Gait recognition method and gait evaluation system based on human body key point detection algorithm

A detection algorithm and gait recognition technology, applied in biometric recognition, character and pattern recognition, calculation, etc., can solve problems such as difficulty in ensuring accuracy, cumbersome operations, and difficulty in walking for patients, and achieve the goal of reducing consumption and ensuring accuracy Effect

Pending Publication Date: 2020-04-17
FUDAN UNIV
View PDF12 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the use of wearable devices, this type of method imposes a heavy physical burden on the patient during the test, making it more difficult for patients with limited mobility to walk, and the resulting gait results are difficult to guarantee accuracy
In addition, the operat...

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
  • Gait recognition method and gait evaluation system based on human body key point detection algorithm
  • Gait recognition method and gait evaluation system based on human body key point detection algorithm
  • Gait recognition method and gait evaluation system based on human body key point detection algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] After obtaining the 3m standing up and walking experiment video, the parameters are extracted. The specific process is as follows:

[0054] 1. Perform key point detection on each frame in the video. Video recording began when the medical staff issued the "go" command and ended when the subject walked back to the chair. The detection process of key point detection specifically includes:

[0055] 1.1 For a single color video, each frame of image is processed separately; for each frame of image, it is first input into the human body detection network, and the network outputs the rectangular frame of all people in the image as the candidate frame of the target person; the existing human body can be used The detection network detects key points; the human body detection network can also be called a key point monitoring network;

[0056] 1.2 For each frame of image, intercept the corresponding single-person area from the original image according to all detected candidate fr...

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 gait recognition method and a gait evaluation system based on a human body key point detection algorithm. The method comprises the following steps: step 1, carrying out key point detection on each frame in a 3m standing walking experiment video shot by a single camera from the side surface of a human body, and extracting position change information of key points along with time so as to obtain a key point sequence; step 2, selecting a key frame for the video according to the key point sequence; wherein the key frame is used as a demarcation point of different actionsin the video; and step 3, extracting gait parameters according to the key point sequence in the video and the selected key frame. Through key point detection, key frames capable of serving as demarcation points of different actions in a video are obtained, and then gait parameter estimation is carried out. According to the method, automatic analysis is carried out by using an algorithm, and the consistency of gait evaluation is ensured.

Description

technical field [0001] The invention relates to the technical field of gait recognition, in particular to a gait recognition method and system based on a human body key point detection algorithm. Background technique [0002] Experimental studies have demonstrated that the severity of gait disturbance and its rate of progression are strongly associated with the risk of death. With the aging of the social structure, it is urgent to pay attention to the diagnosis and treatment needs of these senile diseases. Gait disturbance is very common in older adults and is a precursor to many underlying medical conditions. [0003] Gait disturbances such as slow walking can be used as the first objective clinical symptoms of many underlying cerebrovascular diseases, however, these subtle signals are easily overlooked, especially some elderly people have always believed that this is a natural manifestation of physical aging. If the recessive disease is not detected and treated in time, ...

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): G06K9/00G16H50/30
CPCG16H50/30G06V40/25G06V40/10
Inventor 王艳红邹乔莎冯新宇史传进
Owner FUDAN 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