MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing Images
The classification of land use information is important for land resource management. With the purpose of extracting precise spatial information, we present a novel land use classification model based on a mixed attention module and adjustable feature enhancement layer (MAAFEU-net). Our unique desig...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | ISPRS International Journal of Geo-Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2220-9964/12/5/206 |
_version_ | 1797599898558791680 |
---|---|
author | Yonghong Zhang Huajun Zhao Guangyi Ma Donglin Xie Sutong Geng Huanyu Lu Wei Tian Kenny Thiam Choy Lim Kam Sian |
author_facet | Yonghong Zhang Huajun Zhao Guangyi Ma Donglin Xie Sutong Geng Huanyu Lu Wei Tian Kenny Thiam Choy Lim Kam Sian |
author_sort | Yonghong Zhang |
collection | DOAJ |
description | The classification of land use information is important for land resource management. With the purpose of extracting precise spatial information, we present a novel land use classification model based on a mixed attention module and adjustable feature enhancement layer (MAAFEU-net). Our unique design, the mixed attention module, allows the model to concentrate on target-specific discriminative features and capture class-related features within different land use types. In addition, an adjustable feature enhancement layer is proposed to further enhance the classification ability of similar types. We assess the performance of this model using the publicly available GID dataset and the self-built Gwadar dataset. Six semantic segmentation deep networks are used for comparison. The experimental results show that the F1 score of MAAFEU-net is 2.16% and 2.3% higher than the next model and that MIoU is 3.15% and 3.62% higher than the next model. The results of the ablation experiments show that the mixed attention module improves the MIoU by 5.83% and the addition of the adjustable feature enhancement layer can further improve it by 5.58%. Both structures effectively improve the accuracy of the overall land use classification. The validation results show that MAAFEU-net can obtain land use classification images with high precision. |
first_indexed | 2024-03-11T03:40:50Z |
format | Article |
id | doaj.art-b3384035af334ed8ab3891054dd67ab3 |
institution | Directory Open Access Journal |
issn | 2220-9964 |
language | English |
last_indexed | 2024-03-11T03:40:50Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | ISPRS International Journal of Geo-Information |
spelling | doaj.art-b3384035af334ed8ab3891054dd67ab32023-11-18T01:36:10ZengMDPI AGISPRS International Journal of Geo-Information2220-99642023-05-0112520610.3390/ijgi12050206MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing ImagesYonghong Zhang0Huajun Zhao1Guangyi Ma2Donglin Xie3Sutong Geng4Huanyu Lu5Wei Tian6Kenny Thiam Choy Lim Kam Sian7School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Electronics and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Atmospheric Science and Remote Sensing, Wuxi University, Wuxi 214105, ChinaThe classification of land use information is important for land resource management. With the purpose of extracting precise spatial information, we present a novel land use classification model based on a mixed attention module and adjustable feature enhancement layer (MAAFEU-net). Our unique design, the mixed attention module, allows the model to concentrate on target-specific discriminative features and capture class-related features within different land use types. In addition, an adjustable feature enhancement layer is proposed to further enhance the classification ability of similar types. We assess the performance of this model using the publicly available GID dataset and the self-built Gwadar dataset. Six semantic segmentation deep networks are used for comparison. The experimental results show that the F1 score of MAAFEU-net is 2.16% and 2.3% higher than the next model and that MIoU is 3.15% and 3.62% higher than the next model. The results of the ablation experiments show that the mixed attention module improves the MIoU by 5.83% and the addition of the adjustable feature enhancement layer can further improve it by 5.58%. Both structures effectively improve the accuracy of the overall land use classification. The validation results show that MAAFEU-net can obtain land use classification images with high precision.https://www.mdpi.com/2220-9964/12/5/206remote sensingland use classificationmixed attention moduleadjustable feature enhancement layer |
spellingShingle | Yonghong Zhang Huajun Zhao Guangyi Ma Donglin Xie Sutong Geng Huanyu Lu Wei Tian Kenny Thiam Choy Lim Kam Sian MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing Images ISPRS International Journal of Geo-Information remote sensing land use classification mixed attention module adjustable feature enhancement layer |
title | MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing Images |
title_full | MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing Images |
title_fullStr | MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing Images |
title_full_unstemmed | MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing Images |
title_short | MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing Images |
title_sort | maafeu net a novel land use classification model based on mixed attention module and adjustable feature enhancement layer in remote sensing images |
topic | remote sensing land use classification mixed attention module adjustable feature enhancement layer |
url | https://www.mdpi.com/2220-9964/12/5/206 |
work_keys_str_mv | AT yonghongzhang maafeunetanovellanduseclassificationmodelbasedonmixedattentionmoduleandadjustablefeatureenhancementlayerinremotesensingimages AT huajunzhao maafeunetanovellanduseclassificationmodelbasedonmixedattentionmoduleandadjustablefeatureenhancementlayerinremotesensingimages AT guangyima maafeunetanovellanduseclassificationmodelbasedonmixedattentionmoduleandadjustablefeatureenhancementlayerinremotesensingimages AT donglinxie maafeunetanovellanduseclassificationmodelbasedonmixedattentionmoduleandadjustablefeatureenhancementlayerinremotesensingimages AT sutonggeng maafeunetanovellanduseclassificationmodelbasedonmixedattentionmoduleandadjustablefeatureenhancementlayerinremotesensingimages AT huanyulu maafeunetanovellanduseclassificationmodelbasedonmixedattentionmoduleandadjustablefeatureenhancementlayerinremotesensingimages AT weitian maafeunetanovellanduseclassificationmodelbasedonmixedattentionmoduleandadjustablefeatureenhancementlayerinremotesensingimages AT kennythiamchoylimkamsian maafeunetanovellanduseclassificationmodelbasedonmixedattentionmoduleandadjustablefeatureenhancementlayerinremotesensingimages |