Calibration mapping method and device, equipment and storage medium

Abstract

The invention relates to a calibration mapping method and device, equipment and a storage medium. The method comprises the steps that a first image of a calibration plate at a first set position in a mechanical coordinate system is acquired; determining first feature information of a plurality of calibration points on the calibration plate based on the first image, and obtaining a second image of the calibration plate at a second set position in the mechanical coordinate system; identifying a plurality of calibration points from the second image based on the first feature information; determining a mapping relation between a first image coordinate system of the first set position and a second image coordinate system of the second set position based on first image coordinates of the plurality of calibration points in the first image and second image coordinates of the plurality of calibration points in the second image; and based on the mapping relationship and a predetermined corresponding relationship between the first image coordinate system and the mechanical coordinate system, mapping the coordinates of the second image coordinate system to the mechanical coordinate system. The calibration mapping efficiency can be improved, the error probability of calibration points is reduced, and the calibration mapping accuracy is improved.

Description

technical field [0001] The present disclosure relates to the technical field of machine vision, and in particular, to a calibration mapping method, apparatus, device, and storage medium. Background technique [0002] In machine vision applications, hand-eye calibration is a very critical fundamental problem. Simply put, the purpose of hand-eye calibration is to obtain the correspondence between the mechanical coordinate system and the camera image coordinate system, and finally convert the result of visual recognition to the mechanical coordinate system. The accuracy and precision of the calibration results directly determine whether the vision system can work normally, and the calibration board is the basis of the calibration, and the calibration board fundamentally determines the effect of the calibration. [0003] The nine-point method is a commonly used calibration mapping method, which requires the camera and a marker (eg, a calibration plate, etc.) to move 9 points re...

AI Technical Summary

Problems solved by technology

However, in the process of the calibration mapping method in the related art, it is necessary to manually find multiple calibration points from the image coordinate system of one station that are the same as those in the image coordinate system of another station, which is not only labor-intensive, but also Low efficiency and cannot guarantee the accuracy of calibration mapping

Images