Double-target fixed-precision online detection method and device
A technology for calibration accuracy and detection methods, which is applied in image analysis, instruments, calculations, etc., can solve problems that affect camera functions, cannot be detected in time, and are easy to deform, so as to achieve the effect of ensuring calibration accuracy, ensuring accuracy, and efficient evaluation
Active Publication Date: 2021-04-30
CHANGSHA XINGSHEN INTELLIGENT TECH CO LTD
View PDF1 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The change of the calibration accuracy cannot be observed intuitively. The speed of decline may be related to various factors such as the fixing method and material of the binocular camera. For example, plastic material is easier to deform than metal material.
The traditional regular offline calibration method cannot obtain the calibration accuracy status of the camera in real time. When the external parameters of the camera change, the change cannot be discovered in time, which will affect the camera function.
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
[0041] The present invention will be further described below in conjunction with the accompanying drawings and specific preferred embodiments, but the protection scope of the present invention is not limited thereby.
[0042] like figure 2 As shown, the steps of the dual-objective precision online detection method in this embodiment include:
[0043] S1. Feature point extraction and matching: extract feature points from the binocular images obtained by collecting the same image from the binocular camera to be tested, and match the feature points extracted from the binocular images to obtain multiple feature point pairs;
[0044] S2. Feature point pair screening: select some feature point pairs from multiple feature point pairs as target feature point pairs;
[0045] S3. Calculation of error evaluation parameters: calculate the basic matrix of each target feature point pair, and synthesize the calculated basic matrices to obtain error evaluation parameters for evaluating the ...
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 double-target fixed-precision online detection method and device, and the method comprises the steps: S1, respectively carrying out feature point extraction of a binocular image obtained through the collection of the same image through a to-be-detected binocular camera, carrying out the matching of feature points extracted from the binocular image, and obtaining a plurality of feature point pairs; S2, screening out part of the feature point pairs from the plurality of feature point pairs to serve as target feature point pairs; S3, calculating a basic matrix of each target feature point pair, and calculating an error evaluation parameter for evaluating the calibration precision of the current binocular camera according to the basic matrix of each target feature point pair; and S4, evaluating the calibration precision of the binocular camera to be measured by using the obtained error evaluation parameters. The binocular camera calibration precision real-time online detection method can realize binocular camera calibration precision real-time online detection, and has the advantages of simple implementation method, low cost, high detection efficiency and precision and the like.
Description
technical field [0001] The invention relates to the technical field of camera precision detection and evaluation, in particular to a method and device for on-line detection of dual-target precision determination. Background technique [0002] Binocular calibration refers to obtaining the relative rotation and translation relationship between the binocular cameras through measurement, and the relative rotation and translation are the external parameters (external parameters) of the binocular cameras. The essence of calibration accuracy estimation is to estimate whether the positional relationship between different cameras deviates from the pre-estimated value. like figure 1 As shown, C1 and C2 respectively represent two different camera coordinate systems. When the positional relationship between C1 and C2 is known, then according to the external three-dimensional space point P falls on the point P on the left-eye imaging plane 1 The coordinates of the point P falling on th...
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): G06T7/80G06K9/46
CPCG06T7/85G06V10/40
Inventor 宋堃安向京胡庭波
Owner CHANGSHA XINGSHEN INTELLIGENT TECH CO LTD