One-step deep learning-based method for pixel-level detection of fine cracks in steel girder images

被引:8
|
作者
Li, Zhihang [1 ]
Huang, Mengqi [1 ]
Ji, Pengxuan [1 ]
Zhu, Huamei [1 ]
Zhang, Qianbing [1 ]
机构
[1] Monash Univ, Dept Civil Engn, Clayton, Vic 3800, Australia
关键词
CNN; crack detection; data imbalance; feature extraction; loss function;
D O I
10.12989/sss.2022.29.1.153
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by
引用
收藏
页码:153 / 166
页数:14
相关论文
empty
未找到相关数据