Vehicle-mounted camera on-line self-calibration method based on road surface identification geometrical characteristics
A geometric feature and camera technology, applied in the field of online self-calibration of vehicle cameras based on the geometric features of road markings, can solve problems such as driving safety hazards, high site accuracy requirements, and regular maintenance of the site, and achieve timely state change detection and automation The effect of high and low labor cost
Pending Publication Date: 2021-07-02
TUNG THIH ELECTRONICS (XIAMEN) CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] (1) The precision of the site is high, and site construction costs need to be invested, and the site needs regular maintenance;
[0006] (2) The calibration process requires manual participation, which greatly increases the complexity of calibration;
[0007] (3) When the status of the camera changes, such as the replacement of the rearview mirror of the camera, the vehicle must be returned to the after-sales point for calibration, which increases the manpower and material costs of the after-sales service;
[0008] (4) As time goes by, the camera bracket will inevitably have problems such as vibration and aging, resulting in changes in the camera attitude. If the camera parameters cannot be recalibrated in time, the ADAS system will not be able to make correct decisions, which will affect driving safety. cause great danger;
[0009] (5) Calibration is carried out when the vehicle is stationary, there are few feature points (lines) in the image, and only single frame image information can be used, and the calibration accuracy is not high
[0010] Due to the above problems, the existing vehicle camera calibration technology cannot meet the needs of future unmanned driving
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
[0031] Such as figure 1 As shown, the present invention discloses a method for on-line self-calibration of a vehicle-mounted camera based on the geometric characteristics of road markings, which comprises the following steps:
[0032] Step 1. After the self-calibration of the vehicle camera is started, the current frame image is collected in real time; at the same time, it is detected whether the scene of the current frame image has the characteristics required for calibration. When a scene that meets the conditions is found, perform step 2, otherwise repeat step 1.
[0033] The self-calibration start of the vehicle camera can be triggered in various ways. For example, self-calibration can be initiated by manually triggering a button or switch. Or use the relevant parameters of the on-board camera to start: when the angle of view or focal length of the on-board camera changes, it means that the original calibration parameters of the on-board camera may no longer be applicable...
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 a vehicle-mounted camera on-line self-calibration method based on road surface identification geometrical characteristics, which comprises the following steps: acquiring road surface characteristic information in real time in a vehicle driving process, and using various identification marking lines on a road surface, such as national standard lane lines, sidewalks, or self-defined square and round calibration blocks and the like, for calculating various parameters of the camera automatically. The invention is low in site requirement, low in labor cost, high in calibration precision and timely in camera state change detection, and can solve the problems existing in existing vehicle-mounted camera calibration. The invention has the advantages of being high in automation degree, free of manual participation and high in calibration precision.
Description
technical field [0001] The invention relates to the technical field of vehicle camera calibration, in particular to an online self-calibration method for a vehicle camera based on the geometric characteristics of road surface markings. Background technique [0002] At present, computer vision technology has been widely applied to various advanced driver assistance systems. [0003] (ADAS). Perceiving the road information and road condition information around the vehicle through visual technology can provide the ADAS system with the basic data needed for decision-making. In order to improve the perception accuracy and reliability of the driving environment, accurate calibration of the vehicle camera is an important basis for accurate vehicle positioning. [0004] The traditional vehicle camera calibration algorithm generally adopts a fixed site calibration method. When the vehicle is stationary, high-contrast targets such as black and white checkerboards are placed in adva...
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): G06T7/80G06K9/00G06K9/46
CPCG06T7/80G06T2207/30256G06V20/588G06V10/44Y02T10/40
Inventor 周帝杨梅英苏剑华吴伟花李树应
Owner TUNG THIH ELECTRONICS (XIAMEN) CO LTD