This project focuses on developing a deep learning-based fire detection system using a Convolutional Neural Network (CNN) model trained on a dataset containing images of fire and non-fire scenarios.
The CNN model is built using TensorFlow, leveraging its powerful machine learning capabilities to distinguish between fire and non-fire images with high accuracy.
In addition to model training, the project integrates OpenCV to create a real-time fire detection system.
OpenCV handles live video input and feeds images to the trained model for immediate fire detection, making it suitable for surveillance and early fire warning systems.
1. Train a Convolutional Neural Network (CNN) using a dataset of fire and non-fire images to classify fire accurately.
2. Utilize TensorFlow to design, implement, and optimize the CNN model for image classification.
3. Implement a real-time fire detection system using OpenCV to process live video feeds.
4. Integrate the trained deep learning model with OpenCV to detect fire in real-time.
5. Test and validate the system's performance on live video input and ensure high accuracy in fire detection.
6. Develop a scalable and efficient solution for use in fire surveillance and early warning systems.
