Local stereo matching method

Abstract

The invention discloses a local stereo matching method. The method comprises the following steps of 1, image acquisition and epipolar correction; 2, RGB three-component extraction; 3, acquisition of color matching cost; 4, acquisition of gradient matching cost; 5, acquisition of a matching cost function; 6, acquisition of a judgment window area; 7, aggregation of matching cost; 8, parallax optimization. The method is simple in step, local matching is carried out based on the color image, color information of the color image is effectively utilized, the accuracy of stereo matching is improved,the disparity map is optimized, the accuracy of the disparity map is improved, and subsequent depth information analysis of the disparity map is facilitated.

Description

technical field

[0001] The invention belongs to the technical field of stereo matching, and in particular relates to a local stereo matching method. Background technique

[0002] Stereo matching is a key technology in binocular stereo vision. The disparity map is obtained by establishing a one-to-one correspondence between the left and right image pixels, and then the depth information is obtained by calculating the disparity information based on the similarity principle of mathematical triangles. In recent years, with the development of technology, various high-precision and high-efficiency stereo matching algorithms have been proposed. The existing stereo matching algorithms are divided into global stereo matching and local stereo matching. The local algorithm is less computationally intensive and faster than the global algorithm. , but at present, when performing partial matching based on a color image, the first step is to convert the color image into a grayscale image a...

Images