Wildfire detection using satellite images is a widely studied task in remote
sensing with many applications to fire delineation and mapping. Recently, deep
learning methods have become a scalable solution to automate this task,
especially in the field of unsupervised learning where no training data is
available. This is particularly important in the context of emergency risk
monitoring where fast and effective detection is needed, generally based on
high-resolution satellite data. Among various approaches, Anomaly Detection
(AD) appears to be highly potential thanks to its broad applications in
computer vision, medical imaging, as well as remote sensing. In this work, we
build upon the framework of Vector Quantized Variational Autoencoder (VQ-VAE),
a popular reconstruction-based AD method with discrete latent spaces, to
perform unsupervised burnt area extraction. We integrate VQ-VAE into an
end-to-end framework with an intensive post-processing step using dedicated
vegetation, water and brightness indexes. Our experiments conducted on
high-resolution SPOT-6/7 images provide promising results of the proposed
technique, showing its high potential in future research on unsupervised burnt
area extraction.

利用卫星图像进行野火检测是遥感领域中广泛研究的任务，最近，深度学习方法已成为自动化此任务的可扩展解决方案，尤其是在无监督学习领域，其中没有训练数据可用。本文以矢量量化变分自动编码器 (VQ-VAE) 作为框架，通过离散潜在空间执行无监督的烧伤区域提取，并将其与专用的植被、水和亮度指数进行深度融合，实验结果显示了该技术在未来无监督烧伤区域提取研究中具有很高的潜力。