EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSP U-Net: Crack Segmentation for Low-Resolution Images Based on Multi-Scale Parallel Attention U-Net

Joon-Hyeok Kim, Ju-Hyeon Noh, Jun-Young Jang, Hee-Deok Yang

Applied Sciences · 11.12.2024 · 14 (24) · 11541

DOI: 10.3390/app142411541 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 11.12.2024. Verfasst von Joon-Hyeok Kim und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the expected lifespans of structures and road approaches, as well as the importance of road maintenance, increase globally, safety inspections have emerged as a crucial task. Nonetheless, the existing crack detection models focus on multi-scale feature loss and performance degradation in learning various types of cracks. We propose the Multi-Scale Parallel Attention U-Net (MSP U-Net) as a network designed for low-resolution images that considers the irregular characteristics of cracks. MSP U-Net applies a large receptive field flock to an attention U-Net, minimizing feature loss across multiple scales. Using the Crack500 dataset, our network achieved a mean intersection of union (mIoU) of 0.7752, outperforming the existing methods on low-resolution images.

Förderung

  • Ministry of Education

Zitieren

APA

Kim, J., Noh, J., Jang, J., & Yang, H. (2024). MSP U-Net: Crack Segmentation for Low-Resolution Images Based on Multi-Scale Parallel Attention U-Net. Applied Sciences, 14(24), 11541. https://doi.org/10.3390/app142411541

Vancouver

Kim J, Noh J, Jang J, Yang H. MSP U-Net: Crack Segmentation for Low-Resolution Images Based on Multi-Scale Parallel Attention U-Net. Applied Sciences. 2024;14(24):11541. doi:10.3390/app142411541

BibTeX
@article{Kim2024,
  author = {Kim, Joon-Hyeok and Noh, Ju-Hyeon and Jang, Jun-Young and Yang, Hee-Deok},
  title = {MSP U-Net: Crack Segmentation for Low-Resolution Images Based on Multi-Scale Parallel Attention U-Net},
  journal = {Applied Sciences},
  year = {2024},
  volume = {14},
  number = {24},
  pages = {11541},
  doi = {10.3390/app142411541}
}
Kostenlos starten →