Lane line generation method and device, computer readable storage medium and terminal

Abstract

The invention discloses a lane line generation method and device, a computer readable storage medium and a terminal, and the method comprises the steps: carrying out the plane fitting of a part of scene point cloud data, so as to obtain a pavement function; extracting points from the scene point cloud data, wherein the distance between the points and a plane represented by the pavement function is smaller than or equal to a preset distance, so as to obtain pavement point cloud data; dividing at least one part of the road surface point cloud data into a plurality of voxels; the method comprises the steps of sequentially determining a height difference value of two adjacent voxels on a plurality of planes perpendicular to a forward direction according to the forward direction of a vehicle and a preset sequence, and taking at least a part of points in the voxels with relatively large height values as boundary feature points when the height difference value is greater than a preset threshold value; and generating the lane line according to the boundary feature points. In the vehicle driving process, the boundary of the lane can be accurately detected in real time, and the accurate and stable lane line is automatically generated.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, and in particular, to a method and device for generating lane lines, a computer-readable storage medium, and a terminal. Background technique [0002] In the field of autonomous driving, lane lines are an important basis for the driving process of unmanned vehicles. How to detect the boundaries of lanes and generate lane lines has become a very important research topic. [0003] In the prior art, the lane line recognition method is often used to construct the lane line map. For example, image sensors such as cameras are used to identify the road lane lines on which the vehicle is traveling, but this method is easily affected by factors such as light and obstacles. In complex scenes such as tunnels with low light, construction sections with many obstacles, etc., accurate lane lines may not be obtained; alternatively, the existing technology adopts the method of pre-constructing a...

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, lane line recognition is often used to construct lane line maps. For example, image sensors such as cameras are used to identify road lane lines on which vehicles are driving. However, this method is easily affected by factors such as light and obstacles. For example, in In complex scenes such as dark tunnels and construction roads with many obstacles, it may not be possible to obtain accurate lane lines; or, the existing technology uses the method of pre-constructing offline lane line maps, but this method still depends on the location of the vehicle. For specific scenarios, for example, on a road section with poor signal, there is an error between the positioning of the vehicle during automatic driving and the pre-built offline lane line map, which may cause the vehicle to fail to drive normally and safely

Images