Traffic lane detection method based on equidistant curves

Abstract

The invention discloses a traffic lane detection method based on an equidistant curve modle. The method can be used for recognizing multiple traffic lanes in an image obtained by an on-board camera, is large in recognition range, ensures that the recognition result is not confined to simple curves of straight lines, arcs and the like, also can be used for recognizing traffic lanes with variable curvature radius, recognizing the type of each traffic lane and discriminating real lines from dashed lines and is high in recognition accuracy. The method disclosed by the invention comprises the following steps: performing reversed projection conversion on a panoramic image of the front part of a vehicle, wherein the panoramic image is obtained by the on-board camera; performing filtration and binarization pretreatment on a ground overhead view; performing Hough conversion on the image subjected binarization pretreatment; recognizing the traffic lanes and types thereof in a Hough space.

Description

technical field [0001] The invention relates to a lane line detection method, in particular to a lane line detection method based on an equidistant curve model, and belongs to the technical field of image processing. Background technique [0002] In today's society, cars have become one of the indispensable means of transportation for human beings. With the continuous expansion of car usage, its safety issues have become increasingly prominent. Relevant data from the United States and China's transportation departments show that accidents caused by vehicles deviating from the lane during driving are an important part of traffic accidents. Another report pointed out that nearly 51% of traffic accidents have a lot to do with the driver not realizing that the vehicle has deviated from the lane. Therefore, there is a need for a device that can recognize the position of the lane, and give the driver an early warning signal when the vehicle is about to deviate from the lane. [...

AI Technical Summary

Problems solved by technology

When the detection range is expanded, it is approximated on more complex road surfaces, especially on curves with variable curvature. This detection technology cannot well represent the actual position and shape of the lane line, and even affects the recognition rate.

In addition, most of the existing technologies do not recognize the types of lane lines, such as solid lines and dashed lines

These problems restrict the application of lane line detection technology in unmanned vehicles and other fields that require high detection results to a certain extent.

Images