High-efficiency focusing stereo matching method based on image segmentation

Abstract

The invention provides a high-efficiency focusing stereo matching method based on image segmentation. A reference image is segmented into different image blocks by utilizing an image segmentation method; Census transformation is simultaneously performed on the reference image and a to-be-matched image to obtain sequence values; dynamic rectification is performed on a to-be-matched pixel parallax scope by utilizing neighborhood pixel parallax; a matching cost function is employed, segmentation blocks are used as support windows, and a cost calculation is performed on the sequence values; and acost aggregation value in each segmentation block is calculated by the movement of windows in a horizontal direction, and a horizontal offset amount corresponding to a minimum cost aggregation value represents an optimal parallax value of a segmentation block. According to the invention, the matching precision of deep discontinuous regions is improved, the calculation efficiency is high, and robustness is good in different illumination environments.

Description

technical field [0001] The invention belongs to the technical field of stereo vision, and in particular relates to a high-efficiency focus stereo matching method based on image segmentation. Background technique [0002] Stereo matching is one of the most important fields in computer vision. Its main purpose is to find corresponding points from stereo image pairs and calculate dense disparity maps. Many algorithms have been proposed in recent decades, which can be divided into global matching algorithm and local matching algorithm based on the difference of cost aggregation process (see literature 1 D.Scharstein and R.Szeliski.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J ]. [0003] IJCV, 47 (1 / 2 / 3:7-42, 2002.). The global matching algorithm usually establishes an energy function according to the respective constraints, and then obtains the disparity result through multiple iterations and optimization of the energy function. The disparit...

AI Technical Summary

Problems solved by technology

However, the rectangular fixed window will bring the boundary blur problem, resulting in the mis-matching of the depth discontinuity area

At the same time, for images with illumination changes and noise, the algorithm also has mismatching

[0007] Document 5 Man Li, Jing Han, Yi Zhang, Lianfa Bai: An improved stereo based oneffective cost aggregation.Proc.SPIE9675AOPC 2015: Image Processing and Analysis, 2015 improved on the existing basis, and did not significantly reduce the error of the depth discontinuity area matching rate

Images