Attitude estimation method based on decoupling step network

A pose estimation and decoupling technology, applied in neural learning methods, biological neural network models, calculations, etc., can solve problems such as reducing the accuracy of human pose estimation, improve training and reasoning speed, facilitate fusion, and reduce the amount of parameters Effect

Active Publication Date: 2021-02-26
HUAQIAO UNIVERSITY +1
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method ensures the diversity of image features, improves the recognition accuracy and speeds up the network operation speed. For th...

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
  • Attitude estimation method based on decoupling step network
  • Attitude estimation method based on decoupling step network
  • Attitude estimation method based on decoupling step network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The general idea of ​​the technical solution in the embodiment of the application is as follows:

[0058] First of all, the decoupling ladder network is built based on the decoupling residual module, which greatly reduces the parameter amount of the deep convolutional neural network, and the reduced accuracy is within an acceptable range; secondly, each decoupling residual in the decoupling ladder network The flow of information between groups enables the decoupled ladder network to effectively utilize and fuse spatial information and semantic information, making the pose estimation results more accurate; then, add waterfall to every two decoupled residual modules of the decoupled ladder network The module effectively makes up for the lack of receptive field caused by the decoupling residual module, which makes the accuracy of each joint point of the human body more balanced, greatly improves the accuracy of attitude estimation, and provides an attitude reference for beh...

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 an attitude estimation method based on a decoupling step network in the technical field of human body attitude estimation. The attitude estimation method comprises the followingsteps of S10, building the decoupling step network based on a decoupling residual module and a waterfall module; S20, acquiring a large number of human body sample images, and training a decoupling step network by using the human body sample images; and S30, inputting a to-be-tested image into the trained decoupling step network, calculating the position of each joint point in the to-be-tested image, and forming a complete human body posture based on the position of each joint point. The method has the advantage that the speed and precision of human body posture estimation are greatly improved.

Description

technical field [0001] The present invention relates to the technical field of human body pose estimation, in particular to a pose estimation method based on a decoupling ladder network. Background technique [0002] Human body posture estimation is a key step for computer vision to further understand human behavior. Through an RGB image, all relevant nodes of the human body can be effectively predicted and the correct posture can be formed. Accurately predicting human body posture is essential for higher-level computer vision tasks, such as human It is of great significance for behavior recognition, human-computer interaction, pedestrian re-identification, and abnormal behavior detection. [0003] Although the field of human pose estimation is developing rapidly, both top-down and bottom-up methods have the problem of complex network structure and large number of parameters, which makes it difficult to know which part is more critical when training the network, which leads ...

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): G06K9/00G06K9/32G06K9/62G06N3/04G06N3/08G06T5/30G06T7/62
CPCG06N3/08G06T5/30G06T7/62G06T2207/10004G06T2207/30196G06T2207/20081G06T2207/20084G06V40/20G06V10/25G06N3/045G06F18/241
Inventor 骆炎民欧志龙林躬耕
Owner HUAQIAO 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