Error evaluation method for binocular camera calibration result

A technology for binocular camera and error evaluation, which is used in image data processing, instrumentation, computing, etc.

Pending Publication Date: 2020-03-17
南京美基森信息技术有限公司
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This image is dedicated to the evaluation of calibration results

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Error evaluation method for binocular camera calibration result
  • Error evaluation method for binocular camera calibration result

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be further described below in conjunction with drawings and embodiments.

[0025] 1. The calibration board used for error evaluation can be different from the calibration board used for dual-objective calibration. Since the method of error evaluation is to compare the Y-axis coordinates of the corner point pairs, and the average maximum value of the curvature of the curve, the number of corner point pairs, and the number of curves, the more accurate and stable the error evaluation is, therefore, for The calibration board for error evaluation is specially made. The number of corner points on the calibration board can be 30*30 pairs, and the number of corresponding curves is 30+30.

[0026] 2. The process of image binarization operation, because the average intensity of light in different areas is different, if the same threshold is used globally, it is easy to filter out the curve of a certain image area, or the non-curve error of a certain ima...

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

No PUM Login to view more

Abstract

The invention provides an error evaluation method for a binocular camera calibration result. In industrial production, for binocular camera calibration, a stable and reliable method is needed to determine the calibration quality so as to help to judge a calibration result and determine whether re-calibration is needed or not. Existing double-target positioning accuracy evaluation researches are few, and the method has obvious limitation and cannot be applied to the industrial environment. According to the error evaluation method special for the binocular camera calibration result, through corner detection and curve detection, the matching error of the corrected positions of the left corner and the right corner and the curvature of the curve are further calculated and used for judging whether double-target calibration is qualified or not. The method is simple and accurate, can give a clear calibration evaluation result, and is suitable for meeting the requirements of binocular camera calibration result evaluation in an industrial scene.

Description

technical field [0001] The invention relates to a method for evaluating camera calibration results, in particular to an error evaluation method for binocular camera calibration results. Background technique [0002] In the field of binocular stereo vision, the calibration of binocular cameras is the basis of subsequent calculations, and its calibration accuracy has a great impact on the accuracy of subsequent calculations: large calibration errors will lead to calculation errors, which will lead to a decrease in the calculation accuracy of the entire disparity map. reduced sex. [0003] In industrial production, for binocular camera calibration, a stable and reliable method is needed to determine the quality of the calibration to help judge the calibration results and determine whether re-calibration is required; [0004] The binocular camera calibration is divided into two steps: (1) monocular camera calibration; (2) binocular correction, that is, to correct the images of ...

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
no application Login to view more
IPC IPC(8): G06T7/80
CPCG06T7/80
Inventor 李行李杨丁鹏飞霍志坤蒋桐古峥
Owner 南京美基森信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap