A Method of Detecting Object Surface Data Point Set Based on Machine Vision

Abstract

The invention relates to a method for detecting an object surface data point set based on machine vision, and belongs to the technical field of machine vision measurement. Firstly, a plurality of thinrings with known inner and outer diameters are pasted on the surface of an object, and the central point of each thin ring can be approximately regarded as a point on the surface of the object; secondly, a world coordinate system of each thin ring is established, an object surface image adhered with the thin ring is shot by using a CCD camera, inner and outer edge curves of each thin ring are fiton a theoretical image plane, and theoretical image coordinates of a central point of each thin ring are solved; and finally, the camera coordinates of the central point of each thin ring are solvedby using the coefficients of the inner and outer edge curve equations of each thin ring and the quadratic curve invariants, thereby obtaining an object surface data point set represented by the cameracoordinates of the central point of each thin ring. Only one camera is used, and under the condition of not calibrating external parameters of the camera, a method of pasting a plurality of thin rings with known internal and external diameters on the surface of an object is adopted, so that non-contact online measurement of a data point set on the surface of the object is realized.

Description

technical field [0001] The invention relates to the technical field of machine vision measurement, in particular to a method for detecting object surface data point sets based on machine vision. Background technique [0002] The detection technology of object surface data point set has a wide range of applications in the fields of component size and position measurement, robot guidance, industrial design, defect detection, reverse engineering and so on. The object surface data point set is an important basis for surface model reconstruction and relative position measurement, and its detection speed and accuracy directly affect the speed and accuracy of object surface construction and position measurement. The existing main methods of detecting object surface data point sets in the industry can generally be divided into contact detection methods and non-contact detection methods. Compared with the traditional contact detection method, the non-contact detection method can rea...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for detecting object surface data point sets based on machine vision, which solves the problem that the detection process of existing object surface data point sets requires more equipment, and the process of calibrating the external parameters of the camera cannot be avoided, resulting in There are technical problems such as cumbersome, inconvenient application and poor accuracy in the process of using machine vision technology to detect data point sets on the surface of objects

Images