Pixel-level Crack Detection using U-Net

• Published in: TENCON ... IEEE Region Ten Conference pp. 0462 - 0466
• Main Authors: Cheng, Jierong, Xiong, Wei, Chen, Wenyu, Gu, Ying, Li, Yusha
• Format: Conference Proceeding
• Language: English
• 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

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...