EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamic Dual-Branch Encoder and Deformable Spatial Focusing for Accurate Pavement Crack Segmentation

Ruikang Liu, Zixiao Wang, Cheng Zha iD, Kaijing Song, Lu Hu

Entropy · 01.07.2026 · 28 (7) · 740

DOI: 10.3390/e28070740 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 01.07.2026. Verfasst von Ruikang Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Software Engineering, East China Jiaotong University, Nanchang 330013, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Jiangxi Province, National Natural Science Foundation of China, Early-Career Young Scientists and Technologists Project of Jiangxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pavement crack segmentation is crucial for enhancing traffic safety, improving maintenance efficiency, extending road lifespan, and supporting smart city development. Utilising computer vision technology to automate crack detection can significantly reduce time and labour costs, improving both accuracy and efficiency. However, pavement crack images exhibit complex visual features, irregular distributions, and diverse shapes and textures, posing challenges for accurate segmentation. To address these issues, a pavement crack segmentation network (PCSNet) based on a dynamic dual-branch encoder and deformable spatial focusing is proposed. The dual-branch encoder employs pre-trained and self-trained branches to extract general and specific crack features, respectively. Dynamic feature fusion optimises the contribution of each branch, enhancing model generalisation. The deformable spatial focusing module refines crack morphological features, improving the model’s ability to identify and localise cracks of varying shapes. Extensive experiments on the DeepCrack dataset show that PCSNet achieves precision, recall, F1 score, and Mean Intersection over Union of 85.34%, 86.16%, 85.75% and 75.23%, respectively, outperforming all comparative methods, thereby validating its superiority.

Schlagwörter

Stichwörter der Autor:innen

deep learningdual-branch encoderdynamic feature fusionpavement crack segmentation

Autor:innen und Institutionen

  • School of Information and Software Engineering, East China Jiaotong University, Nanchang 330013, China.
  • JiangXi ShineTech Precision Optical Co., Ltd., Xinyu 336600, China.

ORCID-Profile: Cheng Zha

Förderung

  • Natural Science Foundation of Jiangxi Province
  • National Natural Science Foundation of China
  • Early-Career Young Scientists and Technologists Project of Jiangxi Province

Zitieren

APA

Liu, R., Wang, Z., Zha, C., Song, K., & Hu, L. (2026). Dynamic Dual-Branch Encoder and Deformable Spatial Focusing for Accurate Pavement Crack Segmentation. Entropy, 28(7), 740. https://doi.org/10.3390/e28070740

Vancouver

Liu R, Wang Z, Zha C, Song K, Hu L. Dynamic Dual-Branch Encoder and Deformable Spatial Focusing for Accurate Pavement Crack Segmentation. Entropy. 2026;28(7):740. doi:10.3390/e28070740

BibTeX
@article{Liu2026,
  author = {Liu, Ruikang and Wang, Zixiao and Zha, Cheng and Song, Kaijing and Hu, Lu},
  title = {Dynamic Dual-Branch Encoder and Deformable Spatial Focusing for Accurate Pavement Crack Segmentation},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {7},
  pages = {740},
  doi = {10.3390/e28070740}
}
Kostenlos starten →