COMPARATIVE EVALUATION OF SEMANTIC SEGMENTATION MODELS FOR CRACK DETECTION
DOI:
https://doi.org/10.37943/WAGZ5973Keywords:
crack detection, structural health monitoring, dam inspection, semantic segmentation, deep learning, computer vision, unmanned aerial vehicles, convolutional neural networks, transformer modelsAbstract
Cracks on concrete and asphalt surfaces are an early warning that a dam, a bridge, or a road is starting to fail, and missing them can be expensive. Inspection is increasingly done with drones, which produce far more images than an engineer can check by hand, so the analysis has to be automated. In this paper we compare five semantic segmentation networks for crack detection and, unlike most such comparisons, we push all of them through exactly the same pipeline. Four are convolutional (U-Net, UNet++, DeepLabV3+, and a Feature Pyramid Network) and one is a transformer (SegFormer-B2). Every model sees the same data, the same 320 x 320 inputs, the same augmentation, the same Binary Cross-Entropy plus Dice loss, and the same 0.5 threshold, and all are trained with mixed precision on the public Crack500 benchmark and its official train, validation, and test split. We repeat each training five times with different seeds, report the mean and standard deviation on the test set, and check the gap between the two best models with a paired significance test. To see whether the ranking survives outside Crack500, we then run the trained networks, untouched, on a second dataset (DeepCrack). SegFormer-B2 was the most accurate model on Crack500 (IoU 0.595, F1 0.746), and the t-test shows its margin over UNet++ is well beyond chance. It stayed first on DeepCrack too (IoU 0.704, F1 0.826). We also report parameters, FLOPs, inference time, and memory, so the accuracy can be weighed against the cost of running each model.
References
Albertoni, V. (2019). Structural health monitoring of concrete dams: A review and a case study (Master of Science Thesis). Politecnico di Milano, Faculty of Civil, Environmental and Land Management Engineering, Milan, Italy. https://hdl.handle.net/10589/145613
Oliveira, S., Rodrigues, J., Campos Costa, A., & Mendes, P. (2026). Damage detection in concrete dams using dynamic continuous monitoring and numerical models. In Proceedings of the International Conference on Structural Health Monitoring of Intelligent Infrastructure (pp. 435–442). Taylor & Francis. https://doi.org/10.1201/9781003762553-53
Qi, Y., Lin, P., Yang, G., & Liang, T. (2025). Crack detection and 3D visualization of crack distribution for UAV-based bridge inspection using efficient approaches. Structures, 78, 109075. https://doi.org/10.1016/j.istruc.2025.109075
Ding, W., Yang, H., Yu, K., & Shu, J. (2023). Crack detection and quantification for concrete structures using UAV and transformer. Automation in Construction, 152, 104929. https://doi.org/10.1016/j.autcon.2023.104929
Nguyen, C. K., Kawamura, K., & Nakamura, H. (2023). Deep learning-based crack detection and classification for concrete structures inspection. In Proceedings of the 17th East Asian-Pacific Conference on Structural Engineering and Construction (EASEC 2022) (pp. 710–717). Springer. https://doi.org/10.1007/978-981-19-7331-4_58
Maalej, M., Cherif, R., Yaddaden, Y., & Khoumsi, A. (2022). Automatic crack detection on concrete structure using a deep convolutional neural network and transfer learning. In 2022 2nd International Conference on Advanced Electrical Engineering (ICAEE) (pp. 1–6). IEEE. https://doi.org/10.1109/ICAEE53772.2022.9962029
Merembayev, T., & Amanbek, Y. (2025). Natural fracture network model using Gaussian simulation and machine learning algorithms. Applied Computing and Geosciences, 100258. https://doi.org/10.1016/j.acags.2025.100258
Merembayev, T., & Amanbek, Y. (2023). Natural fracture network model using machine learning approach. In International Conference on Computational Science and Its Applications (pp. 384–397). Springer. https://doi.org/10.1007/978-3-031-37114-1_26
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 234–241). https://doi.org/10.1007/978-3-319-24574-4_28
Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., & Liang, J. (2018). UNet++: A nested U-Net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (pp. 3–11). https://doi.org/10.1007/978-3-030-00889-5_1
Xia, X., Su, J., Wang, Y., Liu, Y., & Li, M. (2024). Lightweight pavement crack detection model based on DeepLabv3+. Laser & Optoelectronics Progress, 61(8), 0812001. https://doi.org/10.3788/LOP231323
