Robot visual calibrating method based on perspective transformation model

Abstract

The invention discloses a robot visual calibrating method based on a perspective transformation model. The relation between a pixel coordinate system and a robot coordinate system is built according to a perspective transformation principle between plane coordinate systems; and four sets of pixel coordinates and robot coordinates are acquired by using four non-collinear marking points to calibrateand calculate coordinate conversion model parameters for visual guide robot positioning. The method can be used for calibrating fixed cameras or terminal cameras mounted on robots without consideringthe depth direction, and is low in cost, high in calibrating precision and suitable for visual positioning requirements of industrial scene robots.

Description

technical field [0001] The invention belongs to the technical field of robots and relates to visual calibration technology, in particular to a robot visual calibration method based on a perspective transformation model. Background technique [0002] With the continuous development of science and technology, the use of robots is becoming more and more frequent, and more and more industrial fields are beginning to use robots to replace manual work, such as using machine vision to replace traditional detection, measurement, identification and positioning guidance that require human eyes and other repetitive work. In vision applications, such as measurement and positioning, vision calibration is essential. Existing calibration methods can be roughly divided into three categories: traditional calibration methods, active vision calibration methods and self-calibration methods. [0003] The calibration methods in the prior art have different problems and defects, mainly including:...

AI Technical Summary

Problems solved by technology

[0003] The calibration methods in the prior art have different problems and defects, mainly including: the accuracy of the active visual calibration method and the self-calibration method is not as good as the traditional calibration method, and cannot meet the accuracy requirements of the industrial field robot vision calibration; the traditional calibration method combined with high-precision calibration board, the calibration results are highly accurate, but the calibration process is cumbersome; for example, the representative Zhang Zhengyou checkerboard calibration method requires about 20 checkerboard images taken in different directions to detect all checkerboard corners, and the calibration process is more complicated

Images