Accuracy Assessment of Satellite Image Classification Depending on Training Sample

Accuracy Assessment of Satellite Image Classification Depending on Training Sample

The paper presents a method of predicting classification accuracy of remote sensing data by means of training set analysis. Various sampling plans were applied to satellite image and its complete ground truth to derive different training sets. The quality of these training sets was determined by qua...

Full description

Bibliographic Details
Main Authors: Georg Ruppert, Mushtaq Hussain, Heimo Müller
Format: Article
Language:English
Published: Austrian Statistical Society 2016-04-01
Series:Austrian Journal of Statistics
Online Access:http://www.ajs.or.at/index.php/ajs/article/view/522
id doaj-0d2a8086873a44aeb74c84c5904ccc37
record_format Article
spelling doaj-0d2a8086873a44aeb74c84c5904ccc372021-04-22T12:32:46ZengAustrian Statistical SocietyAustrian Journal of Statistics1026-597X2016-04-0128410.17713/ajs.v28i4.522Accuracy Assessment of Satellite Image Classification Depending on Training SampleGeorg Ruppert0Mushtaq Hussain1Heimo Müller2Joanneum Research, GrazEurostat, LuxembourgTechnikum Joanneum, GrazThe paper presents a method of predicting classification accuracy of remote sensing data by means of training set analysis. Various sampling plans were applied to satellite image and its complete ground truth to derive different training sets. The quality of these training sets was determined by quantifying the similarity of the training set distributions to the ones of the entire satellite image. Each training set was then used to learn a classifier. The paper shows how the accuracy of classifications that were carried out using these classifiers depends upon the quality of the corresponding training sets.http://www.ajs.or.at/index.php/ajs/article/view/522
collection DOAJ
language English
format Article
sources DOAJ
author Georg Ruppert
Mushtaq Hussain
Heimo Müller
spellingShingle Georg Ruppert
Mushtaq Hussain
Heimo Müller
Accuracy Assessment of Satellite Image Classification Depending on Training Sample
Austrian Journal of Statistics
author_facet Georg Ruppert
Mushtaq Hussain
Heimo Müller
author_sort Georg Ruppert
title Accuracy Assessment of Satellite Image Classification Depending on Training Sample
title_short Accuracy Assessment of Satellite Image Classification Depending on Training Sample
title_full Accuracy Assessment of Satellite Image Classification Depending on Training Sample
title_fullStr Accuracy Assessment of Satellite Image Classification Depending on Training Sample
title_full_unstemmed Accuracy Assessment of Satellite Image Classification Depending on Training Sample
title_sort accuracy assessment of satellite image classification depending on training sample
publisher Austrian Statistical Society
series Austrian Journal of Statistics
issn 1026-597X
publishDate 2016-04-01
description The paper presents a method of predicting classification accuracy of remote sensing data by means of training set analysis. Various sampling plans were applied to satellite image and its complete ground truth to derive different training sets. The quality of these training sets was determined by quantifying the similarity of the training set distributions to the ones of the entire satellite image. Each training set was then used to learn a classifier. The paper shows how the accuracy of classifications that were carried out using these classifiers depends upon the quality of the corresponding training sets.
url http://www.ajs.or.at/index.php/ajs/article/view/522
work_keys_str_mv AT georgruppert accuracyassessmentofsatelliteimageclassificationdependingontrainingsample
AT mushtaqhussain accuracyassessmentofsatelliteimageclassificationdependingontrainingsample
AT heimomuller accuracyassessmentofsatelliteimageclassificationdependingontrainingsample
_version_ 1721514419204128768

Similar Items