Automatic driving lane information detection method based on radar point cloud and image fusion

Abstract

The invention discloses an automatic driving lane information detection method based on radar point cloud and image fusion, and relates to the technical field of automatic driving perception. According to the method, more precise driving semantic information including a center line, a course angle, a stop line and the like is calculated through lane line information detected in real time. The method has an exception handling function, deals with exceptions such as lane line recognition errors and lane line loss, and prevents unknown errors in the running process of the vehicle. The unmanned vehicle can perceive the road semantic information of the surrounding road surface in real time by deploying the method, the vehicle is assisted to carry out a driving task, and the method has very good robustness and detection success rate.

Description

technical field [0001] The invention relates to the technical field of automatic driving perception, in particular to a detection method for automatic driving lane information based on radar point cloud and image fusion. Background technique [0002] The traditional lane line detection method is mainly based on the image method for lane line detection, which is divided into traditional methods and deep learning methods, and the hardware system mainly depends on the camera and the corresponding computing unit. In addition, based on the laser radar lane line detection system, the laser radar sensor sends and receives laser pulses to form a radar point cloud image. The early lane line detection method based on the radar point cloud is to separate the lanes in the point cloud by setting the point cloud reflectivity threshold. Line points and non-lane line points rely mainly on the hardware system of lidar and corresponding computing units. [0003] In the traditional lane line ...

AI Technical Summary

Problems solved by technology

[0003] In the traditional lane detection system, the normal operation of the image-based lane detection algorithm depends on good lighting conditions, and in the face of complex road environments such as vehicles blocking the lack of lane lines, the accuracy of the algorithm model is significantly reduced, and it is difficult to meet the requirements of unmanned vehicles. Driving task requirements; the lane line detection system based on radar point cloud, due to the discontinuity of radar point cloud, it is easy to cause false detection and missed detection, and at the same time, it is difficult to match the model obtained by training the point cloud data collected on different models to other models. On the radar, this has caused a situation where a single lane line detection method cannot 100% meet the needs of lane line detection

Images