In order to meet the practical needs of regular inspection of submarine pipelines, an optical vision inspection method for submarine pipelines mounted on Autonomous Underwater Vehicle (AUV) is proposed. Methods by improving the dark channel algorithm, an adaptive red channel coefficient method was proposed to obtain the submarine pipeline image with higher quality and less noise. The improved Hough transform line feature extraction method is proposed as the strategy of submarine pipeline, so as to reduce the false detection rate and improve the calculation efficiency. The KCF filter is introduced to track the submarine pipeline. The accuracy and accuracy of the proposed algorithm are 94% and meet the requirements of real-time pipeline detection.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    AUV Optical Vision Submarine Pipeline Inspection


    Contributors:


    Publication date :

    2024-05-07


    Size :

    1767668 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Submarine pipeline inspection robot

    ZHANG XIAOFENG | European Patent Office | 2024

    Free access

    Underwater robot meeting submarine pipeline searching and inspection requirements

    QIAN MINGXING / QING CHEN / ZHU JIHONG | European Patent Office | 2022

    Free access


    Submarine pipeline inner wall autonomous inspection underwater vehicle and working method thereof

    ZOU TAO / YU YIFAN / HE ZIXIAO et al. | European Patent Office | 2023

    Free access

    Submarine cable inspection method

    CHEN YIKANG / LI XIAOJUN / ZHU DEGAO et al. | European Patent Office | 2024

    Free access