Binalarda Çatlak Kontrolünde CNN Tabanlı Görüntü İşleme Ölçüm Sisteminin Kullanılması

Abstract

Binadaki çatlaklar yapısal sorunlara işaret edebileceğinden endişe kaynağıdır. Binalarda çatlaklar, binanın görünüşünü etkilediği gibi, duvarın bütünlüğünü bozmakta, yapı güvenliğini tehlikeye atmakta ve yapının dayanıklılığını azalttığı için beton yapıların önemli sorunlarından biridir. Binalardaki çatlaklar endişe kaynağı olabilir ve binanın güvenliğini ve sağlamlığını tehlikeye atabilecek potansiyel bir yapısal soruna işaret edebilir. Bu çatlakların temel nedenlerini anlamak, uygun önleyici tedbirlerin ve onarım yöntemlerinin belirlenmesinde çok önemlidir. Bu çalışmada binalarda çatlak ve eğim kontrolü CNN derin öğrenme algoritmaları kullanılarak geliştirilen görüntü işleme temelli ölçüm sistemi ile gerçekleştirilmiştir. Çalışma için 63 fotoğraftan oluşturulan veri seti kullanılmıştır. Veriler görüntü işleme ön işlemlerden geçirilerek CNN ile tespiti gerçekleştirilmiştir. İnşaatlarda kalınlığı 2 mm büyük 4 cm sürekliliği olan tüm dikey ve yatay çatlakların tespiti %88,2 doğrulukla yapılmıştır. Böylece hızlı, güvenilir bir şekilde binalardaki çatlak kontrolü yapılabilecek ve bina güvenliği sağlanacaktır.

Keywords

• Görüntü işleme
• CNN
• çatlak

Crack Control in Buildings with a CNN-based Image Processing Measurement System

Abstract

Cracks in buildings are a source of concern as they may indicate structural problems. Cracks in buildings are one of the major problems with concrete structures, as they affect the appearance of the building, compromise the integrity of the masonry, jeopardize building safety, and reduce the durability of the structure. Cracks in buildings can be a cause for concern and may indicate a potential structural problem that could jeopardize the safety and stability of the building. Understanding the root causes of these cracks is crucial to determining appropriate preventive measures and repair methods. In this study, crack and slope control in buildings was performed with an image processing-based measurement system developed using CNN deep learning algorithms. A dataset of 63 photographs was used for the study. The data was pre-processed by image processing and detected with CNN. All vertical and horizontal cracks with a thickness of 2 mm and a continuity of 4 cm were detected with an accuracy of 88.2%. Thus, crack control in buildings can be done quickly and reliably, and building safety will be ensured.

Keywords

• Image processing
• CNN
• crack

References

1. [1] H. S. Munawar, A. W. Hammad, A. Haddad, C .A. P. Soares and S. T. Waller, “Image-based crack detection methods: A review” Infrastructures, vol. 6, no. 8, pp. 115-135, 2021. doi: 10.3390/infrastructures6080115
2. [2] M. Gonthina, R. Chamata, J. Duppalapudi and V. Lute, “Deep CNN-based concrete cracks identification and quantification using image processing techniques”, Asian Journal of Civil Engineering, vol. 24, no. 3, pp. 727-740, 2023. doi: 10.1007/s42107-022-00526-9
3. [3] G. L. Golewski, “The phenomenon of cracking in cement concretes and reinforced concrete structures: the mechanism of cracks formation, causes of their initiation, types and places of occurrence, and methods of detection—a review”. Buildings, vol. 13, no. 3, pp. 765. 2023. doi: 10.3390/buildings13030765
4. [4] C. J. Chitte and Y. N. Sonawane, “Study on causes and prevention of cracks in building”. International Journal for Research in Applied Science and Engineering Technology, vol. 6, no. 3, pp. 453-461, 2018. doi: 10.22214/ijraset.2018.3073
5. [5] Construction Placements, “Cracks in Buildings: Understanding the Causes, Prevention, and Repair Methods”, constructionplacements.com, March 2, 2023. [Online]. Available: https://www.constructionplacements.com/cracks-in-buildings. [Accessed: Oct. 2023].
6. [6] X. Yang, H. Li, Y. Yu, X. Luo, T. Huang and X. Yang, “Automatic pixel‐level crack detection and measurement using fully convolutional network”. Computer‐Aided Civil and Infrastructure Engineering, vol. 33, pp. 1090–1109, 2018. doi: 10.1111/mice.12412
7. [7] L. Pauly, D. Hogg, R. Fuentes and H. Peel, “Deeper networks for pavement crack detection”. In Proceedings of the 34th ISARC, pp. 479-485, April 2017. doi: 10.22260/ISARC2017/0066
8. [8] A. N. Soni, “Crack Detection in buildings using convolutional neural Network”, Journal for Innovative Development in Pharmaceutical and Technical Science, vol. 2, no. 6, pp. 54-59, May 2019.

