MSARN: A Deep Neural Network Based on an Adaptive Recalibration Mechanism for Multiscale and Arbitrary-Oriented SAR Ship Detection

被引:40
|
作者
Chen, Chen [1 ]
He, Chuan [1 ,2 ]
Hu, Changhua [1 ]
Pei, Hong [2 ]
Jiao, Licheng [1 ]
机构
[1] Xian Inst High Technol, Xian 710025, Shaanxi, Peoples R China
[2] Xidian Univ, Sch Artificial Intelligence, Xian 710071, Shaanxi, Peoples R China
基金
中国国家自然科学基金;
关键词
Marine vehicles; Synthetic aperture radar; Radar polarimetry; Feature extraction; Detection algorithms; Remote sensing; Adaptation models; Ship detection; synthetic aperture radar (SAR); adaptive recalibration; neural network; IMAGES;
D O I
10.1109/ACCESS.2019.2951030
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Ship detection plays an important role in synthetic aperture radar (SAR) image interpretation. However, there are still some difficulties in SAR ship detection. First, ships often have a large aspect ratio and arbitrary directionality in SAR images. Traditional detection algorithms can cause the detection area to be redundant, which makes it difficult to accurately locate the target in complex scenes. Second, ships in ports are often densely arranged, and the effective identification of densely arranged ships is complicated. Finally, ships in SAR images exist at a variety of scales due to the multiresolution imaging modes used and ship shape variations, which pose a considerable challenge for ship detection. To solve the above problems, we propose a multiscale adaptive recalibration network (MSARN) to detect multiscale and arbitrarily oriented ships in complex scenarios. The recalibration of the extracted multiscale features through global information increases the sensitivity of the network to the target angle, thereby increasing the accuracy of positioning. In particular, we designed a pyramid anchor and a loss function to match the rotated target. In addition, we modified the rotation non-maximum suppression (RNMS) method to solve the problem of the large overlap ratio of the detection box. The proposed model combines the positioning advantage of rotation detection with the speed advantage of a single-stage framework. Experiments show that based on the SAR rotation ship detection (SRSD) data set, the proposed algorithm has a faster detection speed and higher accuracy than some state-of-the-art methods.
引用
收藏
页码:159262 / 159283
页数:22
相关论文
共 50 条
  • [1] BENCHMARK FOR ARBITRARY-ORIENTED SAR SHIP DETECTION
    Zhou, Yue
    Jiang, Xue
    Li, Zhou
    Liu, Xingzhao
    [J]. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 1472 - 1475
  • [2] A Single-Stage Arbitrary-Oriented Detector Based on Multiscale Feature Fusion and Calibration for SAR Ship Detection
    Zhao, Shuang
    Liu, Qi
    Yu, Weidong
    Lv, Jiyu
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 8179 - 8198
  • [3] A Deep Neural Network Based on an Attention Mechanism for SAR Ship Detection in Multiscale and Complex Scenarios
    Chen, Chen
    He, Chuan
    Hu, Changhua
    Pei, Hong
    Jiao, Licheng
    [J]. IEEE ACCESS, 2019, 7 : 104848 - 104863
  • [4] A Semisupervised Arbitrary-Oriented SAR Ship Detection Network Based on Interference Consistency Learning and Pseudolabel Calibration
    Zhou, Yue
    Jiang, Xue
    Chen, Zeming
    Chen, Lin
    Liu, Xingzhao
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 5893 - 5904
  • [5] Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
    He, Yishan
    Gao, Fei
    Wang, Jun
    Hussain, Amir
    Yang, Erfu
    Zhou, Huiyu
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 3846 - 3859
  • [6] Ellipse Encoding for Arbitrary-Oriented SAR Ship Detection Based on Dynamic Key Points
    Gao, Fei
    Huo, Yiyang
    Sun, Jinping
    Yu, Tao
    Hussain, Amir
    Zhou, Huiyu
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [7] SAR Ship Detection Based on Convolutional Neural Network with Deep Multiscale Feature Fusion
    Long, Yang
    Juan, Su
    Hua, Huang
    Xiang, Li
    [J]. ACTA OPTICA SINICA, 2020, 40 (02)
  • [8] FSFADet: Arbitrary-Oriented Ship Detection for SAR Images Based on Feature Separation and Feature Alignment
    Mingming Zhu
    Guoping Hu
    Shuai Li
    Hao Zhou
    Shiqiang Wang
    [J]. Neural Processing Letters, 2022, 54 : 1995 - 2005
  • [9] FSFADet: Arbitrary-Oriented Ship Detection for SAR Images Based on Feature Separation and Feature Alignment
    Zhu, Mingming
    Hu, Guoping
    Li, Shuai
    Zhou, Hao
    Wang, Shiqiang
    [J]. NEURAL PROCESSING LETTERS, 2022, 54 (03) : 1995 - 2005
  • [10] Morphology-Based Feature Extraction Network for Arbitrary-Oriented SAR Vehicle Detection
    Chen, Ting
    Huang, Xiaohong
    [J]. Photogrammetric Engineering and Remote Sensing, 2024, 90 (11): : 665 - 673