Advertisement

Initial Classification Algorithm for Pavement Distress Images Using Features Fusion

  • Zhigang Xu
  • Yanli Che
  • Haigen Min
  • Zhongren Wang
  • Xiangmo Zhao
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 98)

Abstract

In this paper, a novel two-staged pavement image processing framework is presented. The pavement images are classified into four general categories in the first stage, so that the images can be processed using category-specific algorithms in the 2nd stage. The proposed algorithm first fuses a local contrast enhanced image with a global grayscale corrected image to obtain an enhanced distressed pavement image. The enhanced image is then decomposed with a three-layer wavelet transform to obtain three texture features of the entire image including High-Amplitude Wavelet Coefficient Percentage (HAWCP), the High-Frequency Energy Percentage (HFEP), and the Standard Deviation (STD). In the meantime, an improved P-tile method is used to obtain the binary image. From the binary image, three additional shape features are extracted including the Average Area of all Connected Components (AA), the Area of the Maximum Connected Component (AM), and the Equivalent Length of the longest Connected Component (EL). Finally, a BP neural network is used to fuse both the texture and shape features sequentially to achieve the initial classification. Experimental results show that for the four types of pavement images, the proposed algorithm achieves an effective classification of the pavement distress image with the accuracy rates of 96.5%, 91.4%, 95.2% and 98.1% respectively, which are higher than those of the classification algorithm with a single-type feature.

Notes

Acknowledgements

The authors appreciate the pavement images provided by UCPRC. The authors would also acknowledge financial support from China government under the NFSC and SNFSC programs (Grant no. 51278058, 2013JC9397).

References

  1. 1.
    Tsai, Y., Wu, M., Adams, E.D.: GPS/GIS enhanced road inventory system. In: Transportation Research Board 82nd Annual Meeting, 11–15 January 2003, Washington, DC (2003)Google Scholar
  2. 2.
    Zhang, A., Li, Q., Wang, K.C.P., Qiu, S.: Matched filtering algorithm for pavement cracking detection. Transp. Res. Rec. J. Transp. Res. Board 2367(1), 30–42 (2013)CrossRefGoogle Scholar
  3. 3.
    Cheng, H., Shi, X., Glazier, C.: Real-time image thresholding based on sample space reduction and interpolation approach. J. Comput. Civil Eng. 17(4), 264–272 (2003)CrossRefGoogle Scholar
  4. 4.
    Albert, A.P., Nii, A.O.: Evaluating pavement cracks with bidimensional empirical mode decomposition. EURASIP J. Adv. Signal Process. 2008(1), 1–7 (2008)zbMATHGoogle Scholar
  5. 5.
    Xu, Z., Zhao, X., Yang, L., Wei, N., Zhang, L.: Quick and precise road marking segmentation algorithm based on beamlet. J. Chang’an Univ. (Natural Science Edition) 33(5), 101–108 (2013)Google Scholar
  6. 6.
    Zhou, J., Huang, P.S., Chiang, F.P.: Wavelet-based pavement distress detection and evaluation. Opt. Eng. 45(2), 409–411 (2006)CrossRefGoogle Scholar
  7. 7.
    Wang, K.C.P., Li, Q., Gong, W.: Wavelet-based edge detection with à trous algorithm for pavement distress survey. J. Transp. Res. Board 2024(2024), 73–81 (2007)CrossRefGoogle Scholar
  8. 8.
    Ma, C., Zhao, C., Hou, Y.: Pavement distress detection based on nonsubsampled contourlet transform. In: International Conference on Computer Science and Software Engineering, vol. 1, pp. 28–31 (2008)Google Scholar
  9. 9.
    Alekseychuk, D.I.: Detection of crack-like indications in digital radiography by global optimization of a probabilistic estimation function (2006)Google Scholar
  10. 10.
    Zou, Q., Cao, Y., Li, Q., Mao, Q., Wang, S.: CrackTree: automatic crack detection from pavement images. Pattern Recogn. Lett. 33(3), 227–238 (2012)CrossRefGoogle Scholar
  11. 11.
    Li, Q., Zou, Q., Zhang, D., Mao, Q.: FoSA: f* seed-growing approach for crack-line detection from pavement images. Image Vis. Comput. 29(12), 861–872 (2011)CrossRefGoogle Scholar
  12. 12.
    Kaul, V., Yezzi, A., Tsai, Y.: Detecting curves with unknown endpoints and arbitrary topology using minimal paths. IEEE Comput. Soc. 34(10), 1952–1965 (2012)Google Scholar
  13. 13.
    Wang, H., Zhu, N., Wang, Q.: Fractal features analysis and classification for texture of pavement surfaces. J. Harbin Inst. Technol. 37(6), 816–818 (2005)Google Scholar
  14. 14.
    California Department of Transportation, Caltrans Pavement Management System, Automated Pavement Condition Survey Manual, Interim version, October 2009Google Scholar
  15. 15.
    Xu, Z., Zhao, X., Zhang, L.: Asphalt pavement crack recognition algorithm using shape analysis. ICIC Expr. Lett. Int. J. Res. Surv. part B Appl. 2, 671–678 (2011)Google Scholar
  16. 16.
    Gao, J., Ren, M., Yang, J.: A practical and fast method for non-uniform illumination correction. J. Image Graph. 7(6), 548–552 (2002)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Zhigang Xu
    • 1
  • Yanli Che
    • 1
  • Haigen Min
    • 1
  • Zhongren Wang
    • 2
  • Xiangmo Zhao
    • 1
  1. 1.School of Information EngineeringChang’an UniversityXi’anPeople’s Republic of China
  2. 2.California Department of TransportationSacramentoUSA

Personalised recommendations