Minimal sum cache acceleration strategy based binocular stereo vision matching method for generalized confidence spread

Abstract

The invention discloses a minimal sum cache acceleration strategy based binocular stereo vision matching method for generalized confidence spread, comprising the following steps of: (1) acquiring the left image and the right image of two eyes and establishing a markov random field; (2) generating a multi-scale markov random field, wherein the size of the kth layer is one fourth that of the (k+1)th layer; (3) arranging n layers of multi-scale markov random fields, respectively solving the n markov random fields in the sequence from 1 to n and transmitting the calculation result of the ith layer to the (i+1)th layer; and (4) after finishing the solution to the utmost bottom layer of the markov random field, taking the state with a minimum value as a final state of a variable which is a vision difference value of a point in an image, which corresponds to the variable. The invention effectively reduces the complexity and the calculated amount.

Description

technical field [0001] The invention relates to the fields of image processing, computer vision, calculation method, mathematics and numerical method, especially the binocular stereo vision matching method of computer vision. Background technique [0002] At present, the research on stereo vision matching problem has made great progress. Especially the matching algorithm based on global optimization has become the main method to solve the matching problem and has been widely used. The reason it has received so much attention is because the matching problem can be well modeled as an optimization problem of Markov Random Field (MRF) or Conditional Random Field (CRF). This type of problem has been designed in many disciplines, and many of the resulting algorithms can be applied to the solution of matching problems. [0003] Among them, the algorithm based on belief propagation (Belief Propagation) is a method that has received extensive attention at present. Its main idea is...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the high complexity of the existing binocular image matching method for the generalized confidence propagation algorithm and the lack of a large amount of calculation, the present invention proposes a cache acceleration strategy based on the minimum sum, so that the generalized confidence propagation algorithm The performance of the method has been greatly enhanced, and it has been successfully applied to the solution of the matching problem in binocular vision, providing a generalized belief propagation based on the minimum and cache acceleration strategy that effectively reduces complexity and reduces the amount of calculation. binocular stereo vision matching method

Images