FIRE AND GUN DETECTION SYSTEM USING DEEP NEURAL NETWORKS

Computer Science

Systems for detecting anomalies are essential for ensuring public safety, particularly in area significant risk of fire and violent entertainment. According to the study, we present a real-time fire and gun detection system that uses deep neural networks to identify anomalous events. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) implemented in combination with the suggested system, which uses video surveillance data as input to identify anomalies. While the RNNs record the temporal dependencies between frames, the CNNs takes the responsisbility of extracting spatial features from the input frames. The proposed system are viewd against a benchmark dataset of actual surveillance footage after being trained using a sizable dataset of fire and gun violence-related events. The outcomes show that our system achieves high detection accuracy and outperforms existing state-of-the-art methods. Object detection is a different program in computer vision applications such as surveillance, autonomous driving, and robotics. Deep neural networks have shown promising results in object detection, but real-time performance is often a challenge due to the large computational requirements of these models. According to this report, we present a real-time object detection system based on a deep neural network architecture. The proposed system uses a combination of convolutional neural networks (CNNs) and region proposal networks (RPNs) to detect objects in the current world. The system is evaluated on a benchmark dataset and compared with state-of-the-art methods. The results demonstrate that our system achieves high detection accuracy and real-time performance.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.