当前位置: X-MOL 学术Int. J. Appl. Earth Obs. Geoinf. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Fusion of Hyperspectral-Multispectral images joining Spatial-Spectral Dual-Dictionary and structured sparse Low-rank representation
International Journal of Applied Earth Observation and Geoinformation ( IF 7.6 ) Pub Date : 2021-10-20 , DOI: 10.1016/j.jag.2021.102570
Nan Chen 1 , Lichun Sui 1 , Biao Zhang 2 , Hongjie He 3 , Kyle Gao 3 , Yandong Li 1 , José Marcato Junior 4 , Jonathan Li 3
Affiliation  

High spatial resolution hyperspectral images (HR-HSIs) have shown considerable potential in urban green infrastructure monitoring. A prevalent scheme to overcome spatial resolution limitations in HSIs is by fusing low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs). Existing methods considering the spectral dictionary or spatial dictionary can only reflect the unilateral characteristics of the HSI and cannot completely restore full information in the latent HSI. To overcome this issue, we propose a novel HSI-MSI fusion method, named DDSSLR, which joins spatial-spectral dual-dictionary and structured sparse low-rank representation. The spectral dictionary characterizing generalized spectra and the corresponding spectral sparse coefficients are extracted from LR-HSI and HR-MSI, while sparse low-rank priors of the local structure are imposed on the spectral pixels within the same superpixel in HR-MSI. Additionally, in the spatial domain, we exploit the remaining high-frequency components to learn the spatial dictionary and use the unitary transformation to factorize the spatial sparse coefficient into the sparse low-rank matrix in subspace, establishing the relationship between low-rank and sparse. We formulate the two fusion models as variational optimization problems, which are effectively solved by the alternating direction methods of multipliers (ADMM). Experiments on three HSI datasets show that DDSSLR achieves state-of-the-art performance.



中文翻译:

高光谱-多光谱图像融合加入空间-光谱双字典和结构化稀疏低秩表示

高空间分辨率高光谱图像 (HR-HSI) 在城市绿色基础设施监测中显示出相当大的潜力。克服 HSI 空间分辨率限制的一种流行方案是融合低分辨率高光谱图像 (LR-HSI) 和高分辨率多光谱图像 (HR-MSI)。现有考虑光谱字典或空间字典的方法只能反映HSI的单边特征,不能完全还原潜在HSI中的全部信息。为了克服这个问题,我们提出了一种新的 HSI-MSI 融合方法,称为 DDSSLR,它结合了空间光谱双字典和结构化稀疏低秩表示。从LR-HSI和HR-MSI中提取表征广义谱的谱字典和相应的谱稀疏系数,而局部结构的稀疏低秩先验被强加在 HR-MSI 中相同超像素内的光谱像素上。此外,在空间域中,我们利用剩余的高频分量学习空间字典,并使用酉变换将空间稀疏系数分解为子空间中的稀疏低秩矩阵,建立低秩和稀疏矩阵之间的关系。 . 我们将两个融合模型表述为变分优化问题,通过乘法器的交替方向方法(ADMM)有效地解决了这些问题。在三个 HSI 数据集上的实验表明,DDSSLR 实现了最先进的性能。我们利用剩余的高频分量学习空间字典,并使用酉变换将空间稀疏系数分解为子空间中的稀疏低秩矩阵,建立低秩和稀疏之间的关系。我们将两个融合模型表述为变分优化问题,通过乘法器的交替方向方法(ADMM)有效地解决了这些问题。在三个 HSI 数据集上的实验表明,DDSSLR 实现了最先进的性能。我们利用剩余的高频分量学习空间字典,并使用酉变换将空间稀疏系数分解为子空间中的稀疏低秩矩阵,建立低秩和稀疏之间的关系。我们将两个融合模型表述为变分优化问题,通过乘法器的交替方向方法(ADMM)有效地解决了这些问题。在三个 HSI 数据集上的实验表明,DDSSLR 实现了最先进的性能。乘法器的交替方向方法(ADMM)有效地解决了这些问题。在三个 HSI 数据集上的实验表明,DDSSLR 实现了最先进的性能。乘法器的交替方向方法(ADMM)有效地解决了这些问题。在三个 HSI 数据集上的实验表明,DDSSLR 实现了最先进的性能。

更新日期:2021-10-21
down
wechat
bug