Multiscale Low-Rank Spatial Features for Hyperspectral Image Classification
Multiscale Low-Rank Spatial Features for Hyperspectral Image Classification
复制标题
DOI：
10.1109/lgrs.2020.3034631
复制
发表时间：
2020-11
影响因子：
4.8
通讯作者：
Weiwei Sun;Wen Shao;Jiangtao Peng;Gang Yang;Xiangchao Meng;Q. Du
中科院分区：
文献类型：
--
作者：
Weiwei Sun;Wen Shao;Jiangtao Peng;Gang Yang;Xiangchao Meng;Q. Du
本文提出了一种从高光谱图像中提取多尺度空间结构的多尺度低秩分解（MSLRD）方法。MSLRD假设地物在变化的空间尺度上具有不同的特征。它将每个波段图像分解成一系列块矩阵，其中这些低秩块在多个尺度上获取详细的空间结构。将低秩矩阵分解问题表述为最小化所有分块矩阵的秩，并采用乘子法的备选方向进行优化。在Indian Pines和Pavia University数据集上的实验表明，MSLRD可以大大提高常规光谱特征（即所有波段）分类的分类性能，并且优于目前五种最先进的空间特征提取方法。
This letter presents a multiscale low-rank decomposition (MSLRD) method to extract multiscale spatial structures from hyperspectral images. The MSLRD assumes that ground objects have divergent characteristics in changing spatial scales. It decomposes each band image into a series of block-wise matrices, where these low-rank blocks take detailed spatial structures at multiple scales. It formulates the low-rank matrix decomposition problem into minimizing the ranks of all block matrices and adopts the alternative direction of the multiplier method to optimize it. Experiments on Indian Pines and Pavia University data sets show that the MSLRD can greatly improve the classification performance of regular classification on spectral features (i.e., all bands) and perform better than five state-of-the-art spatial feature extraction methods.