CrackW-Net: A Novel Pavement Crack Image Segmentation Convolutional Neural Network
CrackW-Net: A Novel Pavement Crack Image Segmentation Convolutional Neural Network
Chengjia Han,Tengyu Ma,2 Authors,Yanning Zhang
2022 · DOI: 10.1109/TITS.2021.3095507
158 Citations
TLDR
A skip-level round-trip sampling block structure with the implementation of convolutional neural networks is proposed, thereby constructed a novel pixel level semantic segmentation network called CrackW-Net, which performs the best in the task of pavement crack segmentation.