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
  • [21] Medical Hyperspectral Image Classification Based on End-to-End Fusion Deep Neural Network
    Wei, Xueling
    Li, Wei
    Zhang, Mengmeng
    Li, Qingli
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2019, 68 (11) : 4481 - 4492
  • [22] Feature Extraction and Scene Classification for Remote Sensing Image Based on Sparse Representation
    Guo, Youliang
    Zhang, Junping
    Zhong, Shengwei
    ALGORITHMS, TECHNOLOGIES, AND APPLICATIONS FOR MULTISPECTRAL AND HYPERSPECTRAL IMAGERY XXV, 2019, 10986
  • [23] REMOTE SENSING SCENE CLASSIFICATION BASED ON GLOBAL AND LOCAL CONSISTENT NETWORK
    Ma, Jingjing
    Ma, Qiushuo
    Tang, Xu
    Zhang, Xiangrong
    Zhu, Cheng
    Peng, Qunnie
    Jiao, Licheng
    IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 537 - 540
  • [24] FUSENET: END-TO-END MULTISPECTRAL VHR IMAGE FUSION AND CLASSIFICATION
    Bergado, John Ray
    Persello, Claudio
    Stein, Alfred
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 2091 - 2094
  • [25] Adjacent-Atrous Mechanism for Expanding Global Receptive Fields: An End-to-End Network for Multiattribute Scene Analysis in Remote Sensing Imagery
    Li, Zhengpeng
    Hu, Jun
    Wu, Kunyang
    Miao, Jiawei
    Wu, Jiansheng
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 1
  • [26] End-to-end image feature extraction - aggregation loop closure detection network for visual SLAM
    Yin, Jiaqi
    Dai, Kun
    Cheng, Lan
    Xu, Xinying
    Zhang, Zhe
    2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2023, : 857 - 863
  • [27] Global Context-Based Multilevel Feature Fusion Networks for Multilabel Remote Sensing Image Scene Classification
    Wang, Xin
    Duan, Lin
    Ning, Chen
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 11179 - 11196
  • [28] Attentional Feature Fusion for End-to-End Blind Image Quality Assessment
    Zhou, Mingliang
    Lang, Shujun
    Zhang, Taiping
    Liao, Xingran
    Shang, Zhaowei
    Xiang, Tao
    Fang, Bin
    IEEE TRANSACTIONS ON BROADCASTING, 2023, 69 (01) : 144 - 152
  • [29] Multilevel Feature Fusion for End-to-End Blind Image Quality Assessment
    Lan, Xuting
    Zhou, Mingliang
    Xu, Xueyong
    Wei, Xuekai
    Liao, Xingran
    Pu, Huayan
    Luo, Jun
    Xiang, Tao
    Fang, Bin
    Shang, Zhaowei
    IEEE TRANSACTIONS ON BROADCASTING, 2023, 69 (03) : 801 - 811
  • [30] A DYNAMIC END-TO-END FUSION FILTER FOR LOCAL CLIMATE ZONE CLASSIFICATION USING SAR AND MULTI-SPECTRUM REMOTE SENSING DATA
    Feng, Pengming
    Lin, Youtian
    He, Guangjun
    Guan, Jian
    Wang, Jin
    Shi, Huifeng
    IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 4231 - 4234