基于稀疏点云的ADAS三维地图构建方法

ADAS 3D Map Construction Method Based on the Sparse Point Cloud

提出了一种基于机载LiDAR稀疏点云与已有道路二维导航地图快速构建ADAS三维地图的方法。通过稀疏点云与导航地图拓扑叠加分析和三维空间关系检验,实现了对复杂道路结构的高程平滑和面向ADAS的道路三维地图构建。以香港地区ADAS地图为例,采用该方法进行了三维地图构建。结果表明,该方法合理且效率高,精度满足先进自动驾驶三维地图要求。

In this paper an approach was proposed for quickly constructing3 D road maps for advanced driver assistance system(ADAS) based on sparse airborne LiDAR point clouds and existed 2D navigation road maps.Considering that sparse airborne LiDAR point clouds and maps were different kinds of data,making point clouds and maps topological overlay was necessary To this end,every point would be assigned elevation value in maps.At last,elevation was smoothed within every simple road construct.Experiments with Hong Kong ADAS maps in different conditions were taken in this paper to validate the proposed method.The experiments show that this method is rational and efficient,and meets requirements of 3D maps used in ADAS.