RPFusionNet: An Efficient Semantic Segmentation Method for Large-Scale Remote Sensing Images via Parallel Region–Patch Fusion

Mainstream deep learning segmentation models are designed for small-sized images, and when applied to high-resolution remote sensing images, the limited information contained in small-sized images greatly restricts a model’s ability to capture complex contextual information at a global scale. To mit...

Full description

Saved in:
Bibliographic Details
Main Authors: Shiyan Pang, Weimin Zeng, Yepeng Shi, Zhiqi Zuo, Kejiang Xiao, Yujun Wu
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2158
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319781458509824
author Shiyan Pang
Weimin Zeng
Yepeng Shi
Zhiqi Zuo
Kejiang Xiao
Yujun Wu
author_facet Shiyan Pang
Weimin Zeng
Yepeng Shi
Zhiqi Zuo
Kejiang Xiao
Yujun Wu
author_sort Shiyan Pang
collection DOAJ
description Mainstream deep learning segmentation models are designed for small-sized images, and when applied to high-resolution remote sensing images, the limited information contained in small-sized images greatly restricts a model’s ability to capture complex contextual information at a global scale. To mitigate this challenge, we present RPFusionNet, a novel parallel semantic segmentation framework that is specifically designed to efficiently integrate both local and global features. RPFusionNet leverages two distinct feature representations: REGION (representing large areas) and PATCH (representing smaller regions). This framework comprises two parallel branches: the REGION branch initially downsamples the entire image, then extracts features via a convolutional neural network (CNN)-based encoder, and subsequently captures multi-level information using pooled kernels of varying sizes. This design enables the model to adapt effectively to objects of different scales. In contrast, the PATCH branch utilizes a pixel-level feature extractor to enrich the high-dimensional features of the local region, thereby enhancing the representation of fine-grained details. To model the semantic correlation between the two branches, we have developed the Region–Patch scale fusion module. This module ensures that the network can comprehend a wider range of image contexts while preserving local details, thus bridging the gap between regional and local information. Extensive experiments were conducted on three public datasets: WBDS, AIDS, and Vaihingen. Compared to other state-of-the-art methods, our network achieved the highest accuracy on all three datasets, with an IoU score of 92.08% on the WBDS dataset, 89.99% on the AIDS dataset, and 88.44% on the Vaihingen dataset.
format Article
id doaj-art-71f88a46ea9346f386eb03908ba5baa2
institution Kabale University
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-71f88a46ea9346f386eb03908ba5baa22025-08-20T03:50:20ZengMDPI AGRemote Sensing2072-42922025-06-011713215810.3390/rs17132158RPFusionNet: An Efficient Semantic Segmentation Method for Large-Scale Remote Sensing Images via Parallel Region–Patch FusionShiyan Pang0Weimin Zeng1Yepeng Shi2Zhiqi Zuo3Kejiang Xiao4Yujun Wu5Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaFaculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaFaculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaCollege of Informatics, Huazhong Agricultural University, Wuhan 430070, ChinaFaculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaCollege of Informatics, Huazhong Agricultural University, Wuhan 430070, ChinaMainstream deep learning segmentation models are designed for small-sized images, and when applied to high-resolution remote sensing images, the limited information contained in small-sized images greatly restricts a model’s ability to capture complex contextual information at a global scale. To mitigate this challenge, we present RPFusionNet, a novel parallel semantic segmentation framework that is specifically designed to efficiently integrate both local and global features. RPFusionNet leverages two distinct feature representations: REGION (representing large areas) and PATCH (representing smaller regions). This framework comprises two parallel branches: the REGION branch initially downsamples the entire image, then extracts features via a convolutional neural network (CNN)-based encoder, and subsequently captures multi-level information using pooled kernels of varying sizes. This design enables the model to adapt effectively to objects of different scales. In contrast, the PATCH branch utilizes a pixel-level feature extractor to enrich the high-dimensional features of the local region, thereby enhancing the representation of fine-grained details. To model the semantic correlation between the two branches, we have developed the Region–Patch scale fusion module. This module ensures that the network can comprehend a wider range of image contexts while preserving local details, thus bridging the gap between regional and local information. Extensive experiments were conducted on three public datasets: WBDS, AIDS, and Vaihingen. Compared to other state-of-the-art methods, our network achieved the highest accuracy on all three datasets, with an IoU score of 92.08% on the WBDS dataset, 89.99% on the AIDS dataset, and 88.44% on the Vaihingen dataset.https://www.mdpi.com/2072-4292/17/13/2158RPFusionNetremote sensinglarge-scale remote sensing imagesREGIONPATCH
spellingShingle Shiyan Pang
Weimin Zeng
Yepeng Shi
Zhiqi Zuo
Kejiang Xiao
Yujun Wu
RPFusionNet: An Efficient Semantic Segmentation Method for Large-Scale Remote Sensing Images via Parallel Region–Patch Fusion
Remote Sensing
RPFusionNet
remote sensing
large-scale remote sensing images
REGION
PATCH
title RPFusionNet: An Efficient Semantic Segmentation Method for Large-Scale Remote Sensing Images via Parallel Region–Patch Fusion
title_full RPFusionNet: An Efficient Semantic Segmentation Method for Large-Scale Remote Sensing Images via Parallel Region–Patch Fusion
title_fullStr RPFusionNet: An Efficient Semantic Segmentation Method for Large-Scale Remote Sensing Images via Parallel Region–Patch Fusion
title_full_unstemmed RPFusionNet: An Efficient Semantic Segmentation Method for Large-Scale Remote Sensing Images via Parallel Region–Patch Fusion
title_short RPFusionNet: An Efficient Semantic Segmentation Method for Large-Scale Remote Sensing Images via Parallel Region–Patch Fusion
title_sort rpfusionnet an efficient semantic segmentation method for large scale remote sensing images via parallel region patch fusion
topic RPFusionNet
remote sensing
large-scale remote sensing images
REGION
PATCH
url https://www.mdpi.com/2072-4292/17/13/2158
work_keys_str_mv AT shiyanpang rpfusionnetanefficientsemanticsegmentationmethodforlargescaleremotesensingimagesviaparallelregionpatchfusion
AT weiminzeng rpfusionnetanefficientsemanticsegmentationmethodforlargescaleremotesensingimagesviaparallelregionpatchfusion
AT yepengshi rpfusionnetanefficientsemanticsegmentationmethodforlargescaleremotesensingimagesviaparallelregionpatchfusion
AT zhiqizuo rpfusionnetanefficientsemanticsegmentationmethodforlargescaleremotesensingimagesviaparallelregionpatchfusion
AT kejiangxiao rpfusionnetanefficientsemanticsegmentationmethodforlargescaleremotesensingimagesviaparallelregionpatchfusion
AT yujunwu rpfusionnetanefficientsemanticsegmentationmethodforlargescaleremotesensingimagesviaparallelregionpatchfusion