Comparison of Traditional and Neural Classifiers for Pavement‐Crack Detection
Publication: Journal of Transportation Engineering
Volume 120, Issue 4
Abstract
This paper presents a comparative evaluation of traditional and neural‐network classifiers to detect cracks in video images of asphalt‐concrete pavement surfaces. The traditional classifiers used are the Bayes classifier and the neighbor decision rule. The neural classifiers are the multilayer feed‐forward (MLF) neural‐network classifier and a two‐stage piecewise linear neural‐network classifier. Included in the paper is a theoretical background of the classifiers, their implementation procedures, and a case study to evaluate their performance in detection and classification of crack segements in pavement images. The results are presented and compared, and the relative merits of these techniques are discussed. The research reported in this paper is part of an ongoing research project, the objective of which is to develop a neural‐network‐based methodology for the processing of video images for automated detection, classification, and quantification of cracking on pavement surfaces.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Butler, B. (1989). “Pavement surface distress segmentation using real‐time imaging.” Proc., 1st Int. Conf. on Applications of Advanced Technol. in Transp. Engrg., ASCE, New York, N.Y.
2.
Carroff, G., Leycure, P., Prudhomme, F., and Soussain, G. (1990). “MACADAM: An operating system of pavement deterioration diagnosis by image processing.” Paper No. 890393, 69th Annu. Transp. Res. Board Meeting, Washington, D.C.
3.
Cove, T. M., and Hart, P. E. (1967). “Nearest neighbor pattern classification.” IEEE Trans. on Information Theory, 13(1), 21–27.
4.
Duda, R. O., and Hart, P. E. (1973). Pattern classification and scene analysis. John Wiley & Sons, New York, N.Y.
5.
El‐Korchi, T., Gennert, M. A., Ward, M. O., and Wittels, N. (1990). “An engineering approach to automated pavement surface distress evaluation.” Proc., Automated Pavement Distress Data Collection Equipment Seminar, Federal Highway Administration, Ames, Iowa, 165–172.
6.
Fukuhara, T., Terada, K., Nagao, M., Kasahara, S., and Ichihashi, J. (1989). “Automatic pavement distress system.” Proc., 1st Int. Conf. on Applications of Advanced Technol. in Transp. Engrg., ASCE, New York, N.Y.
7.
Fukunaga, K. (1972). Introduction to statistical pattern recognition. Academic Press, New York, N.Y.
8.
Fundakowski, R. A., Graber, R. K., Fitch, R. C., Skok, E. L., and Lukanen, E. O. (1991). “Video image processing for evaluating pavement surface distress.” Final Rep. for the Nat. Cooperative Hwy. Res. Program (NCHRP), Triple Vision, Inc., Project 1‐27, Minneapolis, Minn.
9.
Hosin, L. (1990). “Evaluation of pavedex‐computerized pavement image processing system in Washington.” Proc., Automated Pavement Distress Data Collection Equipment Seminar, Federal Highway Administration (FHWA), Washington, D.C.
10.
Kaseko, M. S., and Ritchie, S. G. (1993). “A neural network‐based methodology for pavement crack detection and classification.” Transp. Res., Part C, 1(4), 275–291.
11.
Kohonen, T., Barna, G., and Chrisley, R. (1988). “Statistical pattern recognition with neural networks: benchmarking studies.” Proc., IEEE Int. Conf. on Neural Networks, Vol. 1, IEEE, San Diego, Calif., 182–185.
12.
Koutsopoulos, H. N., and Sanhouri, I. E. (1991). “Methods and algorithms for automated analysis of pavement images.” Transp. Res. Record, No. 1311, National Research Council, Washington, D.C., 103–111.
13.
Lan, L., Chan, P., and Lytton, R. L. (1991). “Detection of thin cracks on noisy pavement images.” Transp. Res. Record, No. 1311, National Research Council, Washington, D.C., 133–135.
14.
Lo, Z. P., and Bavarian, B. (1991a). “Comparison of a neural network and linear classifier.” Pattern Recognition Letters, Vol. 12, 649–655.
15.
Lo, Z. P., and Bavarian, B. (1991b). “A neural piecewise linear classifier for pattern classification.” Proc., IEEE Int. Joint Neural Network Conf., Vol. 1, 264–268.
16.
Lo, Z. P., Yu, Y. Q., and Bavarian, B. (1992). “Derivation of learning vector quantization algorithms.” Proc., IEEE Int. Joint Conf. on Neural Networks, Vol. 3, IEEE Neural Network Council, Baltimore, Md., 561–567.
17.
Mahler, D. S., Kharoufa, Z. B., Wong, E. K., and Shaw, L. G. (1991). “Pavement distress analysis using image processing techniques.” Microcomp. in Civ. Engrg., Vol. 6, Elsevier Science Publishers Ltd., New York, N.Y., 1–14.
18.
Mendelsohn, D. H. (1987). “Automated pavement crack detection: an assessment of leading technologies.” Proc., 2nd North Am. Conf. on Managing Pavements, Vol. 3, FHWA, Washington, D.C., 297–314.
19.
Otsu, N. (1984). “Karhunen‐Loeve line fitting and linearity measure.” Proc., Int. Conf. on Pattern Recognition, IEEE Computer Society Press, Silver Spring, Md., 486–489.
20.
Ritchie, S. G. (1990). “Digital imaging concepts and applications in pavement management.” J. Transp. Engrg., ASCE, 116(3).
21.
Ritchie, S. G., Kaseko, M. S., and Bavarian, B. (1991). “Development of an intelligent system for automated pavement evaluation.” Transp. Res. Record, No. 1311, National Research Council, Washington, D.C., 112–119.
22.
Rumelhart, D. E., McClelland, J. L., and the PDP Research Group. (1986). Parallel distributed processing: explorations in the microstructure of cognition, Vol. I, MIT Press, Cambridge, Mass.
23.
Wittels, N., El‐Korchi, T., Gennert, M. A., and Ward, M. O. (1990). “Images for testing pavement surface distress evaluation systems.” Proc., Automated Pavement Distress Data Collection Equipment Seminar, Federal Highway Administration, Ames, Iowa, 153–163.
Information & Authors
Information
Published In
Journal of Transportation Engineering
Volume 120 • Issue 4 • July 1994
Pages: 552 - 569
Copyright
Copyright © 1994 American Society of Civil Engineers.
History
Received: Oct 16, 1992
Published online: Jul 1, 1994
Published in print: Jul 1994
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.