【摘要】 针对车载激光点云中道路边界提取不精确、复杂度高等问题,提出一种基于路缘特征的城市道路边界自动提取方法。首先对点云进行平面规则格网投影,根据测量车行驶轨迹点进行高程过滤,保留地面和路缘石等近地面点云;然后分析路缘石的空间邻域特征,构建路缘石特征描述算子,自动识别不同类型的路缘石边界;最后通过路缘石连续分布特性进行聚类去噪处理,获取精确的道路边界点云。以车载移动测量系统获取的某段道路点云数据为例进行实验,验证了该方法的可行性和有效性。更多还原

【Abstract】 Aiming at the problems that road boundary results are inaccurate in vehicle laser point clouds,and the extraction process is highly complex,this paper proposes a new method to automatically extract urban road boundaries based on curb features for vehicle-borne laser scanning point clouds.Firstly,it projects the point clouds onto regular grids of planes,and it carries out elevation filtering according to the measurement vehicle traveling track points and keeps near ground points such as ground,curb and so on.Then,it analyzes the spatial neighborhood features of curbs and constructs the curb feature description operator to automatically recognize the different types of curb boundaries.Finally,it gets the precise road boundary by clustering and denoising using the continuous distribution of curbs.Some road point clouds data provided by Vehicle Survey System are used in the experiment.The experimental results show the feasibility and effectiveness of the proposed method.更多还原