Dense matching method using confidence weight-based bilateral filtering

Abstract

The present invention discloses a dense matching method using confidence weight-based bilateral filtering. The method comprises the following steps that: 1, a reference image and a reference image are selected according to a stereo image pair, and a traditional window operator is adopted to calculate a matching cost matrix; 2, the cost reliability of a central pixel is judged according to the distribution of gray level in a cost calculation window; 3, confidence weight-based bilateral filtering is performed on cost suspicious pixels, so that matching cost is obtained; and 4, a traditional semi-global dense matching method is adopted to quickly obtain an accurate disparity map according to the new matching cost. The dense matching method using confidence weight-based bilateral filtering of the invention is high in filtering speed and can effectively eliminate the problem of disparity edge mismatch commonly existing in a traditional stereo image dense matching algorithm. In the generated matching disparity map, the line features of the edges of ground object are obvious, and therefore, three-dimensional reconstruction accuracy is high.

Description

technical field [0001] The invention relates to the technical field of stereo image dense matching, in particular to a dense matching method based on confidence weight bilateral filtering. Background technique [0002] Stereo image dense matching refers to the process of matching points with the same name between two images pixel by pixel according to the pixel similarity measure and cost optimization method. Stereo image dense matching is one of the core technologies in the fields of 3D modeling, virtual reality, computer vision, etc. Applications such as virtual e-commerce. [0003] Traditional dense stereo image matching techniques use window operators as the matching cost measure. Commonly used window operators include Sobel operator, ZNCC operator, HOG operator, Census operator, etc. The algorithm of the window operator is simple, the calculation efficiency is high, and it has the ability to resist image radiation distortion to a certain extent. However, window oper...

AI Technical Summary

Problems solved by technology

If the window operator is used for dense matching, it is easy to generate false matching at the edge of the parallax, which is specifically manifested as serious "burrs" on the edge of the parallax, excessive smoothing of the edge of the parallax, etc.

Mis-matching of parallax edges will seriously affect the reconstruction accuracy and 3D display effect of the 3D model

Images