DETECTING CRACKS IN CONCRETE BASED ON IMAGES USING AMAZON WEB SERVICE REKOGNITION

Roman Mysiuk, Volodymyr Yuzevych, Iryna Mysiuk, Ihor Ohirko

Abstract


Concrete is the basis for many structures in architecture and infrastructure. Under the influence of external factors and load from use, this material can be destroyed. At first, microcracks may form in the concrete, which grows into larger cracks over time. Detection of such cracks can be performed with the help of information technologies. Cloud technologies are gaining popularity today. Among the largest service providers in this direction is Amazon Web Service. There are many opportunities in this cloud environment for computing using artificial intelligence. In the work, the recognition of cracks in concrete is performed using the Amazon Web Service Rekognition. The images with the concrete crack and the corroded pipe are analyzed for label matches. Based on the given test and training images with defects, cracks are recognized using Amazon Rekognition Custom Labels. The main elements of the image are identified, namely concrete and cracks. As a result, the described recognition method can be used for the automatic detection of defects in concrete.

Keywords: machine learning, concrete, crack, bounding box, label, cloud technologies.


Full Text:

PDF

References


  1. Georgiana-Lucia Coca, Ștefan-Cosmin Romanescu, Șerban-Mihai Botez, Adrian Iftene // Crack detection system in AWS Cloud using Convolutional neural networks, Procedia Computer Science, 2020, Vol. 176, P. 400-409, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2020.08.041.
  2. G. K. Choudhary and S. Dey. Crack detection in concrete surfaces using image processing, fuzzy logic, and neural networks // 2012 IEEE Fifth International Conference on Advanced Computational Intelligence (ICACI), Nanjing, 2012, P. 404-411. https://doi.org/10.1109/ICACI.2012.6463195.
  3. Vedrtnam, A., Kumar, S., Barluenga, G. et al. // Early crack detection using modified spectral clustering method assisted with FE analysis for distress anticipation in cement-based composites. Sci Rep 11. 2021. https://doi.org/10.1038/s41598-021-99010-8
  4. Chen X, Lian Q, Chen X, Shang J. (2022) Surface Crack Detection Method for Coal Rock Based on Improved YOLOv5. Applied Sciences. 12(19), 9695. https://doi.org/10.3390/app12199695
  5. Golding VP, Gharineiat Z, Munawar HS, Ullah F. // Crack Detection in Concrete Structures Using Deep Learning. Sustainability. 2022. 14(13), 8117. https://doi.org/10.3390/su14138117.
  6. Overview of Amazon Web Services. [Online]. URL: https://d1.awsstatic.com/whitepapers/aws-overview.pdf
  7. Vivek Kumar Singh & Kailash Joshi // Automated Machine Learning (AutoML): an overview of opportunities for application and research, Journal of Information Technology Case and Application Research, 2022, 24(2), pp. 75-85 10.1080/15228053.2022.2074585
  8. Indla, Raghavendra Kumar // An Overview on Amazon Rekognition Technology. Electronic Theses, Projects, and Dissertations. 2021. 1263. https://scholarworks.lib.csusb.edu/etd/1263
  9. Delhi Venkata Santosh Kumar, Sankarlal R., Thomas Albert // Detection of Personal Protective Equipment (PPE) Compliance on Construction Site Using Computer Vision Based Deep Learning Techniques. Frontiers in Built Environment, 2020. Vol. 6, https://doi.org/10.3389/fbuil.2020.00136
  10. Xiaokang Ren, Wenqiao Wang, Jie Ren, Xuetao Mao, Mai Zhang // Research and Application of Label Defect Detection Method Based on Machine Vision. Journal of Physics: Conference Series 1453 2020 https://doi.org/10.1088/1742-6596/1453/1/012084
  11. Amazon Simple Storage Service Documentation [Online]. URL: https://docs.aws.amazon.com/s3/index.html
  12. Metrics to Evaluate your Machine Learning Algorithm [Online]. URL: https://towardsdatascience.com/metrics-to-evaluate-your-machine-learning-algorithm-f10ba6e38234.




DOI: http://dx.doi.org/10.30970/eli.20.3

Refbacks

  • There are currently no refbacks.