A method for human motion recognition base on a generated antagonism network

A human action recognition and network technology, applied in the field of computer vision, can solve the problems of low recognition rate, achieve high recognition efficiency, shorten training time, improve recognition rate and robustness

Active Publication Date: 2019-01-11
NANTONG UNIVERSITY
View PDF2 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Many researchers [Document 5] (Wang Zhongmin, Cao Hongjiang, Fan Lin. A Human Behavior Recognition Method Based on Convolutional Neural Network Deep Learning [J]. Computer Science, 2016, 43(s2): 56-58.) Use the convolutional neural netw

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
  • A method for human motion recognition base on a generated antagonism network
  • A method for human motion recognition base on a generated antagonism network
  • A method for human motion recognition base on a generated antagonism network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The technical scheme of the present invention is further described in conjunction with specific embodiments and accompanying drawings.

[0039] like figure 1 , the human action recognition method based on the generative confrontation network provided by the present invention is based on the generative confrontation network, adding a classifier to establish a step-by-step generation recognition model, and constructing two modules of image generation and classification; using structural similarity to improve the quality of generated images , using automatic feature extraction to achieve classification; its specific implementation includes the following steps:

[0040] Step 1): Generator Design. Input the uniformly distributed noise z and the corresponding label y, combine the input noise with its label, and transform the dimension; the image generation process includes 3 layers of deconvolution layers, and the kernel size of each layer of deconvolution is 5×5, step The ...

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 provides a method for human motion recognition base on a generated antagonism network. The method firstly designs a step-by-step generation recognition network model, constructs a classifier on the basis of the antagonistic network, and realizes image generation and classification functions. Secondly, the structure similarity is introduced into the discriminator to improve the quality of the generated image by adding constraints. Finally, the image is generated and recognized in the human motion image database which accords with the daily life. The invention solves the problem oflow recognition rate under the condition of insufficient samples by combining the natural generation and recognition of images. In the aspect of image expansion and recognition, the method has the characteristics of natural sample expansion, high recognition rate and strong robustness.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a human action recognition method based on a generative confrontation network. Background technique [0002] At present, human motion recognition technology is used in various fields such as medical and health care, smart home, and interactive entertainment. Existing research methods mainly include template matching method and machine learning algorithm. Liu et al [Document 1] (Liu L, Ma S, FuQ. Human action recognition based on locality constrained linear coding and two-dimensional spatial-temporal templates [C]. Chinese Automation Congress. USA: IEEE, 2018.1879-1883.) proposed The locally constrained linear coding method based on the two-dimensional spatiotemporal template calculates the two-dimensional spatiotemporal template and uses it as a global feature to describe human action information, and uses the locally constrained linear coding method to encod...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V40/28G06N3/045G06F18/24
Inventor 李洪均李超波胡伟
Owner NANTONG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap