Improving the Accuracy of Land Cover Mapping by Distributing Training Samples

High-quality training samples are essential for accurate land cover classification. Due to the difficulties in collecting a large number of training samples, it is of great significance to collect a high-quality sample dataset with a limited sample size but effective sample distribution. In this pap...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chenxi Li, Zaiying Ma, Liuyue Wang, Weijian Yu, Donglin Tan, Bingbo Gao, Quanlong Feng, Hao Guo, Yuanyuan Zhao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	training samples spatial distribution land cover supervised classification Science Q
Acceso en línea:	https://doaj.org/article/b0bc70df5eb945b388d9c44cf78368d3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b0bc70df5eb945b388d9c44cf78368d3
record_format	dspace
spelling	oai:doaj.org-article:b0bc70df5eb945b388d9c44cf78368d32021-11-25T18:54:36ZImproving the Accuracy of Land Cover Mapping by Distributing Training Samples10.3390/rs132245942072-4292https://doaj.org/article/b0bc70df5eb945b388d9c44cf78368d32021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4594https://doaj.org/toc/2072-4292High-quality training samples are essential for accurate land cover classification. Due to the difficulties in collecting a large number of training samples, it is of great significance to collect a high-quality sample dataset with a limited sample size but effective sample distribution. In this paper, we proposed an object-oriented sampling approach by segmenting image blocks expanded from systematically distributed seeds (object-oriented sampling approach) and carried out a rigorous comparison of seven sampling strategies, including random sampling, systematic sampling, stratified sampling (stratified sampling with the strata of land cover classes based on classification product, Latin hypercube sampling, and spatial Latin hypercube sampling), object-oriented sampling, and manual sampling, to explore the impact of training sample distribution on the accuracy of land cover classification when the samples are limited. Five study areas from different climate zones were selected along the China–Mongolia border. Our research identified the proposed object-oriented sampling approach as the first-choice sampling strategy in collecting training samples. This approach improved the diversity and completeness of the training sample set. Stratified sampling with strata defined by the combination of different attributes and stratified sampling with the strata of land cover classes had their limitations, and they performed well in specific situations when we have enough prior knowledge or high-accuracy product. Manual sampling was greatly influenced by the experience of interpreters. All these sampling strategies mentioned above outperformed random sampling and systematic sampling in this study. The results indicate that the sampling strategies of training datasets do have great impacts on the land cover classification accuracies when the sample size is limited. This paper will provide guidance for efficient training sample collection to increase classification accuracies.Chenxi LiZaiying MaLiuyue WangWeijian YuDonglin TanBingbo GaoQuanlong FengHao GuoYuanyuan ZhaoMDPI AGarticletraining samplesspatial distributionland coversupervised classificationScienceQENRemote Sensing, Vol 13, Iss 4594, p 4594 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	training samples spatial distribution land cover supervised classification Science Q
spellingShingle	training samples spatial distribution land cover supervised classification Science Q Chenxi Li Zaiying Ma Liuyue Wang Weijian Yu Donglin Tan Bingbo Gao Quanlong Feng Hao Guo Yuanyuan Zhao Improving the Accuracy of Land Cover Mapping by Distributing Training Samples
description	High-quality training samples are essential for accurate land cover classification. Due to the difficulties in collecting a large number of training samples, it is of great significance to collect a high-quality sample dataset with a limited sample size but effective sample distribution. In this paper, we proposed an object-oriented sampling approach by segmenting image blocks expanded from systematically distributed seeds (object-oriented sampling approach) and carried out a rigorous comparison of seven sampling strategies, including random sampling, systematic sampling, stratified sampling (stratified sampling with the strata of land cover classes based on classification product, Latin hypercube sampling, and spatial Latin hypercube sampling), object-oriented sampling, and manual sampling, to explore the impact of training sample distribution on the accuracy of land cover classification when the samples are limited. Five study areas from different climate zones were selected along the China–Mongolia border. Our research identified the proposed object-oriented sampling approach as the first-choice sampling strategy in collecting training samples. This approach improved the diversity and completeness of the training sample set. Stratified sampling with strata defined by the combination of different attributes and stratified sampling with the strata of land cover classes had their limitations, and they performed well in specific situations when we have enough prior knowledge or high-accuracy product. Manual sampling was greatly influenced by the experience of interpreters. All these sampling strategies mentioned above outperformed random sampling and systematic sampling in this study. The results indicate that the sampling strategies of training datasets do have great impacts on the land cover classification accuracies when the sample size is limited. This paper will provide guidance for efficient training sample collection to increase classification accuracies.
format	article
author	Chenxi Li Zaiying Ma Liuyue Wang Weijian Yu Donglin Tan Bingbo Gao Quanlong Feng Hao Guo Yuanyuan Zhao
author_facet	Chenxi Li Zaiying Ma Liuyue Wang Weijian Yu Donglin Tan Bingbo Gao Quanlong Feng Hao Guo Yuanyuan Zhao
author_sort	Chenxi Li
title	Improving the Accuracy of Land Cover Mapping by Distributing Training Samples
title_short	Improving the Accuracy of Land Cover Mapping by Distributing Training Samples
title_full	Improving the Accuracy of Land Cover Mapping by Distributing Training Samples
title_fullStr	Improving the Accuracy of Land Cover Mapping by Distributing Training Samples
title_full_unstemmed	Improving the Accuracy of Land Cover Mapping by Distributing Training Samples
title_sort	improving the accuracy of land cover mapping by distributing training samples
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b0bc70df5eb945b388d9c44cf78368d3
work_keys_str_mv	AT chenxili improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples AT zaiyingma improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples AT liuyuewang improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples AT weijianyu improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples AT donglintan improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples AT bingbogao improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples AT quanlongfeng improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples AT haoguo improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples AT yuanyuanzhao improvingtheaccuracyoflandcovermappingbydistributingtrainingsamples
_version_	1718410612511342592

Improving the Accuracy of Land Cover Mapping by Distributing Training Samples

Ejemplares similares