A Geographically Weighted Total Composite Error Analysis for Soft Classification
A Geographically Weighted Total Composite Error Analysis for Soft Classification
复制标题
软分类的地理加权总复合误差分析
DOI：
10.1109/igarss39084.2020.9323939
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Nakaya Tomoki
中科院分区：
文献类型：
--
作者：
Tsutsumida Narumasa;Yoshida Takahiro;Murakami Daisuke;Nakaya Tomoki
土地覆盖分类中的错误通常是空间异构的，即使实现了诸如光谱解混的软分类模型来减轻混合像素问题。估计的土地覆盖是目标类别的分数，限制总和为1，并且是非负的。考虑到空间异质性的分类进行评估，我们提出了一个地理加权总复合误差分析。利用美国地质调查局全球参考数据库，我们评估了ALOS AVNIR-2数据的光谱分解分类为4个土地覆盖类的误差。结果产生一个空间表面的局部误差的艾奇逊距离和地址，跨空间的误差幅度与土地覆盖的复杂性。
Errors in land cover classification are often spatially heterogeneous even though a soft classification model such as spectral unmixing is implemented to mitigate a mixed pixel problem. The estimated land covers are fractions of targeted classes with the restriction of the sum to one and being non-negative. To assess the classification with considering a spatial heterogeneity, we propose a geographically weighted total composite error analysis. By using the USGS global reference database, we assessed errors of spectral unmixing classification of ALOS AVNIR-2 data into 4 land cover classes. Results yield a spatial surface of local errors by the Aitchison distance and address that the error magnitude across space is associated with the complexity of land covers.
影响因子：
13.5
作者：
Bruce W. Pengra;Jordan B. Long;D. Dahal;S. Stehman;T. Loveland
通讯作者：
Bruce W. Pengra;Jordan B. Long;D. Dahal;S. Stehman;T. Loveland