GLF-Net: A Semantic Segmentation Model Fusing Global and Local Features for High-Resolution Remote Sensing Images
Semantic segmentation of high-resolution remote sensing images holds paramount importance in the field of remote sensing. To better excavate and fully fuse the features in high-resolution remote sensing images, this paper introduces a novel Global and Local Feature Fusion Network, abbreviated as GLF...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/19/4649 |
_version_ | 1797575219764789248 |
---|---|
author | Wanying Song Xinwei Zhou Shiru Zhang Yan Wu Peng Zhang |
author_facet | Wanying Song Xinwei Zhou Shiru Zhang Yan Wu Peng Zhang |
author_sort | Wanying Song |
collection | DOAJ |
description | Semantic segmentation of high-resolution remote sensing images holds paramount importance in the field of remote sensing. To better excavate and fully fuse the features in high-resolution remote sensing images, this paper introduces a novel Global and Local Feature Fusion Network, abbreviated as GLF-Net, by incorporating the extensive contextual information and refined fine-grained features. The proposed GLF-Net, devised as an encoder–decoder network, employs the powerful ResNet50 as its baseline model. It incorporates two pivotal components within the encoder phase: a Covariance Attention Module (CAM) and a Local Fine-Grained Extraction Module (LFM). And an additional wavelet self-attention module (WST) is integrated into the decoder stage. The CAM effectively extracts the features of different scales from various stages of the ResNet and then encodes them with graph convolutions. In this way, the proposed GLF-Net model can well capture the global contextual information with both universality and consistency. Additionally, the local feature extraction module refines the feature map by encoding the semantic and spatial information, thereby capturing the local fine-grained features in images. Furthermore, the WST maximizes the synergy between the high-frequency and the low-frequency information, facilitating the fusion of global and local features for better performance in semantic segmentation. The effectiveness of the proposed GLF-Net model is validated through experiments conducted on the ISPRS Potsdam and Vaihingen datasets. The results verify that it can greatly improve segmentation accuracy. |
first_indexed | 2024-03-10T21:36:39Z |
format | Article |
id | doaj.art-44c3c35372b64a44b401c7801da305ed |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T21:36:39Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-44c3c35372b64a44b401c7801da305ed2023-11-19T14:58:01ZengMDPI AGRemote Sensing2072-42922023-09-011519464910.3390/rs15194649GLF-Net: A Semantic Segmentation Model Fusing Global and Local Features for High-Resolution Remote Sensing ImagesWanying Song0Xinwei Zhou1Shiru Zhang2Yan Wu3Peng Zhang4Xi’an Key Laboratory of Network Convergence Communication, School of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaXi’an Key Laboratory of Network Convergence Communication, School of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaXi’an Key Laboratory of Network Convergence Communication, School of Communication and Information Engineering, Xi’an University of Science and Technology, Xi’an 710054, ChinaSchool of Electronics Engineering, Xidian University, Xi’an 710071, ChinaSchool of Electronics Engineering, Xidian University, Xi’an 710071, ChinaSemantic segmentation of high-resolution remote sensing images holds paramount importance in the field of remote sensing. To better excavate and fully fuse the features in high-resolution remote sensing images, this paper introduces a novel Global and Local Feature Fusion Network, abbreviated as GLF-Net, by incorporating the extensive contextual information and refined fine-grained features. The proposed GLF-Net, devised as an encoder–decoder network, employs the powerful ResNet50 as its baseline model. It incorporates two pivotal components within the encoder phase: a Covariance Attention Module (CAM) and a Local Fine-Grained Extraction Module (LFM). And an additional wavelet self-attention module (WST) is integrated into the decoder stage. The CAM effectively extracts the features of different scales from various stages of the ResNet and then encodes them with graph convolutions. In this way, the proposed GLF-Net model can well capture the global contextual information with both universality and consistency. Additionally, the local feature extraction module refines the feature map by encoding the semantic and spatial information, thereby capturing the local fine-grained features in images. Furthermore, the WST maximizes the synergy between the high-frequency and the low-frequency information, facilitating the fusion of global and local features for better performance in semantic segmentation. The effectiveness of the proposed GLF-Net model is validated through experiments conducted on the ISPRS Potsdam and Vaihingen datasets. The results verify that it can greatly improve segmentation accuracy.https://www.mdpi.com/2072-4292/15/19/4649high-resolution remote sensingsemantic segmentationglobal context informationfine-grained featurefeature fusion |
spellingShingle | Wanying Song Xinwei Zhou Shiru Zhang Yan Wu Peng Zhang GLF-Net: A Semantic Segmentation Model Fusing Global and Local Features for High-Resolution Remote Sensing Images Remote Sensing high-resolution remote sensing semantic segmentation global context information fine-grained feature feature fusion |
title | GLF-Net: A Semantic Segmentation Model Fusing Global and Local Features for High-Resolution Remote Sensing Images |
title_full | GLF-Net: A Semantic Segmentation Model Fusing Global and Local Features for High-Resolution Remote Sensing Images |
title_fullStr | GLF-Net: A Semantic Segmentation Model Fusing Global and Local Features for High-Resolution Remote Sensing Images |
title_full_unstemmed | GLF-Net: A Semantic Segmentation Model Fusing Global and Local Features for High-Resolution Remote Sensing Images |
title_short | GLF-Net: A Semantic Segmentation Model Fusing Global and Local Features for High-Resolution Remote Sensing Images |
title_sort | glf net a semantic segmentation model fusing global and local features for high resolution remote sensing images |
topic | high-resolution remote sensing semantic segmentation global context information fine-grained feature feature fusion |
url | https://www.mdpi.com/2072-4292/15/19/4649 |
work_keys_str_mv | AT wanyingsong glfnetasemanticsegmentationmodelfusingglobalandlocalfeaturesforhighresolutionremotesensingimages AT xinweizhou glfnetasemanticsegmentationmodelfusingglobalandlocalfeaturesforhighresolutionremotesensingimages AT shiruzhang glfnetasemanticsegmentationmodelfusingglobalandlocalfeaturesforhighresolutionremotesensingimages AT yanwu glfnetasemanticsegmentationmodelfusingglobalandlocalfeaturesforhighresolutionremotesensingimages AT pengzhang glfnetasemanticsegmentationmodelfusingglobalandlocalfeaturesforhighresolutionremotesensingimages |