Cargando…

A vegetation classification method based on improved dual-way branch feature fusion U-net

Aiming at the problems of complex structure parameters and low feature extraction ability of U-Net used in vegetation classification, a deep network with improved U-Net and dual-way branch input is proposed. Firstly, The principal component analysis (PCA) is used to reduce the dimension of hyperspec...

Descripción completa

Detalles Bibliográficos
Autores principales: Yu, Huiling, Jiang, Dapeng, Peng, Xiwen, Zhang, Yizhuo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9745139/
https://www.ncbi.nlm.nih.gov/pubmed/36523616
http://dx.doi.org/10.3389/fpls.2022.1047091
_version_ 1784849080647680000
author Yu, Huiling
Jiang, Dapeng
Peng, Xiwen
Zhang, Yizhuo
author_facet Yu, Huiling
Jiang, Dapeng
Peng, Xiwen
Zhang, Yizhuo
author_sort Yu, Huiling
collection PubMed
description Aiming at the problems of complex structure parameters and low feature extraction ability of U-Net used in vegetation classification, a deep network with improved U-Net and dual-way branch input is proposed. Firstly, The principal component analysis (PCA) is used to reduce the dimension of hyperspectral remote sensing images, and the effective bands are obtained. Secondly, the depthwise separable convolution and residual connections are combined to replace the common convolution layers of U-Net for depth feature extraction to ensure classification accuracy and reduce the complexity of network parameters. Finally, normalized difference vegetation index (NDVI), gray level co-occurrence matrix (GLCM) and edge features of hyperspectral remote sensing images are extracted respectively. The above three artificial features are fused as one input, and PCA dimension reduction features are used as another input. Based on the improved U-net, a dual-way vegetation classification model is generated. Taking the hyperspectral remote sensing image of Matiwan Village, Xiong’an, Beijing as the experimental object, the experimental results show that the precision and recall of the improved U-Net are significantly improved with the residual structure and depthwise separable convolution, reaching 97.13% and 92.36% respectively. In addition, in order to verify the effectiveness of artificial features and dual-way branch design, the accuracy of single channel and the dual-way branch are compared. The experimental results show that artificial features in single channel network interfere with the original hyperspectral data, resulting in reduction of the recognition accuracy. However, the accuracy of the dual-way branch network has been improved, reaching 98.67%. It shows that artificial features are effective complements of network features.
format Online
Article
Text
id pubmed-9745139
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-97451392022-12-14 A vegetation classification method based on improved dual-way branch feature fusion U-net Yu, Huiling Jiang, Dapeng Peng, Xiwen Zhang, Yizhuo Front Plant Sci Plant Science Aiming at the problems of complex structure parameters and low feature extraction ability of U-Net used in vegetation classification, a deep network with improved U-Net and dual-way branch input is proposed. Firstly, The principal component analysis (PCA) is used to reduce the dimension of hyperspectral remote sensing images, and the effective bands are obtained. Secondly, the depthwise separable convolution and residual connections are combined to replace the common convolution layers of U-Net for depth feature extraction to ensure classification accuracy and reduce the complexity of network parameters. Finally, normalized difference vegetation index (NDVI), gray level co-occurrence matrix (GLCM) and edge features of hyperspectral remote sensing images are extracted respectively. The above three artificial features are fused as one input, and PCA dimension reduction features are used as another input. Based on the improved U-net, a dual-way vegetation classification model is generated. Taking the hyperspectral remote sensing image of Matiwan Village, Xiong’an, Beijing as the experimental object, the experimental results show that the precision and recall of the improved U-Net are significantly improved with the residual structure and depthwise separable convolution, reaching 97.13% and 92.36% respectively. In addition, in order to verify the effectiveness of artificial features and dual-way branch design, the accuracy of single channel and the dual-way branch are compared. The experimental results show that artificial features in single channel network interfere with the original hyperspectral data, resulting in reduction of the recognition accuracy. However, the accuracy of the dual-way branch network has been improved, reaching 98.67%. It shows that artificial features are effective complements of network features. Frontiers Media S.A. 2022-11-29 /pmc/articles/PMC9745139/ /pubmed/36523616 http://dx.doi.org/10.3389/fpls.2022.1047091 Text en Copyright © 2022 Yu, Jiang, Peng and Zhang https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Yu, Huiling
Jiang, Dapeng
Peng, Xiwen
Zhang, Yizhuo
A vegetation classification method based on improved dual-way branch feature fusion U-net
title A vegetation classification method based on improved dual-way branch feature fusion U-net
title_full A vegetation classification method based on improved dual-way branch feature fusion U-net
title_fullStr A vegetation classification method based on improved dual-way branch feature fusion U-net
title_full_unstemmed A vegetation classification method based on improved dual-way branch feature fusion U-net
title_short A vegetation classification method based on improved dual-way branch feature fusion U-net
title_sort vegetation classification method based on improved dual-way branch feature fusion u-net
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9745139/
https://www.ncbi.nlm.nih.gov/pubmed/36523616
http://dx.doi.org/10.3389/fpls.2022.1047091
work_keys_str_mv AT yuhuiling avegetationclassificationmethodbasedonimproveddualwaybranchfeaturefusionunet
AT jiangdapeng avegetationclassificationmethodbasedonimproveddualwaybranchfeaturefusionunet
AT pengxiwen avegetationclassificationmethodbasedonimproveddualwaybranchfeaturefusionunet
AT zhangyizhuo avegetationclassificationmethodbasedonimproveddualwaybranchfeaturefusionunet
AT yuhuiling vegetationclassificationmethodbasedonimproveddualwaybranchfeaturefusionunet
AT jiangdapeng vegetationclassificationmethodbasedonimproveddualwaybranchfeaturefusionunet
AT pengxiwen vegetationclassificationmethodbasedonimproveddualwaybranchfeaturefusionunet
AT zhangyizhuo vegetationclassificationmethodbasedonimproveddualwaybranchfeaturefusionunet