Skip to content
naulon
Not checkedNot checked for notices yet.

Fusion of Hyperspectral-Multispectral images joining Spatial-Spectral Dual-Dictionary and structured sparse Low-rank representation

Nan Chen, Lichun Sui, Biao Zhang and 5 more

International Journal of Applied Earth Observations and Geoinformation · 2021

doi:10.1016/j.jag.2021.102570 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

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.

Abstract licence: CC BY-NC

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.