Quick stereo matching method based on graph cut

Abstract

A quick stereo matching method based on graph cut is used for stereo matching of at least two images. The method mainly comprises the following four steps: obtaining and preprocessing an image pair subjected to epipolar calibration, respectively building multi-resolution pyramids for a first image and a second image, carrying out stereo matching on the (low-resolution) image pair of a higher-layer pyramid, and transmitting the matching result of the image pair of the higher-layer pyramid to the lower-layer image layer by layer. The quick stereo matching method uses the global stereo matching algorithm based on graph cut to evaluate the parallax between at least one point in the first image and at least one corresponding point in the second image, and uses the multi-resolution pyramids to accelerate. The method has the advantages of high precision and high operating efficiency and can be applied to three-dimensional measurement.

Description

technical field [0001] The invention relates to a fast stereo matching method based on graph cut, which belongs to the technical field of computer vision. Background technique [0002] Stereo matching is the most important and complex part of the stereo vision system. It mainly uses a series of algorithms to find the matching points in the stereo image pair and obtain the disparity map, and then uses the triangular geometric relationship to calculate the depth of the midpoint in space to generate the depth of the image. picture. When an object in space is projected into a planar image, all the optical information of the object is represented by the gray value in the image. is very difficult. [0003] According to the range of image pixels involved in the calculation, stereo matching methods can be divided into local matching methods and global matching methods. Among them, the local matching method is fast to calculate, but it often has a high error matching rate for low-...

AI Technical Summary

Problems solved by technology

Among them, the local matching method is fast to calculate, but it often has a high error matching rate for low-texture areas, resulting in blurred boundaries, and it is also difficult to deal with occluded areas. The most typical method is the regional matching method; the global matching method is due to It is global optimization, so the matching accuracy is high, but the amount of calculation is too large and the calculation time is long. The most typical method is graph cuts.

Images