DHRNet: A Dual-Branch Hybrid Reinforcement Network for Semantic Segmentation of Remote Sensing Images

被引:2
|
作者
Bai, Qinyan [1 ,2 ]
Luo, Xiaobo [1 ,2 ]
Wang, Yaxu [1 ,2 ]
Wei, Tengfei [1 ,2 ]
机构
[1] Chongqing Univ Posts & Telecommun, Sch Comp Sci & Technol, Chongqing 400065, Peoples R China
[2] Chongqing Engn Res Ctr Spatial Big Data Intelligen, Chongqing 400065, Peoples R China
关键词
Global context modeling; multiscale feature extraction; remote sensing; semantic segmentation; CONVOLUTIONAL NEURAL-NETWORKS; LAND-USE; TEXTURE; CLASSIFICATION; EXTRACTION; COLOR;
D O I
10.1109/JSTARS.2024.3357216
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In the field of remote sensing image processing, semantic segmentation has always been a hot research topic. Currently, deep convolutional neural networks (DCNNs) are the mainstream methods for the semantic segmentation of remote sensing image (RSI). There are two commonly used semantic segmentation methods based on DCNNs: multiscale feature extraction based on deep-level features, and global modeling. The former can better extract object features of different scales in complex scenes. However, this method lacks sufficient spatial information, resulting in poor edge segmentation ability. The latter can effectively solve the problem of limited receptive field in DCNNs obtaining more comprehensive feature extraction results. Unfortunately, this method is prone to misclassification, resulting in incorrect predictions of local pixels. To address these issues, we propose the dual-branch hybrid reinforcement network (DHRNet) for more precise semantic segmentation of RSI. This model is a dual-branch parallel structure with a multiscale feature extraction branch and a global context and detail enhancement branch. This structure decomposes the complex semantic segmentation task, allowing each branch to extract features with different emphases while retaining sufficient spatial information. The results of both branches are fused to obtain a more comprehensive segmentation result. After conducting extensive experiments on three publicly available RSI datasets, ISPRS Potsdam, ISPRS Vaihingen, and LoveDA, DHRNet demonstrates excellent results with the mean intersection over union of 86.97%, 83.53%, and 54.48% on the three datasets, respectively.
引用
收藏
页码:4176 / 4193
页数:18
相关论文
共 50 条
  • [1] DBDAN: Dual-Branch Dynamic Attention Network for Semantic Segmentation of Remote Sensing Images
    Che, Rui
    Ma, Xiaowen
    Hong, Tingfeng
    Wang, Xinyu
    Feng, Tian
    Zhang, Wei
    [J]. PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT IV, 2024, 14428 : 306 - 317
  • [2] PSR-Net: A Dual-Branch Pyramid Semantic Reasoning Network for Segmentation of Remote Sensing Images
    Wang, Lijun
    Li, Bicao
    Wang, Bei
    Li, Chunlei
    Huang, Jie
    Song, Mengxing
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT II, 2023, 14255 : 582 - 592
  • [3] Dual-branch hybrid network for lesion segmentation in gastric cancer images
    He, Dongzhi
    Zhang, Yuanyu
    Huang, Hui
    Si, Yuhang
    Wang, Zhiqiang
    Li, Yunqi
    [J]. SCIENTIFIC REPORTS, 2023, 13 (01)
  • [4] Dual-branch hybrid network for lesion segmentation in gastric cancer images
    Dongzhi He
    Yuanyu Zhang
    Hui Huang
    Yuhang Si
    Zhiqiang Wang
    Yunqi Li
    [J]. Scientific Reports, 13
  • [5] TCUNet: A Lightweight Dual-Branch Parallel Network for Sea-Land Segmentation in Remote Sensing Images
    Xiong, Xuan
    Wang, Xiaopeng
    Zhang, Jiahua
    Huang, Baoxiang
    Du, Runfeng
    [J]. REMOTE SENSING, 2023, 15 (18)
  • [6] DBENet: Dual-Branch Ensemble Network for Sea-Land Segmentation of Remote-Sensing Images
    Ji, Xun
    Tang, Longbin
    Lu, Tongwei
    Cai, Chengtao
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
  • [7] SPNet: Dual-Branch Network with Spatial Supplementary Information for Building and Water Segmentation of Remote Sensing Images
    Zhao, Wenyu
    Xia, Min
    Weng, Liguo
    Hu, Kai
    Lin, Haifeng
    Zhang, Youke
    Liu, Ziheng
    [J]. REMOTE SENSING, 2024, 16 (17)
  • [8] A Dual-Branch Deep Learning Architecture for Multisensor and Multitemporal Remote Sensing Semantic Segmentation
    Bergamasco, Luca
    Bovolo, Francesca
    Bruzzone, Lorenzo
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 2147 - 2162
  • [9] DSHNet: A Semantic Segmentation Model of Remote Sensing Images Based on Dual Stream Hybrid Network
    Fu, Yujia
    Zhang, Xiangrong
    Wang, Mingyang
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 4164 - 4175
  • [10] Multilateral Semantic With Dual Relation Network for Remote Sensing Images Segmentation
    Zhao, Weiheng
    Cao, Jiannong
    Dong, Xueyan
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 506 - 518