Learned Design of a Compressive Hyperspectral Imager for Remote Sensing by a Physics-Constrained Autoencoder

Designing and optimizing systems by end-to-end deep learning is a recently emerging field. We present a novel physics-constrained autoencoder (PyCAE) for the design and optimization of a physically realizable sensing model. As a case study, we design a compressive hyperspectral imaging system for re...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Remote sensing (Basel, Switzerland) Jg. 14; H. 15; S. 3766
Hauptverfasser: Heiser, Yaron, Stern, Adrian
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.08.2022
Schlagworte:
Case studies
Coders
Compression
compressive hyperspectral imaging
Deep learning
Design
design learning
Design optimization
Etalons
geometry
hyperspectral imagery
Hyperspectral imaging
landscapes
Light modulators
Neural networks
Optics
Physics
Reconstruction
Remote sensing
Sensors
Spectral bands
Vegetation
ISSN:2072-4292, 2072-4292
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Designing and optimizing systems by end-to-end deep learning is a recently emerging field. We present a novel physics-constrained autoencoder (PyCAE) for the design and optimization of a physically realizable sensing model. As a case study, we design a compressive hyperspectral imaging system for remote sensing based on this approach, which allows capturing hundreds of spectral bands with as few as four compressed measurements. We demonstrate our deep learning approach to design spectral compression with a spectral light modulator (SpLM) encoder and a reconstruction neural network decoder. The SpLM consists of a set of modified Fabry–Pérot resonator (mFPR) etalons that are designed to have a staircase-shaped geometry. Each stair occupies a few pixel columns of a push-broom-like spectral imager. The mFPR’s stairs can sample the earth terrain in along-track scanning from an airborne or spaceborne moving platform. The SpLM is jointly designed with an autoencoder by a data-driven approach, while spectra from remote sensing databases are used to train the system. The SpLM’s parameters are optimized by integrating its physically realizable sensing model in the encoder part of the PyCAE. The decoder part of the PyCAE implements the spectral reconstruction.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2072-4292
2072-4292
DOI:10.3390/rs14153766