Skeleton action recognition method based on multi-stream spatial attention graph convolution SRU network

An action recognition and attention technology, applied in the field of pattern recognition, can solve the problems of lack of consideration of bone structure connection, single use of bone data, etc., and achieve the effect of improving the efficiency of action recognition

Pending Publication Date: 2021-04-30
HANGZHOU DIANZI UNIV
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method lacks consideration of the structural connection between bones, and the use of bone data is relatively simple.

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
  • Skeleton action recognition method based on multi-stream spatial attention graph convolution SRU network
  • Skeleton action recognition method based on multi-stream spatial attention graph convolution SRU network
  • Skeleton action recognition method based on multi-stream spatial attention graph convolution SRU network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings: this embodiment is implemented on the premise of the technical solution of the present invention, and provides detailed implementation plans and specific operating procedures.

[0022] Such as figure 1 , the method of the present invention mainly includes three steps: (1) the multi-stream data fusion method processes the original data; (2) replaces the fully connected calculation in the SRU gate structure with the graph convolution calculation, and constructs a graph convolution simple loop network (GC -SRU); (3) Introduce the spatial attention mechanism in the GC-SRU network, and finally get the result of action classification.

[0023] Each step will be described in detail below one by one.

[0024] step one:

[0025] The present invention uses 4 modes of data streams, which are node streams with original joint point coordinates as input, bone st...

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 skeleton action recognition method based on a multi-stream spatial attention graph convolution SRU network. The method comprises the following steps: firstly, embedding a graph convolution operator into a simple cycle unit to construct a graph convolution model to capture time-space domain information of skeleton data; meanwhile, in order to enhance the discrimination between the joint points, a spatial attention network and a multi-stream data fusion mode are designed, and a graph convolution simple cycle network model is further expanded into a multi-stream spatial attention graph convolution SRU. According to the method, the high classification precision is maintained, the complexity of the method is remarkably reduced, the reasoning speed of the model is increased, the balance between the calculation efficiency and the classification precision is achieved, and the method has a very wide application prospect.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and is a method for modeling skeleton data and classifying actions by using graph convolution and a simple recurrent unit (SRU) in combination with a spatial attention mechanism and a multi-stream data fusion method. Background technique [0002] The recognition of human actions is a basic yet challenging task in computer vision, which has facilitated the generation of many applications, such as intelligent video surveillance, human-computer interaction, video summarization and understanding, abnormal behavior detection, etc. Compared with the traditional method of using RGB image stream or video stream for action recognition, skeleton-based action recognition is not limited by background clutter, illumination changes, etc., and the representation of target actions is more robust. Most of the early skeleton-based action recognition methods simply used the joint point coordinates to construct a ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V40/20G06N3/045G06F18/24G06F18/251
Inventor 赵俊男佘青山陈云马玉良梅从立
Owner HANGZHOU DIANZI UNIV
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