Computer-vision-based three-dimensional reconstruction method of workpiece surface

Abstract

The invention discloses a computer-vision-based three-dimensional reconstruction method of a workpiece surface. The method comprises: S1, acquiring a microscopic sequence image and performing preprocessing; S2, carrying out fusion on a multi-layer sequence image; and S3, restoring a three-dimensional shape of a workpiece surface and calculating a three-dimensional parameter value. According to theinvention, on the basis of the characteristics of the limited depth of field, multi-layer sequence shooting is carried out on the workpiece surface, image fusion is carried out by software and accurate height information of the workpiece surface is restored, the three-dimensional morphology of the surface is reconstructed, and then the three-dimensional parameters of the roughness of the workpiece surface is calculated. Therefore, the three-dimensional morphology of the common workpiece surface can be evaluated effectively and reasonably.

Description

technical field [0001] The invention belongs to the technical field of machine vision recognition, and relates to a method for three-dimensional reconstruction of workpiece surfaces based on computer vision. Background technique [0002] Surface roughness has a great influence on the working performance of the workpiece surface, so the accurate measurement and reasonable evaluation of surface roughness is particularly important. [0003] At present, among the many detection methods, the stylus method and the optical method are the most traditional, but due to the limited size of the needle of the stylus method and the disadvantages of the needle being easy to damage the surface to be tested, the scope of application is limited; the optical method mostly needs the help of special instruments , the price is expensive, the detection cost is too high, and it also has certain limitations for roughness detection, such as being limited by the wavelength of light. [0004] In the r...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a three-dimensional reconstruction method of workpiece surface based on computer vision, which utilizes the characteristics of limited depth of field of the microscope to take pictures of the workpiece surface in a multi-layer sequence, and then fuses the images by software to recover the accurate height information of the workpiece surface , reconstruct the three-dimensional topography of the surface, and finally calculate the three-dimensional parameters of the surface roughness of the workpiece. On the surface, traditional focusing methods, interferometric methods, and scattering methods have slow measurement speed and inaccurate and comprehensive information.

Images