Texture-free three-dimensional object tracking method based on confidence and feature fusion

Abstract

The invention relates to a texture-free three-dimensional object tracking method based on confidence coefficient and feature fusion. The tracking method comprises the following steps: (1) establishinga color model; (2) dividing the pixel points into contour points and region points by using a cluster structure; (3) determining the weight alpha i of the edge item, the weight beta i of the color item and the cluster weight omega i according to the confidence coefficient of the contour point and the confidence coefficient of the region point; (4) solving an optimal pose according to the total energy equation corresponding to all the clusters, and rendering the three-dimensional model of the object to obtain an object area on the current frame image; and (5) repeating the steps until the tracking is finished. According to the method, a clustering structure is used, contour points and regional points are re-unified into one energy function, and the problem of non-uniform sampling points issolved; the confidence coefficients of the edge points and the region points are calculated respectively, the edge points and the region points are normalized automatically, the weight of each energyitem is calculated according to the confidence coefficients, and the problem of non-uniform error measurement of different features is solved.

Description

Technical field [0001] The invention relates to a texture-free three-dimensional object tracking method based on confidence and feature fusion, and belongs to the field of computer vision. Background technique [0002] Three-dimensional object tracking can continuously obtain the spatial position relationship between three-dimensional objects and the camera, which is an important task in computer vision. At present, 3D tracking has a wide range of application scenarios, such as industrial manufacturing, medical diagnosis, entertainment games, robotics and other fields. Three-dimensional object tracking can be roughly divided into two categories according to the types of video data used: three-dimensional tracking based on RGB-D video data and three-dimensional tracking based on RGB video data [Lepetit V, FuaP. Monocular model-based 3d tracking of rigid objects :A survey.Foundations and in Computer Graphics and Vision,2005,1(1):1-89.]. [0003] The method based on RGB-D data trac...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the deficiencies of the prior art, the present invention provides a textureless 3D object tracking method based on confidence and feature fusion. The tracking method solves the problem of single-type features in a specific scene on the basis of fusing color features and edge features. failure problem

[0010] The present invention calculates confidence degrees for edge points and area points respectively, automatically normalizes them, and calculates the weight of each energy item according to the confidence degrees, so as to solve the problem of inconsistency in error measurement of different features, and avoid the setting of additional hyperparameters at the same time; Confidence calculates the weight of each cluster, so as to set its weight to participate in optimization, and shield the negative impact of outliers

Images