期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 12, 页码 10438-10454出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3046038
关键词
Tensors; Noise reduction; Hyperspectral imaging; Correlation; Covariance matrices; Training data; Image denoising; 3-D patches; hyperspectral image (HSI) denoising; low-rank tensor factorization; self-similarity
类别
资金
- National Natural Science Foundation of China [42001287]
- Hong Kong Research Grants Council (HKRGC) General Research Fund (GRF) [12306616, 12200317, 12300218, 12300519, 17201020]
- University of Hong Kong (HKU) [104005583]
This article focuses on denoising of hyperspectral images by utilizing the correlation between reflectance vectors and self-similarity in images. The method proposed significantly reduces computational complexity, is insensitive to parameters, and demonstrates good performance and user-friendliness through comparison with other methods.
The ever-increasing spectral resolution of hyperspectral images (HSIs) is often obtained at the cost of a decrease in the signal-to-noise ratio of the measurements, thus calling for effective denoising techniques. HSIs from the real world lie in low-dimensional subspaces and are self-similar. The low dimensionality stems from the high correlation existing among the reflectance vectors, and self-similarity is common in real-world images. In this article, we exploit the above two properties. The low dimensionality is a global property that enables the denoising to be formulated just with respect to the subspace representation coefficients, thus greatly improving the denoising performance and reducing the computational complexity during processing. The self-similarity is exploited via a low-rank tensor factorization of nonlocal similar 3-D patches. The proposed factorization hinges on the optimal shrinkage/thresholding of the singular value decomposition (SVD) singular values of low-rank tensor unfoldings. As a result, the proposed method is user friendly and insensitive to its parameters. Its effectiveness is illustrated in a comparison with state-of-the-art competitors. A MATLAB demo of this work is available at https://github.com/LinaZhuang for the sake of reproducibility.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据