Edge detection on hyperspectral imagery via manifold techniques

Yuan Zhou; Bo Wu; Deren Li; Rongxing Li

doi:10.1109/WHISPERS.2009.5288984

Edge detection on hyperspectral imagery via manifold techniques

Yuan Zhou
, Bo Wu
, Deren Li
, Rongxing Li

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

9 Citations (Scopus)

Abstract

For hyperspectral imagery, the term "spectral edge" has not been clearly defined because of the complexity of the high dimensional properties in spectral space. In this paper, a new definition of the spectral edge is presented based on a data-driven mathematic approach Manifold Learning. It considers both the spectral features in spectral space and the discontinuity of image function in image space. Experimental analysis using EO-1 hyperspectral imagery shows that the spectral edge based method has desired performance to describe the edge contours in the hyperspectral imagery.

Original language	English
Title of host publication	WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publication	Evolution in Remote Sensing
DOIs	https://doi.org/10.1109/WHISPERS.2009.5288984
Publication status	Published - 21 Dec 2009
Externally published	Yes
Event	WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing - Grenoble, France Duration: 26 Aug 2009 → 28 Aug 2009

Conference

Conference	WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing
Country/Territory	France
City	Grenoble
Period	26/08/09 → 28/08/09

Keywords

Edge detection
Hyperspectral imagery
LTSA
Manifold learning
Spectral edge

ASJC Scopus subject areas

Computer Networks and Communications
Computer Vision and Pattern Recognition
Signal Processing

More information

10.1109/WHISPERS.2009.5288984

Cite this

@inproceedings{0f05b9c588194d76a2206daa0d271358,

title = "Edge detection on hyperspectral imagery via manifold techniques",

abstract = "For hyperspectral imagery, the term {"}spectral edge{"} has not been clearly defined because of the complexity of the high dimensional properties in spectral space. In this paper, a new definition of the spectral edge is presented based on a data-driven mathematic approach Manifold Learning. It considers both the spectral features in spectral space and the discontinuity of image function in image space. Experimental analysis using EO-1 hyperspectral imagery shows that the spectral edge based method has desired performance to describe the edge contours in the hyperspectral imagery.",

keywords = "Edge detection, Hyperspectral imagery, LTSA, Manifold learning, Spectral edge",

author = "Yuan Zhou and Bo Wu and Deren Li and Rongxing Li",

year = "2009",

month = dec,

day = "21",

doi = "10.1109/WHISPERS.2009.5288984",

language = "English",

isbn = "9781424446872",

booktitle = "WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing",

note = "WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing ; Conference date: 26-08-2009 Through 28-08-2009",

}

Zhou, Y, Wu, B, Li, D & Li, R 2009, Edge detection on hyperspectral imagery via manifold techniques. in WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing., 5288984, WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Grenoble, France, 26/08/09. https://doi.org/10.1109/WHISPERS.2009.5288984

Edge detection on hyperspectral imagery via manifold techniques. / Zhou, Yuan; Wu, Bo; Li, Deren et al.
WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. 2009. 5288984.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Edge detection on hyperspectral imagery via manifold techniques

AU - Zhou, Yuan

AU - Wu, Bo

AU - Li, Deren

AU - Li, Rongxing

PY - 2009/12/21

Y1 - 2009/12/21

N2 - For hyperspectral imagery, the term "spectral edge" has not been clearly defined because of the complexity of the high dimensional properties in spectral space. In this paper, a new definition of the spectral edge is presented based on a data-driven mathematic approach Manifold Learning. It considers both the spectral features in spectral space and the discontinuity of image function in image space. Experimental analysis using EO-1 hyperspectral imagery shows that the spectral edge based method has desired performance to describe the edge contours in the hyperspectral imagery.

AB - For hyperspectral imagery, the term "spectral edge" has not been clearly defined because of the complexity of the high dimensional properties in spectral space. In this paper, a new definition of the spectral edge is presented based on a data-driven mathematic approach Manifold Learning. It considers both the spectral features in spectral space and the discontinuity of image function in image space. Experimental analysis using EO-1 hyperspectral imagery shows that the spectral edge based method has desired performance to describe the edge contours in the hyperspectral imagery.

KW - Edge detection

KW - Hyperspectral imagery

KW - LTSA

KW - Manifold learning

KW - Spectral edge

UR - https://www.scopus.com/pages/publications/72049085824

U2 - 10.1109/WHISPERS.2009.5288984

DO - 10.1109/WHISPERS.2009.5288984

M3 - Conference article published in proceeding or book

SN - 9781424446872

BT - WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing

T2 - WHISPERS '09 - 1st Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing

Y2 - 26 August 2009 through 28 August 2009

ER -

Edge detection on hyperspectral imagery via manifold techniques

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this