Unlock instant, AI-driven research and patent intelligence for your innovation.

Human skeleton compression method, device and equipment for action recognition

A human skeleton and action recognition technology, applied in character and pattern recognition, instruments, calculations, etc., to achieve high-precision results

Active Publication Date: 2020-05-22
PEKING UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If each sample has 25 connection points at 25 frames per second, the amount of data generated will be as high as 3000Mbit / sec. In a crowded scene such as this, the skeleton data may put a lot of pressure on the network transmission

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
  • Human skeleton compression method, device and equipment for action recognition
  • Human skeleton compression method, device and equipment for action recognition
  • Human skeleton compression method, device and equipment for action recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to understand the characteristics and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the embodiments of the present disclosure. In the following technical description, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may be practiced without these details. In other instances, well-known structures and devices may be shown simplified in order to simplify the drawings.

[0051] figure 1 It is a schematic flowchart of a human skeleton compression method for action recognition according to an exemplary embodiment;

[0052] In some embodiments, a human skeleton compression method for...

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 a human skeleton compression method for motion recognition, and the method comprises the steps: obtaining to-be-recognized human skeleton data which is a matrix composed of time and joints; calculating a movement score of each joint in the human skeleton data, sorting each joint in the human skeleton data according to the sequence of the movement scores from high to low, and selecting a preset number of joints as reserved joints according to the sequence; compressing the human skeleton data according to the reserved joints to obtain compressed data; and recognizing thehuman body action according to the compressed data. Through the method, the skeleton data stream can be compressed to a relatively small bandwidth, and meanwhile, the action recognition precision is kept as high as possible.

Description

technical field [0001] The present invention relates to the technical field of behavior recognition, in particular to a human body skeleton compression method, device and equipment for motion recognition. Background technique [0002] Human poses, also known as skeletons, can be used as a form of data for action recognition. Skeleton-based motion analysis is more efficient and less noisy than video-based motion analysis. Human behavior recognition based on three-dimensional skeleton sequences has the characteristics of less storage capacity and less interference with environmental factors such as illumination changes and background changes, and skeleton data is highly abstract of human characteristics, so skeleton sequences have become the focus of research on behavior recognition in recent years . [0003] Skeleton data is essentially a matrix of size time × joints. And with the popularity of depth cameras, the acquisition of human skeleton data has become more and more ...

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): G06K9/00
CPCG06V40/23
Inventor 蒋婷婷李晟黄铁军田永鸿
Owner PEKING UNIV