9. [9] H. G. Sohn, Y. M. Lim, K. H. Yun and G. H. Kim, “Monitoring crack changes in concrete structures”, Computer‐Aided Civil and Infrastructure Engineering, vol. 20, no. 1, pp. 52-61, 2005. doi: 10.1111/j.1467-8667.2005.00376.x
10. [10] T. Yamaguchi and S. Hashimoto, “Automated crack detection for concrete surface image using percolation model and edge information”. Proceedings of the 32nd annual conference on IEEE industrial electronics, Paris, France, April 2007, New York: IEEE., 2007, pp. 3355–3360. doi: 10.1109/IECON.2006.348070
11. [11] M. Zheng, Z. Lei and K. Zhang, “Intelligent detection of building cracks based on deep learning”, Image and Vision Computing, vol. 103, pp. 103987, 2020. doi: 10.1016/j.imavis.2020.103987
12. [12] K. Kawamura, A. Miyamoto, H. Nakamura and R. Sato, "Proposal of a crack pattern extraction method from digital images using an interactive genetic algorithm", JSCE Journal, vol. 60, no. 742, pp. 115-141, 2003. doi: 10.2208/jscej.2003.742_115
13. [13] A. Ito, Y. Aoki and S. Hashimoto, “Accurate extraction and measurement of fine cracks from concrete block surface image”, in 28th Annual Conference of the Industrial Electronics Society. IECON 02, Sevilla, Spain, 5-8 Nov. 2002, Piscataway, NJ: IEEE, 2002. pp. 2202–2207.
14. [14] T. C. Hutchinson and Z. Chen, "Improved image analysis for evaluating concrete damage", Journal of Computing in Civil Engineering, American Society of Civil Engineers, vol. 20, no. 3, pp. 210-216, 2006. doi: 10.1061/(ASCE)0887-3801(2006)20:3(210)
15. [15] X.P. Luo, J. Tian, Y. Zhu, J. Wang and R. Dai, “A survey on image segmentation methods”, Pattern Recognition, vol. 12, no.3, pp. 300–312, 1999.
16. [16] Q. X. Zhou, H. Q. Yuan, and Y. Y. Tao, “Research on 3D data model of apparent damage features for concrete structures”. Journal of Wuhan University of Technology, vol. 32, no. 11, pp. 31–35, 2010.
17. [17] M. Kayakuş ve F.Y. Açikgöz, “Twitter'da makine öğrenmesi yöntemleriyle sahte haber tespiti”, Abant Sosyal Bilimler Dergisi, vol. 23, no. 2, pp. 1017-1027, 2023. doi: 10.11616/asbi.1266179
18. [18] M. Kayakuş, M. Terzioğlu, D. Erdoğan, S.A. Zetter, O. Kabas, and G. Moiceanu, “European Union 2030 carbon emission target: The case of Turkey”, Sustainability, vol. 15, no. 17, pp. 13025, 2023. doi: 10.3390/su151713025
19. [19] M. A. Kızrak ve B. Bolat, B, “Derin öğrenme ile kalabalık analizi üzerine detaylı bir araştırma”, Bilişim Teknolojileri Dergisi, vol. 11, no. 3, 263-286, 2018. doi: 10.17671/gazibtd.419205
20. [20] M. Kayakuş, and F. Y. Açikgöz, “Classification of news texts by categories using machine learning methods,” Alphanumeric Journal, vol. 10, no. 2, pp. 55-166 2022. doi: 10.17093/alphanumeric.1149753
