Ship Formation Identification with Spatial Features and Deep Learning for HFSWR

被引:1
|
作者
Wang, Jiaqi [1 ]
Liu, Aijun [1 ]
Yu, Changjun [1 ]
Ji, Yuanzheng [1 ]
机构
[1] Harbin Inst Technol Weihai, Sch Informat Sci & Engn, Weihai 264209, Peoples R China
关键词
high-frequency surface wave radar (HFSWR); cascade identification algorithm; ship formation identification; deep learning; TARGET DETECTION; RADAR; REGULARIZATION; CLUTTER;
D O I
10.3390/rs16030577
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Ship detection has been an area of focus for high-frequency surface wave radar (HFSWR). The detection and identification of ship formation have proven significant in early warning, while studies on the formation identification are limited due to the complex background and low resolution of HFSWR. In this paper, we first establish a spatial distribution model of ship formation in HFSWR. Then, we propose a cascade identification algorithm of ship formation in the clutter edge. The proposed algorithm includes a preprocessing stage and a two-stage formation identification stage. The Faster R-CNN is introduced in the preprocessing stage to locate the clutter regions. In the first stage, we propose an extremum detector based on connected regions to extract suspicious regions. The suspicious regions contain ship formations, single-ship targets, and false targets. In the second stage, we design a network connected by a convolutional neural network (CNN) and an extreme learning machine (ELM) to identify two densely distributed ship formations from inhomogeneous clutter and single-ship targets. The experimental results based on the factual HFSWR background demonstrate that the proposed cascade identification algorithm is superior to the extremum detector combined with the classical CNN algorithm for ship formation identification. Meanwhile, the proposed algorithm performs well in weak formation and deformed formation identification.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] Classification of hyperspectral images by deep learning of spectral-spatial features
    Ding, Haiyong
    Xu, Luming
    Wu, Yue
    Shi, Wenzhong
    ARABIAN JOURNAL OF GEOSCIENCES, 2020, 13 (12)
  • [22] Deep Learning With Grouped Features for Spatial Spectral Classification of Hyperspectral Images
    Zhou, Xichuan
    Li, Shengli
    Tang, Fang
    Qin, Kai
    Hu, Shengdong
    Liu, Shujun
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2017, 14 (01) : 97 - 101
  • [23] Classification of hyperspectral images by deep learning of spectral-spatial features
    Haiyong Ding
    Luming Xu
    Yue Wu
    Wenzhong Shi
    Arabian Journal of Geosciences, 2020, 13
  • [24] Deep-Person: Learning discriminative deep features for person Re-Identification
    Bai, Xiang
    Yang, Mingkun
    Huang, Tengteng
    Dou, Zhiyong
    Yu, Rui
    Xu, Yongchao
    PATTERN RECOGNITION, 2020, 98
  • [25] Ship detection with deep learning: a survey
    Er, Meng Joo
    Zhang, Yani
    Chen, Jie
    Gao, Wenxiao
    ARTIFICIAL INTELLIGENCE REVIEW, 2023, 56 (10) : 11825 - 11865
  • [26] Ship detection with deep learning: a survey
    Meng Joo Er
    Yani Zhang
    Jie Chen
    Wenxiao Gao
    Artificial Intelligence Review, 2023, 56 : 11825 - 11865
  • [27] Ship Detection Based on Deep Learning
    Wang, Yuchao
    Ning, Xiangyun
    Leng, Binghan
    Fu, Huixuan
    2019 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (ICMA), 2019, : 275 - 279
  • [28] Visualization of spatial matching features during deep person re-identification
    Chang, Heyu
    Zhao, Dongning
    Wu, C. H.
    Li, Li
    Si, Nianwen
    He, Rongyu
    JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2020,
  • [29] Learning deep features for source color laser printer identification based on cascaded learning
    Kim, Do-Guk
    Hou, Jong-Uk
    Lee, Heung-Kyu
    NEUROCOMPUTING, 2019, 365 : 219 - 228
  • [30] Fusing deep learning features for parameter identification of a stochastic airfoil system
    Feng, Jing
    Wang, Xiaolong
    Liu, Qi
    Xu, Yong
    Kurths, Juergen
    NONLINEAR DYNAMICS, 2025, 113 (05) : 4211 - 4233