影像辅助下基于地面LiDAR的建筑物特征精细提取方法

Fine Feature Extraction for Architecture Based on Terrestrial Li DAR Assisted by Image

面向建筑物精细建模,探讨了在影像辅助下基于地面Li DAR的建筑物几何特征精细提取方法.首先在基于梯度方向进行建筑物特征初步提取的基础上,引入建筑结构完整性约束规则,进行了特征边缘线段合并与角点处特征线的闭合处理.然后利用影像与Li DAR点云配准关系将建筑物影像特征线映射到三维点云空间,即获得影像三维空间坐标.在此辅助下,最后通过估算点云法向、曲率,得到精细的几何特征,从而更好地表达地理场景中的建筑物.研究实例表明,本文的特征提取方法严谨可靠,能有效提高点云特征提取的效率和精度.

Geometrical feature exaction method based on terrestrial LiDAR （Light Detection And Ranging ） assisted by image was put forward for architecture fine modeling. The processing programs included 3 steps. Firstly, primary features were extracted based on the gradient direction,and the feature lines merging and the closure in the inflection points were further processed according to the integrity rules of building elements.Secondly,2D image feature lines＇ project to 3D point cloud space was implemented based on the registration model of image and LiDAR（ data from the Riegl LMS-Z420i three-dimensional laser scanner system）, and then the 3D point cloud data around 3D feature lines were searched with the restraint of feature lines, which narrowed and defined the searching area. Finally, the accurate 3D feature lines were obtained after a serious of operations of ＂area classification-plane fitting-feature line extraction＂ on the point cloud data around the feature lines, which involved the estimation of the normal vector and curvature of point cloud for the better presentation of architecture modeling. At the end of the paper, the precision estimation of the method from some sampled line segments proves that the feature extraction method is precise and reliable, improving the efficiency and precision of the feature extraction as well.