Three-dimensional object characteristic view selection method

Abstract

The invention provides a three-dimensional object characteristic view selection method, which comprises the following steps of: selecting a three-dimensional object as a target three-dimensional object, and acquiring multi-angle views of three-dimensional objects homogeneous with the target three-dimensional object; acquiring reserved multi-views for the multi-angle views of the three-dimensional objects, and setting initial weights; calculating a view distance matrix of any two groups of multi-angle views which belong to different three-dimensional objects; performing on-view reinforcement learning on the weights of the multi-views of all the three-dimensional objects to obtain final weights; and selecting a plurality of views with the maximum weights as representative views from the reserved views of the original three-dimensional objects. The method analyzes the multiple views of the analyzed object and considers the relevance of the multiple views of the homogeneous objects so as to select the representative multiple views by a novel on-view reinforcement learning method. The method has the advantages of simple design and easy realization.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for selecting feature views of three-dimensional objects. Background technique [0002] With the continuous advancement of multimedia technology, 3D object data is growing at an astonishing rate, and is widely used in many fields such as computer-aided manufacturing, virtual reality, medicine and entertainment. Since a three-dimensional object can better describe the characteristics and attributes of the object compared to a plane image, the understanding, identification and detection of the three-dimensional object become more and more important. [0003] The traditional description methods of 3D objects are all based on virtual models. The virtual three-dimensional model can be displayed by tools such as AutoCAD, and the original three-dimensional object can be displayed from a three-dimensional perspective through the three-dimensional coordinate system of X...

AI Technical Summary

Problems solved by technology

However, this feature view selection method only considers the view relationship of a single object, and does not consider the common attributes of the entire class of views, so it cannot select an effective representative view.

Images