Low-cost fine map automatic generation method and device and readable medium
An automatic generation, low-cost technology, applied in the direction of measuring devices, image analysis, image data processing, etc., can solve the problem of high cost of fine map collection, and achieve the effect of improving fineness and reliable road information
Active Publication Date: 2022-07-08
SICHUAN DEPT OF TRANSPORTATION HIGHWAY PLANNING PROSPECTING & DESIGN RES INST
View PDF19 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to use the method of "obtaining road geometric information through sensory sensors" to draw a fine map. In view of the current problem of high cost of fine map collection, a low-cost digital camera is used to collect images to generate a fine map. A low-cost fine map automatic generation method, device and readable medium
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
[0046] The flow chart of a low-cost fine map automatic generation method is as follows figure 2 It mainly includes the following steps:
[0047] S1, through the three-dimensional calibration field, the internal parameters of the camera are calibrated, and the internal parameters of the camera are calculated;
[0048] S2, install the calibrated camera on the vehicle, adjust the camera pitch angle so that the bottom of the vertical field of view is tangent to the edge of the front hood of the vehicle, and capture images while the vehicle is traveling to obtain images to be processed;
[0049] S3, extracting lane markings from the to-be-processed image to obtain a lane marking map;
[0050] S4, performing distortion correction and grayscale processing on the lane marking map according to the camera internal parameters and distortion coefficients to obtain a corrected image;
[0051] S5, performing sub-pixel corner detection on the lane markings in the corrected image to obtain...
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 relates to the technical field of digital road map generation, in particular to a low-cost fine map automatic generation method and device and a readable medium. The method comprises the following steps: S1, calibrating internal parameters of a camera through a three-dimensional calibration field; s2, the calibrated camera is installed on the vehicle, images are shot in the vehicle advancing process, and a to-be-processed image is obtained; s3, extracting a lane marking line from the to-be-processed image to obtain a lane marking line graph; s4, performing distortion correction and gray processing on the lane marking image according to the camera internal parameters and the distortion coefficient to obtain a corrected image; s5, performing sub-pixel angular point detection on the lane marking in the corrected image to obtain an angular point coordinate of the lane marking; and S6, adding the angular point coordinates of the lane markings into the navigation map to generate a refined map. According to the method, a low-cost digital camera and a GNSS can be used for collecting road marking information to generate a refined map.
Description
technical field [0001] The present invention relates to the technical field of digital road map generation, in particular to a low-cost fine map automatic generation method, device and readable medium. Background technique [0002] With the development of intelligent driving technology, fine map, as one of its important "sensors", has also entered the public eye and has become one of the key technologies for major Internet companies to compete. Compared with traditional navigation maps, fine maps can provide intelligent driving vehicles with rich and precise lane-level road information, which can not only assist intelligent vehicles in path planning and collision warning, but also improve the accuracy and environmental perception of other sensors in intelligent vehicles. stability. [0003] At present, there are mainly two types of fine map generation technologies. One is to collect road trajectory information by detecting vehicles, such as the patent "Digital Road Map Gene...
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): G01C21/32G01C21/00G06T7/80
CPCG01C21/32G01C21/3815G01C21/3841G01C21/3859G06T7/80G06T2207/30252G06T2207/10004
Inventor 李升甫贾洋周剑郭圆周栓科杨天宇达乾龙南轲许濒支孙晓鹏徐选清易守东叶朋飞
Owner SICHUAN DEPT OF TRANSPORTATION HIGHWAY PLANNING PROSPECTING & DESIGN RES INST