Building corner space position automatic extraction method in vehicle laser scanning point cloud

Abstract

The present invention discloses a building corner space position automatic extraction method in a vehicle laser scanning point cloud. The method comprises: obtaining the space layering point cloud in a vehicle direction in a local range according to the height of a local building, performing planar projection of the space layering point cloud, and projecting the dispersed laser scanning point cloud to a plane according to the range of the space layering point cloud and the plane coordinates of the space layering point cloud; defining the brightness value of a pixel according to the number of the laser scanning point cloud in a unit pixel on the plane, converting the brightness value of the pixel to a planar projection image; performing linear detection of an area having high brightness in the plane projection image, extracting the line sections having linear features, and merging the line sections; and analyzing the relative position relation and the intersecting angle of the extracted line sections, screening out the line sections which accord with the building corner features through intersecting, solving the coordinates of the line section intersecting corner points in the planar projection image, and calculating the space position information of a corner object according to the coordinates of the line section intersecting corner points in the planar projection image.

Description

technical field [0001] The invention belongs to the technical field of vehicle-mounted laser scanning point cloud data processing, and in particular relates to a method for automatically extracting spatial positions of building corners in a vehicle-mounted laser scanning point cloud. Background technique [0002] The measurement of building corners is one of the important tasks in the survey of topographic maps and cadastral maps. At present, the location information of building corners is mainly obtained through traditional manual measurement methods. The update cycle is long and resource consumption is large, which can no longer meet the requirements of urban construction and management. data requirements. As an advanced measurement method, the vehicle-mounted mobile laser measurement system has the characteristics of fast, non-contact with the measurement object, real-time, dynamic, active, high density and high precision. The building corner extraction methods based on ...

AI Technical Summary

Problems solved by technology

The building corner extraction methods based on the vehicle-mounted mobile laser measurement system mainly include projection image method, feature clustering and scan line method. Influence of Noise Points in Laser Scanning Point Cloud Data

Images