Synthesis of High-Resolution Formosat-8 Satellite Image using Fast Convex Deep Learning Algorithm

Synthesis of high-resolution (HR) FORMOSAT-8 satellite image is a critical task with high economical values, not only for avoiding related issues before launching FORMOSAT-8, but also for predicting and understanding the potential applications like precision agriculture. Nevertheless, there is no ex...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin, Chia-Hsiang, Young, Si-Sheng, Chang, Li-Yu, Liu, Cynthia S.J.
Format: Conference Proceeding
Language:English
Subjects:
Codes
convex optimization
Deep learning
FORMOSAT-8 satellite
Fuses
image fusion
image super-resolution
Pléiades satellite
Precision agriculture
Satellite images
Sentinel-2 satellite
Spatial resolution
Superresolution
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Synthesis of high-resolution (HR) FORMOSAT-8 satellite image is a critical task with high economical values, not only for avoiding related issues before launching FORMOSAT-8, but also for predicting and understanding the potential applications like precision agriculture. Nevertheless, there is no existing techniques for this mission, motivating us to reconsider the synthesis problem as a super-resolution problem under the satellite image fusion framework. Specifically, we employ the Sentinel-2 and Pléiades satellite images based on their fundamental properties (e.g., band alignment, and spatial resolution), and trickily fuse them to generate the target image (i.e, the HR FORMOSAT-8 image). Our fusion algorithm adopts the convex/deep (CODE) small-data learning theory, recently invented in the remote sensing area, resulting in a fast (closed-form) and high-quality synthesis 4m product.
ISSN:2153-7003
DOI:10.1109/IGARSS53475.2024.10640913