Image Processing and Artificial Neural Network Based Determination of Surface Mean Texture Depth on Lab-Controlled Chip Seal Pavement Samples

Abstract

Because surface texture is nearly the sole indicator of pavement functional properties and highly correlated with critical operational characteristics of roadways like traffic noise and safety, the change in pavement surface texture because of traffic loadings and environment has to be evaluated routinely. There are numerous direct or indirect evaluation techniques in the market. However, most of these methods have some limitations like requiring lane closure or being expensive. In this study, a 2D image processing method was established to estimate the surface mean texture depth (MTD) of chip sealed pavements. We produced chip sealed pavement samples in the laboratory with different aggregate type, shape, and size ranging between 2 and 19 mm to cover wide range of live conditions. Two well-known conventional test methods, Sand Patch (SP) and Hydrotimer (HT), were used to determine MTDs of chip seal samples. Subsequently numerous photos were taken on surface of the samples with a camera for 2-D image processing that was done based on surface void ratio (SVR) approach. With the image processing, SVR of all samples were determined. At the point of whether there is a relationship or not, correlation analysis was made between the MTDs obtained with SP and HT and the data obtained by SVR approach with the artificial neural network method. The results show that the proposed SVR approach construed on 2D image processing method can be a reliable alternative to evaluate the surface texture of pavements.