EUVIMEDEUVIMED entdecken
Crossref

CrackFormer Network for Pavement Crack Segmentation

Huajun Liu, Jing Yang, Xiangyu Miao, Christoph Mertz, Hui Kong

IEEE Transactions on Intelligent Transportation Systems · 2023-09 · 24 (9) · 9240-9252

DOI: 10.1109/tits.2023.3266776 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2023-09. Verfasst von Huajun Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 194-mal zitiert (Crossref) und nennt 52 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we rethink our earlier work on self-attention based crack segmentation, and propose an upgraded CrackFormer network (CrackFormer-II) for pavement crack segmentation, instead of only for fine-grained crack-detection tasks. This work embeds novel Transformer encoder modules into a SegNet-like encoder-decoder structure, where the basic module is composed of novel Transformer encoder blocks with effective relative positional embedding and long range interactions to extract efficient contextual information from feature-channels. Further, fusion modules of scaling-attention are proposed to integrate the results of each respective encoder and decoder block to highlight semantic features and suppress non-semantic ones. Moreover, we update the Transformer encoder blocks enhanced by the local feed-forward layer and skip-connections, and optimize the channel configurations to compress the model parameters. Compared with the original CrackFormer, the CrackFormer-II is trained and evaluated on more general crack datasets. It achieves higher accuracy than the original CrackFormer, and the state-of-the-art (SOTA) method with $6.7 \times $ fewer FLOPs and $6.2 \times $ fewer parameters, and its practical inference speed is comparable to most classical CNN models. The experimental results show that it achieves the F-measures on Optimal Dataset Scale (ODS) of 0.912, 0.908, 0.914 and 0.869, respectively, on the four benchmarks. Codes are available at https://github.com/LouisNUST/CrackFormer-II.

Zitieren

APA

Liu, H., Yang, J., Miao, X., Mertz, C., & Kong, H. (2023). CrackFormer Network for Pavement Crack Segmentation. IEEE Transactions on Intelligent Transportation Systems, 24(9), 9240-9252. https://doi.org/10.1109/tits.2023.3266776

Vancouver

Liu H, Yang J, Miao X, Mertz C, Kong H. CrackFormer Network for Pavement Crack Segmentation. IEEE Transactions on Intelligent Transportation Systems. 2023;24(9):9240-9252. doi:10.1109/tits.2023.3266776

BibTeX
@article{Liu2023,
  author = {Liu, Huajun and Yang, Jing and Miao, Xiangyu and Mertz, Christoph and Kong, Hui},
  title = {CrackFormer Network for Pavement Crack Segmentation},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2023},
  volume = {24},
  number = {9},
  pages = {9240--9252},
  doi = {10.1109/tits.2023.3266776}
}
Kostenlos starten →