Predicting Classification Performance for Benchmark Hyperspectral Datasets
The classification of hyperspectral images (HSIs) is an essential application of remote sensing and it is addressed by numerous publications every year. A large body of these papers present new classification algorithms and benchmark them against established methods on public hyperspectral datasets....
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9772265/ |
_version_ | 1811339844069097472 |
---|---|
author | Bin Zhao Haukur Isfeld Ragnarsson Magnus O. Ulfarsson Gabriele Cavallaro Jon Atli Benediktsson |
author_facet | Bin Zhao Haukur Isfeld Ragnarsson Magnus O. Ulfarsson Gabriele Cavallaro Jon Atli Benediktsson |
author_sort | Bin Zhao |
collection | DOAJ |
description | The classification of hyperspectral images (HSIs) is an essential application of remote sensing and it is addressed by numerous publications every year. A large body of these papers present new classification algorithms and benchmark them against established methods on public hyperspectral datasets. The metadata contained in these research papers (i.e., the size of the image, the number of classes, the type of classifier, etc.) present an unexploited source of information that can be used to estimate the performance of classifiers before doing the actual experiments. In this article, we propose a novel approach to investigate to what degree HSIs can be classified by using only metadata. This can guide remote sensing researchers to identify optimal classifiers and develop new algorithms. In the experiments, different linear and nonlinear prediction methods are trained and tested by using data on classification accuracy and metadata from 100 HSIs classification papers. The experimental results demonstrate that the proposed ensemble learning voting method outperforms other comparative methods in quantitative assessments. |
first_indexed | 2024-04-13T18:32:36Z |
format | Article |
id | doaj.art-cb56629bf55440079a6af90b9baa56ff |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-04-13T18:32:36Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-cb56629bf55440079a6af90b9baa56ff2022-12-22T02:35:00ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01154180419310.1109/JSTARS.2022.31738939772265Predicting Classification Performance for Benchmark Hyperspectral DatasetsBin Zhao0Haukur Isfeld Ragnarsson1Magnus O. Ulfarsson2https://orcid.org/0000-0002-0461-040XGabriele Cavallaro3https://orcid.org/0000-0002-3239-9904Jon Atli Benediktsson4https://orcid.org/0000-0003-0621-9647Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, IcelandFaculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, IcelandFaculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, IcelandJülich Supercomputing Centre, Jülich, GermanyFaculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, IcelandThe classification of hyperspectral images (HSIs) is an essential application of remote sensing and it is addressed by numerous publications every year. A large body of these papers present new classification algorithms and benchmark them against established methods on public hyperspectral datasets. The metadata contained in these research papers (i.e., the size of the image, the number of classes, the type of classifier, etc.) present an unexploited source of information that can be used to estimate the performance of classifiers before doing the actual experiments. In this article, we propose a novel approach to investigate to what degree HSIs can be classified by using only metadata. This can guide remote sensing researchers to identify optimal classifiers and develop new algorithms. In the experiments, different linear and nonlinear prediction methods are trained and tested by using data on classification accuracy and metadata from 100 HSIs classification papers. The experimental results demonstrate that the proposed ensemble learning voting method outperforms other comparative methods in quantitative assessments.https://ieeexplore.ieee.org/document/9772265/Hyperspectral image (HSI) classificationpredictionremote sensing |
spellingShingle | Bin Zhao Haukur Isfeld Ragnarsson Magnus O. Ulfarsson Gabriele Cavallaro Jon Atli Benediktsson Predicting Classification Performance for Benchmark Hyperspectral Datasets IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Hyperspectral image (HSI) classification prediction remote sensing |
title | Predicting Classification Performance for Benchmark Hyperspectral Datasets |
title_full | Predicting Classification Performance for Benchmark Hyperspectral Datasets |
title_fullStr | Predicting Classification Performance for Benchmark Hyperspectral Datasets |
title_full_unstemmed | Predicting Classification Performance for Benchmark Hyperspectral Datasets |
title_short | Predicting Classification Performance for Benchmark Hyperspectral Datasets |
title_sort | predicting classification performance for benchmark hyperspectral datasets |
topic | Hyperspectral image (HSI) classification prediction remote sensing |
url | https://ieeexplore.ieee.org/document/9772265/ |
work_keys_str_mv | AT binzhao predictingclassificationperformanceforbenchmarkhyperspectraldatasets AT haukurisfeldragnarsson predictingclassificationperformanceforbenchmarkhyperspectraldatasets AT magnusoulfarsson predictingclassificationperformanceforbenchmarkhyperspectraldatasets AT gabrielecavallaro predictingclassificationperformanceforbenchmarkhyperspectraldatasets AT jonatlibenediktsson predictingclassificationperformanceforbenchmarkhyperspectraldatasets |