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

Human body gait monitoring algorithm based on dynamic time planning

A technology of dynamic time planning and human body, applied in computing, complex mathematical operations, computer parts, etc., and can solve problems such as low recognition accuracy

Pending Publication Date: 2022-01-07
黑龙江省科学院智能制造研究所
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to propose a human gait monitoring algorithm based on dynamic time planning in order to solve the problem of low recognition accuracy existing in existing gait recognition methods

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 body gait monitoring algorithm based on dynamic time planning
  • Human body gait monitoring algorithm based on dynamic time planning
  • Human body gait monitoring algorithm based on dynamic time planning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0043] A human gait monitoring algorithm based on dynamic time planning in this embodiment, such as Figure 8 As shown, the algorithm is implemented through the following steps:

[0044] Human gait video acquisition using visual sensors, such as image 3 Shown, the steps of building a human gait model;

[0045] Based on the human gait video collected by the visual sensor, a human gait model including space, time, and motion trends is established through deep convolution, and the skeleton nodes of the human body during normal walking are obtained; 20 human skeletons are selected from these skeleton nodes through in-depth analysis Key nodes, and calculate the corresponding position of the key skeletal nodes of each gait; conduct in-depth analysis on the movement and position changes of human skeletal data nodes during walking, extract the characteristic parameters of human walking posture, and analyze based on the combination of dynamic time warping and gait parameters Under t...

specific Embodiment approach 2

[0067] The difference from Embodiment 1 is that in this embodiment, a human gait monitoring algorithm based on dynamic time planning, the K-means clustering algorithm uses dynamic time warping, the full name is Dynamic Time Warping, abbreviated as DTW: Use dynamic programming (DP) to find the smallest matching path of two different sequences, eliminate the difference on the time axis, and expand or shorten the length of the unknown until it is consistent with the length of the reference template, this method can maximize the degree of overlap . Since the time for different people to perform the same action is not exactly the same, the general algorithm requires that the lengths of the feature quantities of the two sequences should be equal, and the feature values ​​of the two sequences on the time axis should also correspond to each other. The DTW algorithm is currently the most effective solution to this problem. way.

[0068] Let the sequence of the reference template be X ...

specific Embodiment approach 3

[0077] The difference from Embodiment 1 or Embodiment 2 is that in this embodiment, the human gait monitoring algorithm based on dynamic time planning, the human gait video collection using the visual sensor, and the establishment of the human gait model In the step, it is also necessary to assemble a PC, an infrared emitter and an infrared sensor;

[0078] The visual sensor adopts the Kinect somatosensory controller launched by Microsoft. The device is equipped with a three-dimensional somatosensory camera sensor, which can simultaneously obtain human body depth image information, color image information and human skeleton information, and can communicate with a PC through a USB interface. The infrared emitter is used in conjunction with the infrared sensor to obtain 3D depth information. According to the principle of infrared emission and reception, the closer the object is to the camera, the brighter it will be, otherwise it will be darker. Use the self-developed detection ...

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 body gait monitoring algorithm based on dynamic time planning, and belongs to the field of human body gait recognition methods. An existing gait recognition method is low in recognition precision. The human body gait monitoring algorithm based on dynamic time planning comprises the following steps: acquiring a human body gait video by using a visual sensor, and establishing a human body gait model; acquiring skeleton movement information by adopting a sensor skeleton technology; training a gait monitoring recognition algorithm; performing motion recognition; and performing human gait skeleton diagnosis and evaluation. According to the gait diagnosis and evaluation carried out by the method, the recognition rate can reach 98% at most.

Description

technical field [0001] The invention relates to the field of gait recognition methods, in particular to a human gait monitoring algorithm based on dynamic time planning. Background technique [0002] The traditional diagnosis of abnormal gait is mainly through the patient's awareness of abnormal posture and seeking medical treatment. The doctor judges by the patient's chief complaint and observation of the patient's clinical manifestations and past medical history. It is impossible to accurately quantitatively analyze and qualitatively diagnose abnormal gait. There is a lack of early detection, early warning and rehabilitation guidance for diseases. The current state of development of related technologies is as follows: [0003] With the development of skeletal data extraction technology, the motion parameters of the human body are obtained through technical means, and based on the characteristics of gait analysis, such as figure 1 Shown is the analysis of walking posture ...

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): G06V40/20G06V10/762G06V10/82G06K9/62G06F17/16G06N3/04G06N3/08
CPCG06F17/16G06N3/08G06N3/045G06F18/23213
Inventor 周丽丽刘彤军杜寅甫王涛朱明清刘琦张志超王金玉
Owner 黑龙江省科学院智能制造研究所
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