This GitHub repository hosts a comprehensive project that leverages deep learning techniques for the real-time detection of fire and smoke. The system is designed to seamlessly integrate with an Arduino-based alarm, ensuring timely alerts and responses in the event of a fire or smoke incident.
-
Deep Learning-Based Detection: We employ state-of-the-art deep learning algorithms to analyze real-time video feeds for the presence of fire and smoke. The use of convolutional neural networks (CNNs) and other advanced models ensures high accuracy and reliability in detecting these critical safety hazards.
-
Real-Time Monitoring: The system continuously monitors the video feed, providing instantaneous detection and alerting capabilities. This ensures swift action can be taken to mitigate potential risks.
-
Arduino-Based Alarm: Upon detecting fire or smoke, the system triggers an Arduino-based alarm system. This alarm can be customized to suit your specific needs, such as sounding sirens, activating sprinklers, or sending notifications to relevant personnel.
By making use of this repository, you can create a robust and efficient fire and smoke detection system that not only safeguards lives and property but also serves as a valuable resource for research and development in the field of computer vision and IoT-based safety solutions. Join us in enhancing fire safety with cutting-edge technology.
- Training Networks: Folder that contains the IPYNB file for training and testing the Neural Networks used in this project.
- video_real_time.py: Python file that uses our trained model to detect fire and smoke from real-time feed and connect this project with our Arduino-Based Alarm.
Link: https://drive.google.com/file/d/1-IUZg3000aCQ38kc9GV0y0vUTJiv2vg1/view?usp=sharing