An Efficient Model for Forest Fire Detection using Deep Convolutional Neural Networks

Abstract

Forest fires are a significant natural disaster that causes extensive damage to both human and wildlife habitats. Early detection and management of forest fires are critical in preventing potential losses. In recent years, deep learning-based approaches have emerged as promising solutions for forest fire detection. This paper proposes a deep learning-based approach for forest fire detection using SqueezeNet model.The proposed approach utilizes still images captured from forest areas under different weather conditions to classify whether an image contains a fire or not. The models were trained and tested using accuracy, precision, and recall metrics. The experimental results show that SqueezeNet achieve high precision, and recall in detecting forest fires.SqueezeNet is a Convolutional Neural Networks (CNN) architecture designed to reduce the number of parameters and computations required in a deep learning model while maintaining high accuracy in image classification tasks..