Road marking extraction method based on forward camera in automatic driving

Abstract

The invention provides a method for extracting road markings based on a forward-facing camera in automatic driving, which obtains an orthographic view of the road markings in front of the current vehicle through inverse perspective transformation, and constrains Currently solve the road segmentation initialization threshold, use the initialization threshold to segment the orthophoto view, judge whether the edge pixels are parallel, and the projection histogram is equidistant, and finally extract the lane lines, road traffic signs, and vehicle stop lines. , Zebra crossing and other road markings. The method for extracting road markings in the present invention has a high execution rate, and by operating the projection histogram, the influence of incomplete image details on detection and extraction can be reduced, and the robustness of the extraction method can be improved. At the same time, a small amount of prior knowledge constraints are added, and the technical means of approximation, divide and conquer, and dimensionality reduction are used to further reduce the range of extraction accuracy and limit the processing of some road scene sub-regions.

Description

technical field [0001] The invention relates to the field of traffic information detection in the automatic driving industry, in particular to a method for extracting road markings based on a forward camera in automatic driving. Background technique [0002] With the development of computer science and robotics, self-driving vehicles have been widely used in military, civil and scientific research, etc., and it has concentrated the latest research results of multiple disciplines such as structure, electronics, cybernetics and artificial intelligence. ,have a broad vision of application. [0003] Being able to detect the current road driving environment in real time is the core function of autonomous driving and vehicle autonomous driving technology, and the real-time extraction of road markings such as lane lines and road traffic signs is an important prerequisite for a safe and intelligent driving environment. [0004] At this stage, most camera-based road marking extracti...

AI Technical Summary

Problems solved by technology

[0004] At this stage, most camera-based road marking extraction methods have high requirements on the image acquisition environment. For example, the collected image may only contain the part of the road where the current vehicle is driving. Once it is applied in a complex urban traffic environment, it is extremely difficult. It is susceptible to interference from environmental factors such as other vehicle bodies and tree shadows on both sides of the road, and cannot obtain accurate extraction results

Images