A method for determining vehicle yaw angle based on hough transform
A method for determining the yaw angle, which is applied in the field of vehicle active safety systems, can solve problems such as difficult detection and easy wear of lane lines, and achieve the effects of strong anti-interference ability, reliable detection results, and fast recognition speed
Active Publication Date: 2020-11-13
南方电网互联网服务有限公司
View PDF15 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The lane position and shape of structured roads are mainly obtained by detecting lane markings and lane boundaries; however, in actual situations, lane lines on roads are easily worn out, making detection difficult, so special processing is required to accurately determine lane damage lane location
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
[0028] like figure 1 Shown, the present invention is based on the vehicle yaw angle determination method of Hough transform, comprises the following steps:
[0029] S1: Continuously acquire images in front of the vehicle through the vehicle camera with a resolution of 640x 480 pixels.
[0030] S2: Capture each frame of image and cut out the part of the vehicle in front of the sky part, named Roil. Cutting out the sky part in the image can make the subsequent distance calculation more accurate, such as the calculation in step S7.
[0031] S3: Preprocessing Roil, which includes: converting the color image of Roil into a grayscale image, using the Sobel operator to obtain the first-order differential sobelx in the x direction and the first-order differential sobely in the y direction, and obtain the gradient and direction , converted to an 8-bit single-channel image for display.
[0032] S4: Binarize the 8-bit single-channel image converted in step S3 by using the global adapt...
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 vehicle yaw angle determination method based on Hough transform. The method converts the image in front of the vehicle into an 8-bit single-channel image, uses the global adaptive threshold obtained by OTSU to perform binarization, and uses the cumulative probability Hough Transform to obtain a straight line; obtain the length and arc tangent of the slope of the lane line, and judge whether the lane line is a solid line or a dashed line; obtain the distance of the solid line, and take the smallest distance as the real lane line solid line; find the arc tangent of the slope of the dashed line and its weight The difference between the average values, the dotted line with the smallest difference is determined as the real lane line dotted line; finally, according to the detected left and right lane lines, the angle bisector of the angle between the left and right lane lines and the Y axis of the coordinate system is calculated, which is the vehicle yaw angle. The invention has small calculation amount, high recognition accuracy rate, fast recognition speed, can quickly calculate the yaw angle of the vehicle, and can well filter various noise interferences on the ground.
Description
technical field [0001] The invention relates to the field of vehicle active safety systems, in particular to a method for determining a road line yaw angle. Background technique [0002] At present, lane detection is mainly used in the development of smart cars, and most of them are used in the visual navigation system or high lane warning system of smart cars. Due to the complexity of the road environment, most researches on lane detection technology are based on structured roads. Structured roads generally refer to expressways and some well-structured roads. The lane lines and road boundaries on these highways are clear, and the lane lines are generally continuous straight lines, curved lines or dashed lines. The lane position and shape of structured roads are mainly obtained by detecting lane markings and lane boundaries; however, in actual situations, lane lines on roads are easily worn out, making detection difficult, so special processing is required to accurately de...
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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V20/588
Inventor 朱静黄文恺汪程辉陈文达何俊峰江吉昌韩晓英吴羽伍冯洁
Owner 南方电网互联网服务有限公司