Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Posture recognition method and device based on skeleton separation and unification and attention mechanism

A recognition method and attention technology, applied in biometrics recognition, neural learning methods, character and pattern recognition, etc., can solve problems such as low accuracy, low real-time performance, and difficulty in accurately detecting people's positions, achieving accuracy High, improve the efficiency of skeleton recognition, high real-time effect

Pending Publication Date: 2022-01-28
杭州轻象科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, most of the current human pose estimation methods are difficult to accurately detect the position of the person due to the complex environment background.
In addition, the current human pose recognition method is limited to local joint connectivity, and human joints are regarded as a set of independent features, which has problems such as low real-time performance and low accuracy.

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
  • Posture recognition method and device based on skeleton separation and unification and attention mechanism
  • Posture recognition method and device based on skeleton separation and unification and attention mechanism
  • Posture recognition method and device based on skeleton separation and unification and attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] This embodiment implements a gesture recognition method based on skeleton separation and unification and attention mechanism, such as figure 1 shown, including:

[0066] S1. Obtain skeleton data;

[0067] S2. Select a graph sequence from the skeleton data, and then perform multi-scale learning graph convolution processing on the graph sequence based on a unified spatio-temporal operator of a time window to obtain the first skeleton feature, wherein the graph sequence includes multiple Frame space-time subgraph;

[0068] S3. Perform attention mechanism processing on the first skeleton feature and complete the recalibration of the first skeleton feature to obtain a weighted feature map as the second skeleton feature;

[0069] S4. Perform global average pooling processing on the second skeleton feature, and input the global average pooling processing result into the Softmax classifier;

[0070] S5. The Softmax classifier identifies and outputs the gesture type.

[0071...

Embodiment 2

[0089] This embodiment implements a gesture recognition method based on skeleton separation and unification and attention mechanism, and the steps are described in detail as follows.

[0090] The first step is to obtain the skeleton data.

[0091] Specifically, obtaining skeleton data includes obtaining skeleton data of workers' sitting postures in an actual factory workshop scene. It should be noted that this application uses a graph convolution based on skeleton separation and unification and attention mechanism module to recognize the pose of workers in the factory workshop production line. Considering that when the workshop production line is in operation, the workers' sitting posture is relatively fixed, and the upper body movements on the production line are relatively single. We process the skeleton data by paying attention to the characteristics of the workers' arm joint points, so the first step is to obtain information about the workers' sitting posture on the factor...

Embodiment 3

[0115] This embodiment provides a skeleton neural network model. The skeleton neural network model includes an input module, a multi-scale feature extraction module, an attention mechanism module, a pooling module, a classification module, and an output module. The multi-scale feature extraction module Execute the step of performing the graph convolution processing of multi-scale learning on the graph sequence based on the unified spatio-temporal operator based on the time window to obtain the first skeleton feature; the attention mechanism module executes the step of paying attention to the first skeleton feature The force mechanism processes and completes the recalibration of the first skeleton feature to obtain a weighted feature map, as a step of the second skeleton feature.

[0116] Preferably, the input module is used to input a graph sequence; the pooling module is used to perform a pooling operation on the processing result of the attention mechanism module; the classif...

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 relates to a posture recognition method and device based on skeleton separation and unification and an attention mechanism. The method comprises the following steps: acquiring skeleton data; selecting a graph sequence from the skeleton data, and performing multi-scale learning graph convolution processing on the graph sequence based on a unified time-space operator of a time window to obtain a first skeleton feature; carrying out attention mechanism processing on the first skeleton feature and completing re-calibration on the first skeleton feature to obtain a weighted feature map, and taking the weighted feature map as a second skeleton feature; performing global average pooling processing on the second skeleton feature, and inputting a global average pooling processing result into a Softmax classifier; enabling the Softmax classifier to perform recognition and outputs a posture type. According to the invention, skeleton data is processed, multi-scale structural features and the long-term dependency relationship are extracted, attention mechanism processing is added at important joint points of limbs, and skeleton features with enhanced data are obtained, so that accurate recognition of limb actions and postures of factory workshop workers during working on a production line is realized, and skeleton recognition efficiency is improved.

Description

technical field [0001] The present application relates to the technical field of target detection and gesture recognition, in particular to a gesture recognition method and device based on skeleton separation and unification and attention mechanism. The method includes: obtaining skeleton data; selecting a graph sequence from the skeleton data, and then performing multi-scale learning graph convolution processing on the graph sequence based on a unified spatio-temporal operator of a time window to obtain the first skeleton feature; Perform attention mechanism processing and complete the recalibration of the first skeleton feature to obtain a weighted feature map as the second skeleton feature; perform global average pooling processing on the second skeleton feature, and input the global average pooling processing result into Softmax Classifier; Softmax classifier identifies and outputs the pose type. This application processes the skeleton data, extracts multi-scale structura...

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): G06V40/10G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2415
Inventor 贾冰佟达宿南
Owner 杭州轻象科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com