Two-Tier AI Surveillance: Enhancing Weapon Detection Through Edge and Cloud Collaboration

Simple item page
dc.contributor.authorSun, Sanchai
dc.contributor.authorSongsuwankit, Kanoknuch
dc.contributor.authorThamrongrongveerachart, Chawapon
dc.contributor.authorYanyong, Sarucha
dc.contributor.authorSri-on, Jiramate
dc.contributor.authorKoomklang, Nattapat
dc.contributor.authorKriangudom, Thanakorn
dc.contributor.authorThepsit, Thitipong
dc.contributor.authorKonghuayrob, Poom
dc.date.accessioned2026-08-06T10:54:14Z
dc.date.available2026-08-06T10:54:14Z
dc.date.issued2026-01-01
dc.description.abstractThis research presents a novel two-tier AI-based surveillance system designed for real-time weapon detection to enhance security and prevent potential robberies. The system leverages the computational capabilities of both edge and cloud resources, integrating a YOLOv5s model on a Jetson Nano for initial detection and a YOLOv8l model on a server equipped with an Nvidia A100 for refined analysis. The initial detection performed by the Jetson Nano rapidly identifies potential threats and forwards compressed images to the server, optimizing bandwidth usage and transmission speed. Upon receipt, the server applies image enhancement techniques to restore and upscale the images from 640 pixels back to 1280 pixels before further verification. Utilizing Python Django, the server processes the enhanced images with a more sophisticated model to ensure high accuracy in detection. The integration of edge computing optimizes the system’s performance by enabling real-time processing and reducing latency. This hybrid approach enhances the efficiency and scalability of the surveillance system, ensuring robust and timely detection. Upon confirming the presence of a weapon, the system sends immediate alerts via LINE Notify to both users and local law enforcement, thereby enabling prompt responses to potential security threats. Additionally, the Jetson Nano hosts a Flask application, allowing users to download previously recorded videos for further review and evidence collection. The proposed solution combines edge computing, cloud processing, and image optimization techniques to provide an efficient, scalable, and high-performance solution for real-time weapon detection which enhancing accuracy and reliability in real-world surveillance.
dc.identifier.citationLecture Notes in Networks and Systems, 1510 LNNS, 439-450, 2026
dc.identifier.doi10.1007/978-981-96-9275-0_37
dc.identifier.issn23673370
dc.identifier.other2-s2.0-105028250135
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/17763
dc.sourceLecture Notes in Networks and Systems
dc.subjectEdge computing
dc.subjectImage compression
dc.subjectReal-time weapon detection
dc.subjectSecurity alert system
dc.subjectYOLO-based surveillance
dc.titleTwo-Tier AI Surveillance: Enhancing Weapon Detection Through Edge and Cloud Collaboration
dc.typeConference Paper

Files

Collections

Research