Polyurethane-bound porous mixture (PPM) is a new type of pavement material that has shown some potential for overcoming common asphalt mixtures mechanical failures. However, little research has been done on its skid resistance performance. This work presents a comparative study of the skid resistance development between PPM and asphalt mixtures at their early stage. In this study, the three mixtures were bonded by three type binders. The three type binders were polyurethane, 70# virgin bitumen, and styrene-butadiene-styrene (SBS) modified asphalt. In order to distinguished the three type mixtures, we named them PPM, BAM, and SAM respectively. A Taber abraser was used to test the polishing property of binders. A third-scale model mobile loading simulator (MMLS3) was used to simulate the traffic loadings on mixtures, and a British pendulum tester was used to measure the skid resistance of the three types of mixtures in the loading process. The binder polishing test results show a good linear relationship between the binder's mass loss and the polishing cycle. The slope of the fitting line of the two parameters was defined as binder coefficient (BC) to characterize the polishing property of the binder. The mixture test results show that the skid resistance development trend of three mixtures is similar, as it first increases, then decreases, then finally flattens. However, the British pendulum number peak value and stable value of PPM are lower than that of SAM. The order of the number of loading times of peak (NLTP) of the three mixtures is SAM>PPM>BAM. Another good linear relationship is found between BC and NLTP, and the R2 of the fitting model is 0.85, which indicates that the polishing property of binder is effective for predicting the moment of occurrence of the mixture skid resistance peak.

Segregation in hot-mix asphalt pavement is a common failure during the construction process. The prevailing segregation detection methods can be used to detect and evaluate segregation only after segregation occurs. This study proposes a real time segregation detection method by using machine learning classifier to categorize the images of the paved mixture (IPM) during construction. The study first manually labeled 224 various levels of hot mix asphalt segregation images. Then, 14 texture features such as contrast, correlation of the IPM were calculated by the gray level co-occurrence matrix (GLCM). Next, the principal component analysis (PCA) was done to reduce the 14 features to 6 main components. Later on, the 6 main components were fed to a Naive Bayesian classifier to categorize the segregation level. Finally, the classification results indicate that the Naïve Bayesian classifier has 80% accuracy when compared with the manually labelled results. Results of this study can potentially be adapted for real-time and large-scale hot mix asphalt segregation evaluation.