Attitude recognition method and system based on thermodynamic diagram and offset vector and storage medium

A technology of offset vector and recognition method, applied in the field of deep learning, can solve problems such as offset and accuracy loss, and achieve the effect of accurate attitude information

Active Publication Date: 2020-05-22
SOUTH CHINA NORMAL UNIVERSITY
View PDF2 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these methods can improve the accuracy of human key point detection, they ignore the slight deviation of the pre...

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 recognition method and system based on thermodynamic diagram and offset vector and storage medium
  • Attitude recognition method and system based on thermodynamic diagram and offset vector and storage medium
  • Attitude recognition method and system based on thermodynamic diagram and offset vector and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further explained and described below in conjunction with the accompanying drawings and specific embodiments of the description. For the step numbers in the embodiment of the present invention, it is only set for the convenience of explanation and description, and there is no limitation on the order of the steps. The execution order of each step in the embodiment can be carried out according to the understanding of those skilled in the art Adaptive adjustment.

[0062] Since most of the existing technologies are only innovative heat map methods for the network structure, and mainly focus on the loss function. However, the heat map-based method has a coordinate mapping process, which ignores the loss caused by the coordinate mapping of the predicted points from the low-resolution heat map back to the original image loss, which limits the improvement of accuracy.

[0063] Therefore, this application provides a human body pose estimation meth...

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 discloses an attitude recognition method and a system based on a thermodynamic diagram and an offset vector, and a storage medium. The method comprises the following steps: obtaining a to-be-recognized target image; performing feature extraction on the to-be-recognized target image; predicting key point positions according to the extracted features; correcting the predicted key points, and determining final positions of the key points; and determining attitude information of a to-be-recognized target according to the key points. According to the method, the features of the imageare extracted, then the key point positions are predicted, the prediction result can be corrected, and finally, the attitude information is obtained through recognition. More accurate attitude information can be obtained, and the method can be widely applied to the technical field of deep learning.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a gesture recognition method, system and storage medium based on a heat map and an offset vector. Background technique [0002] Heat map: It is a probability map. The closer the pixel is to the center, the closer the probability is to 1, and the farther the pixel is to 0, it can be simulated by corresponding functions, such as Gaussian. [0003] Offset Vector: The displacement between points is inferred from the distance between the point and the reference point. [0004] Pose estimation: determine the pose of an object in an image (or stereo image, image sequence), and reconstruct the specific tasks of human joints and limbs. [0005] In daily life, people usually use the way of taking photos to record their lives. In order to better understand the information of the characters in the pictures, we want to locate people's positions and understand the activities of people. ...

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): G06K9/00G06K9/46G06N3/08
CPCG06N3/08G06V40/20G06V10/462
Inventor 肖菁李海超屈光卓
Owner SOUTH CHINA NORMAL 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