Assault Rifle Detection and Identification Based on Convolutional Neural Network YOLOv3

Yunfei Ma, Huimin Chen, Jian Huo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

In modern war, armies from different countries have different weapons for infantry. Therefore, identifying the weapons held by infantry helps to determine their affiliations. In this paper, we have built our dataset of different types of assault rifles from photos. The dataset was trained using the convolutional neural network YOLOv3. Several different real videos were used to verify the YOLOv3 training results. The experiments show that the model can detect and identify assault rifles in different scenes. It proves to work with a good accuracy and can be used in real time on battlefield.

Original languageEnglish
Title of host publication2021 3rd World Symposium on Artificial Intelligence, WSAI 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9780738143033
DOIs
Publication statusPublished - 18 Jun 2021
Event3rd World Symposium on Artificial Intelligence, WSAI 2021 - Virtual, Online, China
Duration: 18 Jun 202120 Jun 2021

Publication series

Name2021 3rd World Symposium on Artificial Intelligence, WSAI 2021

Conference

Conference3rd World Symposium on Artificial Intelligence, WSAI 2021
Country/TerritoryChina
CityVirtual, Online
Period18/06/2120/06/21

Keywords

  • YOLOv3
  • deep learning
  • object detection
  • real-time detection

Fingerprint

Dive into the research topics of 'Assault Rifle Detection and Identification Based on Convolutional Neural Network YOLOv3'. Together they form a unique fingerprint.

Cite this