danaroth/urban
收藏资源简介:
--- license: unknown --- # Description Urban is one of the most widely used hyperspectral data used in the hyperspectral unmixing study. There are 307x307 pixels, each of which corresponds to a 2x2 m2 area. In this image, there are 210 wavelengths ranging from 400 nm to 2500 nm, resulting in a spectral resolution of 10 nm. After the channels 1-4, 76, 87, 101-111, 136-153 and 198-210 are removed (due to dense water vapor and atmospheric effects), 162 channels are left (this is a common preprocess for hyperspectral unmixing analyses). There are three versions of ground truth, which contain 4, 5 and 6 endmembers respectively, which are introduced in the ground truth. # Quick look <figure> <img src= "assets/D9_1.png" alt="Urban" width="500" /> <figcaption>Urban and its ground truths.</figcaption> </figure> # Characteristics Ground Truth: three versions, including 4, 5 and 6 endmembers respectively. - 4 endmembers version: The 4 endmembers are "#1 Asphalt", "#2 Grass", "#3 Tree" and "#4 Roof" respectively. - 5 endmembers version: The 5 endmembers are "#1 Asphalt", "#2 Grass", "#3 Tree", "#4 Roof" and "#5 Dirt" respectively. - 6 endmembers version: The 6 endmembers are "#1 Asphalt", "#2 Grass", "#3 Tree", "#4 Roof", "#5 Metal", and "#6 Dirt" respectively. # Credits Dataset originally collected by Feiyun Zhu and originally available at: http://www.escience.cn/people/feiyunZHU/Dataset_GT.html To use this dataset, cite the associated paper: ``` @misc{zhu2017hyperspectral, title={Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey}, author={Feiyun Zhu}, year={2017}, eprint={1708.05125}, archivePrefix={arXiv}, primaryClass={cs.CV} }
--- 许可协议:未知 --- # 数据集描述 Urban是高光谱解混(hyperspectral unmixing)研究中应用最为广泛的高光谱数据集(hyperspectral data)之一。该数据集包含307×307个像素,每个像素对应2×2平方米的区域。该图像拥有210个光谱波段,波长范围为400 nm至2500 nm,光谱分辨率(spectral resolution)为10 nm。由于通道1-4、76、87、101-111、136-153以及198-210受密集水汽与大气效应影响,已将这些通道移除,最终保留162个通道——这是高光谱解混分析中常见的预处理步骤。该数据集包含三种版本的地面真值(ground truth),分别包含4、5、6种端元(endmembers),相关细节将在地面真值部分说明。 # 快速预览 <figure> <img src= "assets/D9_1.png" alt="Urban" width="500" /> <figcaption>Urban及其地面真值。</figcaption> </figure> # 数据集特性 地面真值包含三种版本,分别对应4、5、6种端元。 - 4端元版本:4种端元依次为#1沥青(Asphalt)、#2草地(Grass)、#3树木(Tree)和#4屋顶(Roof)。 - 5端元版本:5种端元依次为#1沥青(Asphalt)、#2草地(Grass)、#3树木(Tree)、#4屋顶(Roof)和#5泥土(Dirt)。 - 6端元版本:6种端元依次为#1沥青(Asphalt)、#2草地(Grass)、#3树木(Tree)、#4屋顶(Roof)、#5金属(Metal)和#6泥土(Dirt)。 # 数据集致谢 本数据集最初由Feiyun Zhu采集,原始发布地址为:http://www.escience.cn/people/feiyunZHU/Dataset_GT.html 使用本数据集时,请引用以下论文: @misc{zhu2017hyperspectral, title={Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey}, author={Feiyun Zhu}, year={2017}, eprint={1708.05125}, archivePrefix={arXiv}, primaryClass={cs.CV} }
数据集描述
Urban 是高光谱解混研究中使用最广泛的高光谱数据之一。该图像包含 307x307 像素,每个像素对应一个 2x2 平方米的区域。图像中包含 210 个波长,范围从 400 nm 到 2500 nm,光谱分辨率为 10 nm。在去除 1-4、76、87、101-111、136-153 和 198-210 通道(由于密集水蒸气和大气效应)后,剩下 162 个通道(这是高光谱解混分析的常见预处理)。数据集包含三个版本的地面实况,分别包含 4、5 和 6 个端元。
快速浏览

特征
地面实况:三个版本,分别包含 4、5 和 6 个端元。
- 4 端元版本:包含 "#1 Asphalt"(沥青)、"#2 Grass"(草地)、"#3 Tree"(树木)和 "#4 Roof"(屋顶)。
- 5 端元版本:包含 "#1 Asphalt"(沥青)、"#2 Grass"(草地)、"#3 Tree"(树木)、"#4 Roof"(屋顶)和 "#5 Dirt"(泥土)。
- 6 端元版本:包含 "#1 Asphalt"(沥青)、"#2 Grass"(草地)、"#3 Tree"(树木)、"#4 Roof"(屋顶)、"#5 Metal"(金属)和 "#6 Dirt"(泥土)。
致谢
数据集最初由 Feiyun Zhu 收集,原始地址为:http://www.escience.cn/people/feiyunZHU/Dataset_GT.html
使用此数据集时,请引用相关论文:
@misc{zhu2017hyperspectral, title={Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey}, author={Feiyun Zhu}, year={2017}, eprint={1708.05125}, archivePrefix={arXiv}, primaryClass={cs.CV} }




