Limb rehabilitation training auxiliary method and system, medium and equipment

A rehabilitation training and limb technology, applied in the application field of computer vision processing technology, can solve problems such as inconvenient wearing of auxiliary equipment, inconvenient installation process, physical injury of patients, poor practicability of auxiliary systems, etc., to achieve outstanding training effects and improved recognition accuracy. , the effect of improving the accuracy of gesture recognition

Inactive Publication Date: 2019-10-01
JINAN UNIVERSITY
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, similar rehabilitation training auxiliary equipment is basically realized based on sensors, which is a big obstacle for patients with limb motor dysfunction, and some auxiliary equipment are extremely inconvenient to wear and install, and some patients are therefore passively involved Rehabilitation training or even refusal to do rehabilitation training, resulting in poor practicability and ineffective effects of this type of auxiliary system
And because the wearing of complex sensors or mechanical auxiliary devices may also cause physical damage to the patient's body during rehabilitation training is also a major problem

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
  • Limb rehabilitation training auxiliary method and system, medium and equipment
  • Limb rehabilitation training auxiliary method and system, medium and equipment
  • Limb rehabilitation training auxiliary method and system, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] In recent years, computer technology has made rapid advances and image recognition technology has become more mature. The 2D video image captured by the camera can be used to recognize human body gestures and accurately obtain the position and direction of the user's limbs. At the same time, the increase in computer computing power (that is, the speed of computer operations) and the enhancement of image processing technology have made real-time recognition of posture data for human-computer interaction a reality. In addition, the human body gesture recognition device is more convenient to use, has a larger recognition range, and is cheaper than a sensor device.

specific Embodiment approach

[0051] Such as figure 1 As shown, this embodiment provides a specific implementation of a method for assisting limb rehabilitation training based on human posture recognition, including the following steps:

[0052] Step 1. Use the color camera on the video capture module to capture the user's action posture, collect the user's action posture image and transfer the frame to the joint point recognition module in real time. In order to increase the processing speed and ensure real-time performance, the image will be reduced Pixels and processing to reduce the transmission frame rate. First, process the image pixels of the user's action posture, calculate the ratio of the length and width of the image pixels to the length and width of the sampled pixels (the pixel size is 256*256) as the interval length, and take the pixels on the original image according to the interval length to make the screen The size is fixed at a pixel size of 256*256, and the frame rate of the picture process...

Embodiment 2

[0069] Such as Figure 4 As shown, this embodiment is another implementation of the rehabilitation training auxiliary method, in this embodiment, keep figure 1 The basic structure of the system remains unchanged, and the external devices of the system (ie, video capture module, application module, output module) are replaced with mobile devices (can be mobile phones, tablets, etc.). The back-end architecture is built into a cloud server framework, and the external architecture and back-end architecture are connected through the network. The specific steps of this implementation are as follows:

[0070] Step 1. The mobile APP software obtains the permission of the mobile device camera. The mobile device camera captures the patient's rehabilitation training action picture data and delivers it to the real-time image processing module of the mobile APP. The real-time image processing module reduces the real-time image resolution and stream data (A set of sequential, large, fast, and c...

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 limb rehabilitation training assisting method and system, a medium and equipment. The method comprises: collecting a user action posture image; carrying out convolution calculation on the image to obtain an image feature map; predicting an articulation point hot spot map and a limb direction vector field of the feature map, performing t times of prediction iteration, synthesizing the identification information of the two training branches into one stage prediction during each iteration, generating a user articulation point hot spot map and a limb direction vector field, and obtaining an articulation point position from the articulation point hot spot map; performing joint point connection by utilizing a limb connection greedy algorithm to obtain posture information of a user; and according to the trained action posture model, evaluating the posture information of the user, and obtaining and feeding back a user action posture evaluation result and to the user.According to the method, multi-branch prediction and multi-stage iteration are carried out, the posture recognition accuracy is improved by improving the accuracy of joint point hotspot map and limb direction vector field prediction, and then the auxiliary effect of rehabilitation training is enhanced.

Description

Technical field [0001] The present invention relates to the application field of computer vision processing technology, in particular to a method, system, medium and equipment for assisting limb rehabilitation training based on human posture recognition. Background technique [0002] Including for patients with neurological diseases such as stroke and Parkinson's disease, they will have muscle stiffness, clumsy behavior and other movement disorders to a large extent, and a large number of studies have also shown that targeted rehabilitation training is helpful for neurological diseases Treatment, especially the relief of movement disorders such as limb paralysis caused by it, is of great help. Therefore, limb rehabilitation training has become an important part of the treatment of neurological diseases. At the same time, neurological diseases are also one of the high-risk diseases. The number of patients suffering from Parkinson’s disease in my country exceeds 2 million. The numb...

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): G06K9/00G06K9/62G16H20/30
CPCG16H20/30G06V40/23G06F18/2411
Inventor 雷小林陈俊颖姚泽鑫林子斌罗晓峰林越郑晓鹏温钊迪
Owner JINAN 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