Pavement Distress Image Recognition Based on Multilayer Autoencoders

  • Lukui Shi
  • Chunying Gao
  • Jun Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7530)

Abstract

Pavement distress images are typical high dimensional nonlinear data. Manifold learning algorithms can find the intrinsic characteristic hidden in the distress images, which helps to better recognize them. Unlike most of manifold learning algorithms, multilayer autoencoders have solved the data reconstructed problem through building a bi-directional mapping between the high dimensional data and the low dimensional data. An automatic pavement distress image recognition method based on multilayer autoencoders was proposed, which combined the image processing method and multilayer autoencoders. In the method, the distress images were firstly processed with the image processing method. Then the images were reduced dimensions and reconstructed with multilayer autoencoders. Lastly, the distress type was recognized through the network. Experiments showed that the recognition accuracy with the proposed method was great higher than that with the BP neural network.

Keywords

Pavement distress image recognition Manifold learning Multilayer autoencoders Image processing BP neural network 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kelvin, C.P.W.: Designs and Implementations of Automated Systems for Pavement Surface Distress Survey. Journal of Infrastructure Systems 6(1), 24–32 (2000)CrossRefGoogle Scholar
  2. 2.
    Kelvin, C.P.W., Robert, P.E.: Investigation of Image Archiving for Pavement Surface Distress Survey. Mack-Blackwell Transportation Center, University of Arkansas, Fayetteville (1999)Google Scholar
  3. 3.
    Zhang, J., Sha, A., Gao, H., Sun, Z.: Automatic Pavement Crack Recognition and Evaluation System Based on Digital Image Processing. Journal of Chang’an University (Natural Science Edition) 24(2), 18–22 (2004)Google Scholar
  4. 4.
    Sun, Y.: Automated Pavement Distress Detection Using Advanced Image Processing Techniques. M.S. Thesis, College of Engineering, The University of Toledo (December 2009)Google Scholar
  5. 5.
    SiriPhan, J.: Development of a New Digital Pavement Image Processing Algorithm for Unified Crack Index Computation. A Dissertation Submitted to the Faculty of the University of Utah (1997)Google Scholar
  6. 6.
    Velisky, S.A., Kirsehke, K.R.: Design Considerations for Automated Pavement Crack Sealing Machinery. In: 2nd International Conference on Applications of Advanced Technologies in Transportation Engineering, pp. 77–80 (1991)Google Scholar
  7. 7.
    Peng, H., Li, J., Mu, J.: A Method of Edge Detection Based on Canny Regulation for Detecting Road Surface Image. Journal of Xi’an Institute of Technology 22(4), 322–325 (2002)Google Scholar
  8. 8.
    Xiao, W., Zhang, X., Huang, W.: A New Method for Distress Automation Recognition of Pavement Surface Based on Density Factor and Image Processing. Journal of Transportation Engineering and Information 2(2), 82–89 (2004)Google Scholar
  9. 9.
    Li, G., He, Y., Zhao, Y.: Automatic Recognition Algorithm of Pavement Defect Image Based on OTSU and Maximizing Mutual Information. Microelectronics & Computer 26(7), 241–243, 247 (2009)Google Scholar
  10. 10.
    Tenenbaum, J.B., de Silva, V., Langford, J.C.: A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science 290(5500), 2319–2323 (2000)CrossRefGoogle Scholar
  11. 11.
    Nadler, B., Lafon, S., Coifman, R.R., Kevrekidis, I.G.: Diffusion Maps, Spectral Clustering and the Reaction Coordinates of Dynamical Systems. Applied and Computational Harmonic Analysis 21, 113–127 (2006)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Schölkopf, B., Smola, A.J., Müller, K.R.: Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation 10(5), 1299–1319 (1998)CrossRefGoogle Scholar
  13. 13.
    Rowei, S.T., Saul, L.K.: Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  14. 14.
    Belkin, M., Niyogi, P.: Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Neural Computation 15(6), 1373–1396 (2003)MATHCrossRefGoogle Scholar
  15. 15.
    Donoho, D.L., Grimes, C.: Hessian Eigenmaps: New Locally Linear Embedding Techniques for High-Dimensional Data. Proceedings of the National Academy of Sciences 102(21), 7426–7431 (2005)CrossRefGoogle Scholar
  16. 16.
    Zhang, Z., Zha, H.: Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment. SIAM Journal of Scientific Computing 26(1), 313–338 (2005)CrossRefMathSciNetGoogle Scholar
  17. 17.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the Dimensionality of Data with Neural Networks. Science 313(5786), 504–507 (2006)MATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Hu, Z., Song, Y.: Dimensionality Reduction and Reconstruction of Data Based on Autoencoder Network. Journal of Electronics & Information Technology 31(5), 1189–1192 (2009)MathSciNetGoogle Scholar
  19. 19.
    Al-Mansour, A.: Flexible Pavement Distress Prediction Model for the City of Riyadh. Emirates Journal for Engineering Research 9(1), 8–88 (2004)Google Scholar
  20. 20.
    Hinton, G.E.: Training Products of Experts by Minimizing Contrastive Divergence. Neural Computation 14(8), 1771–1800 (2000)CrossRefGoogle Scholar
  21. 21.
    Li, G.: Pavement Distress Recognition Based on Image. M.S. Thesis, School of Computer Science and Engineering, Hebei University of Technology (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Lukui Shi
    • 1
  • Chunying Gao
    • 1
  • Jun Zhang
    • 1
  1. 1.School of Computer Science and EngineeringHebei University of TechnologyTianjinChina

Personalised recommendations