Automatic Groove Measurement and Evaluation with High Resolution Laser Profiling Data.

摘要: Grooving is widely used to improve airport runway pavement skid resistance during wet weather. However, grooves deteriorate over time due the combined effects of traffic loading, climate, and weather, which brings about a potential safety risk at aircraft takeoff landing. Accordingly, periodic measurement evaluation groove performance are critical for runways maintain adequate resistance. Nevertheless, such difficult implement lack sufficient technologies identify shallow or worn slab joints. This paper proposes new strategy automatically joints using high resolution laser profiling data. First, K-means clustering based filter moving window traversal algorithm developed locate deepest point dips (including noises, true grooves, joints). Subsequently improved average algorithms determine left right endpoint positions each identified dip. Finally, modified heuristic method separate out from dips, then polynomial support vector machine introduced distinguish noises candidate grooves), so that PCC slab-based can be performed. The proposed compared with other two methods, findings indicate more powerful in joint identification, F-measure score 0.98. study would beneficial subsequent maintenance rehabilitation runway.