Lightweight CNN–Mamba Hybrid Network for Multi-Scale Concrete Crack Segmentation Using Vision Sensors
Electronics · 25.03.2026 · 15 (7) · 1362
DOI: 10.3390/electronics15071362 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 25.03.2026. Verfasst von Jinfu Guan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Open Research Fund of Anhui Provincial Key Laboratory of Building Earthquake Disaster Mitigation and Green Operations.
Abstract (Originalsprache)
Surface cracking is a key visible indicator of deterioration in concrete infrastructure and is routinely captured by vision sensors during field inspections. To translate inspection imagery into actionable maintenance information, crack delineation must be accurate at the pixel level and robust to challenging conditions where cracks are slender, discontinuous, low-contrast, and easily confused with joints, stains, texture patterns, and illumination artifacts. This study proposes a lightweight CNN–Mamba hybrid segmentation framework built upon Vm-unet for reliable crack mapping under heterogeneous inspection scenarios and resource-constrained deployment. The framework couples boundary-sensitive convolutional features with long-range state-space representations via a spatially modulated convolution design, refines skip-connection features using reciprocal co-modulation attention to suppress background interference, and enhances cross-scale interactions through a decoder interaction fusion scheme to preserve fine-crack continuity and sharp boundaries. Experiments on a multi-source composite dataset and public benchmarks show consistent improvements over representative CNN-, Transformer-, and Mamba-based baselines. The proposed method achieves 80.11% mIoU and 82.05% Dice on the composite dataset, while maintaining an efficient accuracy–cost trade-off (36.049 GFLOPs, 25.991 M parameters). The resulting crack masks provide a dependable basis for inspection-driven quantitative assessment and maintenance decision support.
Förderung
- Open Research Fund of Anhui Provincial Key Laboratory of Building Earthquake Disaster Mitigation and Green Operations
Zitieren
APA
Guan, J., Cui, L., Chen, Y., Yang, C., Wang, J., & Huo, Y. (2026). Lightweight CNN–Mamba Hybrid Network for Multi-Scale Concrete Crack Segmentation Using Vision Sensors. Electronics, 15(7), 1362. https://doi.org/10.3390/electronics15071362
Vancouver
Guan J, Cui L, Chen Y, Yang C, Wang J, Huo Y. Lightweight CNN–Mamba Hybrid Network for Multi-Scale Concrete Crack Segmentation Using Vision Sensors. Electronics. 2026;15(7):1362. doi:10.3390/electronics15071362
BibTeX
@article{Guan2026,
author = {Guan, Jinfu and Cui, Linzhao and Chen, Yanjun and Yang, Chenglin and Wang, Jingwu and Huo, Yinuo},
title = {Lightweight CNN–Mamba Hybrid Network for Multi-Scale Concrete Crack Segmentation Using Vision Sensors},
journal = {Electronics},
year = {2026},
volume = {15},
number = {7},
pages = {1362},
doi = {10.3390/electronics15071362}
}
EUVIMED