基于特征金字塔网络的超大尺寸图像的裂缝识别检测方法
DOI:
作者:
作者单位:

浙江大学

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(U1709216);国家重点研发计划(2018YFE0125400)


Crack detection method based on feature pyramid network for super large-scale images
Author:
Affiliation:

Zhejiang University

Fund Project:

National Natural Science Foundation of China (No. U1709216); The National Key Research and Development Program of China (No. 2018YFE0125400)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    基于图像分析的裂缝自动检测识别一直是桥梁结构健康检测的热点问题之一。深度学习作为裂缝检测的重要解决方法,需要大量的数据的支持。公开数据集提供的小尺寸裂缝图像不足以解决超大尺寸的细长裂缝图像的检测问题。本研究提出了一个基于特征金字塔深度学习网络的超大尺寸图像中细长裂缝的检测方法。通过对编码器提取的四个不同层次的特征图分别进行预测,网络能够实现对细小裂缝的高精度分割。实验使用了120张大小为3264×4928像素的桥钢箱梁表面裂缝图像对特征金字塔网络进行训练、测试;并将本方法获得的训练模型与通过双线性插值方法缩放图像至1600×2400像素和2112×3168像素两种规格生成的数据集的训练后的模型进行对比。结果表明:本方法能够在对比测试中能够获得最高的裂缝检测交并比(IoU)为0.78,和最低的Dice Loss为0.12。测试中,裂缝检测图像显示,缩放图像会导致部分裂缝信息的丢失,本方法能够稳定的保留裂缝信息,并实现复杂背景下超大尺寸图像中的细长裂缝高精度自动检测。

    Abstract:

    Automatic crack detection based on image analysis is a hot issue in bridge structure health inspection. Crack segmentation based on deep learning is a significant solution, which needs lots database. The small-scale crack images of open datasets are not enough for the detection of long and thin cracks of super large-scale image. The study proposes an automatic crack detection method for super large-scale images, based on feature pyramid network. Through four different feature maps in various sizes, the proposed network yields predictions, respectively, which means a highly precise crack segmentation. Experiments are carried on 120 steel box girder crack images in a resolution of 3264 × 4928. These images are used to train and test the network in our method. The comparison study is conducted between our method and the models trained with crack images resized into 1600 × 2400 and 2112 × 3168 with bilinear interpolation algorithm. The results show that our method can achieve the highest crack Intersection over Union (IoU) of 0.78, and the lowest Dice Loss of 0.12 in the comparison study. The predictions of crack images in testing indicate that resizing images sometimes result in the loss of crack information, and our method can maintain the detail of cracks and detect cracks of super large-scale images automatically and precisely.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-04-28
  • 最后修改日期:2021-07-22
  • 录用日期:2021-07-31
  • 在线发布日期:
  • 出版日期: