Decoding method based on binocular vision color strip encoding

Abstract

The invention discloses a decoding method based on binocular visual color stripe encoding. The method comprises the following steps that step 1, projection images are shot by adopting a binocular camera; the number of the projection images is two, and the projection images comprise a left image and a right image; step 2, the obtained projection images are preprocessed; the preprocessing means thata median filter is adopted for treatment; step 3, a center line of each stripe is extracted; step 4, a codeword corresponding to each stripe color is identified; and step 5, stripe matching and parallax calculation are carried out, wherein, step2, step3, step4 and step5 respectively process the two images. The decoding method based on the binocular vision color stripe encoding can evaluate a sub-pixel-level pixel coordinate of each center line and pixel-level matching of the left and right images, thereby obtaining a parallax matrix of the images.

Description

technical field [0001] The invention relates to a decoding method based on binocular vision color stripe coding. Background technique [0002] In the past twenty or thirty years, with the rapid development of computer technology, the application of computer vision has transitioned from a fixed two-dimensional plane to an intuitive and flexible three-dimensional three-dimensional. In the highly automated industrial era, the traditional two-dimensional measurement and three-dimensional contact measurement methods can no longer meet the needs of modern production. Therefore, modern industrial production has put forward an urgent demand for three-dimensional non-contact measurement. [0003] Optical three-dimensional measurement technology is a non-contact measurement, which has the advantages of high measurement accuracy, easy implementation and the ability to measure objects with complex surfaces. Therefore, optical three-dimensional measurement technology has been widely used...

AI Technical Summary

Problems solved by technology

However, the detection effect on objects with no texture or less texture on the surface of the measured object is not ideal

With the rapid development of industrial production automation, there is an increasing demand for the detection of objects with no or less texture on the surface of the object, but the current three-dimensional detection technology cannot fully meet its needs.

[0006] The traditional binocular vision system has the characteristics of simple principle and convenient operation, but it is difficult to obtain depth information in scenes and objects with sparse texture, the cost of matching calculation is very high, and the matching success rate is not high. Therefore, it is necessary to design a system based on Decoding Method of Binocular Vision Color Stripe Coding

Images