Method for enhancing limb motion parameter detection of depth camera

A technology of depth camera and motion parameters, applied in neural learning methods, computer parts, instruments, etc., can solve the problems of insufficient human body posture information, lack of frame data, insufficient data volume, etc.

Active Publication Date: 2021-08-20
CHONGQING UNIV
View PDF12 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this solution is only aimed at the human body in a lying posture, and the types of detection and recognition of human motion postures are too single
[0007] At present, the solutions given on the market are basically aimed at some specific postures, that is, restricting the movement of the subjects, which leads to the lack of rich and comprehensive detected human posture information.
In addition, various problems may occur during the data collection process, such as improper operation of hardware equipment, physical conditions of the subjects, etc., resulting in a serious shortage of collected data, missing many frames of data, and missing data will affect the follow-up The data analysis results will also have a certain impact. During the data collection process, some bone joint data may also be missing. This will cause the data collectors to re-collect the data of the subjects. very time consuming

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
  • Method for enhancing limb motion parameter detection of depth camera
  • Method for enhancing limb motion parameter detection of depth camera
  • Method for enhancing limb motion parameter detection of depth camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1: a technical method and realization for enhancing the depth camera detection of upper limb motion parameters, comprising the following steps:

[0048] like Figure 1 ~ Figure 2 As shown in the figure, the subject stood in front of the depth camera, and within the specified time, the subject performed various movements with the upper limbs without any restraint, such as stretching, elbow bending and stretching, etc. This process needs to be repeated n times by the subjects, and the value of n is judged by the operator according to the situation at that time.

[0049] Select the most complete and calibrated set of n experimental data as the training set data;

[0050] When collecting the three-dimensional coordinates of the skeletal joint points of the subject's upper limb movement, there may be insufficient data. For example, the subject's upper limb movement is inconvenient, and the coordinate sequence collected within the specified time is relatively shor...

Embodiment 2

[0052] Embodiment 2: The technical method and realization for enhancing the depth camera to detect human gait parameters include the following steps:

[0053] like figure 1 As shown in , the subject stood in front of the range depth camera to complete the gait data acquisition process, and the subject was required to repeat this process n times;

[0054] Select a group with the most complete data among the n experimental data and calibrated by 3D motion capture data as the training set data;

[0055] In the process of data collection, various emergencies may occur. If the three-dimensional coordinate data of skeletal joint points in the process of collecting the subject's human body is collected, the coordinate sequence is too short, that is, the amount of data is insufficient to For subsequent gait analysis, it is necessary to predict and reconstruct the three-dimensional coordinate data of the skeletal joint points during the walking process of the subject to obtain suffici...

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 method for enhancing limb motion parameters detected by a depth camera, and belongs to the field of human body posture information detection. The method comprises the following steps: acquiring limb movement data of a human body by using a depth camera; s2, when it is detected that all mark points of the collected human body limb movement data are missing after a certain moment, namely, the data volume is insufficient, using the trained neural network with the attention mechanism to predict and reconstruct the missing data, and obtaining complete skeleton three-dimensional coordinate data; and when it is detected that part of mark points of the collected human body limb movement data are missing at a certain moment, that is, three-dimensional coordinate data of individual skeleton joint points are missing at certain moments, complementing the missing data points by using the trained neural network with the attention mechanism, and finally obtaining complete skeleton three-dimensional coordinate data. According to the invention, non-contact human body free motion detection is achieved, and the problem of data missing possibly occurring when a depth camera is used for collecting data is effectively eliminated.

Description

technical field [0001] The invention belongs to the field of human posture information detection, and relates to a method for enhancing a depth camera to detect limb motion parameters. Background technique [0002] Human posture includes static posture and motion posture. Human motion posture detection refers to the detection of posture information of the human body or parts of the human body during motion through a certain detection method, such as: spatial position, spatial shape, movement speed, joint angle , EMG signals, etc., and by analyzing these human body posture information, we can understand the instantaneous posture of people and the law of human body posture changes. [0003] Human motion posture detection is an indispensable detection technology for obtaining human body information, and it has a wide range of applications in sports training, gait analysis, action recognition, medical rehabilitation and military fields. [0004] The patent application with the ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/23G06N3/045G06F18/213G06F18/214
Inventor 张若琦吴小鹰朱业安张丽张琳侯文生陈琳
Owner CHONGQING UNIV
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