论文标题
倾向于基于变压器的卫星图像的Landsat-8和Sentinel-2的同质化
Towards Transformer-based Homogenization of Satellite Imagery for Landsat-8 and Sentinel-2
论文作者
论文摘要
Landsat-8（NASA）和Sentinel-2（ESA）是两个著名的多光谱成像卫星项目，可提供公开数据。卫星的多光谱成像传感器在电磁光谱的可见和红外区域捕获了地球表面的图像。由于地球表面的大部分表面都被云覆盖，这些云在这些波长下不透明，因此许多图像没有提供太多信息。为了增加某个区域的无云图像的时间可用性，可以将观察结果结合在一起。但是，卫星的传感器可能在其性质上有所不同，从而使图像不相容。这项工作乍一看了使用基于变压器的模型来减少两个卫星项目观测值之间的光谱和空间差异的可能性。我们将结果与基于完全卷积的UNET体系结构的模型进行比较。令人惊讶的是，我们发现，尽管深层建模优于经典方法，但UNET在我们的实验中显着优于变压器。
Landsat-8 (NASA) and Sentinel-2 (ESA) are two prominent multi-spectral imaging satellite projects that provide publicly available data. The multi-spectral imaging sensors of the satellites capture images of the earth's surface in the visible and infrared region of the electromagnetic spectrum. Since the majority of the earth's surface is constantly covered with clouds, which are not transparent at these wavelengths, many images do not provide much information. To increase the temporal availability of cloud-free images of a certain area, one can combine the observations from multiple sources. However, the sensors of satellites might differ in their properties, making the images incompatible. This work provides a first glance at the possibility of using a transformer-based model to reduce the spectral and spatial differences between observations from both satellite projects. We compare the results to a model based on a fully convolutional UNet architecture. Somewhat surprisingly, we find that, while deep models outperform classical approaches, the UNet significantly outperforms the transformer in our experiments.
