Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for selecting characteristics of three-dimensional objects

A feature selection method and three-dimensional object technology, applied in the multimedia field, can solve problems such as heavy workload, and achieve the effect of avoiding feature redundancy and reducing workload.

Active Publication Date: 2009-11-11
TSINGHUA UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] If the 3D object has many features, or the number of 3D objects in the database is relatively large, the workload will become quite heavy when the user performs feature selection

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for selecting characteristics of three-dimensional objects
  • Method and device for selecting characteristics of three-dimensional objects
  • Method and device for selecting characteristics of three-dimensional objects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] see figure 1 , the present embodiment provides a feature selection method of a three-dimensional object, the specific process of the method is as follows:

[0025] 101: Respectively obtain similar class sets of three-dimensional objects under each feature;

[0026] 102: Select the smallest set of similar classes;

[0027] 103: Combine the features corresponding to the minimum similarity class set with other features to obtain a new combination feature, and obtain the similarity class set of the 3D object under the new combination feature until an empty similarity set is obtained. class set, using the new combined feature corresponding to the similar class set which is an empty set as the approximate optimal feature of the three-dimensional object.

[0028] The method provided in this embodiment, by making full use of the different features of the 3D object, obtains the similar class set of the 3D object under each feature, so as to obtain the approximate optimal featu...

Embodiment 2

[0030] This embodiment provides a method for feature selection of 3D objects. Before the feature selection of 3D objects, all 3D objects in the 3D object database are manually divided into several categories, and each category is marked; secondly, the Each 3D object is placed in the camera array for shooting, and a 2D view set corresponding to each 3D object is obtained, and these 2D view sets form a multi-view based 3D object database. The premise of implementing the method provided in this embodiment is: after feature extraction has been performed on the view set, if all the features of the 3D object are used, each 3D object should be able to be distinguished from other 3D objects of different categories from itself, if If the effect of distinction cannot be achieved, it is necessary to increase the characteristics of the 3D object or change the category label of the 3D object until this premise is met.

[0031] For the sake of illustration, take the feature selection of the...

Embodiment 3

[0059] see image 3 , the present embodiment provides a device for feature selection of a three-dimensional object, the device comprising:

[0060] An acquisition module 301, configured to acquire similar sets of three-dimensional objects under each feature;

[0061] Selection module 302, for selecting the minimum similar class set;

[0062] The processing module 303 is used to combine the features corresponding to the smallest similar class set with other features to obtain a new combined feature, and obtain the similar class set of the three-dimensional object under the new combined feature until an empty similar class set is obtained , will use the new combined feature corresponding to the similar class set of the empty set as the approximate optimal feature of the 3D object.

[0063] Further, see Figure 4 , the above acquisition module 301, including:

[0064] An extraction unit 301a, configured to extract each feature of the three-dimensional object;

[0065] Calcul...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method and a device for selecting characteristics of three-dimensional objects, belonging to the field of multimedia technology. The method comprises the steps of: obtaining similarity sets of the three-dimensional objects in the condition of each characteristic; selecting a least-similarity set; combining the characteristic corresponding to the least-similarity set withother characteristics, obtaining new combined characteristics, obtaining a similarity set of the three-dimensional objects in the condition of the new combined characteristics till obtaining a similarity set which is an empty set, and taking the new combined characteristic corresponding to the similarity set which is an empty set as an optimum similarity characteristic of the three-dimensional objects. By obtaining the similarity sets of the three-dimensional objects in the condition of each characteristic, the method and the device obtain the optimum similarity characteristic of the three-dimensional objects, reduce the wok load during characteristic selection and facilitate the marking, identification, retrieval and other operations conducted on the three-dimensional objects.

Description

technical field [0001] The invention relates to the field of multimedia technology, in particular to a feature selection method and device for a three-dimensional object. Background technique [0002] In recent years, with the development of image-based 3D object representation and rendering technology, technologies such as annotation, recognition, and retrieval of 3D objects based on multi-view have gradually become hot spots. In these technologies, the view of a 3D object is often represented by one or several sets of low-level visual features, which are mainly pixel-level features, including color, texture, shape, etc. The importance of these features is different when describing different types of objects, and their roles are often different when comparing two types of objects, so it is necessary to select the features. [0003] In existing technologies such as labeling, recognition, and retrieval of 3D objects based on multi-view, the feature selection of 3D objects is...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T15/00
Inventor 戴琼海路瑶尔桂花
Owner TSINGHUA UNIV