Geosr: A Computer Vision Package for Deep Learning Based Single-Frame Remote Sensing Imagery Super-Resolution
Geosr: A Computer Vision Package for Deep Learning Based Single-Frame Remote Sensing Imagery Super-Resolution
复制标题
DOI：
10.1109/igarss.2019.8900416
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Zhiling Guo;Guangming Wu;Xiaodan Shi;Mingzhou Sui;Xiaoya Song;Yongwei Xu;Xiaowei Shao;R. Shibasaki
中科院分区：
文献类型：
--
作者：
Zhiling Guo;Guangming Wu;Xiaodan Shi;Mingzhou Sui;Xiaoya Song;Yongwei Xu;Xiaowei Shao;R. Shibasaki
近年来，由于深度学习在解决不适定问题方面的突出能力，单帧超分辨率(SR)的研究往往集中在深度学习方法上。然而，相关研究是通过不同的数据集和不同的深度学习框架来实现和评估的，这阻碍了不同方法之间的性能比较，严重阻碍了SR技术的进步。在这项研究中，我们提出了一个开源的计算机视觉包GeoSR，用于基于深度学习的单帧遥感图像超分辨率，以促进SR社区的发展。作为一个统一、简单、灵活的包，GeoSR包含了从数据检索到最终结果评估的流水线式的集成工具，使用户可以方便地开发自定义模型；包中还提供了通过同一高质量数据集训练的多个最先进的模型作为基线。此外，所提出的包可以作为其他相关包的可行的后端，例如高效的图像分割。
Recently, owing to the outstanding capability of deep learning in solving ill-posed problems, the single-frame super-resolution (SR) researches tend to focus on deep learning methods largely. However, related researches are implemented and evaluated through various datasets and different deep learning frameworks, which hinders the comparison of performance among different methods and heavily hampers the progress of SR techniques. In this study, we present GeoSR, an open source computer vision package for deep learning based single-frame remote sensing imagery super-resolution to facilitate the development of the SR community. As a unified, simple, and flexible package, GeoSR contains pipeline-like integrated tools from data retrieval to final result evaluation, which enables users to develop self-defined models conveniently; several state-of-the-art models trained through the same high-quality dataset are provided as the baseline in the package as well. Moreover, the proposed package could potentially serve as a viable backend for other related packages such as image segmentation with high efficiency.