Lane line detection method based on straight lines with maximum length

Abstract

The invention provides a lane line detection method based on straight lines with the maximum length.The lane line detection method includes the steps that 1, the lower half of a driving image is cut out, and edge detection is conducted on the lower half, an image is obtained after edge detection, and Hough straight line expansion is conducted on the image obtained after edge detection; 2, the straight lines, with the maximum length, located at the left side and the right side of the vertical center line of the image are selected from straight lines obtained through Hough straight line expansion; 3, the straight line, with the maximum length, on the left side is used as the left edge, the straight line, with the maximum length, on the right side is used as the right edge to define a binarization processing region, and the binarization processing region is processed in a binarization mode to obtain a binarization graph; 4, Hough straight line detection is conducted on the binarization graph, and the left and right straight lines close to the vertical center line of the image are selected as the true left and right lane lines.Color and shape information of lane line markers is fully used, and correctness of detected lane lines is ensured by using the method based on the straight lines with the maximum length and gray scale verification.

Description

technical field [0001] The invention belongs to image processing and pattern recognition technology, in particular to lane line detection and tracking. Background technique [0002] CN103617412 The lane line detection method based on the vanishing point adopts the process of area segmentation, straight line detection, vanishing point calculation, vanishing line calculation, and reverse solution to the lane line. It is essentially a statistics-based lane line detection method. The effect is better when it is a real lane line, but for the virtual lane line, this method shows its instability, repeatedly jumping between the real lane line and the virtual lane line, and when the real lane line is detected incorrectly The tracking will always go wrong. Considering the fact that there are a large number of virtual lane lines, the lane line detection method based on the vanishing point is unreliable. [0003] The biggest feature of lane markings is color and shape information. Howe...

AI Technical Summary

Problems solved by technology

[0002] CN103617412 The lane line detection method based on the vanishing point adopts the process of area segmentation, straight line detection, vanishing point calculation, vanishing line calculation, and reverse solution to the lane line. It is essentially a statistics-based lane line detection method. The effect is better when it is a real lane line, but for the virtual lane line, this method shows its instability, repeatedly jumping between the real lane line and the virtual lane line, and when the real lane line is detected incorrectly The tracking will always go wrong, considering the fact that there are a large number of virtual lane lines, the lane line detection method based on the vanishing point is unreliable

[0003] The biggest feature of lane markings is color and shape information. However, it is difficult to correctly identify lane markings by using color or shape information alone, especially in complex scenarios such as lighting, damaged lane markings, and heavy vehicle traffic. Each individual features become unreliable

Images