A Multi-View View Modeling Method for 3D Objects Based on Feature Clustering

Abstract

The invention relates to a three-dimensional target multi-viewpoint view modeling method on the basis of the feature clustering, which comprises four steps of: 1, acquiring an all attitude image of a test target; 2, extracting a target feature vector set <xi|i=1,2,...N> from an acquired all attitude image set and adopting a 7-dimensional invariant moment formed by integrating an affine invariant moment with a geometric invariant moment and further carrying out regularization to describe an appearance feature of the all attitude image; 3, determining an optimal cluster number Cop; and 4, clustering target feature vectors into the Cop type by adopting a k-means clustering method and using a small amount of finally obtained clustering centers as modeling results. Aiming at the defect that under different viewpoints, due to difference of target images, the single target view description cannot identify the target, the invention establishes the three-dimensional target multi-viewpoint view modeling method which has a small description number and little redundant information and can be used for well describing the target all-attitude feature vector set. The three-dimensional target multi-viewpoint view modeling method has high practical value and wide application prospect in the field of the pattern recognition.

Description

technical field [0001] The invention relates to a three-dimensional target multi-view point view modeling method based on feature clustering, which belongs to the field of pattern recognition, and specifically relates to target recognition, target modeling, data reduction and the like. It is used for multi-viewpoint modeling of 3D targets, and is suitable for the problem that the single target view description cannot recognize the target caused by the difference of target images under different viewpoints. Background technique [0002] 3D object recognition is an important research direction in the field of computer vision. At present, it is often very difficult to obtain the three-dimensional information of the target in practical applications, and the recognition of the three-dimensional target is still mainly completed by recognizing the image formed by the two-dimensional projection of the target. The process of two-dimensional imaging (projection) of the target leads t...

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to provide a method for modeling multi-viewpoint views of three-dimensional objects based on feature clustering, which aims at the disadvantage that the description of a single object view cannot identify the object caused by the difference of object images under different viewpoints, and constructs a method with a small number of descriptions. 3D target multi-viewpoint view modeling method with less redundant information and better description of target full pose feature vector set

Images