Multi-view target searching method based on probability model

Abstract

The invention discloses a multi-view target searching method based on a probability model. The multi-view target searching method comprises the following steps of extracting Zernike moments of initial view sets of various objects from a multi-view model library to obtain an initial feature vector set; gathering initial feature vectors of all the objects to obtain a total initial feature vector set and defining the total initial feature vector set as a multi-view feature library; randomly selecting an object from the multi-view model library and using the selected object as a query target; selecting an optional object as a comparing target; finding out an object which is similar to the query target from the multi-view model library; performing theoretical analysis to obtain a probability function based on a Gaussian model; performing sample training to obtain model parameters; calculating matching probability of the query target and the comparing target; and arraying the matching probabilities of the query target and all models in the multi-view model library in a descending order to obtain a final searching result. By the multi-view target searching method, dependence on space position information of a camera is avoided when initial views are acquired. The multi-view target searching method can be used for any multi-view target databases based on views.

Description

technical field [0001] The invention relates to the field of multi-view object retrieval, in particular to a multi-view object retrieval method based on a probability model. Background technique [0002] Humans live in three-dimensional space and perceive external information through vision. Three-dimensional objects can provide a more vivid experience than text, and a more intuitive and three-dimensional visual experience than two-dimensional images, so they are widely used in computer graphics, computer-aided design, medical imaging and other fields. A 3D object that can be represented by its multi-view views is called a multi-view object. With the application and development of Internet technology, the number of multi-view objects is increasing exponentially [1] . How to enable users to quickly and accurately find targets that meet their needs from massive databases, and then realize resource reuse has attracted the attention of many researchers. Multi-view target retr...

AI Technical Summary

Problems solved by technology

[0004] The main challenge currently faced in the field of multi-view object retrieval is: when collecting the initial view, most methods have a high dependence on the camera's placement angle and spatial position, resulting in only when the angle and number of each corresponding view of the two objects are exactly the same. At the same time, mutual retrieval can be performed, which limits the scope of practical application

Images