Method for detecting boundary of lane where vehicle is

Abstract

The invention discloses a method for detecting a boundary of a lane where a vehicle is, which comprises the steps of: first adaptively extracting edge points for the part below a horizon of a road image according to pixel gradient amplitudes and calculating an edge direction, then searching and positioning a lane boundary by utilizing the particle swarm optimization in a parameter vector space ofa lane boundary projection model according to the extracted edge points, the edge direction and the lane boundary projection model; finally, calculating a plane geometric structure of the lane wherein the vehicle is, a position of the vehicle in the lane and an angle of deviation according to the searched lane boundary projection model parameter values and a parameter calculation method. The method can reflect an actual lane boundary curve more accurately, has better environment self-adaption capability, enhances the robustness of the lane detection, and has high reliability and strong antijamming capability.

Description

technical field [0001] The invention belongs to the technical field of intelligent vehicle environment perception, and relates to a lane boundary detection method. Background technique [0002] In intelligent transportation systems, lane detection technology is an important part of intelligent vehicle environment perception technology, which is mainly used in vehicle intelligent cruise control, vehicle lateral control, lane departure alarm, vehicle autonomous driving, etc. Vision is the environment perception method most used by human-driven vehicles. Most vehicles drive on structured roads, and the representation of structured roads is oriented to human vision. Visual perception is one of the most effective and important technical means for lane detection. one. [0003] In the existing vision-based lane detection technology, the lane detection method for structured roads can be summarized into three important components: defining a lane model, extracting lane features, and...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the inability of the prior art to detect lane boundaries under complex and harsh conditions and to provide lane plane geometric structure information, the position and direction of vehicles in the lane, the present invention provides a lane boundary detection method where the vehicle is located. The method not only It can detect the boundary of the lane where the vehicle is located in the general road environment, and can detect the boundary of the lane where the vehicle is located in the complex and harsh road environment, such as shadows, cracks, vehicles, sunlight reflection, dim light, worn lane markings, etc. on the road, and It can measure the geometric structure parameter value of the lane, the position and direction of the vehicle in the lane

Images