danaroth/indian_pines
收藏Hugging Face2023-11-09 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/danaroth/indian_pines
下载链接
链接失效反馈官方服务:
资源简介:
Indian Pines数据集由AVIRIS传感器在印第安纳州西北部的Indian Pines测试站点收集,包含145×145像素和224个光谱反射波段,波长范围为0.4–2.5微米。该场景是更大场景的子集,包含三分之二的农业用地和三分之一的森林或其他自然多年生植被。场景中还包括两条主要双车道高速公路、一条铁路线、一些低密度住宅、其他建筑结构和较小的道路。由于场景拍摄于六月,一些作物如玉米和大豆处于早期生长阶段,覆盖率不到5%。数据集提供了16个类别的真实地面数据,这些类别并非完全互斥。此外,通过去除覆盖水吸收区域的波段,波段数量减少到200个。
The Indian Pines dataset was collected by the AVIRIS sensor at the Indian Pines Test Site in northwestern Indiana, featuring dimensions of 145×145 pixels and 224 spectral reflectance bands with a wavelength range of 0.4–2.5 micrometers. This scene is a subset of a larger landscape, where two-thirds of the area is agricultural land and one-third is forest or other natural perennial vegetation. The scene also contains two major two-lane highways, a railway line, several low-density residential areas, other built structures, and smaller roads. As the scene was captured in June, some crops such as corn and soybeans were in their early growth stages with a coverage rate of less than 5%. The dataset provides ground truth data for 16 categories that are not fully mutually exclusive. Additionally, the number of bands was reduced to 200 by removing the bands covering water absorption regions.
提供机构:
danaroth
原始信息汇总
数据集描述
该场景由AVIRIS传感器在印第安纳州西北部的Indian Pines测试站点收集,包含145×145像素和224个光谱反射率波段,波长范围为0.4–2.5×10^(-6)米。该场景是更大场景的一个子集。Indian Pines场景包含三分之二的农业用地和三分之一的森林或其他自然多年生植被。场景中有两条主要的双车道高速公路、一条铁路线,以及一些低密度住宅、其他建筑物和小型道路。由于场景是在6月份拍摄的,一些作物如玉米、大豆正处于生长初期,覆盖率不足5%。地面实况数据被划分为十六个类别,并非所有类别都是互斥的。我们还通过移除覆盖水吸收区域的波段([104-108]、[150-163]、220)将波段数量减少到200。Indian Pines数据可通过Purdue大学MultiSpec网站获取。
数据集特征
Indian Pines场景的地面实况类别及其对应的样本数量如下:
| # | 类别 | 样本数量 |
|---|---|---|
| 1 | Alfalfa | 46 |
| 2 | Corn-notill | 1428 |
| 3 | Corn-mintill | 830 |
| 4 | Corn | 237 |
| 5 | Grass-pasture | 483 |
| 6 | Grass-trees | 730 |
| 7 | Grass-pasture-mowed | 28 |
| 8 | Hay-windrowed | 478 |
| 9 | Oats | 20 |
| 10 | Soybean-notill | 972 |
| 11 | Soybean-mintill | 2455 |
| 12 | Soybean-clean | 593 |
| 13 | Wheat | 205 |
| 14 | Woods | 1265 |
| 15 | Buildings-Grass-Trees-Drives | 386 |
| 16 | Stone-Steel-Towers | 93 |
快速预览
Indian Pines数据集的样本波段。
Indian Pines数据集的地面实况。
数据集来源
该数据集最初由Manuel Graña、Miguel-Angel Veganzones、Borja Ayerdi收集。
原始数据集链接如下:
https://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes
搜集汇总
数据集介绍

背景与挑战
背景概述
Indian Pines是一个高光谱遥感图像数据集,包含16个土地覆盖类别,适用于土地分类研究。数据集经过预处理,移除了水吸收区域的波段,提供了详细的样本数量统计。
以上内容由遇见数据集搜集并总结生成



