Hyperspectral Super-Resolution Via Coupled Tensor Factorization: Identifiability and Algorithms
Hyperspectral Super-Resolution Via Coupled Tensor Factorization: Identifiability and Algorithms
复制标题
DOI：
10.1109/icassp.2018.8462525
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Charilaos I. Kanatsoulis;Xiao Fu;N. Sidiropoulos;Wing-Kin Ma
中科院分区：
文献类型：
--
作者：
Charilaos I. Kanatsoulis;Xiao Fu;N. Sidiropoulos;Wing-Kin Ma
本文主要研究了高光谱图像和多光谱图像的融合问题，以产生具有高空间分辨率和光谱分辨率的超分辨率图像。现有的算法大多是基于矩阵化的HSI和MSI的联合低秩分解。这一框架在一定程度上是有效的，但仍存在一些挑战。首先，目前还不清楚是否超分辨率图像是可识别的，在理论上在这个框架下，而可识别性通常在这样的估计问题中起着至关重要的作用。其次，大多数算法假设从超分辨率图像到HSI和MSI的退化算子是已知的或可以容易地估计-这在实践中几乎是不正确的。在这项工作中，我们提出了一种新的耦合张量分解方法，可以有效地规避这些问题。该方法保证了超分辨率图像在现实条件下的可识别性。即使不知道空间退化算子，该方法也可以工作，这在实践中可能很难准确估计。使用AVIRIS铜数据的仿真证明了所提出的方法的有效性。
This work focuses on the problem of fusing a hyperspectral image (HSI) and a multispectral image (MSI) to produce a super-resolution image that admits high spatial and spectral resolutions. Existing algorithms are mostly based on joint low-rank factorization of the ma-tricized HSI and MSI. This framework is effective to some extent, but several challenges remain. First, it is unclear whether or not the super-resolution image is identifiable in theory under this framework, while identifiability usually plays an essential role in such estimation problems. Second, most algorithms assume that the degradation operators from the super-resolution image to the HSI and MSI are known or can be easily estimated - which is hardly true in practice. In this work, we propose a novel coupled tensor decomposition method that can effectively circumvent these issues. The proposed approach guarantees the identifiability of the super-resolution image under realistic conditions. The method can work even without knowing the spatial degradation operator, which could be hard to accurately estimate in practice. Simulations using AVIRIS Cuprite data are employed to demonstrate the effectiveness of the proposed approach.