The scarcity of rail surface defect samples is the main factor that affects the direct application of deep learning methods to rail surface defect recognition. This paper proposes a method for enhancing orbital defect samples based on Deep Convolution Generating Adversarial Network (DCGAN). First, analyze the reasons for the disappearance of the gradient of the DCGAN generator network, and demonstrate from the mathematical deduction that DCGAN does not completely solve the problem of the disappearance of the gradient; then, by adding noise to the real image and the generated image at the same time to guide the learning process of the sample distribution, JS is realized (Jensen-Shannon) Divergence optimization; Finally, experimental demonstration. The experimental results show that this method effectively realizes the feature restoration of the defect samples in addition to improving the stability of the training process, provides sufficient and effective sample data for the application of deep learning in the detection of track defects, and has certain application value.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Enhancement Method of Track Defect Sample Based on Deep Convolution Generative Adversarial Network


    Contributors:
    Yifan, Li (author) / Yongzhi, Min (author) / Banghuan, Lv (author)


    Publication date :

    2020-10-14


    Size :

    328577 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Fuzzy evidence track association method based on data cleaning and generative adversarial network

    ZHOU ZHIGUO / CAO YUPENG / ZHOU XUEHUA | European Patent Office | 2022

    Free access

    Traffic accident data quality enhancement method based on generative adversarial network

    ZHOU BEI / ZHANG SHENGRUI / ZHANG YING et al. | European Patent Office | 2023

    Free access

    A Generative Adversarial Network-Based Method for LiDAR-Assisted Radar Image Enhancement

    Thilakanayake, Thakshila / De Silva, Oscar / Wanasinghe, Thumeera R. et al. | IEEE | 2024


    Improved Generative Adversarial Network Method for Flight Crew Dialog Speech Enhancement

    Chen, Nongtian / Ning, Weifeng / Man, Yongzheng et al. | AIAA | 2023

    Free access