[论文解读] A Remote Sensing Image Dataset for Cloud Removal

Daoyu Lin, Guangluan Xu+4 more|arXiv (Cornell University)|Jan 3, 2019

Advanced Image Fusion Techniques参考文献 1被引用 73

一句话总结

本文引入了用于遥感图像云去除的 RICE 数据集，包含 RICE-I（500 对云/清晰图像对）和 RICE-II（基于 Landsat 的云/清晰/掩码三元组），并给出基线 pix2pix 在 PSNR 和 SSIM 上的评估结果。

ABSTRACT

Cloud-based overlays are often present in optical remote sensing images, thus limiting the application of acquired data. Removing clouds is an indispensable pre-processing step in remote sensing image analysis. Deep learning has achieved great success in the field of remote sensing in recent years, including scene classification and change detection. However, deep learning is rarely applied in remote sensing image removal clouds. The reason is the lack of data sets for training neural networks. In order to solve this problem, this paper first proposed the Remote sensing Image Cloud rEmoving dataset (RICE). The proposed dataset consists of two parts: RICE1 contains 500 pairs of images, each pair has images with cloud and cloudless size of 512*512; RICE2 contains 450 sets of images, each set contains three 512*512 size images. , respectively, the reference picture without clouds, the picture of the cloud and the mask of its cloud. The dataset is freely available at \url{https://github.com/BUPTLdy/RICE_DATASET}.

研究动机与目标

• 激发对光学遥感图像云去除的需求并促进深度学习方法的应用。
• 提供一个基准数据集（RICE）以支持云去除模型的训练和评估。
• 提供基线定量结果，为未来方法设定参照。

提出的方法

• 通过从 Google Earth 获取云/清晰对，并裁剪为 512x512、无重叠，构建 RICE-I。
• 从 Landsat 8 LandsatLook 图像构建 RICE-II，将含云与无云参考在 15 天内对齐。
• 将 pix2pix 作为去云的基线模型，输入云图像与掩码的拼接。
• 使用 PSNR 和 SSIM 指标评估性能。
• 报告数据集细节并就未来扩展提出定性考虑。

实验结果

研究问题

• RQ1 Paired dataset of cloud and cloudless remote sensing images support learning-based cloud removal?
• RQ2 What are baseline PSNR and SSIM performances for a conditional image translation model on RICE?
• RQ3 How do cloud removal results differ between the RICE-I and RICE-II subsets?

主要发现

Dataset	PSNR	SSIM
RICE-I	31.03	0.91
RICE-II	30.04	0.80

• RICE-I 在基线评估中的 PSNR 为 31.03，SSIM 为 0.91。
• RICE-II 在基线评估中的 PSNR 为 30.04，SSIM 为 0.80。
• 该数据集提供一个公开资源（GitHub），以促进遥感领域的基于深度学习的云去除。
• 基线实验表明该数据集对于有监督的云去除任务具有实用性。