних наук

References

The Ministry of Internal Affairs will make maximum efforts to develop a high-quality legislative framework in the field of arms circulation and its effective law enforcement - Bohdan Drapyaty [Electronic resource] - Access mode: https://mvs.gov.ua/uk/press-center/news/mvs-oklade-maksimalnix-zusil-zadlya-napracyuvannya-yakisnoyi-zakonodavcoyi-bazi-u-sferi-obigu-zbroyi-ta-yiyi-efektivnogo-pravozastosuvannya-bogdan-drapyatii.

Convolutional Neural Network – A simple explanation of CNN and its application [Electronic resource]. - Access mode: https://evergreens.com.ua/ua/articles/cnn.html.

Weapon Detection [Електронний ресурс] – Режим доступу до ресурсу: https://github.com/Manish8798/Weapon-Detection-with-yolov3

Understanding YOLOv8 Architecture, Applications & Features [Electronic resource]. - Access mode: https://arxiv.org/abs/1409.1556.

Improving Detection Capabilities of YOLOv8-n for Small Objects in Remote Sensing Imagery: Towards Better Precision with Simplified Model Complexity [Electronic resource] / V. Sineglazov, O. Chumachenko. - Access mode: https://sightmachine.com/.

UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios [Electronic resource]. - Access mode: https://www.mdpi.com/1424-8220/23/16/7190.

Pistol Detection [Electronic resource] - Access mode: https://www.kaggle.com/datasets/vaibhavtalekar/pistol-classification.

Weapon Detection Dataset [Electronic resource] - Access mode: https://www.kaggle.com/datasets/snehilsanyal/weapon-detection-test.

V.F. Bardachenko, O.K. Kolesnitsky, S.A. Vasiletsky. Prospects for the use of pulsed neural networks with timer representation of information for dynamic pattern recognition // USiM.-2003-№6.- P. 73-82.

O.K. Kolesnitsky. Analytical review of hardware realizations of spike neural networks / OK Kolesnitsky // Mathematical Machines and Systems. - 2015. - №1, P.3-19. ISSN 1028-9763 [Electronic resource]. Access Mode - http://www.immsp.kiev.ua/publications/articles/2015/2015_1/01_2015_Kolesnytskyy.pdf

Neurocomputer architecture based on spiking neural network and its optoelectronic implementation / Oleh K. Kolesnytskyj; Vladislav V. Kutsman; Krzysztof Skorupski; Mukaddas Arshidinova, Proc. SPIE 11176, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, 1117609 (6 November 2019); doi: 10.1117 / 12.2536607

Downloads

Abstract views: 104

Published

2023-12-13

How to Cite

[1]
O. K. Kolesnytsky, E. V. Yankovsky, I. K. Denisov, and I. R. Arsenyuk, “Detection of armed people in a video stream using convolutional neural networks ”, Опт-ел. інф-енерг. техн., vol. 46, no. 2, pp. 76–83, Dec. 2023.

Issue

Section

Systems Of Technical Vision And Artificial Intelligence, Image Processing And Pattern Recognition

Metrics

Downloads

Download data is not yet available.