Remote Sensing Image Segmentation Network That Integrates Global–Local Multi-Scale Information with Deep and Shallow Features

As the spatial resolution of remote sensing images continues to increase, the complexity of the information they carry also grows. Remote sensing images are characterized by large imaging areas, scattered distributions of similar objects, intricate boundary shapes, and a high density of small object...

Full description

Saved in:
Bibliographic Details
Main Authors: Nan Chen, Ruiqi Yang, Yili Zhao, Qinling Dai, Leiguang Wang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/11/1880
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722481549508608
author Nan Chen
Ruiqi Yang
Yili Zhao
Qinling Dai
Leiguang Wang
author_facet Nan Chen
Ruiqi Yang
Yili Zhao
Qinling Dai
Leiguang Wang
author_sort Nan Chen
collection DOAJ
description As the spatial resolution of remote sensing images continues to increase, the complexity of the information they carry also grows. Remote sensing images are characterized by large imaging areas, scattered distributions of similar objects, intricate boundary shapes, and a high density of small objects, all of which pose significant challenges for semantic segmentation tasks. To address these challenges, we propose a Remote Sensing Image Segmentation Network that Integrates Global–Local Multi-Scale Information with Deep and Shallow Features (GLDSFNet). To better handle the wide variations in object sizes and complex boundary shapes, we design a Global–Local Multi-Scale Feature Fusion Module (GLMFM) that enhances segmentation performance by fully leveraging multi-scale information and global context. Additionally, to improve the segmentation of small objects, we propose a Shallow–Deep Feature Fusion Module (SDFFM), which effectively integrates deep semantic information with shallow spatial features through mutual guidance, retaining the advantages of both. Extensive ablation and comparative experiments conducted on two public remote sensing datasets, ISPRS Vaihingen and Potsdam, demonstrate that our proposed GLDSFNet outperforms state-of-the-art methods.
format Article
id doaj-art-9c5359e9ef8f4feb891b6ed2e1a06a0e
institution DOAJ
issn 2072-4292
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-9c5359e9ef8f4feb891b6ed2e1a06a0e2025-08-20T03:11:20ZengMDPI AGRemote Sensing2072-42922025-05-011711188010.3390/rs17111880Remote Sensing Image Segmentation Network That Integrates Global–Local Multi-Scale Information with Deep and Shallow FeaturesNan Chen0Ruiqi Yang1Yili Zhao2Qinling Dai3Leiguang Wang4School of Landscape Architecture, Southwest Forestry University, Kunming 650224, ChinaSchool of Geography, Yunnan Normal University, Kunming 650224, ChinaCollege of Big Data and Intelligence Engineering, Southwest Forestry University, Kunming 650224, ChinaArt and Design College Engineering, Southwest Forestry University, Kunming 650224, ChinaSchool of Landscape Architecture, Southwest Forestry University, Kunming 650224, ChinaAs the spatial resolution of remote sensing images continues to increase, the complexity of the information they carry also grows. Remote sensing images are characterized by large imaging areas, scattered distributions of similar objects, intricate boundary shapes, and a high density of small objects, all of which pose significant challenges for semantic segmentation tasks. To address these challenges, we propose a Remote Sensing Image Segmentation Network that Integrates Global–Local Multi-Scale Information with Deep and Shallow Features (GLDSFNet). To better handle the wide variations in object sizes and complex boundary shapes, we design a Global–Local Multi-Scale Feature Fusion Module (GLMFM) that enhances segmentation performance by fully leveraging multi-scale information and global context. Additionally, to improve the segmentation of small objects, we propose a Shallow–Deep Feature Fusion Module (SDFFM), which effectively integrates deep semantic information with shallow spatial features through mutual guidance, retaining the advantages of both. Extensive ablation and comparative experiments conducted on two public remote sensing datasets, ISPRS Vaihingen and Potsdam, demonstrate that our proposed GLDSFNet outperforms state-of-the-art methods.https://www.mdpi.com/2072-4292/17/11/1880deformable convolutionfeature fusionmultiscale featureremote-sensing imagesemantic segmentation
spellingShingle Nan Chen
Ruiqi Yang
Yili Zhao
Qinling Dai
Leiguang Wang
Remote Sensing Image Segmentation Network That Integrates Global–Local Multi-Scale Information with Deep and Shallow Features
Remote Sensing
deformable convolution
feature fusion
multiscale feature
remote-sensing image
semantic segmentation
title Remote Sensing Image Segmentation Network That Integrates Global–Local Multi-Scale Information with Deep and Shallow Features
title_full Remote Sensing Image Segmentation Network That Integrates Global–Local Multi-Scale Information with Deep and Shallow Features
title_fullStr Remote Sensing Image Segmentation Network That Integrates Global–Local Multi-Scale Information with Deep and Shallow Features
title_full_unstemmed Remote Sensing Image Segmentation Network That Integrates Global–Local Multi-Scale Information with Deep and Shallow Features
title_short Remote Sensing Image Segmentation Network That Integrates Global–Local Multi-Scale Information with Deep and Shallow Features
title_sort remote sensing image segmentation network that integrates global local multi scale information with deep and shallow features
topic deformable convolution
feature fusion
multiscale feature
remote-sensing image
semantic segmentation
url https://www.mdpi.com/2072-4292/17/11/1880
work_keys_str_mv AT nanchen remotesensingimagesegmentationnetworkthatintegratesgloballocalmultiscaleinformationwithdeepandshallowfeatures
AT ruiqiyang remotesensingimagesegmentationnetworkthatintegratesgloballocalmultiscaleinformationwithdeepandshallowfeatures
AT yilizhao remotesensingimagesegmentationnetworkthatintegratesgloballocalmultiscaleinformationwithdeepandshallowfeatures
AT qinlingdai remotesensingimagesegmentationnetworkthatintegratesgloballocalmultiscaleinformationwithdeepandshallowfeatures
AT leiguangwang remotesensingimagesegmentationnetworkthatintegratesgloballocalmultiscaleinformationwithdeepandshallowfeatures