Pavement Image Processing Using Neural Networks

by Mohamed S. Kaseko, Univ of California, Irvine, United States,
Stephen G. Ritchie, Univ of California, Irvine, United States,

Document Type: Proceeding Paper

Part of: Applications of Advanced Technologies in Transportation Engineering


This paper discusses the potential for employing neural network models in the pavement image interpretation and classification stage of an automated pavement condition evaluation system. It discusses the choice of a suitable model for application, the effects of various input parameters on the training of the model and performance of the model in terms of the accuracy of correct classification of pavement images. Preliminary results are presented.

Subject Headings: Model accuracy | Pavements | Imaging techniques | Neural networks | Pavement condition | Parameters (statistics) | Training | Automation

Services: Buy this book/Buy this article


Return to search