Concrete Crack Segmentation Algorithm Based on Hybrid-Attention Feature Enhancement
Buildings · 30.07.2026 · 16 (15) · 3031
DOI: 10.3390/buildings16153031 ↗Kurz gefasst
Fachartikel in der Zeitschrift Buildings, online erschienen am 30.07.2026. Verfasst von Tiecheng Yan und 3 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qingyang City Science and Technology Talents Special Plan Project, Qingyang City Basic Research Project, 2023 University Teachers’ Innovation Fund Project.
Abstract (Originalsprache)
For surface crack detection in in-service concrete buildings, this study proposes DCFYOLO, a lightweight crack instance segmentation algorithm improved from YOLO11n-seg, which enhances feature representation and multi-scale contextual fusion to improve crack detection and segmentation performance in complex scenarios. Frequency Channel Attention (FCA) is introduced into the C3k2 units of the backbone network, where multi-scale pooling extracts multi-spectral information to enhance channel-level feature discrimination. Context Anchor Attention (CAA) is added to the PAN-FPN structure in the neck to address multi-scale feature fusion and long-range context modeling in complex scenes. A Dynamic Snake Convolution with Efficient Channel Attention (DSECA) module is constructed by combining dynamic snake convolution and efficient channel attention. Through a serial design, this module provides the multi-scale feature fusion process with both geometrically adaptive sampling and channel-discriminative optimization. Experimental results on the DeepCrack dataset show that DCFYOLO achieves 73.2% Box mAP@0.5 and 67.4% Mask mAP@0.5 with 2.47 M parameters, improving the baseline YOLO11n-seg by 2.8 and 2.7 percentage points, respectively. Ablation experiments verify the independent contribution of each improved module. The algorithm demonstrates a balance between segmentation accuracy and inference efficiency under lightweight constraints on the DeepCrack dataset, and can provide a reference for research on concrete surface crack instance segmentation.
Förderung
- Qingyang City Science and Technology Talents Special Plan Project
- Qingyang City Basic Research Project
- 2023 University Teachers’ Innovation Fund Project
- Cooperative Project between China Railway No. 3 Engineering Group Co., Ltd. and Longdong University
Zitieren
APA
Yan, T., Zhang, X., Li, P., & Fan, B. (2026). Concrete Crack Segmentation Algorithm Based on Hybrid-Attention Feature Enhancement. Buildings, 16(15), 3031. https://doi.org/10.3390/buildings16153031
Vancouver
Yan T, Zhang X, Li P, Fan B. Concrete Crack Segmentation Algorithm Based on Hybrid-Attention Feature Enhancement. Buildings. 2026;16(15):3031. doi:10.3390/buildings16153031
BibTeX
@article{Yan2026,
author = {Yan, Tiecheng and Zhang, Xingyuan and Li, Ping and Fan, Bingxin},
title = {Concrete Crack Segmentation Algorithm Based on Hybrid-Attention Feature Enhancement},
journal = {Buildings},
year = {2026},
volume = {16},
number = {15},
pages = {3031},
doi = {10.3390/buildings16153031}
}
EUVIMED