Depth map fusion method and device

Abstract

The invention provides a depth map fusion method and a depth map fusion device. The depth map fusion method comprises the following steps of: extracting depth maps from scenes at different visual angles according to scene information acquired by a plurality of cameras; clustering the depth maps extracted from the different visual angles; establishing a deletion matrix according to the clustered information; recovering the deletion matrix to obtain a complete low-rank matrix; selecting a first dimensional subspace from the complete low-rank matrix according to an elastic network algorithm; andreconstructing a three-dimensional model according to the first dimensional subspace. The depth map fusion method has the advantages of effectively processing noise and having high accuracy for processing standard data simultaneously.

Description

technical field [0001] The invention relates to the field of computer vision processing, in particular to a method and device for fusion of noise depth maps in stereo vision. Background technique [0002] Stereo vision-based depth map fusion refers to obtaining a complete surface from a series of partial reconstruction information. A probabilistic model is a fusion method for dealing with conflict points. In the probability map algorithm, the visible depth information is considered as prior knowledge, and then the depth map is fused from the Bayesian model. Second, transforming depth information into an optimization problem for solving discrete marker Markov fields is also a classic fusion method, which is especially applicable when the real depth map cannot be estimated. Selecting the representation of depth information by the minimum distance projected to the original survey map is a fast fusion algorithm. The algorithm can eliminate occlusion and discontinuity under a ...

AI Technical Summary

Problems solved by technology

[0004] 1. Incompleteness between viewpoints, that is, a single camera cannot perceive the overall 3D model under an object

[0005] 2. Existing computer algorithms cannot solve the problem of noise in a large amount of depth information, that is, the depth information extracted by computer vision algorithms is noisy, so none of the existing depth image fusion algorithms can solve the problem of deep fusion in the presence of a large amount of noise

Images