CoSpace: Common Subspace Learning From Hyperspectral-Multispectral Correspondences
CoSpace: Common Subspace Learning From Hyperspectral-Multispectral Correspondences
复制标题
DOI：
10.1109/tgrs.2018.2890705
复制
发表时间：
2019-07-01
影响因子：
8.2
通讯作者：
Zhu, Xiao Xiang
中科院分区：
文献类型：
--
作者：
Hong, Danfeng;Yokoya, Naoto;Zhu, Xiao Xiang
利用大量开放式卫星多光谱（MS）图像（例如，Sentinel-2和Landsat-8），对全球MS土地覆盖分类给予了相当大的关注。然而，其有限的光谱信息阻碍了进一步提高分类性能。高光谱成像能够区分光谱相似的类别，但与MS相比，其空间扫描带宽度较窄。为了在大覆盖范围内实现准确的土地覆盖分类，我们提出了一个跨模态特征学习框架，称为公共子空间学习（CoSpace），通过联合考虑子空间学习和监督分类。通过局部对齐两种模态的流形结构，CoSpace从高光谱MS（HS-MS）对应关系中线性学习共享的潜在子空间。然后可以将MS外样本投影到子空间中，期望利用用于学习的相应高光谱数据的丰富光谱信息，从而导致更好的分类。在两个模拟的HS-MS数据集（休斯顿大学和筑生），HS-MS数据集的覆盖范围和光谱分辨率之间的权衡，进行了广泛的实验，以证明所提出的方法相比，以前的国家的最先进的方法的优越性和有效性。
With a large amount of open satellite multispectral (MS) imagery (e.g., Sentinel-2 and Landsat-8), considerable attention has been paid to global MS land cover classification. However, its limited spectral information hinders further improving the classification performance. Hyperspectral imaging enables discrimination between spectrally similar classes but its swath width from space is narrow compared to MS ones. To achieve accurate land cover classification over a large coverage, we propose a cross-modality feature learning framework, called common subspace learning (CoSpace), by jointly considering subspace learning and supervised classification. By locally aligning the manifold structure of the two modalities, CoSpace linearly learns a shared latent subspace from hyperspectral-MS (HS-MS) correspondences. The MS out-of-samples can be then projected into the subspace, which are expected to take advantages of rich spectral information of the corresponding hyperspectral data used for learning, and thus leads to a better classification. Extensive experiments on two simulated HS-MS data sets (University of Houston and Chikusei), where HS-MS data sets have tradeoffs between coverage and spectral resolution, are performed to demonstrate the superiority and effectiveness of the proposed method in comparison with previous state-of-the-art methods.