Stereo matching method based on full-connection random field combination energy minimization

Abstract

The invention discloses a stereo matching method based on full-connection random field combination energy minimization, and the method comprises the following steps: counting the matching error vector of each pixel in a target image relative to a matching image, wherein the number of dimensions of the matching error vector is equal to the total number of preset parallax error levels; constructing an image parallax error value random field model according to the matching error vector based on the full-connection random field combination energy minimization; taking the energy minimum value of the random field model as a solving object, carrying out the iterative solving of the random field model through employing a mean field approximation algorithm, and obtaining the classification probability vector of all pixels in the target image, so as to construct a parallax error image. The random field model comprises global energy and local energy at the same time. A smoother result is obtained in a flat region through the global energy item, and more details are kept in a fine region through the local energy item. The method guarantees a certain solving speed through employing the mean field approximation algorithm.

Description

technical field [0001] The invention relates to the field of stereo vision, in particular to a stereo matching method based on fully connected random fields combined with energy minimization. On the basis of a model established by using fully connected random fields, disparity maps corresponding to binocular images are calculated through energy minimization. Background technique [0002] Stereo matching has always been one of the most basic, important and difficult problems in computer vision. Given multiple images of the same scene under different viewing angles, the task of stereo matching is to find the matching correspondence between points and points in these images, and then use these correspondences to calculate the distance between the object in the image and the distance from the camera through the three-dimensional geometric relationship. distance information. Stereo matching is widely used in many fields such as 3D environment perception and modeling, robotics, d...

AI Technical Summary

Problems solved by technology

[0005] Researchers often limit the optimization to a single scan line or the method of turning a multi-connected graph into a tree, such as graph cutting and belief propagation methods. The disadvantage of these methods is that they cannot consider global information when solving problems. , so it is difficult to obtain a result close to the global optimum

Some other researchers use the idea of ​​sampling to approach the optimal solution using the Monte Carlo Markov chain, but this type of method is very slow and difficult to be practical

Images