Step-by-step calibration method for camera parameters of binocular stereoscopic vision system

Abstract

The invention relates to a step-by-step calibration method for the camera parameters of a binocular stereoscopic vision system and belongs to the field of image processing and computer vision detection, which relates to a step-by-step calibration method for the camera intrinsic and external parameters of a dimension measurement system for large-scale forgings. According to the calibration method, firstly, the intrinsic parameter matrix of a camera is calibrated in the off-line manner in a laboratory, and the camera is driven to conduct two sets of mutually independent triorthogonal motions by a high-precision electric control platform. Secondly, based on the properties of FOD points, the intrinsic parameters of the camera are listed through the unique solution of a linear equation. At a forging experiment site, a basic matrix between two images is figured out through the 8-point method, and the method of decomposing of an essential matrix is conducted. In this way, the real-time on-line calibration for the external parameters of the camera is realized. Finally, based on the image information, the length of a high-precision three-dimensional scale is reconstructed, so that the solution of a camera scale factor is realized. The above method is simple and convenient in calibration process, short in calibration time and high in precision. The calibration of the camera of the binocular vision measurement system at the forging site can be precisely realized by adopting fewer images.

Description

technical field [0001] The invention belongs to the field of computer vision detection, in particular to a step-by-step calibration method for internal and external parameters of a camera of a binocular stereo vision system. Background technique [0002] Binocular stereo vision is to obtain the geometric three-dimensional information of the object according to the two-dimensional image information of the two pictures captured by the binocular camera at the same time. Recovering the three-dimensional information of an object from two-dimensional image information depends on the model of the binocular vision system. The most important thing is to determine the imaging geometric model of the camera. The parameters of the geometric model are called camera parameters. The camera parameters include internal parameters and external parameters. The internal parameters are parameters related to the geometric and optical characteristics of the camera, and only depend on the manufactur...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art. Aiming at the problem that the traditional calibration method at the forging site strictly relies on high-precision auxiliary calibration, and the calibration method is complicated and has poor real-time performance, a binocular stereo vision system camera internal A step-by-step calibration method of offline calibration of parameters and real-time online calibration of external parameters

Images