Deep learning-based lane line detection and vehicle transverse positioning method

Abstract

The invention discloses a lane line detection and vehicle transverse positioning method based on deep learning, and the method comprises the steps: firstly training a deep learning network, and then obtaining the parameters of each lane line in an image; and finally, according to the parameters of each lane line, obtaining the transverse positioning information (the serial number of the lane where the vehicle is located and the distance between the vehicle and the left and right lane lines of the lane where the vehicle is located) of the vehicle. According to the method, the advantage of deep learning image feature extraction is exerted, a post-processing module which consumes long time is omitted, and the parameters of the lane lines in the image and the transverse positioning information of the vehicle can be predicted more accurately and quickly.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a deep learning-based lane line detection and vehicle lateral positioning method. Background technique [0002] As the input of the automatic driving decision planning module, the lateral positioning information has a very important impact on the safety of automatic driving, and the result of lane line detection directly affects the accuracy of the lateral positioning of automatic driving. At present, lane line detection is mainly divided into two schemes: methods based on traditional image processing and methods based on deep learning. [0003] The main steps of the method based on traditional image processing are: image preprocessing, filtering the interference items in the image, manually selecting features according to the difference between the lane line pixel features and surrounding pixel features, extracting the feature information of the lane lines, and...

AI Technical Summary

Problems solved by technology

This method mainly relies on manual selection of features, and the effect is not good when the lane line is occluded, missing, and illumination changes, and the robustness is poor.

[0004] The method based on deep learning relies on big data. The model obtains the characteristics of lane lines through autonomous learning. Learning has a high demand for computer hardware, and the obtained lane line features need to be clustered, fitted and other post-processing operations to obtain useful lane line parameters, which takes a long time and is difficult to meet the real-time requirements of automatic driving

Images