用特征金字塔网络提升桥梁钢箱梁裂纹检测精度与效率
Deep Learning-Based Fatigue Cracks Detection in Bridge Girders using Feature Pyramid Networks
- 采用特征金字塔网络捕捉裂纹多尺度特征
- 图像分割法比缩放法更精准，且保持高计算效率
- 适合桥梁巡检自动化与智能运维场景
针对结构健康监测中持续自动裂纹检测的难题，本研究提出一种基于特征金字塔网络（FPN）的框架，用于从高分辨率图像中自动分割钢箱梁裂纹。考虑裂纹的多尺度特性，采用两种输入处理方式：图像缩放和分块处理。对120张原始图像进行处理后，构建了基于FPN结构的检测模型。结果表明，所有模型均可在原始图像上自动识别裂纹。图像缩放方法提升了计算效率，且未降低精度；由于裂纹具有可分离特性，分块方法生成的裂纹分割结果优于缩放方法。因此，对于高分辨率图像，结合分块策略的FPN结构是裂纹分割与检测的高效解决方案。
原文摘要 · Abstract (English)
For structural health monitoring, continuous and automatic crack detection has been a challenging problem. This study is conducted to propose a framework of automatic crack segmentation from high-resolution images containing crack information about steel box girders of bridges. Considering the multi-scale feature of cracks, convolutional neural network architecture of Feature Pyramid Networks (FPN) for crack detection is proposed. As for input, 120 raw images are processed via two approaches (shrinking the size of images and splitting images into sub-images). Then, models with the proposed structure of FPN for crack detection are developed. The result shows all developed models can automatically detect the cracks at the raw images. By shrinking the images, the computation efficiency is improved without decreasing accuracy. Because of the separable characteristic of crack, models using the splitting method provide more accurate crack segmentations than models using the resizing method. Therefore, for high-resolution images, the FPN structure coupled with the splitting method is an promising solution for the crack segmentation and detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。