• Home
  • Search
  • GCN-Embedding Swin–Unet for Forest Remote Sensing Image Semantic Segmentation
  • Cite Icon2
  • https://doi.org/10.3390/rs18020242Copy DOI Icon

GCN-Embedding Swin–Unet for Forest Remote Sensing Image Semantic Segmentation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Forest resources are among the most important ecosystems on the earth. The semantic segmentation and accurate positioning of ground objects in forest remote sensing (RS) imagery are crucial to the emergency treatment of forest natural disasters, especially forest fires. Currently, most existing methods for image semantic segmentation are built upon convolutional neural networks (CNNs). Nevertheless, these techniques face difficulties in directly accessing global contextual information and accurately detecting geometric transformations within the image’s target regions. This limitation stems from the inherent locality of convolution operations, which are restricted to processing data structured in Euclidean space and confined to square-shaped regions. Inspired by the graph convolution network (GCN) with robust capabilities in processing irregular and complex targets, as well as Swin Transformers renowned for exceptional global context modeling, we present a hybrid semantic segmentation framework for forest RS imagery termed GSwin–Unet. This framework embeds the GCN model into Swin–Unet architecture to address the issue of low semantic segmentation accuracy of RS imagery in forest scenarios, which is caused by the complex texture features, diverse shapes, and unclear boundaries of land objects. GSwin–Unet features a parallel dual-encoder architecture of GCN and Swin Transformer. First, we integrate the Zero-DCE (Zero-Reference Deep Curve Estimation) algorithm into GSwin–Unet to enhance forest RS image feature representation. Second, a feature aggregation module (FAM) is proposed to bridge the dual encoders by fusing GCN-derived local aggregated features with Swin Transformer-extracted features. Our study demonstrates that, compared with the baseline models TransUnet, Swin–Unet, Unet, and DeepLab V3+, the GSwin–Unet achieves improvements of 7.07%, 5.12%, 8.94%, and 2.69% in the mean Intersection over Union (MIoU) and 3.19%, 1.72%, 4.3%, and 3.69% in the average F1 score (Ave.F1), respectively, on the RGB forest RS dataset. On the NIRGB forest RS dataset, the improvements in MIoU are 5.75%, 3.38%, 6.79%, and 2.44%, and the improvements in Ave.F1 are 4.02%, 2.38%, 4.72%, and 1.67%, respectively. Meanwhile, GSwin–Unet shows excellent adaptability on the selected GID dataset with high forest coverage, where the MIoU and Ave.F1 reach 72.92% and 84.3%, respectively.

Similar Papers
  • PDF
  • Research Article
  • Citations27

High-Resolution Remote Sensing Image Semantic Segmentation via Multiscale Context and Linear Self-Attention

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Peng Yin +4
  • Research Article
  • Citations10

Hierarchical Transfer Learning with Transformers to Improve Semantic Segmentation in Remote Sensing Land Use

  • Jan 15, 2025
  • Remote Sensing
  • Miaomiao Chen +1
  • Research Article

Evolutionary Optimization of U-Net Hyperparameters for Enhanced Semantic Segmentation in Remote Sensing Imagery

  • Feb 27, 2026
  • Earth
  • Laritza Pérez-Enríquez +4
  • PDF
  • Research Article
  • Citations26

TCUNet: A Lightweight Dual-Branch Parallel Network for Sea–Land Segmentation in Remote Sensing Images

  • Sep 07, 2023
  • Remote Sensing
  • Xuan Xiong +4
  • PDF
  • Research Article
  • Citations12

Residual Multi-Attention Classification Network for A Forest Dominated Tropical Landscape Using High-Resolution Remote Sensing Imagery

  • Jan 11, 2021
  • ISPRS International Journal of Geo-Information
  • Tong Yu +3
  • Conference Article
  • Citations3

Land Cover Extraction of Remote Sensing Images with Parallel Convolutional Network

  • Jul 26, 2021
  • Chang Xuhong +5
  • Research Article

Video semantic segmentation with low latency

  • May 26, 2024
  • TELKOMNIKA (Telecommunication Computing Electronics and Control)
  • Chinnappa Gowda D V +1
  • Research Article
  • Citations15

LULC-SegNet: Enhancing Land Use and Land Cover Semantic Segmentation with Denoising Diffusion Feature Fusion

  • Dec 06, 2024
  • Remote Sensing
  • Zongwen Shi +4
  • PDF
  • Research Article
  • Citations14

Multiscale Normalization Attention Network for Water Body Extraction from Remote Sensing Imagery

  • Oct 07, 2022
  • Remote Sensing
  • Xin Lyu +4
  • PDF
  • Research Article
  • Citations17

Cloud and Snow Identification Based on DeepLab V3+ and CRF Combined Model for GF-1 WFV Images

  • Sep 30, 2022
  • Remote Sensing
  • Zuo Wang +4
  • PDF
  • Research Article
  • Citations76

Automatic semantic segmentation of breast tumors in ultrasound images based on combining fuzzy logic and deep learning-A feasibility study.

  • May 20, 2021
  • PLOS ONE
  • Samir M Badawy +5
  • Research Article
  • Citations16

Automatic semantic segmentation of breast tumors in ultrasound images based on combining fuzzy logic and deep learning—A feasibility study

  • May 20, 2021
  • PLoS ONE
  • Samir M Badawy +6
  • Research Article

AED-Net: A High-Resolution Remote Sensing Image Road Extraction Method Integrating Atrous Spatial Pyramid Pooling and Efficient Channel Attention Mechanism

  • Jan 01, 2025
  • IEEE Access
  • Jintong Ren +3
  • Research Article
  • Citations2

A Paddy Image Segmentation Method Based on Improved Mask R-CNN

  • Jan 01, 2024
  • Journal of the ASABE
  • Zhixiang Li +9
  • Conference Article

Intelligent Vehicle Environment Scene Parsing Method Based on Multi-tasking Convolutional Neural Network

  • Dec 18, 2020
  • Jing Lian +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.