Skip to main content
SpringerLink
Log in

Classification of Road Pavement Defects Based on Convolution Neural Network in Keras

  • Published:
Automatic Control and Computer Sciences Aims and scope Submit manuscript

Abstract

The aim of this paper is to propose the convolution neural network—VGG16 structure in Keras to classify pavement defects. In this paper, we present a method to build an automated system to classify different types of defects such as block cracks, longitudinal cracks and potholes. A region of interest is found and features are extracted using image processing techniques and machine learning methods. This system includes the following steps. The first step is to detect the defect location (ROI), then the defect is described by its features. Finally, each defect is classified based on these different features. The system ensures stable operation in the presence of limited lighting conditions, shadowing, and complex shaped defects.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.

Similar content being viewed by others

REFERENCES

  1. Navdeep, B., Convergence and divergence of artificial intelligence, Int. J. Res. Appl. Sci. Eng. Technol., 2020, vol. 8, no. 2, p. 439–441.

    Google Scholar 

  2. Sugata, T.L.I. and Yang, C.K., Leaf app: Leaf recognition with deep convolutional neural networks, IOP Conf. Ser.: Mater. Sci. Eng., 2017, vol. 273, p. 012004.  https://doi.org/10.1088/1757-899X/245/1/012004

  3. Nikhil, K., Introduction to Keras, 2017, pp. 95–109.

  4. Akritidis, L. and Bozanis, P., A supervised machine learning classification algorithm for research articles, Proc 28th Ann. ACM Symp. on Applied Computing, Coimbra, Portugal, 2013, New York: Association for Computing Machinery, 2013, pp. 115–120.  https://doi.org/10.1145/2480362.2480388

  5. Kotsiantis, S.B., Zaharakis, I.D., and Pintelas, P.E., Machine learning: A review of classification and combining techniques, Artif. Intell. Rev., 2006, vol. 26, pp. 159–160.  https://doi.org/10.1007/s10462-007-9052-3

    Article  Google Scholar 

  6. Abu, A.A., Indra, N.H., Rahman, A.H.A., Sapiee, N.A., and Ahmad, I., A study on image classification based on deep learning and Tensorflow, Int. J. Eng. Res. Technol., 2019, vol. 12, no. 4, pp. 563–569.

    Google Scholar 

  7. Bao-Liang, L., Wang, X., and Yang, Y., A study on image classification based on deep learning and Tensorflow, Front. Electr. Electron. Eng. China, 2007, vol. 6, p. 56.

    Article  Google Scholar 

  8. Nguyen, T.H., Nguyen, T.L., Sidorov, D.N., and Dreglea, A.I., Machine learning algorithms application to road defects classification, Intell. Decis. Technol., 2018, vol. 12, no. 1, pp. 59–66.  https://doi.org/10.3233/IDT-170323

    Article  Google Scholar 

  9. Nguyen, H.T., Nguyen, L.T., and Dreglea, A.I., Robust approach to detection of bubbles based on images analysis, Int. J. Artif. Intell., 2018, vol. 16, no. 1, pp. 167–177.

    Google Scholar 

  10. Nguyen, H.T., Nguyen, L.T., and Sidorov, D.N., A robust approach for road pavement defects detection and classification, J. Comput. Eng. Math., 2016, vol. 3, no. 3, pp. 40–52.  https://doi.org/10.14529/jcem160305

    Article  MathSciNet  Google Scholar 

  11. Nguyen, T.L., Nguyen, T.H., and Zhukov, A., Studies of anthropometrical features using machine learning approach, CEUR Workshop Proc., 2015, vol. 1452, pp. 96–105.

    Google Scholar 

  12. Nguyen, H.T. and Nguyen, L.T., Fingerprints classification through image analysis and machine learning method, Algorithms, 2019, vol. 12, no. 11, p. 241.  https://doi.org/10.3390/a12110241

    Article  Google Scholar 

  13. Lee, B.J. and Lee, H.D., Position-invariant neural network for digital pavement crack analysis, Comput.-Aided Civil Infrastruct. Eng., 2004, vol. 19, no. 2, pp. 105–118.  https://doi.org/10.1111/j.1467-8667.2004.00341.x

    Article  Google Scholar 

  14. Xiao, W., Yan, X., and Zhang, X., Pavement distress image automatic classification based on DENSITY-based neural network, Rough Sets and Knowledge Technology. RSKT 2006, Wang, G.Y., Peters, J.F., Skowron, A., and Yao, Y., Eds., Lecture Notes in Computer Science, vol. 4062, Berlin: Springer, 2006, pp. 685–692.  https://doi.org/10.1007/11795131_100

    Book  Google Scholar 

  15. Zhang, D., Qu, S., Li, W., and He, L., Image enhancement algorithm on ridgelet domain in detection of road cracks, China J. Highway Transp., 2009, vol. 2, p. 26.

