WEAPON DETECTION USING ARTIFICIAL INTELLIGENCE AND DEEP LEARNING FOR SECURITY APPLICATIONS

Abstract

Security is often a main concern in each domain, thanks to an increase in rate during a crowded event or suspicious lonely areas. Abnormal detection and watching have major applications of pc vision to tackle numerous issues. thanks to growing demand within the protection of safety, security and private properties, desires and readying of video police investigation systems will acknowledge and interpret the scene and anomaly events play an important role in intelligence watching. This project implements automatic gun (or) weapon detection employing a convolution neural network (CNN) based mostly SSD and quicker RCNN algorithms. projected implementation uses 2 sorts of datasets. One dataset, that had pre-labelled pictures and also the alternative one could be a set of pictures, that were tagged manually. Results area unit tabulated, each algorithms come throughs} good accuracy, however their application in real things is supported the trade-off between speed and accuracy.