WHU-Hi-HongHu

该数据集名为WHU-Hi-HongHu，由安装在DJI M600 Pro无人机上的Headwall Nano-Hyperspec传感器获取，拥有940×475像素的分辨率和270个光谱波段（波长范围在400至1000纳米之间），空间分辨率为0.043米。该数据集特色在于展现了复杂的农业场景，包含23个标注类别。此外，数据集反映了多样的作物类型和类别内的变异性，采用固定样本协议，每个类别采样50个标签。其规模为940×475像素，包含270个光谱波段，任务是对其进行分类。

The dataset named WHU-Hi-HongHu was acquired by a Headwall Nano-Hyperspec sensor mounted on a DJI M600 Pro unmanned aerial vehicle (UAV). It has an image size of 940×475 pixels, 270 spectral bands covering the wavelength range from 400 to 1000 nm, and a spatial resolution of 0.043 meters. This dataset showcases complex agricultural scenarios and contains 23 annotated categories. It reflects diverse crop types and intra-class variability, adopting a fixed-sample protocol where 50 labeled samples are sampled for each category. With the aforementioned specifications, the downstream task for this dataset is hyperspectral image classification.

搜集汇总

背景与挑战

背景概述

WHU-Hi-HongHu是一个高空间分辨率（0.043米）的无人机载高光谱数据集，包含22种农作物和其他地物类别，适用于精确农作物分类研究。数据集采集于多云天气条件下的复杂农业场景，具有270个光谱波段（400-1000nm）。