Fire and Smoke Detection Using Deep Learning

Of late, wildfires and commercial fires like fires in a shopping complex, firework factories, and industries, continue to cause extensive destruction throughout the world, frequently causing human fatalities. The solution is divided into two systems, where the first system focuses on the wildfire and the second system focuses on commercial fires. Identifying the fire and smoke correctly plays an important role. Gradient-weighted Class Activation Mapping (Grad-CAM) is used to identify the smoke region in the image. This algorithm is used to assure the smoke or fire in the image. The algorithms like ResNet, CNN (Convolutional neural network), and VGG16 (Visual Geometry Group) algorithms are used in transfer learning. This aims to increase the accuracy of the detection of fire and smoke in forests to avoid mishaps. The GradCAM is an algorithm that finds out the positive score in the image. This confirms the smoke in the image using the heat map generation. The ReLU activation function is used to show the positive pixels. The saliency map is also used in finding out the difference between smoke and fog in case of wildfire. In the case of the building fire shopping complex, firework shops, factories, and industries would also require a better solution because the detection is easier but the rescue process is more difficult in such places. The same procedure is followed for detecting and finding the origin of the fire as the wildfire model. The YOLOv8 algorithm is used for real-time analysis of the building. The model constantly looks for the unusual behavior of the environment and this in turns induces the notification. The additional feature is added to the model for rescue purposes. Fire control and evacuation have become more complex and hence the solution to such a problem is not yet brought into consideration. Even after detecting the fire, most of the people die due to the poor rescue process. This is because the rescue team cannot find the people inside the building. Our solution takes that into consideration. Our system uses a camera which could alert the people inside and also help in the rescue process. The camera takes photos and videos of the area if the fire or smoke is detected. Then the De-hazing algorithm is used to clarify the smoky images to identify the core details inside it. This is passed to the rescue team with the video of people inside which is given the most priority for extinguishing purposes. A separate mobile application is made for the rescue team. The extinguish process is also a very complex in case of the building fire. Hence the compression of the surrounding air is used to extinguish the fire. The target to extinguish the fire is detected using the images and videos and the targeted place is considered for the extinguish process and the compressed is given out. In this process the water is not wasted much and this reduces the work of fire rescue team.