An Overview of Challenges Associated with Automatic Detection of Concrete Cracks in the Presence of Shadows
Source abstract
Abstract
Detection and assessment of cracks in civil engineering structures such as roads, bridges, dams and pipelines are crucial tasks for maintaining the safety and cost-effectiveness of those concrete structures. With the recent advances in machine learning, the development of ANN- and CNN-based algorithms has become a popular approach for the automated detection and identification of concrete cracks. However, most of the proposed models are trained on images taken in ideal conditions and are only capable of achieving high accuracy when applied to the concrete images devoid of irregular illumination conditions, shadows, shading, blemishes, etc. An overview of challenges related to the automatic detection of concrete cracks in the presence of shadows is presented in this paper. In particular, difficulties associated with the application of deep learning-based methods for the classification of concrete images with shadows are demonstrated. Moreover, the limitations of the shadow removal techniques for the improvement of the crack detection accuracy are discussed.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Structural Health Monitoring Techniques · Geophysical Methods and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Centre for Nonlinear Systems, Department of Mathematical Modelling, Kaunas University of Technology, 51368 Kaunas, Lithuania
Funding
Kaunas University of Technology
References (52)
Show source-provided references
1. Elastic moduli of a cracked solid10.1016/0020-7683(76)90044-5 ↗
2. Stiffness reduction of cracked solids10.1016/0013-7944(87)90129-9 ↗
3. A fully non-contact ultrasonic propagation imaging system for closed surface crack evaluation10.1007/s11340-011-9567-z ↗
4. Crack detection using image processing: A critical review and analysis10.1016/j.aej.2017.01.020 ↗
5. Partial Differential Equation-Based Enhancement and Crack Detection10.1155/2019/8157205 ↗
6. Fully adaptive segmentation of cracks on concrete surfaces10.1016/j.compeleceng.2020.106561 ↗
7. Automated crack segmentation via saturation channel thresholding, area classification and fusion of modified level set segmentation with Canny edge detection10.1016/j.heliyon.2020.e05748 ↗
8. Kim, J.J., Kim, A.R., and Lee, S.W. (2020). Artificial Neural Network-Based Automated Crack Detection and Analysis for the Inspection of Concrete Structures. Appl. Sci., 10.10.3390/app10228105 ↗
9. Deep learning-based crack damage detection using convolutional neural networks10.1111/mice.12263 ↗
10. Deep learning–based autonomous concrete crack evaluation through hybrid image scanning10.1177/1475921718821719 ↗
11. Deep Learning based Thermal Crack Detection on Structural Concrete Exposed to Elevated Temperature10.1177/1369433220986637 ↗
12. Ali, L., Alnajjar, F., Jassmi, H.A., Gochoo, M., Khan, W., and Serhani, M.A. (2021). Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures. Sensors, 21.10.3390/s21051688 ↗
13. Moon, H.G., and Kim, J.H. (July, January 29). Intelligent crack detecting algorithm on the concrete crack image using neural network. Proceedings of the 28th International Symposium on Automation and Robotics in Construction (ISARC), Seoul, Korea.
14. Choudhary, G.K., and Dey, S. (2012, January 18–20). Crack detection in concrete surfaces using image processing, fuzzy logic, and neural networks. Proceedings of the 2012 IEEE Fifth International Conference on Advanced Computational Intelligence (ICACI), Nanjing, China.10.1109/ICACI.2012.6463195 ↗
15. Dinh, T.H., Ha, Q.P., and La, H.M. (2016, January 13–15). Computer vision-based method for concrete-crack detection. Proceedings of the 2016 14th International Conference on control, Automation, Robotics and Vision (ICARCV), Phuket, Thailand.10.1109/ICARCV.2016.7838682 ↗
16. Improved crack detection and recognition based on convolutional neural network
17. Autonomous concrete-crack detection using deep fully convolutional neural network10.1016/j.autcon.2018.11.028 ↗
18. Image-based underwater inspection system for abrasion of stilling basin slabs of dam10.1155/2019/6924976 ↗
19. Crack detection on concrete images using classification techniques in machine learning
20. Review of pavement defect detection methods10.1109/ACCESS.2020.2966881 ↗
21. Vignesh, R., Narenthiran, B., Manivannan, S., Murugan, R.A., and RajKumar, V. (2021). Concrete Bridge Crack Detection Using Convolutional Neural Network. Materials, Design, and Manufacturing for Sustainable Environment, Springer.10.1007/978-981-15-9809-8_58 ↗
22. Simultaneous pixel-level concrete defect detection and grouping using a fully convolutional model10.1177/1475921720985437 ↗
23. Crack detection using fusion features-based broad learning system and image processing10.1111/mice.12753 ↗
24. Da Silva, W.R.L., and de Lucena, D.S. (2018). Concrete cracks detection based on deep learning image classification. Proceedings, 2.10.3390/ICEM18-05387 ↗
25. Image-based concrete crack assessment using mask and region-based convolutional neural network10.1002/stc.2381 ↗
26. Yang, C., Chen, J., Li, Z., and Huang, Y. (2021). Structural Crack Detection and Recognition Based on Deep Learning. Appl. Sci., 11.10.3390/app11062868 ↗
27. Puruncajas, B., Vidal, Y., and Tutivén, C. (2020, January 7–9). Damage Detection and Diagnosis for Offshore Wind Foundations. Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics (ICINCO), Paris, France.10.5220/0009886101810187 ↗
28. O’Byrne, M., Ghosh, B., Pakrashi, V., and Schoefs, F. (2012, January 18–20). Image Processing based Damage Detection of Offshore Infrastructural Elements using Texture Information. Proceedings of the 5th European Conference on Structural Control (EACS 2012), Genoa, Italy.
