Pixel-level Crack Detection using U-Net

In this paper, we proposed an automatic crack detection method based on deep convolutional neural network −U-Net [4]. Unlike existing machine learning based crack detection methods, we can process an image as a whole without patchifying, thanks to the encoder-decoder structure of U-Net. The segmenta...

Full description

Saved in:
Bibliographic Details
Published inTENCON ... IEEE Region Ten Conference pp. 0462 - 0466
Main Authors Cheng, Jierong, Xiong, Wei, Chen, Wenyu, Gu, Ying, Li, Yusha
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2018
Subjects
Conferences
convolutional neural network
crack detection
crack segmentation
IEEE Regions
Image segmentation
Roads
Surface cracks
Testing
Training
U-Net
Online AccessGet full text

Cover

More Information
Summary:In this paper, we proposed an automatic crack detection method based on deep convolutional neural network −U-Net [4]. Unlike existing machine learning based crack detection methods, we can process an image as a whole without patchifying, thanks to the encoder-decoder structure of U-Net. The segmentation result is output from the network as a whole, instead of aggregation from neighborhood patches. In addition, a new cost function based on distance transform is introduced to assign pixel-level weight according to the minimal distance to the ground truth segmentation. In experiments, we test the proposed method on two datasets of road crack images. The pixel-level segmentation accuracy is above 92% which outperforms other state-of-the-art methods significantly.
ISSN:2159-3450
DOI:10.1109/TENCON.2018.8650059