Spatial-spectral-combined sparse representation-based classification for hyperspectral imagery
Spatial-spectral-combined sparse representation-based classification for hyperspectral imagery
复制标题
基于空间光谱组合稀疏表示的高光谱图像分类
DOI：
10.1007/s00500-014-1505-4
复制
发表时间：
2016-12-01
期刊：
影响因子：
4.1
通讯作者：
Zhu, Jiasong
中科院分区：
文献类型：
--
作者：
Jia, Sen;Xie, Yao;Zhu, Jiasong
最近，基于稀疏表示的分类（SRC）通过所有训练样本的稀疏线性组合将测试样本分配给了类，并已成功地应用于高光谱图像。另外，空间信息（这意味着相邻像素属于同一类，具有很高的可能性，是对频谱信息的宝贵补充。在本文中，我们提出了一种新的光谱空间合并的SRC方法，缩写为SSSRC或共同考虑每个像素的光谱和空间邻域信息，以通过SRC方法探索光谱和空间相干性。此外，采用快速的干扰竞争操作来加速命名的分类程序。实验结果表明，拟议的基于SRC的方法，并且可以比其他最先进的方法获得更好的性能。
Recently, sparse representation-based classification (SRC), which assigns a test sample to the class with minimum representation error via a sparse linear combination of all the training samples, has successfully been applied to hyperspectral imagery. Alternatively, spatial information, which means the adjacent pixels belong to the same class with a high probability, is a valuable complement to the spectral information. In this paper, we have presented a new spectral-spatial-combined SRC method, abbreviated as SSSRC or, to jointly consider the spectral and spatial neighborhood information of each pixel to explore the spectral and spatial coherence by the SRC method. Furthermore, a fast interference-cancelation operation is adopted to accelerate the classification procedure of, named. Experimental results have shown that both the proposed SRC-based approaches,and, could achieve better performance than the other state-of-the-art methods.