29. Guo, J., Wu, J., Guo, J., and Jiang, Z. (2018). A damage identification approach for offshore jacket platforms using partial modal results and artificial neural networks. Appl. Sci., 8.10.3390/app8112173 ↗
30. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
31. DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection10.1109/TIP.2018.2878966 ↗
32. DeepCrack: A deep hierarchical feature learning architecture for crack segmentation10.1016/j.neucom.2019.01.036 ↗
33. Padalkar, M.G., Beltrán-González, C., Bustreo, M., Bue, A.D., and Murino, V. (2021, January 10–15). A Versatile Crack Inspection Portable System based on Classifier Ensemble and Controlled Illumination. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.10.1109/ICPR48806.2021.9412039 ↗
34. Finlayson, G.D., Hordley, S.D., and Drew, M.S. (2002, January 28–31). Removing shadows from images. Proceedings of the European Conference on Computer Vision, Copenhagen, Denmark.10.1007/3-540-47979-1_55 ↗
35. On the removal of shadows from images10.1109/TPAMI.2006.18 ↗
36. A survey on shadow detection techniques in a single image
37. Automatic shadow detection and removal from a single image10.1109/TPAMI.2015.2462355 ↗
38. Wang, J., Li, X., and Yang, J. (2018, January 18–23). Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00192 ↗
39. Fan, H., Han, M., and Li, J. (2019). Image shadow removal using end-to-end deep convolutional neural networks. Appl. Sci., 9.10.3390/app9051009 ↗
40. Özgenel, Ç.F. (2018). Concrete crack images for classification. Mendeley Data, 1.
41. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv.
42. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
43. Hicklin, J. (2021, February 04). Videos and Webinars. Retrieved from Mathworks Matlab. Available online: https://www.mathworks.com/videos/deep-learning-with-matlab-transfer-learning-in-10-lines-of-matlab-code-1487714838381.html.
44. Shadow detection and removal from a single image using LAB color space
45. Zosso, D., Tran, G., and Osher, S. (2013, January 3–7). A unifying retinex model based on non-local differential operators. Proceedings of the Computational Imaging XI. International Society for Optics and Photonics, Burlingame, CA, USA.10.1117/12.2008839 ↗
46. Non-Local Retinex—A Unifying Framework and Beyond10.1137/140972664 ↗
47. Interactive removal and ground truth for difficult shadow scenes10.1364/JOSAA.33.001798 ↗
48. Cun, X., Pun, C.M., and Shi, C. (2019). Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN. arXiv.10.1609/aaai.v34i07.6695 ↗
49. Research on Removing Shadow in Workpiece Image Based on Homomorphic Filtering10.1016/j.proeng.2012.01.315 ↗
50. Fu, L., Zhou, C., Guo, Q., Juefei-Xu, F., Yu, H., Feng, W., Liu, Y., and Wang, S. (2021). Auto-exposure Fusion for Single-image Shadow Removal. arXiv.10.1109/CVPR46437.2021.01043 ↗
51. Hu, X., Zhu, L., Fu, C.W., Qin, J., and Heng, P.A. (2018, January 18–23). Direction-Aware Spatial Context Features for Shadow Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00778 ↗
52. Direction-Aware Spatial Context Features for Shadow Detection and Removal10.1109/TPAMI.2019.2919616 ↗