Application of principal component analysis to multisensor classification

B. R. Corner, R. M. Narayanan, Stephen E Reichenbach

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

The potential of high-resolution radar and optical imagery for synoptic and timely mapping in applications such as resource management, disaster delineation, and weather mapping is well-known. Numerous methods have been developed to process and quantify useful information from remotely sensed images. Most image processing techniques use texture based statistics combined with spatial filtering to separate target classes or to infer geophysical parameters from pixel radiometric intensities. The use of spatial statistics to enhance the information content of images, thereby providing better characterization of the underlying geophysical phenomena, is a relatively new technique in image processing. We are currently exploring the relationship between spatial statistical parameters of various geophysical phenomena and those of the remotely sensed image by way of principal component analysis (PCA) of radar and optical images. Issues being explored are the effects of incorporating PCA into land cover classification in an attempt to improve its accuracy. Preliminary results of using PCA in comparison with unsupervised land cover classification are presented.

Original languageEnglish (US)
Pages (from-to)202-210
Number of pages9
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume3584
StatePublished - Jan 1 1999

Fingerprint

principal components analysis
Principal component analysis
Principal Component Analysis
Land Cover
Radar
Image processing
Statistics
Image Processing
image processing
Spatial Filtering
Spatial Statistics
Disasters
statistics
Information Content
radar imagery
Resource Management
resources management
Textures
Disaster
Pixels

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Application of principal component analysis to multisensor classification. / Corner, B. R.; Narayanan, R. M.; Reichenbach, Stephen E.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 3584, 01.01.1999, p. 202-210.

Research output: Contribution to journalConference article

@article{8b432de533ae459eada8eabeaa457610,
title = "Application of principal component analysis to multisensor classification",
abstract = "The potential of high-resolution radar and optical imagery for synoptic and timely mapping in applications such as resource management, disaster delineation, and weather mapping is well-known. Numerous methods have been developed to process and quantify useful information from remotely sensed images. Most image processing techniques use texture based statistics combined with spatial filtering to separate target classes or to infer geophysical parameters from pixel radiometric intensities. The use of spatial statistics to enhance the information content of images, thereby providing better characterization of the underlying geophysical phenomena, is a relatively new technique in image processing. We are currently exploring the relationship between spatial statistical parameters of various geophysical phenomena and those of the remotely sensed image by way of principal component analysis (PCA) of radar and optical images. Issues being explored are the effects of incorporating PCA into land cover classification in an attempt to improve its accuracy. Preliminary results of using PCA in comparison with unsupervised land cover classification are presented.",
author = "Corner, {B. R.} and Narayanan, {R. M.} and Reichenbach, {Stephen E}",
year = "1999",
month = "1",
day = "1",
language = "English (US)",
volume = "3584",
pages = "202--210",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

TY - JOUR

T1 - Application of principal component analysis to multisensor classification

AU - Corner, B. R.

AU - Narayanan, R. M.

AU - Reichenbach, Stephen E

PY - 1999/1/1

Y1 - 1999/1/1

N2 - The potential of high-resolution radar and optical imagery for synoptic and timely mapping in applications such as resource management, disaster delineation, and weather mapping is well-known. Numerous methods have been developed to process and quantify useful information from remotely sensed images. Most image processing techniques use texture based statistics combined with spatial filtering to separate target classes or to infer geophysical parameters from pixel radiometric intensities. The use of spatial statistics to enhance the information content of images, thereby providing better characterization of the underlying geophysical phenomena, is a relatively new technique in image processing. We are currently exploring the relationship between spatial statistical parameters of various geophysical phenomena and those of the remotely sensed image by way of principal component analysis (PCA) of radar and optical images. Issues being explored are the effects of incorporating PCA into land cover classification in an attempt to improve its accuracy. Preliminary results of using PCA in comparison with unsupervised land cover classification are presented.

AB - The potential of high-resolution radar and optical imagery for synoptic and timely mapping in applications such as resource management, disaster delineation, and weather mapping is well-known. Numerous methods have been developed to process and quantify useful information from remotely sensed images. Most image processing techniques use texture based statistics combined with spatial filtering to separate target classes or to infer geophysical parameters from pixel radiometric intensities. The use of spatial statistics to enhance the information content of images, thereby providing better characterization of the underlying geophysical phenomena, is a relatively new technique in image processing. We are currently exploring the relationship between spatial statistical parameters of various geophysical phenomena and those of the remotely sensed image by way of principal component analysis (PCA) of radar and optical images. Issues being explored are the effects of incorporating PCA into land cover classification in an attempt to improve its accuracy. Preliminary results of using PCA in comparison with unsupervised land cover classification are presented.

UR - http://www.scopus.com/inward/record.url?scp=0032677971&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032677971&partnerID=8YFLogxK

M3 - Conference article

VL - 3584

SP - 202

EP - 210

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

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

SN - 0277-786X

ER -