Learned Spectral and Spatial Transforms for Multispectral Remote Sensing Data Compression

Sebastia Mijares

doi:10.1109/LGRS.2025.3554269

Learned Spectral and Spatial Transforms for Multispectral Remote Sensing Data Compression

2025-01-01

0

OA

AI

S

Sebastia Mijares *

J

Joan Bartrina-Rapestà

M

Miguel Hernández-Cabronero

J

Joan Serra-Sagristà

DOI：10.1109/LGRS.2025.3554269

原文链接

原文求助

摘要

En 中文

As more and more multispectral and hyperspectral platforms are deployed for Earth observation (EO), limited downlink capacity increases the pressure for more efficient data compression algorithms. Machine learning (ML) has been successfully applied to produce highly competitive compression models though this performance has typically been at the cost of high computational complexity, a crucial limitation for on-board remote sensing data compression. To address these issues, a reduced-complexity multispectral and hyperspectral data compression architecture is proposed. Using separate spectral and spatial transforms, the complexity of the proposed models is scalable on the number of bands, regardless of the compression ratios. This proposal outperforms state-of-the-art ML compression models as well as established lossy compression methods such as JPEG 2000 prepended with a spectral Karhunen-Lo & egrave;ve transform (KLT) on a variety of remote sensing data sources. The performance improvement is achieved with a lower complexity than said ML models. To reproduce our results, training and test data are publicly available at https://gici.uab.cat/GiciWebPage/datasets.php and source code at https://github.com/smijares/mbhs2025.

Keyword:

Transforms

Computer architecture

Training

Image coding

Data compression

Data models

Principal component analysis

Bit rate

Autoencoders

Vectors

deep learning

lossy compression

multispectral data

remote sensing

Learned Spectral and Spatial Transforms for Multispectral Remote Sensing Data Compression

摘要

期刊

机构

引用论文