Visual detection of cracks in facades of self-built dwellings in Huancayo using deep learning
DOI:
https://doi.org/10.18537/est.v016.n031.a10Keywords:
deep learning, self-constructed housing, crack detection, instance segmentation, image analysisAbstract
In Huancayo, self-constructed dwellings without technical supervision pose a concern within the regional seismic context, particularly when exhibiting visible damage on their facades. This study developed a deep learning–based tool for the preliminary identification of facade elements and visible cracks in images. Two specialized Mask R-CNN instance segmentation models were implemented in Detectron2: one for walls, columns, and openings, and another for cracks incorporating PointRend. Evaluation was conducted on independent test subsets using COCO and operational metrics. For bounding boxes, the facade and crack models achieved AP50 values of 59.87% and 65.16%; for instance segmentation, the AP50 values were 58.30% and 61.13%, with an AP of 20.03% for crack instance segmentation. F1-scores were 65.82% and 72.15% for bounding boxes, and 63.91% and 74.49% for segmentation. The results indicate moderate performance, supporting the tool’s use as an aid for preliminary visual documentation of facades.
Downloads
References
Abid, A., Abdalla, A., Abid, A., Khan, D., Alfozan, A., & Zou, J. (2019). Gradio: Hassle-free sharing and testing of ML models in the wild. arXiv. https://arxiv.org/abs/1906.02569
Aravena, P., Geiß, C., Aguirre, P., Santa María, H., Merino, Y., & Taubenböck, H. (2021). Automated building characterization for seismic risk assessment using street-level imagery and deep learning. ISPRS Journal of Photogrammetry and Remote Sensing, 180, 370–386. https://doi.org/10.1016/j.isprsjprs.2021.07.004
Bai, Y., Zha, B., Sezen, H., & Yilmaz, A. (2023). Engineering deep learning methods on automatic detection of damage in infrastructure due to extreme events. Structural Health Monitoring, 22(1), 338-352. https://doi.org/10.1177/14759217221083649
Bischl, B., Binder, M., Lang, M., Pielok, T., Richter, J., Coors, S., Thomas, J., Ullmann, T., Becker, M., Boulesteix, A.-L., Deng, D., & Lindauer, M. (2023). Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges. WIREs Data Mining and Knowledge Discovery, 13(2), e1484. https://doi.org/10.1002/widm.1484
Cha, Y.-J., Choi, W., & Büyüköztürk, O. (2017). Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering, 32(5), 361–378. https://doi.org/10.1111/mice.12263
Cha, Y.-J., Ali, R., Lewis, J., & Büyüköztürk, O. (2024). Deep learning-based structural health monitoring. Automation in Construction, 161, 105328. https://doi.org/10.1016/j.autcon.2024.105328
Choi, Y., Bae, B., Han, T. H., & Ahn, J. (2024). Application of Mask R-CNN and YOLOv8 algorithms for concrete crack detection. IEEE Access, 12, 165314-165321. https://doi.org/10.1109/ACCESS.2024.3469951
Dong, C., & Catbas, F. N. (2020). A review of computer vision–based structural health monitoring at local and global levels. Structural Health Monitoring, 20(2), 692–743. https://doi.org/10.1177/1475921720935585
Ferguson, M., Ak, R., Lee, Y. T., & Law, K. H. (2018). Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning. Smart and Sustainable Manufacturing Systems, 2(1), 137-164. https://doi.org/10.1520/SSMS20180033
García, M. E. (2022). Riesgo sísmico de las viviendas autoconstruidas en el barrio de Yanama del distrito de Huancayo [Tesis de maestría, Universidad Nacional del Centro del Perú]. http://hdl.handle.net/20.500.12894/8854
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Gouveia, F., Silva, V., Lopes, J., Moreira, R. S., Torres, J. M., & Guerreiro, M. S. (2024). Automated identification of building features with deep learning for risk analysis. Discover Applied Sciences, 6, 466. https://doi.org/10.1007/s42452-024-06070-2
Kandel, I., & Castelli, M. (2020). The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset. ICT Express, 6(4), 312–315. https://doi.org/10.1016/j.icte.2020.04.010
Kirillov, A., Wu, Y., He, K., & Girshick, R. (2020). PointRend: Image segmentation as rendering. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 9796–9805). https://doi.org/10.1109/CVPR42600.2020.00982
Koch, C., Georgieva, K., Kasireddy, V., Akinci, B., & Fieguth, P. (2015). A review on computer vision-based defect detection and condition assessment of concrete and asphalt civil infrastructure. Advanced Engineering Informatics, 29(2), 196–210. https://doi.org/10.1016/j.aei.2015.01.008
