Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods
Six Advanced Very High-Resolution Radiometer local area coverage (AVHRR LAC) arctic scenes are classified into ten classes. Three different classifiers are examined: (1) the traditional stepwise discriminant analysis (SDA) method; (2) the feed-forward back-propagation (FFBP) neural network; and (3)...
Main Authors: | , , , , , |
---|---|
Format: | Other/Unknown Material |
Language: | unknown |
Published: |
1992
|
Subjects: | |
Online Access: | http://ntrs.nasa.gov/search.jsp?R=19920055458 |
id |
ftnasantrs:oai:casi.ntrs.nasa.gov:19920055458 |
---|---|
record_format |
openpolar |
spelling |
ftnasantrs:oai:casi.ntrs.nasa.gov:19920055458 2023-05-15T14:59:41+02:00 Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods Welch, R. M. Sengupta, S. K. Goroch, A. K. Rabindra, P. Rangaraj, N. Navar, M. S. Unclassified, Unlimited, Publicly available May 1, 1992 http://ntrs.nasa.gov/search.jsp?R=19920055458 unknown http://ntrs.nasa.gov/search.jsp?R=19920055458 Accession ID: 92A38082 Copyright Other Sources 42 Journal of Applied Meteorology; 31; 5, Ma; 405-420 1992 ftnasantrs 2012-02-15T19:33:52Z Six Advanced Very High-Resolution Radiometer local area coverage (AVHRR LAC) arctic scenes are classified into ten classes. Three different classifiers are examined: (1) the traditional stepwise discriminant analysis (SDA) method; (2) the feed-forward back-propagation (FFBP) neural network; and (3) the probabilistic neural network (PNN). More than 200 spectral and textural measures are computed. These are reduced to 20 features using sequential forward selection. Theoretical accuracy of the classifiers is determined using the bootstrap approach. Overall accuracy is 85.6 percent, 87.6 percent, and 87.0 percent for the SDA, FFBP, and PNN classifiers, respectively, with standard deviations of approximately 1 percent. Other/Unknown Material Arctic NASA Technical Reports Server (NTRS) Arctic |
institution |
Open Polar |
collection |
NASA Technical Reports Server (NTRS) |
op_collection_id |
ftnasantrs |
language |
unknown |
topic |
42 |
spellingShingle |
42 Welch, R. M. Sengupta, S. K. Goroch, A. K. Rabindra, P. Rangaraj, N. Navar, M. S. Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods |
topic_facet |
42 |
description |
Six Advanced Very High-Resolution Radiometer local area coverage (AVHRR LAC) arctic scenes are classified into ten classes. Three different classifiers are examined: (1) the traditional stepwise discriminant analysis (SDA) method; (2) the feed-forward back-propagation (FFBP) neural network; and (3) the probabilistic neural network (PNN). More than 200 spectral and textural measures are computed. These are reduced to 20 features using sequential forward selection. Theoretical accuracy of the classifiers is determined using the bootstrap approach. Overall accuracy is 85.6 percent, 87.6 percent, and 87.0 percent for the SDA, FFBP, and PNN classifiers, respectively, with standard deviations of approximately 1 percent. |
format |
Other/Unknown Material |
author |
Welch, R. M. Sengupta, S. K. Goroch, A. K. Rabindra, P. Rangaraj, N. Navar, M. S. |
author_facet |
Welch, R. M. Sengupta, S. K. Goroch, A. K. Rabindra, P. Rangaraj, N. Navar, M. S. |
author_sort |
Welch, R. M. |
title |
Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods |
title_short |
Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods |
title_full |
Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods |
title_fullStr |
Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods |
title_full_unstemmed |
Polar cloud and surface classification using AVHRR imagery - An intercomparison of methods |
title_sort |
polar cloud and surface classification using avhrr imagery - an intercomparison of methods |
publishDate |
1992 |
url |
http://ntrs.nasa.gov/search.jsp?R=19920055458 |
op_coverage |
Unclassified, Unlimited, Publicly available |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
Other Sources |
op_relation |
http://ntrs.nasa.gov/search.jsp?R=19920055458 Accession ID: 92A38082 |
op_rights |
Copyright |
_version_ |
1766331790921826304 |