Segmentations of hyperspectral imagery: Techniques and applications

Jerry Silverman; Stanley R. Rotman

doi:10.1117/12.457627

Segmentations of hyperspectral imagery: Techniques and applications

Jerry Silverman, Stanley R. Rotman

Department of Electrical & Computer Engineering

Research output: Contribution to journal › Conference article › peer-review

8 Scopus citations

Abstract

Several approaches for segmenting hyperspectral data and automatically detecting unusual objects in natural scenes are discussed. We demonstrate segmentations of hyperspectral imagery based on of the most significant principal components of the hyperspectral data cube. Several applications of the segmented data are treated. Digital morphological operations can be used to isolate segments that match target criteria. Alternatively, background segments can be used to define background endmembers; pixels that are quantitatively spectrally different from the background can then be designated. Analog morphological operations can then be used for clutter rejection and for the detection of objects of particular size and shape.

Original language	English
Pages (from-to)	334-349
Number of pages	16
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	4820
Issue number	1
DOIs	https://doi.org/10.1117/12.457627
State	Published - 1 Dec 2002
Event	Infrared Technology and Applications XXVIII - Seattle, WA, United States Duration: 7 Jul 2002 → 11 Jul 2002

Keywords

Clustering
Hyperspectral data
Morphological operations
Segmentation

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.457627

Cite this

@article{b6fe130787684663bb507d5a444ebe94,

title = "Segmentations of hyperspectral imagery: Techniques and applications",

abstract = "Several approaches for segmenting hyperspectral data and automatically detecting unusual objects in natural scenes are discussed. We demonstrate segmentations of hyperspectral imagery based on of the most significant principal components of the hyperspectral data cube. Several applications of the segmented data are treated. Digital morphological operations can be used to isolate segments that match target criteria. Alternatively, background segments can be used to define background endmembers; pixels that are quantitatively spectrally different from the background can then be designated. Analog morphological operations can then be used for clutter rejection and for the detection of objects of particular size and shape.",

keywords = "Clustering, Hyperspectral data, Morphological operations, Segmentation",

author = "Jerry Silverman and Rotman, {Stanley R.}",

year = "2002",

month = dec,

day = "1",

doi = "10.1117/12.457627",

language = "English",

volume = "4820",

pages = "334--349",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

number = "1",

note = "Infrared Technology and Applications XXVIII ; Conference date: 07-07-2002 Through 11-07-2002",

}

TY - JOUR

T1 - Segmentations of hyperspectral imagery

T2 - Infrared Technology and Applications XXVIII

AU - Silverman, Jerry

AU - Rotman, Stanley R.

PY - 2002/12/1

Y1 - 2002/12/1

N2 - Several approaches for segmenting hyperspectral data and automatically detecting unusual objects in natural scenes are discussed. We demonstrate segmentations of hyperspectral imagery based on of the most significant principal components of the hyperspectral data cube. Several applications of the segmented data are treated. Digital morphological operations can be used to isolate segments that match target criteria. Alternatively, background segments can be used to define background endmembers; pixels that are quantitatively spectrally different from the background can then be designated. Analog morphological operations can then be used for clutter rejection and for the detection of objects of particular size and shape.

AB - Several approaches for segmenting hyperspectral data and automatically detecting unusual objects in natural scenes are discussed. We demonstrate segmentations of hyperspectral imagery based on of the most significant principal components of the hyperspectral data cube. Several applications of the segmented data are treated. Digital morphological operations can be used to isolate segments that match target criteria. Alternatively, background segments can be used to define background endmembers; pixels that are quantitatively spectrally different from the background can then be designated. Analog morphological operations can then be used for clutter rejection and for the detection of objects of particular size and shape.

KW - Clustering

KW - Hyperspectral data

KW - Morphological operations

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=0037986765&partnerID=8YFLogxK

U2 - 10.1117/12.457627

DO - 10.1117/12.457627

M3 - Conference article

AN - SCOPUS:0037986765

SN - 0277-786X

VL - 4820

SP - 334

EP - 349

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

IS - 1

Y2 - 7 July 2002 through 11 July 2002

ER -

Segmentations of hyperspectral imagery: Techniques and applications

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this