Abstract: Due to an increase in crime during big events or in isolated, suspicious areas, security is always a top priority in every field. Computer vision is widely used in abnormal detection and monitoring to address a variety of issues. The need for video surveillance systems that can identify and analyze scenes and anomalous events has grown due to the increased demand for the protection of personal property, safety, and security. These systems are essential for intelligence monitoring. This project uses Faster RCNN techniques and a convolution neural network (CNN) based YOLO Module to provide automatic gun (or) weapon detection. Two kinds of datasets are used in the suggested implementation. There was one dataset with pre-labeled photos and another with a collection of manually labeled images. The algorithms yield tabular results with good accuracy; however, the trade-off between speed and precision may determine how these algorithms are applied in practical scenarios.
Keywords: Weapon detection, convolutional neural network, image classification, object detection, computer vision.
Cite:
K. Mohan Krishna, A. LikhithaReddy, G. Sri Sai Meghana, Ch. Rohith Varma, G. Velugondaiah, "WEAPON DETECTION In A CRIME SCENE USING CONVOLUTION NEURAL NETWORK", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13328.
|
DOI:
10.17148/IJARCCE.2024.13328
