An End-to-End Local-Global-Fusion Feature Extraction Network for Remote Sensing Image Scene Classification

被引:41
|
作者
Lv, Yafei [1 ]
Zhang, Xiaohan [1 ]
Xiong, Wei [1 ]
Cui, Yaqi [1 ]
Cai, Mi [1 ]
机构
[1] Naval Aviat Univ, Res Inst Informat Fus, Yantai 264001, Peoples R China
基金
中国国家自然科学基金;
关键词
Remote sensing image scene classification (RSISC); Gated Recurrent Units (GRUs); discriminative feature representation; local feature; OBJECT DETECTION; SCALE;
D O I
10.3390/rs11243006
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Remote sensing image scene classification (RSISC) is an active task in the remote sensing community and has attracted great attention due to its wide applications. Recently, the deep convolutional neural networks (CNNs)-based methods have witnessed a remarkable breakthrough in performance of remote sensing image scene classification. However, the problem that the feature representation is not discriminative enough still exists, which is mainly caused by the characteristic of inter-class similarity and intra-class diversity. In this paper, we propose an efficient end-to-end local-global-fusion feature extraction (LGFFE) network for a more discriminative feature representation. Specifically, global and local features are extracted from channel and spatial dimensions respectively, based on a high-level feature map from deep CNNs. For the local features, a novel recurrent neural network (RNN)-based attention module is first proposed to capture the spatial layout information and context information across different regions. Gated recurrent units (GRUs) is then exploited to generate the important weight of each region by taking a sequence of features from image patches as input. A reweighed regional feature representation can be obtained by focusing on the key region. Then, the final feature representation can be acquired by fusing the local and global features. The whole process of feature extraction and feature fusion can be trained in an end-to-end manner. Finally, extensive experiments have been conducted on four public and widely used datasets and experimental results show that our method LGFFE outperforms baseline methods and achieves state-of-the-art results.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] End-to-End Convolutional Neural Network Feature Extraction for Remote Sensed Images Classification
    Alem, Abebaw
    Kumar, Shailender
    APPLIED ARTIFICIAL INTELLIGENCE, 2022, 36 (01)
  • [2] Feature Fusion Pyramid Network for End-to-End Scene Text Detection
    Wu, Yirui
    Zhang, Lilai
    Li, Hao
    Zhang, Yunfei
    Wan, Shaohua
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2024, 23 (11)
  • [3] END-TO-END LEARNING OF POLYGONS FOR REMOTE SENSING IMAGE CLASSIFICATION
    Girard, Nicolas
    Tarabalka, Yuliya
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 2083 - 2086
  • [4] Multimodal Image Fusion Framework for End-to-End Remote Sensing Image Registration
    Li, Liangzhi
    Han, Ling
    Ding, Mingtao
    Cao, Hongye
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [5] An End-to-End Neural Network for Road Extraction From Remote Sensing Imagery by Multiple Feature Pyramid Network
    Gao, Xun
    Sun, Xian
    Zhang, Yi
    Yan, Menglong
    Xu, Guangluan
    Sun, Hao
    Jiao, Jiao
    Fu, Kun
    IEEE ACCESS, 2018, 6 : 39401 - 39414
  • [6] A global-local feature adaptive fusion network for image scene classification
    Lv, Guangrui
    Dong, Lili
    Zhang, Wenwen
    Xu, Wenhai
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (03) : 6521 - 6554
  • [7] A global-local feature adaptive fusion network for image scene classification
    Guangrui Lv
    Lili Dong
    Wenwen Zhang
    Wenhai Xu
    Multimedia Tools and Applications, 2024, 83 : 6521 - 6554
  • [8] Multilayer Feature Fusion Network for Scene Classification in Remote Sensing
    Xu, Kejie
    Huang, Hong
    Li, Yuan
    Shi, Guangyao
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2020, 17 (11) : 1894 - 1898
  • [9] Global remote feature modulation end-to-end detection
    Bao, XiaoAn
    Yi, WenJing
    Tu, XiaoMei
    Zhang, Na
    Zhang, QingQi
    Jin, YuTing
    Wu, Biao
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [10] An Attention-Enhanced End-to-End Discriminative Network With Multiscale Feature Learning for Remote Sensing Image Retrieval
    Hou, Dongyang
    Wang, Siyuan
    Tian, Xueqing
    Xing, Huaqiao
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 8245 - 8255