Image matching method, depth data measurement methods and depth data measurement system

Abstract

The invention discloses an image matching method, depth data measurement methods and a depth data measurement system. The image matching method includes: acquiring at least two groups of images respectively obtained by photographing at least two encoded structured lights, which are projected in the same photographing space, by first imaging equipment and second imaging equipment, wherein the firstimaging equipment and the second imaging equipment have a predetermined relative position relationship, and in each group of images, an image shot by the first imaging equipment is a first image, andan image shot by the second imaging equipment is a second image; for each group of images, respectively calculating a confidence degree of matching of each window between the first image and the second image of the same group by the same matching window size; and determining windows of mutual matching between the first image and the second image in each group of images on the basis of the confidence degree of matching of each window between the first image and the second image in each group of images. Therefore, the confidence degrees of the small windows are increased through introducing themultiple groups of images, and thus more precise and clearer depth information calculation is realized.

Description

technical field [0001] The present invention relates to binocular imaging, in particular to an image matching method, and a corresponding depth data measurement method and system. Background technique [0002] Image matching is a very important step in the extraction of depth of field (hereinafter also referred to as "depth data") for binocular stereo vision. The goal of this step is to find the corresponding pixel of each pixel of the image on the image of another perspective, calculate the parallax image, and estimate the depth of field image, that is, mark the corresponding depth data at each pixel. [0003] The local stereo matching algorithm can be used for image matching. The basic principle is to select a sub-window in the neighborhood of the pixel given a certain point on an image, and all possible positions in an area in another image , according to a certain similarity judgment basis, find the sub-image most similar to the sub-window image, and the corresponding p...

AI Technical Summary

Problems solved by technology

[0004] In the actual window selection, if the window is large, it contains more information, so it is easy to match, but the granularity is large; if the window is small, although the granularity is small, it is easy to cause false matching

Images