Positioning pose calibration method based on vision and map lane line matching and automobile
A calibration method and lane line technology, applied in the direction of road network navigator, etc., to achieve the effect of improving the robustness of the algorithm
Pending Publication Date: 2022-04-26
CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF1 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the above-mentioned deficiencies in the prior art, the technical problem to be solved by the present invention is: how to provide a vision-based solution that can avoid the problem that deviation data points are involved in the calculation and affect the accuracy of positioning matching, and at the same time will not increase the calculation cost. A positioning pose calibration method matching with map lane lines
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 Construction
[0038] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0039] as attached figure 1 As shown, a positioning pose calibration method based on vision and map lane matching, including the following steps:
[0040] Step 1) Acquire the image information of the road ahead, the map data information and the initial pose of the vehicle. The vehicle is equipped with a vehicle front-view camera, a positioning device and a map module, and the map module has a built-in high-precision map; the attribute information of the lane line and the roadside curve detected in the front road image is obtained through the vehicle front-view camera, specifically , express the lane line and curb curve obtained by the front-view camera of the vehicle as a cubic curve y=C in the vehicle coordinate system 0 +C 1 x+C 2 x 2 +C 3 x 3 , where: y is the coordinates of the vehicle lateral movement direction in the vehicle coordinate syst...
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 positioning pose calibration method based on vision and map lane line matching and an automobile. The method comprises the steps that (1) front road image information, map data information and the initial pose of the automobile are obtained; 2) determining a lane where the vehicle is located according to the front road image information and the map data information; 3) according to the image information of the road ahead and the map data information, calculating the correction amount of the initial pose calibration of the vehicle; and (4) calculating according to the initial pose of the vehicle and the correction amount for calibrating the initial pose of the vehicle to obtain the corrected pose of the vehicle, and outputting the corrected pose of the vehicle. According to the method, the optimal model parameter is found through iteration by using a small number of points, the data points with large deviation are eliminated, the situation that the large-deviation data points participate in operation and influence the accuracy of matching positioning is avoided, the robustness of the algorithm is improved, meanwhile, the positioning accuracy and the calculation cost in the method have no obvious restriction relation, and the calculation cost cannot be increased.
Description
technical field [0001] The invention relates to the technical field of smart cars, in particular to a positioning pose calibration method based on vision and map lane line matching and a car. Background technique [0002] Vehicle positioning is a very important content in vehicle navigation technology and automatic driving technology. At present, vehicle positioning is mainly based on RTK (Real-time kinematic, real-time dynamic carrier phase difference technology) and high-precision GPS (Global Positioning System), and its accuracy can reach 20 cm. However, this accuracy cannot meet the localization needs of autonomous vehicles on lane lines. [0003] In order to solve the problem of low positioning accuracy in the prior art, a high-precision positioning device and method based on lane line feature matching are disclosed in the invention patent with the application number CN201811023537.4. According to the vehicle position acquired by the positioning module, the method will...
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 IPC IPC(8): G01C21/30G01C21/34G01C21/36
CPCG01C21/30G01C21/3446G01C21/3658
Inventor 汤兆丰王宽任凡
Owner CHONGQING CHANGAN AUTOMOBILE CO LTD