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

3D model classification method based on end-to-end deep ensemble learning network

An integrated learning and three-dimensional model technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve the problems of affecting the effect of deep learning, losing the original information of the three-dimensional model, and being unable to make full use of it. The effect of fitting and improving robustness

Inactive Publication Date: 2020-08-07
BEIFANG UNIV OF NATITIES
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the outstanding advantage of deep learning is that it can complete feature self-learning; and this type of method has already carried out a primary feature extraction when inputting vector data, it is inevitable to lose the original information of the 3D model, and cannot make full use of the advantages of deep learning feature self-learning , affecting the effect of deep learning

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
  • 3D model classification method based on end-to-end deep ensemble learning network
  • 3D model classification method based on end-to-end deep ensemble learning network
  • 3D model classification method based on end-to-end deep ensemble learning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The present invention will be further described below in conjunction with specific examples.

[0072] Such as figure 1 As shown, in order to improve the classification accuracy of the 3D model, this embodiment provides a 3D model classification method based on an end-to-end deep integrated learning network (EnsembleNet). The method adopts an end-to-end deep learning integration strategy and inputs a 3D mesh model, extract multi-view representation, build an integrated deep learning network including base learner and integrated learner, automatically extract composite features of 3D model, and complete model classification.

[0073] There are various ways to obtain the view of the 3D model. A comprehensive comparison of these methods and their corresponding classification results shows that the 12-view rendering method proposed by Su‐MVCNN is a comprehensive and excellent view acquisition method. Therefore, the present invention continues to use this method Construct a ...

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 three-dimensional model classification method based on an end-to-end deep integrated learning network. The method adopts an end-to-end deep learning integration strategy, inputs a three-dimensional grid model, extracts multi-view representations, and establishes a base learner and The integrated deep learning network of the integrated learner automatically extracts the composite features of the 3D model and completes the model classification. Experiments show that the method of the present invention achieves classification accuracies of 96.04%, 92.79%, 98.33%, 98.44% and 98.63% on ModelNet10, ModelNet40, SHREC10, SHREC11, and SHREC15 data sets, respectively. This result is obviously better than other multi-view classification algorithms, and it also preliminarily verifies the effectiveness of this method.

Description

technical field [0001] The invention relates to the technical fields of computer graphics, computer vision and intelligent recognition, in particular to a three-dimensional model classification method based on an end-to-end deep integrated learning network (EnsembleNet). Background technique [0002] At present, with the continuous development of 3D modeling, scanning, and computer vision, the research and application of related technologies such as unmanned driving, 3D scene roaming, and smart city construction have attracted widespread attention. Among them, the effective identification of 3D models is the basic research problem. [0003] The construction of features and the selection of classification models are the key to determine the quality of classification. Especially for complex data types such as 3D models, the establishment of appropriate features is a hot topic for researchers in related fields, and it is also a research difficulty in the industry. Deep learni...

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 Patents(China)
IPC IPC(8): G06N3/04G06N3/08G06K9/62
CPCG06N3/084G06N3/048G06N3/045G06F18/253G06F18/24
Inventor 白静司庆龙刘振刚
Owner BEIFANG UNIV OF NATITIES