{"title":"A Multi-Weapon Detection Using Deep Learning","authors":"Moahaimen Talib, Jamila H. Saud","doi":"10.31987/ijict.7.1.242","DOIUrl":null,"url":null,"abstract":"\n\n\nThe escalating usage of light weapons in criminal and terrorist activities has necessitated the development of advanced weapon detection systems. This study centers on the application of the high-speed deep learning detection model, You Only Look Once version 7 (YOLOv7), to address the need for efficient and swift threat identification. The proposed system, trained on a self-curated dataset rich in images of various dangerous light weapons, is designed to recognize and distinguish multiple weapons simultaneously. The unique value of YOLOv7 in object and specifically weapon detection lies in its outstanding speed and accuracy, as demonstrated by certain weapon categories achieving a mean average precision (mAP) of 97%. The system’s performance can potentially be further enhanced by augmenting the image dataset for each weapon category. This study, therefore, not only validates the critical importance of YOLOv7 in advancing detection methodologies but also presents a practical solution for bolstering public safety. \n\n\n\n ","PeriodicalId":471846,"journal":{"name":"Iraqi journal of information and communication technology","volume":"98 11","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iraqi journal of information and communication technology","FirstCategoryId":"0","ListUrlMain":"https://doi.org/10.31987/ijict.7.1.242","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The escalating usage of light weapons in criminal and terrorist activities has necessitated the development of advanced weapon detection systems. This study centers on the application of the high-speed deep learning detection model, You Only Look Once version 7 (YOLOv7), to address the need for efficient and swift threat identification. The proposed system, trained on a self-curated dataset rich in images of various dangerous light weapons, is designed to recognize and distinguish multiple weapons simultaneously. The unique value of YOLOv7 in object and specifically weapon detection lies in its outstanding speed and accuracy, as demonstrated by certain weapon categories achieving a mean average precision (mAP) of 97%. The system’s performance can potentially be further enhanced by augmenting the image dataset for each weapon category. This study, therefore, not only validates the critical importance of YOLOv7 in advancing detection methodologies but also presents a practical solution for bolstering public safety.
随着轻武器在犯罪和恐怖活动中的使用不断升级,有必要开发先进的武器检测系统。本研究的核心是应用高速深度学习检测模型 You Only Look Once version 7 (YOLOv7),以满足高效、快速识别威胁的需求。所提出的系统是在一个自编的数据集上进行训练的,该数据集包含各种危险轻武器的丰富图像,旨在同时识别和区分多种武器。YOLOv7 在物体(特别是武器)检测方面的独特价值在于其出色的速度和精确度,某些武器类别的平均精确度 (mAP) 达到了 97%。通过增强每个武器类别的图像数据集,该系统的性能有可能得到进一步提升。因此,这项研究不仅验证了 YOLOv7 在推进探测方法方面的关键重要性,而且还为加强公共安全提供了一个实用的解决方案。