Abstract
This study proposes an integrated neural network-based crack imaging system to classify crack types of digital pavement images, which was named DENSITY-based neural network(DNN).The neural network was developed to classify various crack types based on the subimages (crack tiles) rather than crack pixels in digital pavement images. The spatial neural network was trained using artificially generated data following the Federal Highway Administration (FHWA) guidelines. The optimal architecture of each neural network was determined based on the testing results from different sets of the number of hidden units, and the number of training epochs. To validate the system, computer- generated data as well as the actual pavement pictures taken from pavements were used. The final result indicates that the DNN produced the best results with the accuracy of 99.50% for 1591 computer-generated data and 97.59% for 83 actual pavement pictures. The experimental results have demonstrated that DNN is quite effective in classifying crack type, which will be useful for pavement management.
This work was supported by National Basic Research Program of China (2005CB724205).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Luhr, D.R.: A proposed methodology to quantify and verify automated crack survey measurements. Transportation Research Record 1612, 68–81 (1999)
Guralnick, S.A., Sun, E.S., Smith, C.: Automating inspection of highway pavement surface. Journal of Transportation Engineering 119, 35–46 (1993)
Lee, B.J., Lee, H.: A position-invariant neural network for digital pavement crack analysis. Computer-aided civil and infrastructure engineering 19, 105–118 (2004)
Lee, B.J.: Development of an integrated digital pavement imaging and neural network system. A Dissertation. Faculty of the University of Iowa (submitted, 2001)
Roberts, C.A., Attoh-Okine, N.O.A.: Comparative analysis of two artificial neural networks using pavement performance prediction. Computer Aided Civil and Infrastructure Engineering, ASCE 122, 339–348 (1998)
Cheng, H.D., Jiang, X.H., Glazier, C.: Novel approach to pavement cracking detection based on neural network. Transportation Research Board 1764, 119–127 (2001)
Owusu-Ababio, S.: Effect of neural network topology on flexible pavement cracking prediction. Computer-Aided Civil and Infrastructure Engineering 13, 349–355 (1998)
Zhang, G.X., Rong, H.N., Jin, W.D., Hu, L.Z.: Radar emitter signal recognition based on resemblance coefficient features. In: Tsumoto, S., Słowiński, R., Komorowski, J., Grzymała-Busse, J.W. (eds.) RSCTC 2004. LNCS (LNAI), vol. 3066, pp. 665–670. Springer, Heidelberg (2004)
Zhang, G.X., Jin, W.D., Hu, L.Z.: A novel feature selection approach and its application. In: Zhang, J., He, J.-H., Fu, Y. (eds.) CIS 2004. LNCS, vol. 3314, pp. 665–671. Springer, Heidelberg (2004)
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)
Xiao, W.X.: Research on key technology of pavement images automation recognition. A Dissertation Submitted to the Faculty of the University of southeast China (2004)
Joonkee, K.: Development of a low-cost video image system for pavement evaluation. A Thesis Submitted to Oregon State University (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xiao, W., Yan, X., Zhang, X. (2006). Pavement Distress Image Automatic Classification Based on DENSITY-Based Neural Network. In: Wang, GY., Peters, J.F., Skowron, A., Yao, Y. (eds) Rough Sets and Knowledge Technology. RSKT 2006. Lecture Notes in Computer Science(), vol 4062. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11795131_100
Download citation
DOI: https://doi.org/10.1007/11795131_100
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-36297-5
Online ISBN: 978-3-540-36299-9
eBook Packages: Computer ScienceComputer Science (R0)