Zhou, L., Jia, H., Jiang, S., & Xu, F. (2025). Multi-scale crack detection and quantification of concrete bridges based on aerial photography and improved object detection network. Buildings, 15(7), 1117. https://doi.org/10.3390/buildings15071117
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (pp. 833–851). https://doi.org/10.1007/978-3-030-01234-2_49
Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 936–944). https://doi.org/10.1109/CVPR.2017.106
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems, 34, 12077–12090. https://arxiv.org/abs/2105.15203
Zhou, Y., Yang, Z., Bai, X., & Li, C. (2024). Semantic segmentation of surface cracks in urban comprehensive pipe galleries based on global attention. Sensors, 24(3), 1005. https://doi.org/10.3390/s24031005
Noh, J. (2025). Crack segmentation using U-Net and transformer for surface defect detection. Applied Sciences, 15, 10737. https://doi.org/10.3390/app151910737
Yang, F., Zhang, L., Yu, S., Prokhorov, D., Mei, X., & Ling, H. (2019). Feature pyramid and hierarchical boosting network for pavement crack detection. IEEE Transactions on Intelligent Transportation Systems, 21(4), 1525–1535. https://doi.org/10.1109/TITS.2019.2910595
Owor, N. J., Adu-Gyamfi, Y., Aboah, A., & Amo-Boateng, M. (2025). PaveSAM – Segment anything for pavement distress. Road Materials and Pavement Design, 26(3), 593–617. https://doi.org/10.1080/14680629.2024.2374863
Ge, K., Wang, C., Guo, Y. T., Tang, Y. S., Hu, Z. Z., & Chen, H. B. (2024). Fine-tuning vision foundation model for crack segmentation in civil infrastructures. Construction and Building Materials, 431, 136573. https://doi.org/10.1016/j.conbuildmat.2024.136573
Ye, Z., Lovell, L., Faramarzi, A., & Ninić, J. (2024). SAM-based instance segmentation models for the automation of structural damage detection. Advanced Engineering Informatics, 62, 102826. https://doi.org/10.1016/j.aei.2024.102826
Yang, Y. (2025). A transformer-based pavement crack segmentation model with local perception and auxiliary convolution layers. Electronics, 14(14), 2834. https://doi.org/10.3390/electronics14142834
Wang, J., Zeng, Z., Sharma, P. K., Alfarraj, O., Tolba, A., Zhang, J., & Wang, L. (2024). Dual-path network combining CNN and transformer for pavement crack segmentation. Automation in Construction, 158, 105217. https://doi.org/10.1016/j.autcon.2023.105217
Goo, J. M., Milidonis, X., Artusi, A., Boehm, J., & Ciliberto, C. (2025). Hybrid-Segmentor: A hybrid approach for automated fine-grained crack segmentation in civil infrastructure. Automation in Construction, 170, 105960. https://doi.org/10.1016/j.autcon.2024.105960
Han, C., Yang, H., & Yang, Y. (2024). Enhancing pixel-level crack segmentation with visual Mamba and convolutional networks. Automation in Construction, 168, 105770. https://doi.org/10.1016/j.autcon.2024.105770
Jadon, S. (2020). A survey of loss functions for semantic segmentation. In 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) (pp. 1–7). IEEE. https://doi.org/10.1109/CIBCB48159.2020.9277638
Benavoli, A., Corani, G., Demšar, J., & Zaffalon, M. (2017). Time for a change: A tutorial for comparing multiple classifiers through Bayesian analysis. Journal of Machine Learning Research, 18(77). https://www.jmlr.org/papers/v18/16-305.html
Liu, Y., Yao, J., Lu, X., Xie, R., & Li, L. (2019). DeepCrack: A deep hierarchical feature learning architecture for crack segmentation. Neurocomputing, 338, 139–153. https://doi.org/10.1016/j.neucom.2019.01.036
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1412.6980
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Articles are open access under the Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish a manuscript in this journal agree to the following terms:
- The authors reserve the right to authorship of their work and transfer to the journal the right of first publication under the terms of the Creative Commons Attribution License, which allows others to freely distribute the published work with a mandatory link to the the original work and the first publication of the work in this journal.
- Authors have the right to conclude independent additional agreements that relate to the non-exclusive distribution of the work in the form in which it was published by this journal (for example, to post the work in the electronic repository of the institution or publish as part of a monograph), providing the link to the first publication of the work in this journal.
- Other terms stated in the Copyright Agreement.