Pavement defect segmentation is a fundamental task in the field of transport infrastructure inspection. Existing methods mainly focus on detection/segmentation for long and thin cracks. However, there are many other types of defects with various sizes and shapes that are also essential to segment, which brings more challenges toward detailed road inspection. To address the above problems and provide a more comprehensive understanding of the overall road conditions, we propose a three-stream neural network that combines spatial, contextual and boundary information for fine-grained defect segmentation. Specifically, the spatial stream captures rich low-level spatial features. The contextual stream utilizes an attention mechanism and models high-level contextual relationships over local features. To further refine the segmentation results, the boundary stream encodes detailed boundaries using a global gated convolution and generates additional boundary maps. By combining the above different information, our model can effectively produce pixel-wise predictions for fine-grained road inspection. The network is trained using a dual-task loss in an end-to-end manner, and experiments were performed on three newly collected datasets, i.e., a fine-grained defect dataset and two crack datasets, which shows that the proposed method achieves favorable segmentation results on complex multi-class defects, and is also able to segment single-class cracks. Specifically, on the fine-grained dataset, it achieved state-of-the-art performance over other competing baselines (mPA of 0.54, mIoU of 0.38, Mic_F of 0.78 and Mac_F of 0.65), where each image is resized to 512 $\times 512$ and the processing speed is 21 FPS on average.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Beyond Crack: Fine-Grained Pavement Defect Segmentation Using Three-Stream Neural Networks


    Beteiligte:
    Zhang, Yujia (Autor:in) / Wu, Junxian (Autor:in) / Li, Qianzhong (Autor:in) / Zhao, Xiaoguang (Autor:in) / Tan, Min (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2022-09-01


    Format / Umfang :

    12641818 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    CrackFormer Network for Pavement Crack Segmentation

    Liu, Huajun / Yang, Jing / Miao, Xiangyu et al. | IEEE | 2023


    CrackW-Net: A Novel Pavement Crack Image Segmentation Convolutional Neural Network

    Han, Chengjia / Ma, Tao / Huyan, Ju et al. | IEEE | 2022


    Pavement friction reduction due to fine-grained earth contaminants

    Hall,G.J. / Painter,J. / Hall Consulting,US et al. | Kraftfahrwesen | 2007


    Mix design for fine-grained exposed aggregate PCC pavement

    Park, Cheolwoo | Online Contents | 2011