ScholarMate
English简体中文繁體中文
客服熱線:400-1616-289
登入註冊
期刊論文

SAR Target Classification Using the Multikernel-Size Feature Fusion-Based Convolutional Neural Network

Ai, Jiaqiu*; Mao, Yuxiang; Luo, Qiwu; Jia, Lu; Xing, Mengdao西安电子科技大学
IEEE Transactions on Geoscience and Remote Sensing2022DOI: 10.1109/TGRS.2021.3106915
42被引9閱讀
引用收藏
分享

摘要

It is well-known that the convolutional neural network (CNN) is an effective method for synthetic aperture radar (SAR) target classification. In the convolutional layer of CNN, convolutional kernels of different sizes can extract different feature information of the target. The small-size kernel can extract the local texture feature information, and the large-size kernel can extract the global contour feature information. Traditional CNN methods usually use fixed-size kernels for convolution, and they generally lose part of the target's feature information, resulting in the inaccurate classification of the SAR targets. This article proposes a novel CNN model based on multikernel-size feature fusion (MKSFF-CNN) for SAR target classification. MKSFF-CNN designs a convolutional methodology with a multichannel parallel topology, it uses convolutional kernels of different sizes to extract the multikernel-size deep features of the SAR target, and then, these features are fused in an optimal way to acquire the lowest loss. Moreover, MKSFF-CNN concatenates the fused features extracted by the convolutional layers of different dimensions to achieve the finest classification. MKSFF-CNN greatly elevates the feature representation completeness of the SAR targets so that more useful feature information can be exploited for SAR target classification. Undoubtedly, MKSFF-CNN can achieve a better classification performance compared with traditional CNN models with a fixed kernel size. The superiority of MKSFF-CNN is validated on the moving and stationary target acquisition and recognition (MSTAR) dataset with the detailed objective and subjective evaluation.

學科與關鍵詞

關鍵詞
Feature extractionKernelSynthetic aperture radarData miningConvolutionConvolutional neural networksTrainingConvolutional neural network (CNN)multidimensional feature concatenationmultikernel-size-based convolutionoptimal feature fusionsynthetic aperture radar (SAR) target classification
相關
載入中…
  • Feature-Fused SAR Target Discrimination Using Multiple Convolutional Neural Networks
    Ning, Wang; Yinghua, Wang; Hongwei, Liu; Qunsheng, Zuo; Jinglu, HeIEEE Geoscience and Remote Sensing Letters, 2017, 14(10): 1695-1699.被引 18
  • A Survey on the Applications of Convolutional Neural Networks for Synthetic Aperture Radar: Recent Advances
    Oveis, Amir Hosein*; Giusti, Elisa; Ghio, Selenia; Martorella, MarcoIEEE AEROSPACE AND ELECTRONIC SYSTEMS MAGAZINE, 2022, 37(5): 18-+.被引 44
  • SAR Image Classification Using Gated Channel Attention Based Convolutional Neural Network
    Zhang, Anjun*; Jia, Lu; Wang, Jun; Wang, ChuanjianRemote Sensing, 2023, 15(2): 362.被引 1
查看全部 →

發表資訊

論文狀態
公開發表
期刊
IEEE Transactions on Geoscience and Remote Sensing
發表日期
2022
卷期
第 60 卷
DOI
10.1109/TGRS.2021.3106915
語言
ENGLISH
期刊等級
2区
成果收錄
SCIE
資助標註
National Natural Science Foundation of China [62071164, 61701157]; China Postdoctoral Science Foundation [2020T130165]; Fundamental Research Funds for the Central Universities of China [JZ2020HGTB0012, PA2021AKSK0113]

作者

  • A

    Ai, Jiaqiu (通訊) (第一作者)

  • M

    Mao, Yuxiang

查看全部 5 位作者收起作者
  • L

    Luo, Qiwu

  • J

    Jia, Lu

  • X

    Xing, Mengdao

    xidian univ

登入解鎖更多功能

  • 收藏這篇,隨時在「我的 · 收藏」找回
  • 認領你的成果,生成推廣素材
  • 關注作者獲取最新成果
  • 加入項目組、協同寫作
註冊 / 登入

產品服務

  • 科研之友
  • 創新城
  • 科創雲

服務支援

  • 幫助中心
  • 隱私政策
  • 服務條款

聯絡方式

線上客服:【】
客服熱線:400-1616-289
電子郵件:support@scholarmate.com

關注或下載科研之友

微信 QR Code
微信公眾號
客戶端下載 QR Code
下載客戶端
科研成果科研人員科研機構科研動態愛瑞思軟件

©2026 深圳市科研之友网络服务有限公司

公安備案圖示粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417