Highway alignments extraction and 3D modeling from airborne laser scanning point clouds

Abstract

Accurate highway alignments and three-dimensional (3D) models are essential for various intelligent transportation applications. Airborne laser scanning (ALS) provides a desirable means of data collection, which increases data quality and collection efficiency. However, automatic alignments extraction and 3D modeling remain open problems. Therefore, this paper proposes an effective framework to extract highway alignments by minimizing an elaborate energy function and reconstruct highway 3D models with the restrictions of alignments. Specifically, the proposed method contains the following steps: (1) Adopt an adaptive method based on spatially smooth and interconnected grid cells to recognize highway pavement points from ALS data. (2) Extract pavement boundaries and lane markings from the pavement areas using the α-shape algorithm and a marking tracking strategy. (3) Extract highway alignments by minimizing an energy function and reconstruct highway 3D models with the restrictions of alignments. The method was validated in scenes of various highways, where the point density is 10–25 pts/m2. The extracted alignments respectively achieved the correctness of 90.67% and 99.25% and the completeness of 87.60% and 99.55% within 10 cm and 15 cm errors. The root mean square error (RMSE) of the generated 3D model is 2.4 cm on pavement and 5.8 cm on hills and slopes.