Spectral–Spatial Hyperspectral Image Classification Using $\ell_{1/2}$ Regularized Low-Rank Representation and Sparse Representation-Based Graph Cuts
Spectral–Spatial Hyperspectral Image Classification Using $\ell_{1/2}$ Regularized Low-Rank Representation and Sparse Representation-Based Graph Cuts
复制标题
DOI：
10.1109/jstars.2015.2423278
复制
发表时间：
2015-06
影响因子：
5.5
通讯作者：
Sen Jia;Xiujun Zhang;Qingquan Li
中科院分区：
文献类型：
--
作者：
Sen Jia;Xiujun Zhang;Qingquan Li
高光谱传感器收集的数百个狭窄的连续光谱带为识别表面上存在的各种物质提供了机会。此外，空间信息，强制假设相邻像素属于同一类具有很高的概率，是一个有价值的补充光谱信息。在本文中，两个主要的方法已经开发出利用空间信息。首先，通过将每个像素和空间邻域分解成低秩形式，可以有效地将空间信息集成到光谱特征中。同时，为了更精确地描述分解后数据的低秩结构，引入了一种1/2范数正则化方法，并提出了一种基于增广拉格朗日乘子（ALM）和半阈值算子的组合优化离散算法.其次，图割分割算法已被应用于基于稀疏表示的高光谱数据的概率估计，以进一步提高材料分布的空间均匀性。实验结果表明，4个真实的高光谱数据具有不同的光谱和空间分辨率的高光谱图像分类的有效性和通用性的建议的空间信息融合方法。
Hundreds of narrow contiguous spectral bands collected by a hyperspectral sensor have provided the opportunity to identify the various materials present on the surface. Moreover, spatial information, enforcing the assumption that the adjacent pixels belong to the same class with a high probability, is a valuable complement to the spectral information. In this paper, two predominant approaches have been developed to exploit the spatial information. First, by decomposing each pixel and the spatial neighborhood into a low-rank form, the spatial information can be efficiently integrated into the spectral signatures. Meanwhile, in order to describe the low-rank structure of the decomposed data more precisely, an ℓ1/2 norm regularization is introduced and a discrete algorithm is proposed to solve the combined optimization problem by the augmented Lagrange multiplier (ALM) and a half-threshold operator. Second, a graph cuts segmentation algorithm has been applied on the sparse-representation-based probability estimates of the hyperspectral data to further improve the spatial homogeneity of the material distribution. Experimental results on four real hyperspectral data with different spectral and spatial resolutions have demonstrated the effectiveness and versatility of the proposed spatial information-fused approaches for hyperspectral image classification.