Area01DF_surfacemodels

The Brazilian Federal District Area 01 dataset with surface models images to extract road network by deep learning fusion at the suburban area. This dataset contains high-resolution images split into training, validation, and test folders. Each folder contains img, imgm, and mask subfolders with GeoTIFF files (3034x3122 pixels) of 20cm spatial resolution. Subfolder "img" - RGB Orthoimages; "imgm" - surface models image (DSM, DTM, nDSM); "mask" - segmentation binary mask.本数据集为巴西联邦特区01号数据集，附带地表模型影像，旨在通过深度学习融合技术在郊区场景中提取道路网络。本数据集包含高分辨率影像，并划分为训练、验证与测试三个文件夹。每个文件夹下均设有img、imgm及mask三个子文件夹，内含空间分辨率为20厘米、像素尺寸为3034×3122的GeoTIFF（地理标签图像文件格式）文件。其中子文件夹“img”存储RGB正射影像；“imgm”存储地表模型影像（包括数字表面模型DSM、数字地形模型DTM以及归一化数字表面模型nDSM）；“mask”存储分割二值掩码。