Three-dimensional object retrieval method and apparatus

Abstract

The invention provides a method and a device for retrieving a three-dimensional object, wherein, the retrieval method comprises the following steps: obtaining the characteristic view of a three-dimensional object, and extracting the first Shock diagram skeleton descriptor and the first Fourier descriptor of the characteristic view; extracting the second Shock diagram skeleton descriptor and the second Fourier descriptor of an input picture; calculating the first similarity metric of the first and the second diagram skeleton descriptors; calculating the second similarity metric of the first and the second Fourier descriptors; and obtaining a mixed similarity metric according to the first similarity metric and the second similarity metric, confirming that the characteristic view corresponding to the maximum mixed similarity metric is the view most similar to the input picture, and further confirming that a three-dimensional object corresponding to the characteristic view is the three-dimensional object ready for retrieving. The invention effectively combines the Shock diagram skeleton descriptors and the Fourier descriptors, and realizes excellent 3D-object retrieval performance.

Description

technical field [0001] The invention relates to the field of three-dimensional (3D, Three-Dimensional) object processing, in particular to a 3D object retrieval method based on feature view and shape descriptor fusion. Background technique [0002] With the development of 3D technology, a new type of multimedia data——3D model has been widely used. 3D model is different from traditional multimedia data such as text and audio. It has outstanding features such as vividness, image, and lifelikeness. There have been great developments in many fields such as applications and virtual reality. Advances in computer graphics and model digitization tools have created conditions for constructing high-quality 3D models, and the Internet has provided means for disseminating these models. Now, the application of 3D models is penetrating into every aspect of people's work and life. In order to efficiently obtain and reuse the existing 3D model data resources on the network, and save a lo...

AI Technical Summary

Problems solved by technology

However, although the retrieval mechanism by selecting CV saves time, it reduces the accuracy of retrieval to a certain extent due to the reduction of target views.

Images