GID(Gaofen Image Dataset)

GID 是具有高分二号（GF-2）卫星图像的大规模土地覆盖数据集。这个新的数据集被命名为高分图像数据集（GID），由于其覆盖范围大、分布广、空间分辨率高，优于现有的土地覆盖数据集。 GID由两部分组成：大规模分类集和精细土地覆盖分类集。大规模分类集包含 150 个像素级标注的 GF-2 图像，精细分类集由 30,000 个多尺度图像块加上 10 个像素级标注的 GF-2 图像组成。分别基于 5 个类别的训练和验证图像收集和重新标记 15 个类别的训练和验证数据。

GID is a large-scale land cover dataset with GaoFen-2 (GF-2) satellite imagery. This new dataset is named the GaoFen Image Dataset (GID), which outperforms existing land cover datasets due to its large coverage, wide distribution, and high spatial resolution. GID consists of two parts: a large-scale classification set and a fine-grained land cover classification set. The large-scale classification set contains 150 pixel-level annotated GF-2 images. The fine-grained land cover classification set is composed of 30,000 multi-scale image patches plus 10 pixel-level annotated GF-2 images. Training and validation data for 15 categories are collected and relabeled based on the training and validation images of 5 categories, respectively.

搜集汇总

背景与挑战

背景概述

GID是一个基于高分二号卫星图像的大规模土地覆盖数据集，主要用于遥感影像的语义分割任务。它包含大规模分类集和精细土地覆盖分类集两部分，分别提供150个像素级标注图像和30,000个多尺度图像块，覆盖5个和15个类别，具有高空间分辨率和广泛分布的特点，适用于土地覆盖分类研究。