Crack detection mostly benefits from the rapid development of Convolutional Neural Networks (CNNs). However, the improvement of crack detection performance comes from the deeper and wider network structure, which requires heavier computation and storage overhead. This prevents crack detection methods from being deployed on practical platforms, especially mobile devices. To tackle this problem, we propose a novel Split Exchange Convolution (SEConv) modules, which splits the feature maps into high resolution and low resolution parts and then filters out the redundant information of each part. SEConv exchanges the feature information between the two modules to make the feature efficient reuse. Besides, we design a Multi-Scale Feature Exchange (MSFE) module to promote the cross stage features fusion. Benefiting from the SEConv and the MSFE modules, we build an extremely lightweight crack detection model with only 1.3 M parameters and 8 G FLOPs while achieving comparable performance. Extensive experimental results on the crack detection benchmark show that our method consistently outperforms other state-of-the-art methods in the evaluation metrics of F1-score and MIoU.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Lightweight Network for Crack Detection With Split Exchange Convolution and Multi-Scale Features Fusion


    Beteiligte:
    Zhou, Qiang (Autor:in) / Qu, Zhong (Autor:in) / Ju, Fang-rong (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.03.2023


    Format / Umfang :

    5528866 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Multi-Scale Semantic Map Distillation for Lightweight Pavement Crack Detection

    Wang, Xin / Mao, Zhaoyong / Liang, Zhiwei et al. | IEEE | 2024



    Automatic Pavement Crack Detection by Multi-Scale Image Fusion

    Li, Haifeng / Song, Dezhen / Liu, Yu et al. | IEEE | 2019


    DMF-Net: A Dual-Encoding Multi-Scale Fusion Network for Pavement Crack Detection

    Bai, Suli / Yang, Lei / Liu, Yanhong et al. | IEEE | 2024


    Multi‐scale classification network for road crack detection

    Feng, Hui / Xu, Guo‐sheng / Guo, Yanhui | Wiley | 2019

    Freier Zugriff