Simple matching method based on datum point

Abstract

The invention discloses a simple matching method based on a datum point in a stereo vision system. The method comprises the following steps: introducing a characteristic light source transmitter into the stereo vision system; taking the datum point generated by a characteristic light source as a basic point, describing feature points in a reference coordinate system image according to a specific law (longitudinal arrangement); and by adopting a matching restraint rule, finding out the feature points matched with the feather points in the reference coordinate system image from an offset coordinate system image to realize simple, convenient and fast stereo vision matching. The stereo vision system using the method comprises a computer, two CCD cameras arranged on a support, and the light source transmitter arranged in the middle position of the two CCD cameras, wherein, the two cameras are placed in parallel, and the computer is installed with an image processing program. The simple matching method can avoid using a complicated stereo matching algorithm and improve real-time performance and practicability of the stereo vision system without increasing cost of the stereo vision system.

Description

technical field [0001] The embodiment of the present invention relates to a three-dimensional vision processing technology, in particular to a simple matching method based on a reference point in a stereo vision system. Background technique [0002] The basic principle of binocular stereo vision technology is to observe the same scene from two or more viewpoints to obtain images of objects under different perspectives, and to obtain three-dimensional information by calculating the position deviation (ie parallax) between image pixels through the principle of triangulation. A complete stereo vision system includes image acquisition, camera calibration, feature extraction, stereo matching, 3D information recovery and subsequent processing. Among them, feature extraction and stereo matching are the key technologies in stereo vision, and they are also difficult points. The quality of the results seriously affects the accuracy of subsequent 3D information recovery. [0003] Ster...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above-mentioned problems existing in the prior art, after the research on the stereo vision system, it is found that the most time-consuming processing module in the whole system is the stereo matching module. The characteristic light source imaging point pair is used as the initial matching point, which can simplify the matching problem, reduce the difficulty of stereo matching, and improve the real-time performance of the stereo matching algorithm

Images