Three-dimensional lane line information generation method, device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a three-dimensional lane line information generation method, a device, electronic equipment and a medium. A specific embodiment of the method comprises the steps of obtaining data; carrying out lane line detection on the road image to generate a lane line information set, wherein the lane line information comprises a lane line pixel point coordinate valuesequence; in response to determining that the lane line information set satisfies a predetermined condition, taking a lane line pixel point coordinate value sequence included in each piece of lane line information in the lane line information set as a first lane line pixel point coordinate value sequence to obtain a first lane line pixel point coordinate value sequence set; based on the first laneline pixel point coordinate value sequence set, generating a first lane line intersection point coordinate value; and generating three-dimensional lane line information based on the first lane line intersection point coordinate value and data of a vehicle-mounted camera of the target vehicle. The three-dimensional lane line information generated by the embodiment of the invention better meets therequirements of the control terminal of the unmanned vehicle on the functions of controlling the vehicle, planning a route and the like.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, device, electronic device and medium for generating three-dimensional lane marking information. Background technique [0002] The three-dimensional lane line information refers to the lane line information extracted and generated from the vehicle driving road data. A common way to generate 3D lane marking information is to generate 3D lane marking information by adding dimensions to the 2D lane marking information. [0003] However, when the above method is used to generate three-dimensional lane line information, there are often the following technical problems: [0004] First, because the existing technology generates 3D lane line information by adding dimensions to 2D lane line information, rather than processing road images to generate 3D lane line information, the reduction ability of 3D lane line information is relatively weak. I...

AI Technical Summary

Problems solved by technology

[0004] First, because the prior art generates 3D lane line information by adding dimensions to 2D lane line information instead of processing road images to generate 3D lane line information, the reduction ability of 3D lane line information is relatively weak. It cannot better represent the actual lane line, and thus cannot better meet the needs of the control terminal of the unmanned vehicle for vehicle control and route planning;

[0005] Second, the accuracy of generating 3D lane line information is low, wasting computing resources

Images