Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{185807,
        author = {Ms. Prachi Shivaji Bhosale and Dr. Anirudh Krushna Mangore},
        title = {Fire and Gun Violence Based Anomaly Detection using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {12},
        number = {no},
        pages = {43-49},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185807},
        abstract = {One of the popular uses of convolutional neural networks (CNNs) is real-time object detection to enhance surveillance techniques. The detection of firearms and fire in camera-monitored regions has been the focus of this study. Wildfires, industrial explosions, and home fires are all major issues that have a negative impact on the environment. Mass shootings and gun violence are also increasing in other regions of the world. Such occurrences can result in significant losses in terms of both life and property, and they are time-sensitive. Therefore, a deep learning model based on the YOLOv3 algorithm has been developed in the proposed work. It analyzes a video frame by frame to identify such anomalies in real time and send a warning to the relevant authorities. The resulting model has a 45 frames per second detection rate, a validation loss of 0.2864, and has been benchmarked on datasets such as FireNet, UGR, and IMFDB with accuracies of 86.5%, 89.3%, and 82.6%, respectively.  In addition to meeting the objective of the suggested model, the experimental result demonstrates a quick detection rate that can be used both indoors and outdoors.},
        keywords = {Object Detection, Mass Shootings, convolutional neural networks (CNNs), etc},
        month = {},
        }