Real-Time Weapon Detection System for Enhanced Security Monitoring

Innovative technology for weapon detection during security monitoring is necessary today due to the rising threats of violence and terror. The paper discusses a detailed design of a weapon detection system intended for application in enhancing security surveillance specifically using a deep learning approach. The system employs YOLOv3 (You Only Look Once, Version 3) mood and adaption aimed at live footage weapon detection. To do this on broader scale, this system incorporates big data tools Hadoop, Docker, Spark and Kafka for reasons of real time processing and effectiveness in high volume data situations. This model is applied on the live footage surveillance of public and private places to determine if the model can detect weapons, to warn relevant authorities in the aim of decreasing response time and averting security breach occurrences. The experiments conducted confirm that the model is capable of performing weapon detection tasks in an indoor environment with changes in illumination conditions with few false alarms.