EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CrackNet: A Hybrid Model for Crack Segmentation with Dynamic Loss Function

Yawen Fan iD, Zhengkai Hu, Qinxin Li, Yang Sun, Jianxin Chen, Quan Zhou iD

Sensors · 06.11.2024 · 24 (22) · 7134

DOI: 10.3390/s24227134 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.11.2024. Verfasst von Yawen Fan und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Engineering Research Center of Communications and Networking, Nanjing University of Posts & Telecommunications, Nanjing 210003, China. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, The Key Technologies and Applications of the Fujian Jiang Mainstream Flood Control Enhancement Project (Fuzhou Section), Project of Sichuan Provincial Key Laboratory of Artificial Intelligence.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cracks are a common form of damage in infrastructure, posing significant risks to both personal safety and property. Along with the development of deep learning, visual-based crack automatic detection has been widely studied. However, this task is still challenging due to complex crack topology, noisy backgrounds, unbalanced categories, etc. To address these challenges, this research proposes a novel hybrid network, named CrackNet, which leverages the strengths of both CNN and transformer. On the encoder side, CNNs are employed to extract multi-level local features, while transformers are used to model global dependencies. Additionally, a strip pooling module is introduced to suppress irrelevant regions and enhance the network’s ability to segment narrow and elongated cracks. On the decoder side, an attention-based skip connection strategy and a mixed up-sampling module are implemented to restore detailed information. Furthermore, a joint learning loss combining Dice and cross-entropy with dynamic weighting is proposed to mitigate the effects of severe class imbalance. CrackNet is trained and evaluated on three public crack datasets, and experimental results show that the proposed model outperforms several well-known deep neural networks, with a particularly noticeable improvement in recall rate.

Schlagwörter

Stichwörter der Autor:innen

class imbalancecrack segmentationdynamic weight losshybrid model

Autor:innen und Institutionen

  • National Engineering Research Center of Communications and Networking, Nanjing University of Posts & Telecommunications, Nanjing 210003, China.
  • Artificial Intelligence of Key Laboratory of Sichuan Province, Sichuan University of Science and Engineering, Yibin 644000, China.
  • College of Harbour, Coastal and Offshore Engineering, Hohai University, Nanjing 210098, China.

ORCID-Profile: Yawen Fan, Quan Zhou

Förderung

  • National Natural Science Foundation of China
  • The Key Technologies and Applications of the Fujian Jiang Mainstream Flood Control Enhancement Project (Fuzhou Section)
  • Project of Sichuan Provincial Key Laboratory of Artificial Intelligence

Zitieren

APA

Fan, Y., Hu, Z., Li, Q., Sun, Y., Chen, J., & Zhou, Q. (2024). CrackNet: A Hybrid Model for Crack Segmentation with Dynamic Loss Function. Sensors, 24(22), 7134. https://doi.org/10.3390/s24227134

Vancouver

Fan Y, Hu Z, Li Q, Sun Y, Chen J, Zhou Q. CrackNet: A Hybrid Model for Crack Segmentation with Dynamic Loss Function. Sensors. 2024;24(22):7134. doi:10.3390/s24227134

BibTeX
@article{Fan2024,
  author = {Fan, Yawen and Hu, Zhengkai and Li, Qinxin and Sun, Yang and Chen, Jianxin and Zhou, Quan},
  title = {CrackNet: A Hybrid Model for Crack Segmentation with Dynamic Loss Function},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {22},
  pages = {7134},
  doi = {10.3390/s24227134}
}
Kostenlos starten →