Synthetic Aperture Radar (SAR) is an active Earth observation system that can obtain high-resolution ocean images all day and all weather. It can be used for monitoring the marine environment, maritime traffic, and oil spills at sea. SAR provides accurate and real-time ocean information, which can ensure water traffic safety and ecological environment. Therefore, it plays an irreplaceable role in maritime surveillance. At present, deep-learning based object detection methods have achieved certain results in the application of ship detection in SAR images. Ship targets in SAR images have strong angular reflection characteristics, causing some parts of them to have large grayscale values, appearing as scattering points. At the same time, the heading of ship usually has a certain angle with the horizontal direction. Traditional deep-learning models do not have sufficient generalization ability for these situations. Horizontal bounding boxes also contain a large amount of background features, which affects the accuracy of the model. In response to these characteristics, first use convolutional neural network to extract ship features; Secondly, generate oriented proposals to reduce the impact of background features; Thirdly, using Canny and Harris to obtain features of ship edges and scattering points as attention mechanisms to enhance bounding box regression and classification; Finally, optimize the loss function, which will consider the influence of angle. Comparative experiments were conducted on the SSDD dataset, and the experimental results showed that compared to existing methods, the improved model has better ship detection performance and can achieve accurate detection of small ship targets in complex scene SAR images.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An Automated SAR-based Method for Ship Detection in Maritime Surveillance System


    Contributors:
    Xu, Zidong (author) / Zhang, Di (author) / Fan, Liang (author) / Ma, Haowei (author) / Li, Yuli (author)


    Publication date :

    2023-08-04


    Size :

    648602 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Online learning for ship detection in maritime surveillance

    Wijnhoven, Rob / Rens, Kris van / Jaspers, Egbert G.T. et al. | Tema Archive | 2010


    Maritime surveillance system

    KANG YOUNG SHIN / KOO SAM OK / PARK BUM JIN et al. | European Patent Office | 2017

    Free access

    MARITIME SURVEILLANCE SYSTEM

    KANG YOUNG SHIN / KOO SAM OK / PARK BUM JIN et al. | European Patent Office | 2017

    Free access

    Integrated automated driving system for maritime autonomous surface ship (MASS)

    MA YONG / ZHAO YUJIAO | European Patent Office | 2023

    Free access

    Integrated Automated Driving System for Maritime Autonomous Surface Ship (MASS)

    MA YONG / ZHAO YUJIAO | European Patent Office | 2021

    Free access