Dictionary based Hyperspectral Image Reconstruction Captured with CS-MUSI

Yaniv Oiknine; Boaz Arad; Isaac August; Ohad Ben-Shahar; Adrian Stern

doi:10.1109/WHISPERS.2018.8747233

Dictionary based Hyperspectral Image Reconstruction Captured with CS-MUSI

Yaniv Oiknine, Boaz Arad, Isaac August, Ohad Ben-Shahar, Adrian Stern

Research output: Contribution to conference › Paper › peer-review

4 Scopus citations

Abstract

The Compressive Sensing Miniature Ultra-Spectral Imaging (CS-MUSI) camera uses a spectral modulator and a grayscale sensor in order to capture an encoded compressed spectral signal. Using the compressive sensing (CS) theory hyperspectral (HS) cubes with hundreds of spectral bands can be reconstructed from an order of magnitude fewer samples. In this work, we show that by using spectral dictionary, as the sparsifying operator, for reconstruction of CS HS images acquired with our CS-MUSI camera, we can both increase the reconstruction quality and reduce the number of measurements CS theory requires as well.

Original language	English GB
DOIs	https://doi.org/10.1109/WHISPERS.2018.8747233
State	Published - 1 Sep 2018
Event	9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2018 - Amsterdam, Netherlands Duration: 23 Sep 2018 → 26 Sep 2018

Conference

Conference	9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2018
Country/Territory	Netherlands
City	Amsterdam
Period	23/09/18 → 26/09/18

Keywords

CS-MUSI
Compressive sensing
Dictionary
Hyperspectral
Sparsifying operator

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/WHISPERS.2018.8747233

Cite this

@conference{3da02560d494489bae34c16827d45683,

title = "Dictionary based Hyperspectral Image Reconstruction Captured with CS-MUSI",

abstract = "The Compressive Sensing Miniature Ultra-Spectral Imaging (CS-MUSI) camera uses a spectral modulator and a grayscale sensor in order to capture an encoded compressed spectral signal. Using the compressive sensing (CS) theory hyperspectral (HS) cubes with hundreds of spectral bands can be reconstructed from an order of magnitude fewer samples. In this work, we show that by using spectral dictionary, as the sparsifying operator, for reconstruction of CS HS images acquired with our CS-MUSI camera, we can both increase the reconstruction quality and reduce the number of measurements CS theory requires as well.",

keywords = "CS-MUSI, Compressive sensing, Dictionary, Hyperspectral, Sparsifying operator",

author = "Yaniv Oiknine and Boaz Arad and Isaac August and Ohad Ben-Shahar and Adrian Stern",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; null ; Conference date: 23-09-2018 Through 26-09-2018",

year = "2018",

month = sep,

day = "1",

doi = "10.1109/WHISPERS.2018.8747233",

language = "אנגלית",

}

TY - CONF

T1 - Dictionary based Hyperspectral Image Reconstruction Captured with CS-MUSI

AU - Oiknine, Yaniv

AU - Arad, Boaz

AU - August, Isaac

AU - Ben-Shahar, Ohad

AU - Stern, Adrian

PY - 2018/9/1

Y1 - 2018/9/1

N2 - The Compressive Sensing Miniature Ultra-Spectral Imaging (CS-MUSI) camera uses a spectral modulator and a grayscale sensor in order to capture an encoded compressed spectral signal. Using the compressive sensing (CS) theory hyperspectral (HS) cubes with hundreds of spectral bands can be reconstructed from an order of magnitude fewer samples. In this work, we show that by using spectral dictionary, as the sparsifying operator, for reconstruction of CS HS images acquired with our CS-MUSI camera, we can both increase the reconstruction quality and reduce the number of measurements CS theory requires as well.

AB - The Compressive Sensing Miniature Ultra-Spectral Imaging (CS-MUSI) camera uses a spectral modulator and a grayscale sensor in order to capture an encoded compressed spectral signal. Using the compressive sensing (CS) theory hyperspectral (HS) cubes with hundreds of spectral bands can be reconstructed from an order of magnitude fewer samples. In this work, we show that by using spectral dictionary, as the sparsifying operator, for reconstruction of CS HS images acquired with our CS-MUSI camera, we can both increase the reconstruction quality and reduce the number of measurements CS theory requires as well.

KW - CS-MUSI

KW - Compressive sensing

KW - Dictionary

KW - Hyperspectral

KW - Sparsifying operator

UR - http://www.scopus.com/inward/record.url?scp=85063222388&partnerID=8YFLogxK

U2 - 10.1109/WHISPERS.2018.8747233

DO - 10.1109/WHISPERS.2018.8747233

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:85063222388

Y2 - 23 September 2018 through 26 September 2018

ER -

Dictionary based Hyperspectral Image Reconstruction Captured with CS-MUSI

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this