Image matching method based on deep planar constraint graph cut optimization

Abstract

The invention provides an image matching method based on deep planar constraint graph cut optimization. The image matching method includes selecting an image pair to be matched of any view, dividing the areas under the view to obtain all deep planes under the view, establishing energy functions for left and right boundary pixel points for all deep planes, establishing grid charts for all deep planes by using the adjacent relations between the left and right boundary pixel points of the deep planes of the image pair to be matched under the view, solving the minimal cut of the grid chart of each deep plane to obtain the parallax value of the left and right boundary pixel points of all deep planes of the image pair under the view in each energy function scope, shielding to determine the final parallax value of all deep planes of the image pair to be matched under the view according to the parallax result and generating the matching result according to the parallax value. The method overcomes the excess smoothness, and shielding problems and substantially reduces computational complexity.

Description

technical field [0001] The invention relates to processing technology in the field of computer vision, in particular to an image matching method based on depth plane constrained graph cut optimization. Background technique [0002] Stereo matching refers to finding the corresponding relationship between stereo image pairs. It is one of the important problems in the field of computer vision and has been widely cited in the fields of military, aerospace, digital medicine, modern industrial design, and media. [0003] Existing stereo matching methods are mainly divided into two categories: algorithms based on local constraints and algorithms based on global constraints. The algorithm based on local constraints uses the local information around the interest point for calculation, which involves less information and lower computational complexity, but is easily affected by noise, and the matching effect on non-textured or sparsely textured areas is not ideal. The method is the a...

AI Technical Summary

Problems solved by technology

However, due to the convexity requirements of the function term, problems such as occlusion constraints cannot be solved

The second type of method uses smooth terms with non-convex properties. At this time, the optimization problem of the energy function is an NP-hard problem, and only the circular method can be used to obtain the global suboptimal solution.

Due to the use of non-convex function terms, problems such as occlusion constraints can be dealt with, but this part of the process requires a large amount of calculation

Images