Road extraction from remote sensing images based on a multi-scale asymmetric dual attention mechanism

被引:0
|
作者
Qu, Shenming [1 ]
Liu, Suchen [1 ]
Han, Fengyu [1 ]
Xie, Yuan [1 ]
机构
[1] Henan Univ, Software Coll, Henan Int Joint Lab Theories & Key Technol Intelli, Kaifeng 475004, Henan, Peoples R China
基金
中国国家自然科学基金;
关键词
Road extraction; multi-scale asymmetric convolution; asymmetric dual attention mechanism; dilated convolution; strip pooling; encoder-decoder;
D O I
10.1080/2150704X.2024.2370498
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Aiming at the problems of road fracture and detail loss caused by not considering the geometric features in the road extraction method. We proposed an encoder-decoder architecture based on a multi-scale asymmetric dual attention mechanism. Firstly, A multi-scale convolution block in the shape of 'Union Jack' is designed. It includes symmetric convolution and asymmetric convolution along horizontal, vertical, left diagonal, and right diagonal spatial directions, and a multi-scale dilated convolution for extracting features of different scales. Remote dependence relationships are highly converged by using it, and road fracture problems caused by occlusion can be solved effectively. Secondly, a directional dual attention mechanism is proposed, which consists of directional channel attention using strip pooling and a directional spatial attention mechanism using asymmetric convolution along left diagonal and right diagonal spatial directions. It can use the directivity of asymmetric convolution to allocate attention mechanism adaptively in attention mechanism, and effectively avoid the road detail loss problem. Finally, we conducted corresponding experiments on the DeepGlobe and Ottawa road datasets, and the experimental results are superior to the current state-of-the-art methods.
引用
收藏
页码:751 / 761
页数:11
相关论文
共 50 条
  • [21] Remote Sensing Object Detection Method Based on Attention Mechanism and Multi-scale Feature Fusion
    Liu, Yang
    Xiao, Yewei
    2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 7155 - 7160
  • [22] Remote sensing scene image classification model based on multi-scale features and attention mechanism
    Wang, Guowei
    Xu, Haixia
    Wang, Xinyu
    Yuan, Liming
    Wen, Xianbin
    JOURNAL OF APPLIED REMOTE SENSING, 2022, 16 (04)
  • [23] A Multi-Scale Edge Constraint Network for the Fine Extraction of Buildings from Remote Sensing Images
    Wang, Zhenqing
    Zhou, Yi
    Wang, Futao
    Wang, Shixin
    Qin, Gang
    Zou, Weijie
    Zhu, Jinfeng
    REMOTE SENSING, 2023, 15 (04)
  • [24] Remote sensing image target detection combining multi-scale and attention mechanism
    Zhang Y.-Z.
    Guo W.
    Cai Z.-Q.
    Li W.-B.
    Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2022, 56 (11): : 2215 - 2223
  • [25] Cascaded Residual Attention Enhanced Road Extraction from Remote Sensing Images
    Li, Shengfu
    Liao, Cheng
    Ding, Yulin
    Hu, Han
    Jia, Yang
    Chen, Min
    Xu, Bo
    Ge, Xuming
    Liu, Tianyang
    Wu, Di
    ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2022, 11 (01)
  • [26] FMAM-Net: Fusion Multi-Scale Attention Mechanism Network for Building Segmentation in Remote Sensing Images
    Ye, Huanran
    Zhou, Run
    Wang, Jianhao
    Huang, Zhiliang
    IEEE ACCESS, 2022, 10 : 134241 - 134251
  • [27] A Study on a Remote Sensing Image Classification Method Incorporating Multi-scale Feature Extraction and Channel Attention Mechanism
    Hu, Juan
    Du, Xinran
    Wang, Hanyang
    Jin, Ting
    Yang, Houqun
    ARTIFICIAL INTELLIGENCE AND SECURITY, ICAIS 2022, PT I, 2022, 13338 : 524 - 536
  • [28] Multi-Scale Semantic Segmentation and Spatial Relationship Recognition of Remote Sensing Images Based on an Attention Model
    Cui, Wei
    Wang, Fei
    He, Xin
    Zhang, Dongyou
    Xu, Xuxiang
    Yao, Meng
    Wang, Ziwei
    Huang, Jiejun
    REMOTE SENSING, 2019, 11 (09)
  • [29] Aircraft segmentation in remote sensing images based on multi-scale residual U-Net with attention
    Xuqi Wang
    Shanwen Zhang
    Lei Huang
    Multimedia Tools and Applications, 2024, 83 : 17855 - 17872
  • [30] Aircraft segmentation in remote sensing images based on multi-scale residual U-Net with attention
    Wang, Xuqi
    Zhang, Shanwen
    Huang, Lei
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (06) : 17855 - 17872