Intelligent Weapon Detection System for Real-Time Surveillance using Deep Learning with YOLOv8

Surya Kumari S; Padmavathi A; VIJAY M; Pallavi K; Neeharika K

Intelligent Weapon Detection System for Real-Time Surveillance using Deep Learning with YOLOv8

Author(s)	Ms. Surya Kumari S, Padmavathi A, Mr. VIJAY M, Ms. Pallavi K, Ms. Neeharika K
Country	India
Abstract	To provide security to people in high-personality and dense areas like airports, railway stations, and learning institutions purported systems of surveillance must be credible and smart. Conventional weapon detectors heavily depend on the constant human attention of the security guards, which loses its performance at real time and mass scale operations due to human weaknesses, latent reaction, and great chances of overlooking events of threat nature. Moreover, the common surveillance systems are not smartly automated and cannot automatically identify weapons on live video streams. The proposed paper will implement a smart weapon detecting device to overcome these challenges and realize real-time surveillance that utilizes the use of deep learning. The system suggested is that based on a live surveillance video, the suggested system uses the YOLOv8 object detection model that will be used to automatically detect weapon types like guns and knives. Based on annotated datasets, a model is trained and every component is augmented by output of transfer learning and data augmentation methods to enhance the accuracy of detection in low-illumination environments coupled with sophisticated backgrounds. Video frames are processed in real time to scan the image to identify weapons and raise an emergency warning to alert them in case they noticed a possible threat. The evaluation of experimental performance metrics comprise of accuracy, recall, F1-score, mean Average Precision (mAP), and Frames per second (FPS). The findings indicate that the suggested system can generate high detection accuracy and still be able to perform in real-time. YOLOv8 based system has a high accuracy, robustness which is coupled with small object detection capacity compared to constraints of current surveillance methods and previous object-detecting models in the use of intelligent real-time surveillance applications.
Keywords	Weapon Detection, Real-Time Surveillance, Deep Learning, YOLOv8, Object Detection, CCTV Security.
Field	Engineering
Published In	Volume 17, Issue 2, April-June 2026
Published On	2026-04-03

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 17 Isu 1 Cover Page Vol 16 Isu 3 Cover Page Vol 16 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Intelligent Weapon Detection System for Real-Time Surveillance using Deep Learning with YOLOv8

Share this