RICE (Remote sensing Image Cloud rEmoving)
收藏资源简介:
RICE数据集由中国科学院电子学研究所创建,旨在解决光学遥感图像中云层遮挡的问题。数据集分为RICE1和RICE2两部分,RICE1包含500对512*512像素的云和无云图像,RICE2包含450组图像,每组包括无云参考图像、云图像及其云层掩码。数据集通过Google Earth和Landsat 8 OLI/TIRS数据集收集,用于训练神经网络以实现云层去除,广泛应用于地球观测、气候变化和环境监测等领域。
The RICE dataset was developed by the Institute of Electronics, Chinese Academy of Sciences, aiming to address the problem of cloud occlusion in optical remote sensing images. The dataset is divided into two subsets: RICE1 and RICE2. RICE1 includes 500 pairs of 512×512 pixel cloud and cloud-free images. RICE2 contains 450 image groups, each consisting of a cloud-free reference image, a cloud image, and its corresponding cloud mask. The dataset is collected from Google Earth and the Landsat 8 OLI/TIRS dataset, and is used to train neural networks for cloud removal, which is widely applied in fields such as Earth observation, climate change research and environmental monitoring.

- 1A Remote Sensing Image Dataset for Cloud Removal中国科学院电子学研究所 · 2019年