    Google Scholar 

  16. Zhang, L. and Yang, F., A survey on deep learning: Algorithms, techniques, and applications, IEEE Int. Conf. on Image Process. (ICIP), 2016, IEEE, 2016, p. 3708.

  17. Cha, Y.-J., Choi, W., and Büyüköztürk, O., Deep learning-based crack damage detection using convolutional neural networks, Comput.-Aided Civil Infrastruct. Eng., 2017, vol. 32, no. 5, pp. 361–378.  https://doi.org/10.1111/mice.12263

    Article  Google Scholar 

  18. Eisenbach, M., Stricker, R., Seichter, D., Amende, K., Debes, K., Sesselmann, M., Eberesbach, D., Stoeckert, U., and Gross, H.-M., How to get pavement distress detection ready for deep learning? A systematic approach, Int. Joint Conf. on Neural Networks (IJCNN), Anchorage, Alaska, 2017, IEEE, 2017, pp. 2039–2047.  https://doi.org/10.1109/IJCNN.2017.7966101

  19. Oliveira, H. and Correia, P.L., Automatic road crack detection and characterization, IEEE Trans. Intell. Transp. Syst., 2013, vol. 14, no. 1, pp. 155–168.  https://doi.org/10.1109/TITS.2012.2208630

    Article  Google Scholar 

  20. Wang, P. and Huang, H., Comparison analysis on present image-based crack detection methods in concrete structures, 3rd Int. Congress on Image and Signal Processing, Yantai, China, 2010, IEEE, 2010, pp. 2530–2533.  https://doi.org/10.1109/CISP.2010.5647496

  21. Gunkel, C., Stepper, A., Müller, A.C., and Müller, C.H., Micro crack detection with Dijkstra’s shortest path algorithm, Mach. Vision Appl., 2012, vol. 23, pp. 589–601.  https://doi.org/10.1007/s00138-011-0324-1

    Article  Google Scholar 

  22. Zou, Q., Cao, Y., Li, Q., Mao, Q., and Wang, S., CrackTree: Automatic crack detection from pavement images, Pattern Recognit. Lett., 2012, vol. 33, no. 3, pp. 227–238.  https://doi.org/10.1016/j.patrec.2011.11.004

    Article  Google Scholar 

  23. Shi, Y., Cui, L., Qi, Z., Meng, F., and Chen, Z., Automatic road crack detection using random structured forests, IEEE Trans. Intell. Transp. Syst., 2016, vol. 17, no. 12, pp. 3434–3445.  https://doi.org/10.1109/TITS.2016.2552248

    Article  Google Scholar 

  24. L. Breiman, Random forests, Mach. Learn., 2001, vol. 45, pp. 5–32.  https://doi.org/10.1023/A:1010933404324

    Article  MATH  Google Scholar 

  25. Cortes, C. and Vapnik, V., Support-vector networks, Mach. Learn., 1995, vol. 20, pp. 273–297.  https://doi.org/10.1007/BF00994018

    Article  MATH  Google Scholar 

Download references

ACKNOWLEDGMENTS

The authors gratefully thank the referee for careful reading of the paper and valuable suggestions and comments.

Funding

This research was performed at the Baikal School of BRICS and the Laboratory of Artificial Intelligence and Machine Learning, Irkutsk National Research Technical University (Irkutsk, Russia) and was supported by University of Information and Communication Technology, Thai Nguyen University (no. DH2020-TN07-01). Authors also are thankful to the Center for Telecommunications and Multimedia, INESC TEC, Portugal for providing the dataset.

Author information

Authors and Affiliations

  1. Baikal School of BRICS, Irkutsk National Research Technical University, Irkutsk, Russia

    H. T. Nguyen

  2. Laboratory of Artificial Intelligence and Machine Learning, Institute of Information Technology and Data Science, Irkutsk National Research Technical University, Irkutsk, Russia

    L. T. Nguyen & A. D. Afanasiev

  3. University of Information and Communication Technology, Thai Nguyen University, Thai Nguyen, Viet Nam

    H. T. Nguyen & L. T. Pham

Authors
  1. H. T. Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. L. T. Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. A. D. Afanasiev
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. L. T. Pham
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to H. T. Nguyen, L. T. Nguyen, A. D. Afanasiev or L. T. Pham.

Ethics declarations

The authors declare that they have no conflicts of interest.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nguyen, H.T., Nguyen, L.T., Afanasiev, A.D. et al. Classification of Road Pavement Defects Based on Convolution Neural Network in Keras. Aut. Control Comp. Sci. 56, 17–25 (2022). https://doi.org/10.3103/S0146411622010084

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.3103/S0146411622010084

Keywords:

Search

Navigation