Intelligent calibration method for internal and external parameters of binocular camera based on coding plane target

Abstract

The invention discloses an intelligent calibration method for internal and external parameters of a binocular camera based on a coding plane target, and the method comprises the steps: employing two cameras to shoot coding plane targets in different attitudes in a space at the same time, and obtaining a plurality of coding plane target images; respectively obtaining a sub-pixel-level coordinate, a unique coding sequence number and a target coordinate of each calibration angular point in the coding plane target image by using a coding plane target decoding method; obtaining G1 left camera calibration images and G2 right camera calibration images according to a set threshold value of the number of calibration angular points and a space attitude threshold value of the coding plane target; and respectively solving internal and external parameters of the two cameras and a rotation and translation relation between the left camera and the right camera. According to the invention, the automatic calibration of the binocular camera can be realized, the calibration of the binocular camera can be completed by fully utilizing the local coding plane target image when the calibration is limited by the range of a public view field, and the applicability and robustness of the calibration of the multi-camera are improved.

Description

technical field [0001] The invention relates to the field of camera calibration in the field of computer vision, in particular to an intelligent calibration method for internal and external parameters of a binocular camera based on a coded plane target. Background technique [0002] Computer vision technology is widely used in industrial control, metrology and other fields. Computer vision technology mainly uses camera imaging to obtain three-dimensional information of the measured object in space through image information, thereby reconstructing and identifying the object. The fundamental problem of computer vision technology is camera calibration. The mapping relationship between three-dimensional coordinates of space and two-dimensional coordinates of images can be obtained through camera calibration technology. Camera calibration technology is the research focus of computer vision measurement technology. The task of camera calibration is to solve the Internal and externa...

AI Technical Summary

Problems solved by technology

[0003] In 1986, Roger Tsai proposed a camera calibration algorithm based on radial constraints, which required a 3D stereo target, making the calibration process inflexible; around 1999, Zhang Zhengyou (Z.Y Zhang) proposed a camera calibration algorithm based on a plane target, the calibration The algorithm uses a plane target that does not contain direction information and coding information. During the calibration process, the rotation direction of the plane target without direction information cannot be judged, and the camera calibration algorithm based on the plane target proposed by Z.Y Zhang requires the camera to capture the complete However, in the actual calibration process, the camera often fails to capture a complete planar target. At this time, it is difficult to perform camera calibration and ensure the accuracy of camera calibration using traditional planar targets that do not contain direction information and encoding information.

Images