A Scalable Reduced-Complexity Compression of Hyperspectral Remote Sensing Images Using Deep Learning

Research output: Contribution to journalArticleResearchpeer-review

5 Downloads (Pure)

Abstract

Two key hurdles to the adoption of Machine Learning (ML) techniques in hyperspectral data compression are computational complexity and scalability for large numbers of bands. These are due to the limited computing capacity available in remote sensing platforms and the high computational cost of compression algorithms for hyperspectral data, especially when the number of bands is large. To address these issues, a channel clusterisation strategy is proposed, which reduces the computational demands of learned compression methods for real scenarios and is scalable for different sources of data with varying numbers of bands. The proposed method is compatible with an embedded implementation for state-of-the-art on board hardware, a first for a ML hyperspectral data compression method. In terms of coding performance, our proposal surpasses established lossy methods such as JPEG 2000 preceded by a spectral Karhunen-Loève Transform (KLT), in clusters of 3 to 7 bands, achieving a PSNR improvement of, on average, 9 dB for AVIRIS and 3 dB for Hyperion images.
Original languageEnglish
Article number4422
Number of pages15
JournalRemote Sensing
Volume15
Issue number18
DOIs
Publication statusPublished - 8 Sept 2023

Fingerprint

Dive into the research topics of 'A Scalable Reduced-Complexity Compression of Hyperspectral Remote Sensing Images Using Deep Learning'. Together they form a unique fingerprint.

Cite this