Time-Series FY4A Datasets for Super-Resolution Benchmarking of Meteorological Satellite Images
نویسندگان
چکیده
Meteorological satellites are usually operated at high temporal resolutions, but the spatial resolutions too poor to identify ground content. Super-resolution is an economic way enhance details, feasibility not validated for meteorological images due absence of benchmarking data. In this work, we propose FY4ASRgray and FY4ASRcolor datasets assess super-resolution algorithms on applications. The features cloud sensitivity continuity linked proposed datasets. To test usability new datasets, five state-of-the-art gathered contest. Shift learning used shorten training time improve parameters. Methods modified deal with 16-bit challenge. reconstruction results demonstrated evaluated regarding radiometric, structural, spectral loss, which gives baseline performance detail enhancement FY4A satellite images. Additional experiments made sequence super-resolution, spatiotemporal fusion, generalization further test.
منابع مشابه
Super-resolution of Defocus Blurred Images
Super-resolution is a process that combines information from some low-resolution images in order to produce an image with higher resolution. In most of the previous related work, the blurriness that is associated with low resolution images is assumed to be due to the integral effect of the acquisition device’s image sensor. However, in practice there are other sources of blurriness as well, inc...
متن کاملSuper resolution of time-lapse seismic images
We present results of an on-going project to assess the applicability in reflection seismology of emerging super resolution techniques pioneered in digital photography. Our approach involves: (1) construction of a forward model connecting low resolution seismic images to high resolution ones, and (2) solution of a Tikhonov-regularized ill conditioned optimization problem to construct a high res...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Remote Sensing
سال: 2022
ISSN: ['2315-4632', '2315-4675']
DOI: https://doi.org/10.3390/rs14215594