Method for correcting visual inspection target course angle based on radar point cloud and storage medium

Abstract

The invention discloses a method for correcting a visual detection target course angle based on radar point cloud and a storage medium. The method comprises the following steps: S1, acquiring a target attribute and point cloud data of a target vehicle; s2, obtaining coordinates of two angular points, close to the vehicle, of the target vehicle according to the target attribute; s3, solving an equation of the two angular points according to the coordinates; s4, calculating Euclidean distances between all points in the point cloud data and the equation, and removing abnormal points; s5, fitting curves of all points in the point cloud data after the abnormal points are removed, and obtaining a point cloud fitting course angle of the target vehicle; and S6, judging whether the point cloud fitting course angle is valid or not, and if not, returning to the step S4. According to the method, correction of the visual detection target course angle is realized based on the radar point cloud, quantitative analysis is carried out on the course angle fitted by the radar point cloud, and the method has relatively good feasibility and reliability and has very high use value in the aspect of correction of the target course angle in an intelligent driving automobile.

Description

technical field [0001] The invention belongs to the technical field of radar point cloud processing and heading angle, and more particularly relates to a method and a storage medium for correcting the heading angle of a target based on radar point cloud correction. Background technique [0002] In the intelligent driving control system, environmental perception is a vital part of the intelligent driving system, and the forward-looking camera is an indispensable sensor for environmental perception. In addition to identifying lane lines and vehicles, the front-view camera is also an essential part of vehicle heading detection. [0003] At present, when the front-view camera performs vehicle target-level lane line detection, on the one hand, it will be affected by environmental factors such as weather conditions and lighting conditions; on the other hand, it will be affected by factors such as the shape and size of the detected object; It will be affected by the complexity of ...

AI Technical Summary

Problems solved by technology

[0003] At present, when the front-view camera detects vehicle target-level lane lines, on the one hand, it will be affected by environmental factors such as weather conditions and lighting conditions; on the other hand, it will be affected by factors such as the shape and size of the detected object; It will be affected by the complexity of the target detection algorithm and the amount of calculation

The above unfavorable factors have a certain impact on the target accuracy detected by the forward-looking camera, and the target detection accuracy will affect the estimation of the heading angle of the forward-looking target, so there will be a certain probability of abnormality in the target heading angle of the forward-looking detection

Images