FIRe-GAN: A novel Deep Learning-based infrared-visible fusion method for wildfire imagery

TL;DR

This paper introduces FIRe-GAN, a deep learning-based infrared-visible image fusion method tailored for wildfire imagery, addressing the lack of specialized datasets and evaluating existing techniques for fire detection.

Contribution

The paper presents FIRe-GAN, a novel extension to existing DL-based fusion methods, specifically optimized for wildfire imagery, and provides the first evaluation of such methods in this domain.

Findings

FIRe-GAN improves infrared image generation quality.

DL-based fusion methods outperform traditional techniques in fire imagery.

The study highlights the need for specialized datasets in wildfire image fusion.

Abstract

Early wildfire detection is of paramount importance to avoid as much damage as possible to the environment, properties, and lives. Deep Learning (DL) models that can leverage both visible and infrared information have the potential to display state-of-the-art performance, with lower false-positive rates than existing techniques. However, most DL-based image fusion methods have not been evaluated in the domain of fire imagery. Additionally, to the best of our knowledge, no publicly available dataset contains visible-infrared fused fire images. There is a growing interest in DL-based image fusion techniques due to their reduced complexity. Due to the latter, we select three state-of-the-art, DL-based image fusion techniques and evaluate them for the specific task of fire image fusion. We compare the performance of these methods on selected metrics. Finally, we also present an extension to one of the said methods, that we called FIRe-GAN, that improves the generation of artificial infrared images and fused ones on selected metrics.