Chinese Journal of Ship Research, Volume. 19, Issue 5, 95(2024)

Ship crack detection method based on lightweight fast convolution and bidirectional weighted feature fusion network

Chong WANG1...2 and Yuhui ZHU12 |Show fewer author(s)
Author Affiliations
  • 1Key Laboratory of High Performance Ship Technology of Ministry of Education, Wuhan University of Technology, Wuhan 430063, China
  • 2School of Naval Architecture, Ocean and Energy Power Engineering, Wuhan University of Technology, Wuhan 430063, China
  • show less

    Objective

    As traditional ship crack detection methods based on artificial visual inspection and ultrasonic methods in ship repair and inspection processes have the characteristics of low efficiency, high cost and high danger, a ship crack detection method based on deep learning is proposed.

    Methods

    First, a lightweight convolutional structure (GSConv) is used to replace the standard convolution and introduce an attention mechanism in the backbone of YOLOv5s to achieve the reduction of network parameters and computational complexity while enhancing the ability to extract crack features. Second, C3_Faster constructed by a fast convolutional structure is used instead of the original C3 module in the neck of the network to improve the processing speed of the model and enhance its rapidity. Finally, an improved bidirectional weighted feature fusion network (BiFFN) is used to enrich the semantic and positional information of cracks in the feature map and improve the model's crack identification accuracy and location precision.

    Results

    By training on both original and augmented ship crack datasets, the proposed method achieves a detection accuracy of over 94.11% and a recall rate of over 93.50%, while reducing the computational complexity by 17.93% and parameter count by 15.81%.

    Conclusion

    This study demonstrates that the proposed ship crack detection method based on GSConv and BiFFN achieves lightweight model architecture and high detection accuracy and recall rates, providing useful references for the development of UAV/ship autonomous inspection systems.

    Keywords
    Tools

    Get Citation

    Copy Citation Text

    Chong WANG, Yuhui ZHU. Ship crack detection method based on lightweight fast convolution and bidirectional weighted feature fusion network[J]. Chinese Journal of Ship Research, 2024, 19(5): 95

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Ship Structure and Fittings

    Received: Jun. 7, 2023

    Accepted: --

    Published Online: Mar. 14, 2025

    The Author Email:

    DOI:10.19693/j.issn.1673-3185.03401

    Topics