Multi-lane lane line detection method
A lane line detection and lane line technology, which is applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve the problem of not being able to accurately identify multi-lane lane lines in real time, improve detection accuracy, reduce calculation load, Effect of improved detection accuracy
Active Publication Date: 2021-08-10
重庆利龙中宝智能技术有限公司
View PDF10 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005]
The purpose of the present invention is to overcome the shortcomings of the prior art that cannot accurately identify multi-lane lane lines in real time, and provide a multi-lane lane line detection method, which has strong applicability on structured roads and has high accuracy and real-time
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0058] Such as figure 1 As shown, the present embodiment provides a multi-lane lane line detection method, comprising the following steps:
[0059] S1, collect the road image, select the region of interest of the road image, obtain the first image, grayscale the first image, and obtain the grayscale image;
[0060] S2, extracting the image contour in the grayscale image through an edge detection algorithm, and then performing a binarization operation to convert the image into a binary image;
[0061] S3, identifying the lane line candidate line of the current lane through Hough line detection;
[0062] S4, determine the sliding window detection position based on the lane line candidate line of the lane acquired in step S3, and further detect the lane line of the lane by using the sliding window method;
[0063] S5. Judging the color of the lane line of the current lane. If one side of the lane line of the current lane is a yellow line, the side lane detection is not performe...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a multi-lane lane line detection method, which comprises the following steps of: S1, acquiring a road image, selecting an interested area of the road image, and graying to obtain a gray image; S2, extracting an image contour in the grayscale image through an edge detection algorithm, and then converting the image contour into a binary image; S3, identifying lane line candidate lines of the lane through Hough straight line detection; S4, determining a sliding window detection position based on the candidate line of the lane line obtained in S3, and further detecting the lane line of the lane by adopting a sliding window method; S5, judging the color of the lane line of the lane, and if one side of the lane line is a yellow line, not detecting the side lane of the side; if one side of the lane line is not the yellow line, carrying out side lane detection on the side; S6, based on the lane line of the current lane, identifying a side lane candidate line through vanishing point detection and Hough straight line detection; and S7, determining a sliding window detection position based on the candidate line of the side lane line obtained in the step S6, and further detecting the side lane line by adopting a sliding window method.
Description
technical field [0001] The invention relates to the field of image detection, in particular to a multi-lane lane line detection method. Background technique [0002] The lane line detection function is an important part of the road environment perception system. Lane line detection is mainly based on camera images for detection and recognition. At present, there are two mainstream detection methods, one is the traditional image processing algorithm based on Hough line detection and sliding window detection; the other is the deep network detection algorithm based on the semantic segmentation network in deep learning. In the traditional image processing algorithm, the original image is binarized first, and then the algorithm based on Hough line detection is used as the core to detect the line area in the binary image and screened to obtain the lane line; The perspective obtains better preprocessing effect, obtains the key points of the lane line through the sliding window an...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06N3/04
CPCG06V20/588G06V10/48G06V10/44G06V10/56G06N3/045
Inventor 段鸿陈方荣朱浩王强
Owner 重庆利龙中宝智能技术有限公司