Sea Ice Classification Using Synthetic Aperture Radar
This study employs Synthetic Aperture Radar (SAR) imagery from the Marginal Ice Zone Experiment (MIZEX) 1987 to identify an optimal set of statistical descriptors that accurately classify three types of ice (first-year, multiyear, odden) and open water. Two groups of statistics, univariate and textu...
Main Author: | |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Published: |
1990
|
Subjects: | |
Online Access: | http://www.dtic.mil/docs/citations/ADA232248 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA232248 |
id |
ftdtic:ADA232248 |
---|---|
record_format |
openpolar |
spelling |
ftdtic:ADA232248 2023-05-15T16:37:09+02:00 Sea Ice Classification Using Synthetic Aperture Radar Garcia, Jr, Frank W. NAVAL POSTGRADUATE SCHOOL MONTEREY CA 1990-06 text/html http://www.dtic.mil/docs/citations/ADA232248 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA232248 en eng http://www.dtic.mil/docs/citations/ADA232248 Approved for public release; distribution is unlimited. DTIC AND NTIS Snow Ice and Permafrost Active & Passive Radar Detection & Equipment *SYNTHETIC APERTURE RADAR INERTIA STATISTICS ACCURACY VARIATIONS INDEX TERMS CLASSIFICATION TEXTURE DISCRIMINATE ANALYSIS SEA ICE OPEN WATER DISCRIMINATORS OPTIMIZATION ICE *RADAR IMAGES MARGINAL ICE ZONES ICE CLASSIFICATION STATISTICAL ANALYSIS GRAY SCALE ODDEN ICE THESES Text 1990 ftdtic 2016-02-22T22:54:00Z This study employs Synthetic Aperture Radar (SAR) imagery from the Marginal Ice Zone Experiment (MIZEX) 1987 to identify an optimal set of statistical descriptors that accurately classify three types of ice (first-year, multiyear, odden) and open water. Two groups of statistics, univariate and texture, are compared and contrasted with respect to their skill in classifying the ice types and open water. Individual statistical descriptors are subjected to principal component analysis and discriminant analysis. Principal component analysis was of little use in understanding features of each ice and open water group. Discriminant analysis was valuable in identifying which statistics held the most power. When combined, univariate and texture statistics classified the groups with 89.5% accuracy, univariate alone with 86.8% accuracy and texture alone with 75.4% accuracy. Range and inertia were the strongest univariate and texture discriminators with 74.6% and 50.8% accuracy, respectively. Despite the use of a non-calibrated SAR, univariate statistics were able to classify the images with greater accuracy than texture statistics. Text Ice permafrost Sea ice Defense Technical Information Center: DTIC Technical Reports database |
institution |
Open Polar |
collection |
Defense Technical Information Center: DTIC Technical Reports database |
op_collection_id |
ftdtic |
language |
English |
topic |
Snow Ice and Permafrost Active & Passive Radar Detection & Equipment *SYNTHETIC APERTURE RADAR INERTIA STATISTICS ACCURACY VARIATIONS INDEX TERMS CLASSIFICATION TEXTURE DISCRIMINATE ANALYSIS SEA ICE OPEN WATER DISCRIMINATORS OPTIMIZATION ICE *RADAR IMAGES MARGINAL ICE ZONES ICE CLASSIFICATION STATISTICAL ANALYSIS GRAY SCALE ODDEN ICE THESES |
spellingShingle |
Snow Ice and Permafrost Active & Passive Radar Detection & Equipment *SYNTHETIC APERTURE RADAR INERTIA STATISTICS ACCURACY VARIATIONS INDEX TERMS CLASSIFICATION TEXTURE DISCRIMINATE ANALYSIS SEA ICE OPEN WATER DISCRIMINATORS OPTIMIZATION ICE *RADAR IMAGES MARGINAL ICE ZONES ICE CLASSIFICATION STATISTICAL ANALYSIS GRAY SCALE ODDEN ICE THESES Garcia, Jr, Frank W. Sea Ice Classification Using Synthetic Aperture Radar |
topic_facet |
Snow Ice and Permafrost Active & Passive Radar Detection & Equipment *SYNTHETIC APERTURE RADAR INERTIA STATISTICS ACCURACY VARIATIONS INDEX TERMS CLASSIFICATION TEXTURE DISCRIMINATE ANALYSIS SEA ICE OPEN WATER DISCRIMINATORS OPTIMIZATION ICE *RADAR IMAGES MARGINAL ICE ZONES ICE CLASSIFICATION STATISTICAL ANALYSIS GRAY SCALE ODDEN ICE THESES |
description |
This study employs Synthetic Aperture Radar (SAR) imagery from the Marginal Ice Zone Experiment (MIZEX) 1987 to identify an optimal set of statistical descriptors that accurately classify three types of ice (first-year, multiyear, odden) and open water. Two groups of statistics, univariate and texture, are compared and contrasted with respect to their skill in classifying the ice types and open water. Individual statistical descriptors are subjected to principal component analysis and discriminant analysis. Principal component analysis was of little use in understanding features of each ice and open water group. Discriminant analysis was valuable in identifying which statistics held the most power. When combined, univariate and texture statistics classified the groups with 89.5% accuracy, univariate alone with 86.8% accuracy and texture alone with 75.4% accuracy. Range and inertia were the strongest univariate and texture discriminators with 74.6% and 50.8% accuracy, respectively. Despite the use of a non-calibrated SAR, univariate statistics were able to classify the images with greater accuracy than texture statistics. |
author2 |
NAVAL POSTGRADUATE SCHOOL MONTEREY CA |
format |
Text |
author |
Garcia, Jr, Frank W. |
author_facet |
Garcia, Jr, Frank W. |
author_sort |
Garcia, Jr, Frank W. |
title |
Sea Ice Classification Using Synthetic Aperture Radar |
title_short |
Sea Ice Classification Using Synthetic Aperture Radar |
title_full |
Sea Ice Classification Using Synthetic Aperture Radar |
title_fullStr |
Sea Ice Classification Using Synthetic Aperture Radar |
title_full_unstemmed |
Sea Ice Classification Using Synthetic Aperture Radar |
title_sort |
sea ice classification using synthetic aperture radar |
publishDate |
1990 |
url |
http://www.dtic.mil/docs/citations/ADA232248 http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA232248 |
genre |
Ice permafrost Sea ice |
genre_facet |
Ice permafrost Sea ice |
op_source |
DTIC AND NTIS |
op_relation |
http://www.dtic.mil/docs/citations/ADA232248 |
op_rights |
Approved for public release; distribution is unlimited. |
_version_ |
1766027444460978176 |