MSHRNet: a multi-scale high-resolution network for land cover classification from high spatial resolution remote sensing images

Land cover classification is vital for land resource management. However, challenges such as feature similarity among ground objects, blurred boundaries, and indistinct small objects persist. To address these challenges, we propose the Multi-Scale High-Resolution Network (MSHRNet) for classifying gr...

Full description

Saved in:
Bibliographic Details
Main Authors: Fang Chen, Zhihui Ou, Congrong Li, Lei Wang, Bo Yu
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2509090
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224383063654400
author Fang Chen
Zhihui Ou
Congrong Li
Lei Wang
Bo Yu
author_facet Fang Chen
Zhihui Ou
Congrong Li
Lei Wang
Bo Yu
author_sort Fang Chen
collection DOAJ
description Land cover classification is vital for land resource management. However, challenges such as feature similarity among ground objects, blurred boundaries, and indistinct small objects persist. To address these challenges, we propose the Multi-Scale High-Resolution Network (MSHRNet) for classifying ground objects from high-resolution remote sensing images. MSHRNet is an encoder-decoder network that incorporates an attentional boundary refinement branch in the decoder to sharpen object boundaries. It features a multi-scale feature interaction module that integrates feature maps across different resolutions in the encoder and enhances the importance of these fused features using a coordinate attention module. Additionally, we introduce a Laplacian operator-based boundary loss function (LBLoss) to further improve segmentation performance. Evaluated on the GID and Huawei Ascend Cup AI + Remote Sensing Image Competition datasets, MSHRNet demonstrates robustness with a mean Intersection over Union (mIoU) of 82.45% and 72.26%, respectively, and surpasses nine recently published models by at least 1.52% and 1.01% mIoU. Moreover, when tested on the LoveDA dataset without additional training, MSHRNet exhibited strong transferability, achieving an mIoU of 18.53% and surpassing the second-best model by 2.33%. This framework represents a significant advancement in land cover classification, addressing challenges of high-resolution imagery and exhibiting generalization across diverse datasets.
format Article
id doaj-art-964d81d2e57547d3a26173595e1d8eec
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-964d81d2e57547d3a26173595e1d8eec2025-08-25T11:24:34ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2509090MSHRNet: a multi-scale high-resolution network for land cover classification from high spatial resolution remote sensing imagesFang Chen0Zhihui Ou1Congrong Li2Lei Wang3Bo Yu4School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin People’s Republic of ChinaSchool of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin People’s Republic of ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaInternational Research Center of Big Data for Sustainable Development Goals, Beijing, People’s Republic of ChinaInternational Research Center of Big Data for Sustainable Development Goals, Beijing, People’s Republic of ChinaLand cover classification is vital for land resource management. However, challenges such as feature similarity among ground objects, blurred boundaries, and indistinct small objects persist. To address these challenges, we propose the Multi-Scale High-Resolution Network (MSHRNet) for classifying ground objects from high-resolution remote sensing images. MSHRNet is an encoder-decoder network that incorporates an attentional boundary refinement branch in the decoder to sharpen object boundaries. It features a multi-scale feature interaction module that integrates feature maps across different resolutions in the encoder and enhances the importance of these fused features using a coordinate attention module. Additionally, we introduce a Laplacian operator-based boundary loss function (LBLoss) to further improve segmentation performance. Evaluated on the GID and Huawei Ascend Cup AI + Remote Sensing Image Competition datasets, MSHRNet demonstrates robustness with a mean Intersection over Union (mIoU) of 82.45% and 72.26%, respectively, and surpasses nine recently published models by at least 1.52% and 1.01% mIoU. Moreover, when tested on the LoveDA dataset without additional training, MSHRNet exhibited strong transferability, achieving an mIoU of 18.53% and surpassing the second-best model by 2.33%. This framework represents a significant advancement in land cover classification, addressing challenges of high-resolution imagery and exhibiting generalization across diverse datasets.https://www.tandfonline.com/doi/10.1080/17538947.2025.2509090Land cover classificationSemantic segmentationHigh spatial resolutionTransformer networksBoundary refinement
spellingShingle Fang Chen
Zhihui Ou
Congrong Li
Lei Wang
Bo Yu
MSHRNet: a multi-scale high-resolution network for land cover classification from high spatial resolution remote sensing images
International Journal of Digital Earth
Land cover classification
Semantic segmentation
High spatial resolution
Transformer networks
Boundary refinement
title MSHRNet: a multi-scale high-resolution network for land cover classification from high spatial resolution remote sensing images
title_full MSHRNet: a multi-scale high-resolution network for land cover classification from high spatial resolution remote sensing images
title_fullStr MSHRNet: a multi-scale high-resolution network for land cover classification from high spatial resolution remote sensing images
title_full_unstemmed MSHRNet: a multi-scale high-resolution network for land cover classification from high spatial resolution remote sensing images
title_short MSHRNet: a multi-scale high-resolution network for land cover classification from high spatial resolution remote sensing images
title_sort mshrnet a multi scale high resolution network for land cover classification from high spatial resolution remote sensing images
topic Land cover classification
Semantic segmentation
High spatial resolution
Transformer networks
Boundary refinement
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2509090
work_keys_str_mv AT fangchen mshrnetamultiscalehighresolutionnetworkforlandcoverclassificationfromhighspatialresolutionremotesensingimages
AT zhihuiou mshrnetamultiscalehighresolutionnetworkforlandcoverclassificationfromhighspatialresolutionremotesensingimages
AT congrongli mshrnetamultiscalehighresolutionnetworkforlandcoverclassificationfromhighspatialresolutionremotesensingimages
AT leiwang mshrnetamultiscalehighresolutionnetworkforlandcoverclassificationfromhighspatialresolutionremotesensingimages
AT boyu mshrnetamultiscalehighresolutionnetworkforlandcoverclassificationfromhighspatialresolutionremotesensingimages