Aiming at the problem of nearshore ship detection in highresolution optical remote sensing images, this paper proposed a port ship target detection method based on a lightweight multi-scale convolutional network. After verification, the method has a good detection effect on port ships. The network improves the feature expression ability without increasing the computational complexity, and can effectively capture rotation-sensitive features, thereby improving the versatility of rotating samples. The average detection rate of all types of ships in the experiment is 96.92%, and the average false alarm rate is 8.54%. High detection rate of ship target can be guaranteed and various false alarm target interference can be effectively eliminated.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on a port ship target detection method based on lightweight multi-scale convolutional network


    Contributors:
    Hu, Xiaoning (author) / Liu, ShanJunYu (author) / Wu, Zhigang (author) / Chen, Zhuo (author)

    Conference:

    Eighth Symposium on Novel Photoelectronic Detection Technology and Applications ; 2021 ; Kunming,China


    Published in:

    Proc. SPIE ; 12169


    Publication date :

    2022-03-27





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English