Kong, C., & Petchsasithon, A. (2024). Information acquisition and seismic damage prediction of masonry structures in rural areas based on UAV inclined photogrammetry. Journal of Information Systems Engineering and Management, 9(1), 25183. https://doi.org/10.55267/iadt.07.14315
Miseta, T., Fodor, A., & Vathy-Fogarassy, Á. (2024). Surpassing early stopping: A novel correlation-based stopping criterion for neural networks. Neurocomputing, 567, 127028. https://doi.org/10.1016/j.neucom.2023.127028
Mohtasham, M., Vahidnia, S., Ghasemzadeh, L., Ozturk, Y. E., Yuvalaklioglu, M., Akin, S., & Ure, N. K. (2020). Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines. Structural Health Monitoring, 19(5), 1440–1452. https://doi.org/10.1177/1475921719883202
Nakamura, K., Derbel, B., Won, K.-J., & Hong, B.-W. (2021). Learning-rate annealing methods for deep neural networks. Electronics, 10(16), 2029. https://doi.org/10.3390/electronics10162029
Obi-Obuoha, A., Rizama, V. S., Okafor, I., Ovwenkekpere, H. E., Obe, K., & Ekundayo, J. (2024). Real-time traffic object detection using Detectron 2 with Faster R-CNN. World Journal of Advanced Research and Reviews, 24(02), 2173–2189. https://doi.org/10.30574/wjarr.2024.24.2.3559
Osman, A. H. (2025). Cracks Computer Vision Dataset [Open source dataset]. Roboflow Universe. https://universe.roboflow.com/albaraa-hussein-osman/cracks-tfqny
Padsumbiya, M., Brahmbhatt, V., & Thakkar, S. P. (2022). Automatic crack detection using convolutional neural network. Journal of Soft Computing in Civil Engineering, 6(3), 1–17. https://doi.org/10.22115/scce.2022.325596.1397
Palomino Ojeda, J., Quiñones Huatangari, L., Revilla Arce, J., Arce Fernández, N., Gonzales Santiesteban, M., & Martínez Serrano, M. (2024). Assembly algorithms for seismic vulnerability estimation in confined masonry dwellings. International Journal of Safety and Security Engineering, 14(3), 967-984. https://doi.org/10.18280/ijsse.140327
Pandey, V., & Mishra, S. S. (2025). A review of image-based deep learning methods for crack detection. Multimedia Tools and Applications, 84, 35469–35511. https://doi.org/10.1007/s11042-025-20729-x
Roy, S., Yogi, B., Majumdar, R., Ghosh, P., & Das, S. K. (2025). Deep learning-based crack detection and prediction for structural health monitoring. Discover Applied Sciences, 7, 674. https://doi.org/10.1007/s42452-025-07272-y
Tavera, H., Nina, V., Bernal, I., & Mercado, A. (2025). Analysis and evaluation of recent deformation on the Huaytapallana Fault (Central Region of Peru) based on data obtained from a local seismic network. Seismological Research Letters, 96(3), 1687–1702. https://doi.org/10.1785/0220240257
Vilares Ferro, M., Doval Mosquera, Y., Ribadas Pena, F. J., & Darriba Bilbao, V. M. (2023). Early stopping by correlating online indicators in neural networks. Neural Networks, 159, 109–124. https://doi.org/10.1016/j.neunet.2022.11.035
Wang, C., Antos, S., & Triveno, L. (2021). Automatic detection of unreinforced masonry buildings from street view images using deep learning-based image segmentation. Automation in Construction, 132, 103968. https://doi.org/10.1016/j.autcon.2021.103968
Wang, J., Xu, G., Yan, F., Wang, J., & Wang, Z. (2023). Defect transformer: An efficient hybrid transformer architecture for surface defect detection. Measurement, 211, 112614. https://doi.org/10.1016/j.measurement.2023.112614
Zhu, J., Zhong, J., Ma, T., Huang, X., Zhang, W., & Zhou, Y. (2022). Pavement distress detection using convolutional neural networks with images captured via UAV. Automation in Construction, 133, 103991. https://doi.org/10.1016/j.autcon.2021.103991
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Estoa. Journal of the Faculty of Architecture and Urbanism
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The Journal declines any responsibility for possible conflicts derived from the authorship of the works that are published in it.
The University of Cuenca in Ecuador conserves the patrimonial rights (copyright) of the published works and will favor the reuse of the same ones, these can be: copy, use, diffuse, transmit and expose publicly.
Unless otherwise indicated, all contents of the electronic edition are distributed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
