Target vehicle course angle calculation method based on three-dimensional laser radar

Abstract

The invention relates to a target vehicle course angle calculation method based on a three-dimensional laser radar. The method comprises the following steps of 1) using the three-dimensional laser radar installed on a vehicle top to collect a target vehicle and acquiring point cloud data of the target vehicle; 2) establishing a corresponding course angle parameter model of the target vehicle at a moment in a radar coordinate system; 3) according to the point cloud data of the target vehicle, calculating a distribution type of the target vehicle; 4) according to the distribution type of the target vehicle, carrying out cluster on target vehicle point cloud respectively so as to acquire an area of interest, wherein the area of interest indicates a main portion of a representation course angle; 5) according to a cluster result and the distribution type of the target vehicle, carrying out straight line fitting on two kinds of point cloud components respectively; 6) through combining the distribution type of the target vehicle with a corresponding straight line fitting result of the two kinds of point cloud components, calculating the course angle of the target vehicle. The method can be widely used in an intelligent vehicle environment perception technology field.

Description

technical field [0001] The invention relates to the technical field of environment perception of modern traffic intelligent vehicles, in particular to a method for calculating a heading angle of a target vehicle based on a three-dimensional laser radar. Background technique [0002] Three-dimensional lidar can capture the basic shape features of the target and enrich local details, and has the advantages of reliability and high measurement accuracy. It is currently widely used in intelligent vehicle environment perception. As an important content of perception, the vehicle target heading angle plays an important role in judging the target's lane-changing intention and other behaviors, and is the basis of intelligent vehicle path planning and decision-making algorithms. However, due to the inherent characteristics of 3D lidar, the point cloud distribution of the vehicle target is affected by factors such as the position of the observation point and self-occlusion, making it d...

AI Technical Summary

Problems solved by technology

On this basis, some studies first use statistical analysis methods to remove outlier point clouds. Considering the self-occlusion characteristics of the target, the principal component analysis method often cannot obtain the real movement direction of the target, so the random sampling consensus algorithm is used to calculate the vehicle heading angle. However, it is difficult to remove outliers in practical applications, thus limiting the application of this method

Images