Nonlocal stereo matching algorithm combined matching cost algorithm and parallax joint filling algorithm

Abstract

The invention discloses a nonlocal stereo matching algorithm combined matching cost algorithm and parallax joint filling algorithm. According to the algorithm, a nonlocal stereo matching algorithm of cost aggregation based on a minimum spanning tree is used, and noise of an original image is removed in the preprocessing stage by using the algorithm based on the improved minimum spanning tree so that texture information can be enhanced and the enhanced image can be acquired. Then information of the original image is used in the matching cost stage and information of the enhanced image is also used. Therefore, local information of the image is acquired and global information is also acquired so as to have certain effect in later cost aggregation. The joint weight filling algorithm is put forward for the problem of parallax discontinuity and mismatching in the final parallax refinement part. The experiment proves that the algorithm has low mismatching rate and high robustness on the edge area and the repeat texture and occlusion areas in comparison with other nonlocal stereo matching algorithms. The experiment result proves the effectiveness of the algorithm.

Description

technical field [0001] The invention relates to a binocular ranging system, in particular to: a combined matching cost algorithm and a disparity joint filling algorithm of a non-local stereo matching algorithm. Background technique [0002] An important task of computer vision is to use computers to replace human eyes and brains, and to detect and identify the external objective world by acquiring target images, identifying and processing target images. Compared with human vision, the advantage of machine vision is that the digital image information of the target has a definite qualitative description, and the quantitative information of the target can be obtained through in-depth analysis and processing. [0003] Binocular measurement technology is an important research content in the field of computer vision. The image-based distance measurement technology is developed by using this feature of machine vision. It focuses on the position measurement of objects, by extractin...

AI Technical Summary

Problems solved by technology

However, when the algorithm calculates the initial matching cost value, it simply calculates the gray level difference and gradient difference, which is prone to errors when constructing the minimum spanning tree for weak texture and rich texture regions, resulting in inaccurate estimation of disparity values.

Images