Laser radar 3D point cloud ground detection method

Abstract

The invention discloses a laser radar 3D point cloud ground detection method. The problem that an expected ground filtering effect is difficult to achieve in the prior art is solved. The method comprises the following steps: collecting point cloud data of roads around a vehicle; cutting the point cloud data, and determining a region-of-interest range; initializing 3D voxel grids, and obtaining coordinates of each 3D voxel grid in a laser radar coordinate system; traversing all the point cloud data, filling 3D voxel grids corresponding to the coordinates with the point cloud data, and recording indexes; carrying out plane fitting on the point cloud data in each 3D voxel grid, traversing all the point cloud data, calculating the distance from the point cloud data to a plane, comparing a distance threshold value with a height threshold value, and judging whether the corresponding point cloud data is a ground point or not; and sending all point cloud data which are judged to be non-ground points into a clustering algorithm to realize detection of obstacle target points. And for a scene of a single voxel, ground points are identified and distinguished, and an expected ground filtering effect is achieved.

Description

technical field [0001] The invention relates to the field of laser radar detection, in particular to a ground detection method of a laser radar 3D point cloud. Background technique [0002] In recent years, with the development of smart technology, it has been applied in fields such as smart cars or robots. Under certain environmental conditions, the automatic driving of the vehicle can be realized. However, to realize autonomous driving technology, it is necessary to rely on a variety of sensors, such as cameras, lidar, millimeter-wave radar, etc., to perceive the information around the vehicle, and then to control the vehicle to drive within a safe range. This patent involves lidar, which can scan 3D information of objects and is an essential sensor for autonomous driving. [0003] However, when applying the traditional lidar target detection algorithm, one of the key processes is the detection of ground points. The quality of the ground detection results directly affect...

AI Technical Summary

Problems solved by technology

[0006] The present invention mainly solves the problem that the existing technology is difficult to achieve the expected ground filtering effect; it provides a ground detection method of 3D point cloud of laser radar, which divides the point cloud data into grids through 3D voxel grids, and then performs plane simulation Combine and other operations to extract ground points to achieve the expected ground filtering effect

Images