Hierarchical Deep Features Progressive Aggregation for Remote Sensing Images Scene Classification

Remote sensing image scene classification is essential, and it can promote the rational planning of land and ecological monitoring in the practical application of agricultural production. High spatial resolution (HSR) remote sensing images are widely used in smart agriculture because of their wide c...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Zhao, Jiaqi Liang, Sisi Huang, Pingping Huang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10505774/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850225092713250816
author Yang Zhao
Jiaqi Liang
Sisi Huang
Pingping Huang
author_facet Yang Zhao
Jiaqi Liang
Sisi Huang
Pingping Huang
author_sort Yang Zhao
collection DOAJ
description Remote sensing image scene classification is essential, and it can promote the rational planning of land and ecological monitoring in the practical application of agricultural production. High spatial resolution (HSR) remote sensing images are widely used in smart agriculture because of their wide coverage and HSR. The HSR remote sensing images have a more detailed description of the local scene. However, the complexity of scene details intensifies the intraclass diversity and interclass similarity of scenes, and the interference to scene classification is more significant. To distinguish scene categories effectively in complex background, this article proposes a scene classification method of remote sensing images based on progressive aggregation (PA) with local and global cooperative learning. Specifically, multilevel local and global feature modules are employed at different levels to describe the influence of local objects and their global distribution on scene category determination. Then, the PA module is introduced to explore the collaboration of the same level features and reduce the interference of shallow redundancy. The residual structure can establish the correlation between multilevel representations, thereby improving the representation of the aggregate features. To verify the performance of the proposed method, we implemented cross-domain experiments on four internationally available remote sensing image classification datasets: NWPU-RESISC45, WHU-RS19, RSSCN7, and AID. The experimental results show that the proposed method is effective and robust in remote sensing scene classification.
format Article
id doaj-art-394bad45907944eb90f09cd9df2f39cb
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-394bad45907944eb90f09cd9df2f39cb2025-08-20T02:05:28ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-01179442945010.1109/JSTARS.2024.339133210505774Hierarchical Deep Features Progressive Aggregation for Remote Sensing Images Scene ClassificationYang Zhao0https://orcid.org/0000-0002-7302-7787Jiaqi Liang1https://orcid.org/0009-0001-2655-2482Sisi Huang2https://orcid.org/0009-0001-1238-0800Pingping Huang3https://orcid.org/0000-0001-7720-1183School of Information Engineering, Inner Mongolia University of Technology, Hohhot, ChinaSchool of Information Engineering, Inner Mongolia University of Technology, Hohhot, ChinaSchool of Information Engineering, Inner Mongolia University of Technology, Hohhot, ChinaSchool of Information Engineering, Inner Mongolia University of Technology, Hohhot, ChinaRemote sensing image scene classification is essential, and it can promote the rational planning of land and ecological monitoring in the practical application of agricultural production. High spatial resolution (HSR) remote sensing images are widely used in smart agriculture because of their wide coverage and HSR. The HSR remote sensing images have a more detailed description of the local scene. However, the complexity of scene details intensifies the intraclass diversity and interclass similarity of scenes, and the interference to scene classification is more significant. To distinguish scene categories effectively in complex background, this article proposes a scene classification method of remote sensing images based on progressive aggregation (PA) with local and global cooperative learning. Specifically, multilevel local and global feature modules are employed at different levels to describe the influence of local objects and their global distribution on scene category determination. Then, the PA module is introduced to explore the collaboration of the same level features and reduce the interference of shallow redundancy. The residual structure can establish the correlation between multilevel representations, thereby improving the representation of the aggregate features. To verify the performance of the proposed method, we implemented cross-domain experiments on four internationally available remote sensing image classification datasets: NWPU-RESISC45, WHU-RS19, RSSCN7, and AID. The experimental results show that the proposed method is effective and robust in remote sensing scene classification.https://ieeexplore.ieee.org/document/10505774/Multilevel local (MLL) and multilevel global (MLG) feature modulesprogressive aggregation (PA)remote sensing images scene classification
spellingShingle Yang Zhao
Jiaqi Liang
Sisi Huang
Pingping Huang
Hierarchical Deep Features Progressive Aggregation for Remote Sensing Images Scene Classification
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Multilevel local (MLL) and multilevel global (MLG) feature modules
progressive aggregation (PA)
remote sensing images scene classification
title Hierarchical Deep Features Progressive Aggregation for Remote Sensing Images Scene Classification
title_full Hierarchical Deep Features Progressive Aggregation for Remote Sensing Images Scene Classification
title_fullStr Hierarchical Deep Features Progressive Aggregation for Remote Sensing Images Scene Classification
title_full_unstemmed Hierarchical Deep Features Progressive Aggregation for Remote Sensing Images Scene Classification
title_short Hierarchical Deep Features Progressive Aggregation for Remote Sensing Images Scene Classification
title_sort hierarchical deep features progressive aggregation for remote sensing images scene classification
topic Multilevel local (MLL) and multilevel global (MLG) feature modules
progressive aggregation (PA)
remote sensing images scene classification
url https://ieeexplore.ieee.org/document/10505774/
work_keys_str_mv AT yangzhao hierarchicaldeepfeaturesprogressiveaggregationforremotesensingimagessceneclassification
AT jiaqiliang hierarchicaldeepfeaturesprogressiveaggregationforremotesensingimagessceneclassification
AT sisihuang hierarchicaldeepfeaturesprogressiveaggregationforremotesensingimagessceneclassification
AT pingpinghuang hierarchicaldeepfeaturesprogressiveaggregationforremotesensingimagessceneclassification