期刊
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
卷 146, 期 -, 页码 305-319出版社
ELSEVIER
DOI: 10.1016/j.isprsjprs.2018.09.018
关键词
Sentinel-2; Super-resolution; Sharpening of bands; Convolutional neural network; Deep learning
类别
资金
- Swiss National Science Foundation (SNSF) [200021362998]
- Fundacao para a Ciencia e a Tecnologia, Portuguese Ministry of Science, Technology and Higher Education [UID/EEA/50008/2013, ERANETMED/0001/2014]
- Fundação para a Ciência e a Tecnologia [ERANETMED/0001/2014] Funding Source: FCT
The Sentinel-2 satellite mission delivers multi-spectral imagery with 13 spectral bands, acquired at three different spatial resolutions. The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance - GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution. We employ a state-of-the-art convolutional neural network (CNN) to perform end-to-end upsampling, which is trained with data at lower resolution, i.e., from 40 -> 20 m, respectively 360 -> 60 m GSD. In this way, one has access to a virtually infinite amount of training data, by downsampling real Sentinel-2 images. We use data sampled globally over a wide range of geographical locations, to obtain a network that generalises across different climate zones and land-cover types, and can super-resolve arbitrary Sentinel-2 images without the need of retraining. In quantitative evaluations (at lower scale, where ground truth is available), our network, which we call DSen2, outperforms the best competing approach by almost 50% in RMSE, while better preserving the spectral characteristics. It also delivers visually convincing results at the full 10 m GSD.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据