As technology advances, the use of unmanned aerial vehicles (UAVs) and image sensors for structural monitoring and diagnostics is becoming increasingly critical. This approach enables the efficient inspection and assessment of structural conditions. Furthermore, the integration of deep learning techniques has been proven to be highly effective in detecting damage from structural images, as demonstrated in our study. To enable effective learning by deep learning models, a substantial volume of data is crucial, but collecting appropriate instances of structural damage from real-world scenarios poses challenges and demands specialized knowledge, as well as significant time and resources for labeling. In this study, we propose a methodology that utilizes a generative adversarial network (GAN) for image-to-image translation, with the objective of generating synthetic structural damage data to augment the dataset. Initially, a GAN-based image generation model was trained using paired datasets. When provided with a mask image, this model generated an RGB image based on the annotations. The subsequent step generated domain-specific mask images, a critical task that improved the data augmentation process. These mask images were designed based on prior knowledge to suit the specific characteristics and requirements of the structural damage dataset. These generated masks were then used by the GAN model to produce new RGB image data incorporating various types of damage. In the experimental validation conducted across the three datasets to assess the image generation for data augmentation, our results demonstrated that the generated images closely resembled actual images while effectively conveying information about the newly introduced damage. Furthermore, the experimental validation of damage detection with augmented data entailed a comparative analysis between the performance achieved solely with the original dataset and that attained with the incorporation of additional augmented data. The results for damage detection consistently demonstrated that the utilization of augmented data enhanced performance when compared to relying solely on the original images.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Image-to-Image Translation-Based Structural Damage Data Augmentation for Infrastructure Inspection Using Unmanned Aerial Vehicle


    Beteiligte:
    Gi-Hun Gwon (Autor:in) / Jin-Hwan Lee (Autor:in) / In-Ho Kim (Autor:in) / Seung-Chan Baek (Autor:in) / Hyung-Jo Jung (Autor:in)


    Erscheinungsdatum :

    2023




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    Unmanned aerial vehicle inspection equipment and image fusion method

    GONG CHAO / JUTTE / PAN FENG et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Inspection unmanned aerial vehicle

    LI WEI / LIU TIEJUN / YOU BINGBING et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    INSPECTION UNMANNED AERIAL VEHICLE

    GONG CHENG / CHEN HUI | Europäisches Patentamt | 2022

    Freier Zugriff

    Unmanned aerial vehicle depth image acquisition method and unmanned aerial vehicle

    CHEN YOUSHENG | Europäisches Patentamt | 2016

    Freier Zugriff

    Inspection unmanned aerial vehicle

    YANG XIUYU / HUO DONG / SHAO BIN et al. | Europäisches Patentamt | 2023

    Freier Zugriff