Cargando…

Comparing Three Methods of Selecting Training Samples in Supervised Classification of Multispectral Remote Sensing Images

Selecting training samples is crucial in remote sensing image classification. In this paper, we selected three images—Sentinel-2, GF-1, and Landsat 8—and employed three methods for selecting training samples: grouping selection, entropy-based selection, and direct selection. We then used the selecte...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Hongying, He, Jinxin, Chen, Shengbo, Zhan, Ye, Bai, Yanyan, Qin, Yujia
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610573/
https://www.ncbi.nlm.nih.gov/pubmed/37896624
http://dx.doi.org/10.3390/s23208530
_version_ 1785128288467812352
author Zhang, Hongying
He, Jinxin
Chen, Shengbo
Zhan, Ye
Bai, Yanyan
Qin, Yujia
author_facet Zhang, Hongying
He, Jinxin
Chen, Shengbo
Zhan, Ye
Bai, Yanyan
Qin, Yujia
author_sort Zhang, Hongying
collection PubMed
description Selecting training samples is crucial in remote sensing image classification. In this paper, we selected three images—Sentinel-2, GF-1, and Landsat 8—and employed three methods for selecting training samples: grouping selection, entropy-based selection, and direct selection. We then used the selected training samples to train three supervised classification models—random forest (RF), support-vector machine (SVM), and k-nearest neighbor (KNN)—and evaluated the classification results of the three images. According to the experimental results, the three classification models performed similarly. Compared with the entropy-based method, the grouping selection method achieved higher classification accuracy using fewer samples. In addition, the grouping selection method outperformed the direct selection method with the same number of samples. Therefore, the grouping selection method performed the best. When using the grouping selection method, the image classification accuracy increased with the increase in the number of samples within a certain sample size range.
format Online
Article
Text
id pubmed-10610573
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106105732023-10-28 Comparing Three Methods of Selecting Training Samples in Supervised Classification of Multispectral Remote Sensing Images Zhang, Hongying He, Jinxin Chen, Shengbo Zhan, Ye Bai, Yanyan Qin, Yujia Sensors (Basel) Article Selecting training samples is crucial in remote sensing image classification. In this paper, we selected three images—Sentinel-2, GF-1, and Landsat 8—and employed three methods for selecting training samples: grouping selection, entropy-based selection, and direct selection. We then used the selected training samples to train three supervised classification models—random forest (RF), support-vector machine (SVM), and k-nearest neighbor (KNN)—and evaluated the classification results of the three images. According to the experimental results, the three classification models performed similarly. Compared with the entropy-based method, the grouping selection method achieved higher classification accuracy using fewer samples. In addition, the grouping selection method outperformed the direct selection method with the same number of samples. Therefore, the grouping selection method performed the best. When using the grouping selection method, the image classification accuracy increased with the increase in the number of samples within a certain sample size range. MDPI 2023-10-17 /pmc/articles/PMC10610573/ /pubmed/37896624 http://dx.doi.org/10.3390/s23208530 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhang, Hongying
He, Jinxin
Chen, Shengbo
Zhan, Ye
Bai, Yanyan
Qin, Yujia
Comparing Three Methods of Selecting Training Samples in Supervised Classification of Multispectral Remote Sensing Images
title Comparing Three Methods of Selecting Training Samples in Supervised Classification of Multispectral Remote Sensing Images
title_full Comparing Three Methods of Selecting Training Samples in Supervised Classification of Multispectral Remote Sensing Images
title_fullStr Comparing Three Methods of Selecting Training Samples in Supervised Classification of Multispectral Remote Sensing Images
title_full_unstemmed Comparing Three Methods of Selecting Training Samples in Supervised Classification of Multispectral Remote Sensing Images
title_short Comparing Three Methods of Selecting Training Samples in Supervised Classification of Multispectral Remote Sensing Images
title_sort comparing three methods of selecting training samples in supervised classification of multispectral remote sensing images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10610573/
https://www.ncbi.nlm.nih.gov/pubmed/37896624
http://dx.doi.org/10.3390/s23208530
work_keys_str_mv AT zhanghongying comparingthreemethodsofselectingtrainingsamplesinsupervisedclassificationofmultispectralremotesensingimages
AT hejinxin comparingthreemethodsofselectingtrainingsamplesinsupervisedclassificationofmultispectralremotesensingimages
AT chenshengbo comparingthreemethodsofselectingtrainingsamplesinsupervisedclassificationofmultispectralremotesensingimages
AT zhanye comparingthreemethodsofselectingtrainingsamplesinsupervisedclassificationofmultispectralremotesensingimages
AT baiyanyan comparingthreemethodsofselectingtrainingsamplesinsupervisedclassificationofmultispectralremotesensingimages
AT qinyujia comparingthreemethodsofselectingtrainingsamplesinsupervisedclassificationofmultispectralremotesensingimages