Comparative Analysis of Deep Learning Algorithms in Fire Detection

As technology advances rapidly, deep learning applications, a subset of machine learning, are becoming increasingly relevant in various aspects of our lives. Essential daily applications like license plate recognition and optical character recognition are now commonplace. Alongside current technological progress, the development of future-integrated technologies such as suspicious situation detection from security cameras and autonomous vehicles is also accelerating. The success and accuracy of these technologies have reached impressive levels. This study focuses on the early and accurate detection of forest fires before they cause severe damage. Using primarily forest fire images from datasets obtained from Kaggle, various deep learning algorithms were trained via transfer learning using MATLAB. This approach allowed for comparing different deep learning algorithms based on their efficiency and accuracy in detecting forest fires. High success rates, generally exceeding 90%, were achieved.