Periodically monitoring the pavement cracks is of great importance to many transportation infrastructures. This paper proposed an unsupervised deep-learning-based method to match the cracks in multi-temporal unmanned aerial vehicle (UAV) images and identify the changes of pavement cracks over time. A regional focus module was specially designed to enforce the network to focus on regions where cracks were located and enhance its capacity for small-crack identification. Moreover, a data augmentation method which combined Poisson blending and random projective transformations was introduced for generating images with crack variations for model training. The superiority of the method was validated using actual image collected from real pavements. The experimental results showed that the proposed method outperformed the feature-based method and existing unsupervised deep learning-based UAV image registration method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Pavement Crack Registration and Change Identification Method Based on Unsupervised Deep Neural Network


    Contributors:
    Wang, Zhengfang (author) / Zhu, Hongliang (author) / Yang, Yujie (author) / Jiang, Haonan (author) / Li, Wenhao (author) / Li, Bingrui (author) / Li, Peng (author) / Xu, Lei (author) / Sui, Qingmei (author) / Wang, Jing (author)


    Publication date :

    2025-01-01


    Size :

    2241465 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Automatic Pavement Crack Recognition Based on BP Neural Network

    Li Li / Lijun Sun / Guobao Ning et al. | DOAJ | 2014

    Free access


    Automatic Pavement Crack Identification Based on an Improved C-Mask Region-Based Convolutional Neural Network Model

    Xiao, Liyang / Li, Wei / Deng, Nanyi et al. | Transportation Research Record | 2022


    Recognition of asphalt pavement crack length using deep convolutional neural networks

    Tong, Zheng / Gao, Jie / Han, Zhenqiang et al. | British Library Online Contents | 2018


    Grid-based pavement crack analysis using deep learning

    Wang, Xianglong / Hu, Zhaozheng | IEEE | 2017