Weapons Detection for Security and Video Surveillance Using CNN and YOLO-V5s

作     者：Abdul Hanan Ashraf Muhammad Imran Abdulrahman M.Qahtani Abdulmajeed Alsufyani Omar Almutiry Awais Mahmood Muhammad Attique Mohamed Habib 

作者机构：Department of Computer ScienceShaheed Zulfikar Ali Bhutto Institute of Science and TechnologyIslamabad44000Pakistan Department of Computer ScienceCollege of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia College of Applied Computer ScienceKing Saud University(Almuzahmiyah Campus)Riyadh11543Saudi Arabia Department of Computer ScienceHITEC UniversityTaxila47080Pakistan College of Computing and InformaticsSaudi Electronic UniversityRiyadhSaudi Arabia Faculty of EngineeringPort Said UniversityPort Fuad CityEgypt 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第70卷第2期

页      面：2761-2775页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：We deeply acknowledge Taif University for Supporting and funding this study through Taif University Researchers Supporting Project Number(TURSP-2020/115) Taif University Taif Saudi Arabia 

主　　题：Video surveillance weapon detection you only look once convolutional neural networks 

摘      要：In recent years,the number of Gun-related incidents has crossed over 250,000 per year and over 85%of the existing 1 billion firearms are in civilian hands,manual monitoring has not proven effective in detecting *** is why an automated weapon detection system is *** automated convolutional neural networks(CNN)weapon detection systems have been proposed in the past to generate good ***,These techniques have high computation overhead and are slow to provide real-time detection which is essential for the weapon detection *** models have a high rate of false negatives because they often fail to detect the guns due to the low quality and visibility issues of surveillance *** research work aims to minimize the rate of false negatives and false positives in weapon detection while keeping the speed of detection as a key *** proposed framework is based on You Only Look Once(YOLO)and Area of Interest(AOI).Initially,themodels take pre-processed frames where the background is removed by the use of the Gaussian blur *** proposed architecture will be assessed through various performance parameters such as False Negative,False Positive,precision,recall rate,and F1 *** results of this research work make it clear that due to YOLO-v5s high recall rate and speed of detection are *** reached 0.010 s per frame compared to the 0.17 s of the Faster *** is promising to be used in the field of security and weapon detection.