21. [21] N. Ketkar, J. Moolayil, N. Ketkar and J. Moolayil, J. “Convolutional neural networks”, Deep Learning with Python: Learn Best Practices of Deep Learning Models with PyTorch, pp. 197-242, 2021. doi: 10.1007/978-1-4842-5364-9_6
22. [22] F. Türk, “Covid-19 Diagnosis using a deep learning ensemble model with chest X-Ray images”, Computer Systems Science & Engineering, vol. 45, no. 2, pp. 1357-1373, 2023. doi: 10.32604/csse.2023.030772
23. [23] M.F. Aydoğdu, V. Celik, and M.F. Demirci, “Comparison of three different CNN architectures for age classification”, in 2017 IEEE 11th International conference on semantic computing (ICSC), pp. 372-377, 2017. doi: 10.1109/ICSC.2017.61
24. [24] T.C. Lu, “CNN Convolutional layer optimisation based on quantum evolutionary algorithm”, Connection Science, vol. 33, no. 3, pp. 482-494, 2021. doi: 10.1080/09540091.2020.1841111
25. [25] D. Yu, H. Wang, P. Chen and Z. Wei, (2014). “Mixed pooling for convolutional neural networks”, Rough Sets and Knowledge Technology: 9th International Conference, Shanghai, China, 2014, pp. 364-375. doi: 10.1007/978-3-319-11740-9_34
26. [26] K. Liu, G. Kang, N. Zhang and B. Hou, "Breast Cancer Classification Based on Fully-Connected Layer First Convolutional Neural Networks," IEEE Access, vol. 6, pp. 23722-23732, 2018, doi: 10.1109/ACCESS.2018.2817593.
27. [27] W.F. Osgood, “On the gyroscope”, Transactions of the American Mathematical Society, vol. 23, no. 3, pp. 240-264, 1992. doi: 10.1090/S0002-9947-1922-1501201-7
28. [28] F. J. Wagner and A. Trierenberg, “The machine of bohnenberger: bicentennial of the gyro with cardanic suspension”, Proceedings in Applied Mathematics and Mechanics, vol. 10, no.1, pp. 659-660, 2010. doi: 10.1002/pamm.201010322
29. [29] M.W. Davidson, “Pioneers in optics: jean-bernard-leon foucault and willebrord snell”, Microscopy Today, vol. 19, no.1, pp. 44-46, 2011. Doi: 10.1017/S155192951000115X
30. [30] J. Broelmann, “Hermann anschütz-kaempfe-richtungsweiser ohne spuren”, Deutsches Schiffahrtsarchiv, vol. 25, pp. 41-55, 2002.
31. [31] F.S. Wickware, “Elmer sperry and his magic top”, Scientific American, vol. 169, no.2, pp. 66-84, 1943. Doi: 10.1038/scientificamerican0843-66
32. [32] I.S. Üncü and M. Kayakuş, “Analysis of visibility level in road lighting using image processing techniques”, Scientific Research and Essays, vol. 5, no. 18, pp. 2779-2785, 2010.
33. [33] L.K. Huang and M.J.J. Wang, “Image thresholding by minimizing the measures of fuzziness”, Pattern recognition, vol. 28, no. 1, pp. 41-51, 1995. doi: 10.1016/0031-3203(94)E0043-K
34. [34] V.M. Dharampal, “Methods of image edge detection: A review”, Electrical & Electronic Systems, vol. 4, no. 2, pp. 2332-0796, 2015. doi: 10.4172/2332-0796.1000150