Deep Domain Fidelity and Low-Rank Tensor Ring Regularization for Thick Cloud Removal of Multitemporal Remote Sensing Images

Thick cloud contamination in remote sensing (RS) images significantly hinders their utility in subsequent applications. Traditional cloud removal methods predominantly focus on the design of the regularization term, while neglecting the design of the fidelity term. Recently, the proposal of gradient...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-14
Main Authors: Peng, Hao, Huang, Ting-Zhu, Zhao, Xi-Le, Lin, Jie, Wu, Wei-Hao, Li, Li-Yuan
Format: Article
Language:English
Subjects:
Clouds
Data mining
Deep domain fidelity
Deep learning
Design
Electronic mail
Feature extraction
Image reconstruction
Indexes
MODIS
multitemporal remote sensing (MTRS) images
Preservation
Regularization
Remote sensing
tensor ring (TR) decomposition
Tensors
thick cloud removal
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Thick cloud contamination in remote sensing (RS) images significantly hinders their utility in subsequent applications. Traditional cloud removal methods predominantly focus on the design of the regularization term, while neglecting the design of the fidelity term. Recently, the proposal of gradient-domain fidelity has highlighted the significance of the fidelity term design, dedicated to maintaining textures in the gradient domain. However, the handcrafted gradient-domain fidelity still has limitations in capturing invariant and delicate features behind multitemporal RS (MTRS) images, leading to unsatisfactory detail preservation. To address the problem, we suggest a deep domain fidelity to capture deep features by leveraging a pretrained deep network, which matches the intrinsic deep feature between the original images and reference images, instead of matching the shallow features in gradient domain fidelity. Empowered with the deep domain fidelity, we propose a thick cloud removal model (called DFTR) for MTRS images, organically integrating the deep domain fidelity term with a low-rank (LR) regularization term (i.e., tensor ring (TR) decomposition), offering fine detail preservation. Extensive simulated and real experiments on MTRS images demonstrate that the proposed method outperforms the compared methods, including the origin domain-based and the gradient domain-based methods, in thick cloud removal, especially for detail preservation.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2024.3485595