Optimizing asphalt mix design at the indoor stage is of significant importance for enhancing the rutting resistance of asphalt mixture, which is affected by its structural characteristics. In this work, the coordination number of particle contact force (CN_pcf) was proposed as an indicator to represent contact characteristics of skeleton structure aggregates in asphalt mixture. Nine asphalt mixtures with different gradations were designed, and the relationship of CN_pcf with the number of aggregate contact zones (CZ) was established by combining rutting tests and digital image processing technique (DIP). The Mann-Whitney U test was implemented to analyze the distribution properties of inter-particle contacts before and after the rutting test. In addition, the resistance to the further expansion of rutting was analyzed. The results revealed a significant positive correlation (PCCs = 0.843, R² = 0.711) between CN_pcf and CZ. The content of coarse aggregates in the dominant structure did not exhibit monotonic related to anti-rutting performance of the asphalt mixture. Therefore, an optimum aggregate content of 57% was utilized. The Mann-Whitney U test revealed that the mesoscale skeleton structure of the asphalt mixes before and after rutting exhibited excellent stability. This study further indicated the applicability of combining CN_pcf to adjust the mix design to enhance the rutting resistance of asphalt mixture and to prevent rutting expansion in flexible pavement.

The surface texture of asphalt pavement has a significant effect on skid resistance performance. However, its contribution to the performance of skid resistance is non-homogeneous and subjects to local validity. There are also a few deep learning models that take into account the effective contact texture region. This paper proposes a convolutional neural network model based on the effective contact texture region, containing macro- and micro-scale awareness sub-modules. In this study, the asphalt mixture with varying gradations was designed to accurately obtain the effective contact texture region. Then, the textures were disentangled into macro- and micro-texture scales by applying the fast Fourier transform and fed into the model for training. Finally, the area of effective contact texture region was calculated, and the effective contact ratio parameter was then proposed using the triangulation algorithm. The results showed that the effective contact texture area of pavement varies by the asphalt mixture type. The effective contact ratio parameter exhibited a significant positive correlation (Pearson correlation coefficient is 0.901, R²= 0.8129) with skid resistance performance and was also influenced by key sieve aggregate content from 2.36 to 4.75 mm. The data of effective contact texture region following disentanglement significantly released the model performance (the relative error dropped to 1.81%). The model exhibited improved precision and performance, which can be utilized as an efficient, non-contact alternative method for skid resistance analysis.