Laser point cloud data high-precision labeling method and system, server and medium

Abstract

The invention discloses a laser point cloud data high-precision labeling method and system, a server and a storage medium, and the method comprises the steps: firstly obtaining a laser point cloud set, carrying out the projection of laser point clouds in a positive angle direction, and obtaining a plane projection view; drawing a rectangular frame for any target object in the plane projection view, extracting a projection point cloud set of the laser point cloud in a coordinate range of the rectangular frame, obtaining extreme values of plane coordinates of points in the projection point cloudset in four directions of the rectangular frame, and assigning the extreme values to coordinates of the rectangular frame; and finally, obtaining a coordinate extreme value of the projection point cloud set in a third direction, combining the coordinate extreme value with the coordinate of the rectangular frame to obtain three-dimensional labeling information of the target object laser point cloud, and generating a three-dimensional labeling frame of the target object. According to the method, the 3D labeling scene is converted into the 2D scene, and the coordinate extreme value is adopted toperform frame selection labeling on the critical range of the target object, so that the accuracy of labeling data is greatly improved, the labeling process is simplified, and a large amount of timeis saved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method and system for high-precision labeling of laser point cloud data, a server and a medium. Background technique [0002] When a beam of laser light hits the surface of an object, the reflected laser light will carry information such as azimuth and distance. If the laser beam is scanned according to a certain trajectory, the reflected laser point information will be recorded while scanning. Since the scanning is extremely fine, a large number of laser points can be obtained, so a laser point cloud can be formed. The point cloud obtained according to the principle of laser measurement includes three-dimensional coordinates (XYZ) and laser reflection intensity (Intensity), and the point cloud obtained according to the principle of photogrammetry includes three-dimensional coordinates (XYZ) and color information (RGB). The point cloud is obtained by combining the pr...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the above-mentioned technical deficiencies, propose a laser point cloud data high-precision labeling method and system, server and medium, and solve the problems of low labeling efficiency and inaccurate data of existing graphic objects

Images