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

A Multi-Person Pose Estimation Method Based on Fractal Networks and Joint Kinship Patterns

A fractal network, attitude estimation technology, applied in character and pattern recognition, computing, computer parts and other directions, can solve the problem of not guaranteeing the constraint relationship, unable to estimate the pose of multiple people efficiently, etc., to improve the average accuracy, improve the intermediate prediction, Remove the effect of cluttered matching

Active Publication Date: 2021-10-26
HUAQIAO UNIVERSITY +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can effectively constrain the human body parts, but it cannot guarantee the constraint relationship between different joints of multiple people in the image, so it cannot efficiently estimate the poses of multiple people

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 Multi-Person Pose Estimation Method Based on Fractal Networks and Joint Kinship Patterns
  • A Multi-Person Pose Estimation Method Based on Fractal Networks and Joint Kinship Patterns
  • A Multi-Person Pose Estimation Method Based on Fractal Networks and Joint Kinship Patterns

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention discloses a multi-person pose estimation method based on a multi-layer fractal network and a joint kinship model. In the human joint point prediction stage, the multi-scale feature extraction unit is used to replace the remaining units in the original hourglass network, effectively increasing the size of the image The local receptive field area captures the larger local contextual feature information of the human body joints, simultaneously performs multiple up-and-down sampling on the image, extracts the multi-scale features of the human body, and performs intermediate prediction on the heat map position of the human body joints, and passes through the third layer of the fractal network Optimize the prediction results; at the same time, the present invention proposes a layered two-way reasoning algorithm to calculate the degree of kinship between adjacent joint points, effectively avoiding messy matching between multiple joint points, and greatly im...

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 present invention relates to a multi-person pose estimation method based on a multi-layer fractal network and a joint relative model, which uses a three-layer fractal network model to predict key points of a human body, and proposes a layered bidirectional reasoning algorithm to match multi-person joint points, According to the kinship between each pair of joint points and the external space constraint relationship, the best matching between multiple human joint points can be realized, the messy matching between a large number of joint points can be effectively removed, and the average accuracy of multi-person pose estimation can be greatly improved. .

Description

technical field [0001] The invention relates to the field of human body posture estimation, in particular to a multi-person posture estimation method based on a multi-layer fractal network and a joint relative model. Background technique [0002] Human body pose estimation is a key step to further understand human behavior. Effectively predicting human body joints and obtaining corresponding motion poses is of great significance for realizing higher-level computer vision tasks such as behavior recognition, body tracking, and body weight recognition. Although there are many studies on human pose estimation, when there are multiple people in a single image, more limbs may be truncated or occluded, and it is difficult to locate the joint points of all individuals; and the interaction of multiple people's limbs is prone to joint dependence. High-dimensional input space. After the traditional single-person pose estimation method predicts the joint points of the human body, it on...

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): G06K9/00G06K9/62
CPCG06V40/23G06V40/103G06F18/29
Inventor 骆炎民柳培忠徐志通
Owner HUAQIAO UNIVERSITY
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