Porous ultra-thin asphalt overlay (PUAO) is widely used in maintenance and new road surface layers. Since the paving thickness of PUAO is only about 20 mm, it is necessary to study its own performance and the overall performance of the double-layer material formed by the ultra-thin overlay and the under-layer mixture. PUAO and PUAO/asphalt concrete double-layer specimens with different air voids were prepared and the performance of the specimens were studied. The results showed that as the air voids increased from 15.8% to 24.4%, the PUAO’s high-temperature rutting dynamic stability decreased, the tensile strength ratio first decreased and then increased and the acoustic absorption coefficient peak value increased gradually, but the peak value of frequency moved from 400 Hz to 1250 Hz. The dynamic stability and low-temperature bending strength of the PUAO/AC-13 double-layer specimens were higher than those of the PUAO single-layer specimens. However, the double-layer specimen had a smaller permeability coefficient than the single-layer specimen. The International Friction Index showed that after 600,000 abrasion cycles, the F60 values of the five PUAOs were higher than those of the DUAO, indicating that the PUAO material had excellent skid resistance performance.

Unmanned Aerial Vehicle (UAV)-based pavement distress detection offers efficient and safe advantages. However, obstructions from road vehicles and the slender shape of cracks in UAV images challenge accuracy. To address this, this study established specific flight parameters, proposed the Historical Best Matching Image (HBMI) approach for data loss due to obstructions, and created the UAV-Crack500 dataset with 500 finely annotated crack images. Three algorithms with different loss functions were investigated, finding that the U-Net network combined with our Completely Asymmetric Loss (CAL) achieved the best performance, resolving the issue of class imbalance. Morphological analysis of the semantically segmented images provided precise crack morphology features. In complex scenarios, errors in features like crack area, length, mean width, and maximum width remained within 16%. This study establishes a comprehensive UAV-based pavement distress detection system, overcoming obstructions for accurate assessment.