In this paper, we rethink our earlier work on self-attention based crack segmentation, and propose an upgraded CrackFormer network (CrackFormer-II) for pavement crack segmentation, instead of only for fine-grained crack-detection tasks. This work embeds novel Transformer encoder modules into a SegNet-like encoder-decoder structure, where the basic module is composed of novel Transformer encoder blocks with effective relative positional embedding and long range interactions to extract efficient contextual information from feature-channels. Further, fusion modules of scaling-attention are proposed to integrate the results of each respective encoder and decoder block to highlight semantic features and suppress non-semantic ones. Moreover, we update the Transformer encoder blocks enhanced by the local feed-forward layer and skip-connections, and optimize the channel configurations to compress the model parameters. Compared with the original CrackFormer, the CrackFormer-II is trained and evaluated on more general crack datasets. It achieves higher accuracy than the original CrackFormer, and the state-of-the-art (SOTA) method with $6.7 \times $ fewer FLOPs and $6.2 \times $ fewer parameters, and its practical inference speed is comparable to most classical CNN models. The experimental results show that it achieves the F-measures on Optimal Dataset Scale (ODS) of 0.912, 0.908, 0.914 and 0.869, respectively, on the four benchmarks. Codes are available at https://github.com/LouisNUST/CrackFormer-II.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    CrackFormer Network for Pavement Crack Segmentation


    Beteiligte:
    Liu, Huajun (Autor:in) / Yang, Jing (Autor:in) / Miao, Xiangyu (Autor:in) / Mertz, Christoph (Autor:in) / Kong, Hui (Autor:in)


    Erscheinungsdatum :

    2023-09-01


    Format / Umfang :

    3586217 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



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

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


    A Large-Scale Benchmark for Pavement Crack Segmentation

    Chen, Wei / Zhang, Xiaoxiang / Zhao, Qianqian et al. | IEEE | 2023


    The Improvement of Automated Crack Segmentation on Concrete Pavement with Graph Network

    Jiang Chen / Ye Yuan / Hong Lang et al. | DOAJ | 2022

    Freier Zugriff

    PAF-Net: A Progressive and Adaptive Fusion Network for Pavement Crack Segmentation

    Yang, Lei / Huang, Hanyun / Kong, Shuyi et al. | IEEE | 2023


    Deep Learning-Based Real-Time Crack Segmentation for Pavement Images

    Wang, Wenjun / Su, Chao | Springer Verlag | 2021