局部超图拉普拉斯约束的高光谱影像低秩表示去噪方法

Local Hypergraph Laplacian Regularized Low-Rank Representation for Noise Reduction of Hyperspectral Images

针对传统高光谱影像低秩表示去噪方法无法保持影像多元几何结构信息的问题,提出一种基于局部超图拉普拉斯约束的高光谱影像低秩表示去噪方法。在低秩表示模型中增加超图拉普拉斯正则项,保持数据间多元几何流形结构;并对低秩模型系数矩阵增加稀疏和非负约束条件,进一步提高模型对影像局部信息的保持能力,使得模型不仅能够恢复具有低秩性质的影像信号分量,而且可以很好地保持影像的多元几何流形结构。在AVIRIS影像和ProSpecTIR-VS影像上的对比实验表明,所提方法更好地保持了影像的空间和光谱信息,有效地改善了高光谱影像去噪效果。

Low-rank representation is one of the state-of-art hyperspectral image denoising algorithms, but it suffers from ignoring the high-order relations between data points in images. We propose a hypergraph Laplacian regularized low-rank representation algorithm for noise reduction of hyperspectral images, which can represent the high-order relations between data points by using the hypergraph Laplacian regularization. The ability of maintaining the local information is improved, and the sparse and non-negative constraints are added to the model coefficient matrix. The proposed method not only resumes the low-rank signal components, but also represents the high-order relations of the image data. Experimental results on AVIRIS and ProSpecTIR-VS images show that the proposed approach can maintain the spatial and spectral information of images better, which improves the denoising results of hyperspectral images effectively.