Asphalt pavement construction is a large-volume project, with the ability to recycle the industrial waste and reduce carbon emissions. Rubber-modified asphalt is a carbon-neutralized asphalt-based material, facilitating the recycling of waste rubber materials and improving the road performance of the asphalt mixture. To evaluate the interface interaction of the rubber–asphalt system and its effect on the viscosity characteristics of rubber-modified asphalt, the contact properties of rubber particles in asphalt were analyzed on a microscopic level. Rubber swelling tests and solvent elution tests were conducted on the rubber–asphalt system under different preparation conditions. The swelling ratio, degradation ratio, and swelling–degradation ratio were proposed to evaluate the interface interaction. The results show that the interface interaction of the rubber–asphalt system can be divided into the following three stages: swelling, effective degradation, and over-degradation. The degree of swelling is mainly affected by the content and size of the rubber particles and it is physically condensed, while the degradation is mainly affected by the preparation temperature and preparation time. The effective interface interaction greatly affects the viscosity with the building of the stable three-dimensional network structure. The stronger the interface interaction, the greater the viscosity of the rubber-modified asphalt, except for the 25% content of rubber particles. The gel film will be generated on the surface of the rubber particles throughout the swelling and effective degradation, increasing the viscosity of the rubber-modified asphalt.

The intelligent detection of asphalt pavement cracks has become increasingly important for ensuring service performance of road infrastructure. Traditional manual detection has significant safety hazards and insufficient accuracy. Furthermore, existing deep learning models still face challenges, including missed detection, false alarms, and poor performance in small target detection under complex conditions. This investigation adopts unmanned aerial vehicles (UAVs) to acquire pavement distress information and develops an intelligent detection approach for asphalt pavement crack based on improved YOLOv8s. First, the Spatial Pyramid Pooling Fast (SPPF) module is replaced with the Spatial Pyramid Pooling Fast with Cross Stage Partial Connections (SPPFCSPC) module in the backbone network to enhance the multi-scale feature fusion capability. Secondly, the Convolutional Block Attention Module (CBAM) module is introduced to the neck network to optimize the feature weights in both channel and spatial attention. Meanwhile, the Efficient Intersection over Union (EIoU) loss is adopted to improve accuracy. Finally, the Crack_Dataset is established, and the ablation experiments are conducted to verify the reliability of the detection model. The research indicates that the improved model achieves Precision, Recall, and mAP@0.5 of 83.9%, 79.6%, and 83.9%, respectively, representing increases of 1.5%, 1.3%, and 1.4%, compared with the baseline model. In comparison with mainstream object detection algorithms such as YOLOv5s and YOLOv8s, the proposed method attains an F1-score, mAP@0.5, and mAP@[0.5–0.95] of 0.82, 83.9%, and 46.6%, respectively, demonstrating a performance improvement. Based on the improved detection model, a pavement crack detection system was designed and implemented using PyQt5. This system supports image, video, and real-time camera input and detection.