Automated extraction of pavement rutting features is critical for road condition monitoring. Existing methods rely on ground-based sensors with limited efficiency and coverage. This paper proposes a method for extracting rutting features from Airborne Laser Scanning (ALS) point clouds. The method first extracts cross-sectional profiles from ALS point clouds based on geometric features. It then applies a rule-driven baseline fitting strategy to each section, followed by automated quantification of rut depth, width, and area as morphology rutting indicators. Validation using vehicle-mounted and handheld laser data shows that 90 % of points exhibit errors smaller than 5.92 mm, with the root mean square error of rut depth ranging from 1.99 to 4.23 mm. Finally, the proposed methodology is compared with other technologies in terms of accuracy and cost. The method enables reliable rutting feature extraction under complex conditions and supports integration into digital twin systems and automated pavement monitoring frameworks in the future.
