In order to improve the intelligence level of power grid operation and enhance the credibility of rust defect detection in power equipment, this paper addresses the significant differences in image quality in actual situations of unmanned aerial vehicle (UAV) inspection. A rust detection method incorporating an attention mechanism into the Faster R-CNN model and considering background brightness and gamma transformation is proposed. This method can adaptively normalize the images and effectively identify rust areas in complex backgrounds, large brightness differences, and noise-contaminated conditions. By introducing three assessment indicators: rust rate, rust confidence, and rust heat map, comprehensive rust defect information is provided to maintenance personnel, ensuring the safe and stable operation of power equipment.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on the Application of Deep Learning Object Detection in Rust Defect Detection of Power Equipment


    Contributors:
    Xu, Bo (author) / Ding, Yuan (author)


    Publication date :

    2023-07-21


    Size :

    669054 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Research on deep learning method for rail surface defect detection

    Feng, Jiang Hua / Yuan, Hao / Hu, Yun Qing et al. | Wiley | 2020

    Free access

    Research on deep learning method for rail surface defect detection

    Feng, Jiang Hua / Yuan, Hao / Hu, Yun Qing et al. | IET | 2020

    Free access

    Research on ship object detection based on deep learning

    Jin, Junkuan / Xiao, Yingjie | SPIE | 2024


    Rail surface defect detection based on deep learning

    Li, Xiaoqing / Zhou, Ying / Chen, Hu | SPIE | 2020


    DEFECT DETECTION OF BOTTLED LIQUOR BASED ON DEEP LEARNING

    Zhang, X. / Yan, L. / Yan, H. | TIBKAT | 2021