Detection of Road Poles from Mobile Terrestrial Laser Scanner Point Cloud

Modeling of road furniture such as poles from point clouds is important in many applications such as road maintenance and city planning. In this paper a pipeline for point cloud processing to detect road poles and find their dimensions from unorganized point clouds captured from a kinematic terrestrial laser scanner is proposed. The proposed pipeline is based on a covariance based procedure to perform a 3-D segmentation of terrestrial laser scanning point clouds. Linear feature such as poles can be extracted by using local neighborhoods and based on the analysis of the relative sizes of the eigenvalues. The results of the segmentation will be utilized to extract each pole from the rest of the segmented linear features. Finally the dimension and the position of each pole will be defined.