SAT-MTB-VSR: A Satellite Video Super-resolution Dataset

SAT-MTB-VSR is a large-scale dataset for satellite video super-resolution made from original videos of Jilin-1, which is a subset of the satellite video multitasking dataset SAT-MTB. The dataset is cropped from 18 videos captured by the Jilin-1 video satellite, covering a wide range of terrains, such as cities, docks, airports, suburbs, forests, and deserts, with a resolution of about 1 m. And the videos contain dynamic scenes, such as moving cars, airplanes, trains, and ships, which test the ability of the VSR method to deal with moving targets of different sizes and speeds. At the same time, due to the motion of the satellite, the video contains changes in viewing angle and lighting. It contains 431 videos, each of which is 100 consecutive frames, of which 413 are used as the training set and 18 as the validation set, and all the 18 validation sets are from different original videos, while the size of the images is 640 × 640. These images are downsampled 4× by bicubic interpolation to get 160 × 160 low-resolution images, thus obtaining the LR-HR training pairs.

SAT-MTB-VSR是一款面向卫星视频超分辨率的大规模数据集，其数据源自吉林一号（Jilin-1）的原始视频，是卫星视频多任务数据集SAT-MTB的子集。该数据集从吉林一号视频卫星采集的18段原始视频中裁剪得到，覆盖城市、码头、机场、郊区、森林、沙漠等多样地貌，原始分辨率约为1米。视频中包含各类动态场景，例如行驶的汽车、飞机、列车与船舶，可用于检验视频超分辨率（Video Super-Resolution, VSR）方法处理不同尺寸、不同运动速度目标的性能。同时，由于卫星在轨运动，视频中还存在拍摄视角与光照条件的变化。该数据集共包含431段视频，每段视频均包含100帧连续画面，其中413段划分为训练集，18段划分为验证集，且所有18段验证集视频均来自不同的原始视频源；数据集内的高分辨率单帧图像尺寸统一为640×640，通过双三次插值（bicubic interpolation）对其进行4倍下采样后，可得到尺寸为160×160的低分辨率图像，进而构建低分辨率-高分辨率（LR-HR）训练样本对。

搜集汇总

背景与挑战

背景概述

SAT-MTB-VSR是一个用于卫星视频超分辨率的大规模数据集，基于吉林一号卫星视频构建，覆盖城市、码头、机场等多种地形和动态场景，分辨率约1米。数据集包含431个视频（每个100帧），分为训练集和验证集，通过下采样生成低分辨率-高分辨率图像对，旨在测试超分辨率方法处理移动目标和环境变化的能力。