A Dual-Path CNN and Transformer Network for Continuous Pavement Crack Detection
Sensors · 22.05.2026 · 26 (11) · 3286
DOI: 10.3390/s26113286 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.05.2026. Verfasst von Jinhe Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Geomatics, Liaoning Technical University, Fuxin 123000, China. Die Arbeit nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Department of Science and Technology of Inner Mongolia Autonomous Region.
Abstract (Originalsprache)
Cracks are among the most common pavement distresses, and their timely detection is crucial for road maintenance. Existing methods struggle to completely capture elongated and irregular cracks, often resulting in fragmented detection outputs, which leads to the inaccurate assessment of crack length and affects the reliability of pavement condition evaluation. To address this issue, this paper proposes a dual-path crack segmentation network that integrates CNN and Transformers. The CNN branch incorporates a dynamic multi-branch convolution module to enhance the directional perception and structural modeling of elongated cracks. The Transformer branch employs a lightweight DCNv4 module to replace traditional self-attention mechanisms, effectively capturing long-range dependencies while reducing computational complexity. A multi-path fusion module is designed to achieve the collaborative enhancement of dual-path features, improving the semantic representation of continuous crack regions. Additionally, a combined loss function of BCE and Dice is adopted to alleviate the severe class imbalance between crack and background pixels, further improving the completeness of crack segmentation. Experiments on four datasets, including CFD, DeepCrack537, Gaps384, and Crack500, demonstrate that the proposed model outperforms all compared methods in terms of F-score and mIoU. Ablation studies further validate the effectiveness of the dual-path architecture and its key modules in improving performance. Furthermore, in field validation on real road scenarios, the pavement condition index (PCI) calculated based on the proposed method shows an average deviation of only 0.81 compared to manually interpreted ground truth, demonstrating the practical value of continuous crack detection for pavement maintenance assessment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Geomatics, Liaoning Technical University, Fuxin 123000, China.
- Collaborative Innovation Institute of Geospatial Information Service, Liaoning Technical University, Fuxin 123000, China.
- State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China.
ORCID-Profile: Shangyu Sun, Qiaoshuang Teng
Förderung
- National Natural Science Foundation of China
- Department of Science and Technology of Inner Mongolia Autonomous Region
Zitieren
APA
Zhang, J., Sun, S., Song, W., Li, Y., & Teng, Q. (2026). A Dual-Path CNN and Transformer Network for Continuous Pavement Crack Detection. Sensors, 26(11), 3286. https://doi.org/10.3390/s26113286
Vancouver
Zhang J, Sun S, Song W, Li Y, Teng Q. A Dual-Path CNN and Transformer Network for Continuous Pavement Crack Detection. Sensors. 2026;26(11):3286. doi:10.3390/s26113286
BibTeX
@article{Zhang2026,
author = {Zhang, Jinhe and Sun, Shangyu and Song, Weidong and Li, Yuxuan and Teng, Qiaoshuang},
title = {A Dual-Path CNN and Transformer Network for Continuous Pavement Crack Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {11},
pages = {3286},
doi = {10.3390/s26113286}
}
EUVIMED