Data Set Information:

该数据集包含来自Johnson等人（2013）遥感研究的一些训练和测试数据，该研究涉及在Quickbird图像中检测患病树木。“病树”类（74）的训练样本很少，而“其他土地覆盖”类（4265）的训练样本很多。

数据集由图像段组成，这些图像段是通过分割泛锐化图像生成的。这些分段包含来自Quickbird多光谱图像波段的光谱信息和来自全色（Pan）图像波段的纹理信息。测试数据集适用于具有15a欧元分割规模的行？片段和a€？原始多光谱图像参考文献表2中的光谱信息（即第5行）。有关数据集的更多信息，请参见下面的参考资料，如果使用此数据集，请引用参考资料。

Files
training.csv: training data set (4339 image segments)
testing.csv: testing data set (500 image segments)

Attribute Information:

class: 'w' (diseased trees), 'n' (all other land cover)
GLCM_Pan: GLCM mean texture (Pan band)
Mean_G: Mean green value
Mean_R: Mean red value
Mean_NIR: Mean NIR value
SD_Pan: Standard deviation (Pan band)

Relevant Papers:

Johnson, B., Tateishi, R., Hoan, N., 2013. A hybrid pansharpening approach and multiscale object-based image analysis for mapping diseased pine and oak trees. International Journal of Remote Sensing, 34 (20), 6969-6982.

Citation Request:

Please cite: Johnson, B., Tateishi, R., Hoan, N., 2013. A hybrid pansharpening approach and multiscale object-based image analysis for mapping diseased pine and oak trees. International Journal of Remote Sensing, 34 (20), 6969-6982.