Method for recognizing falling of old people and accompanying robot

A technology for the elderly and robots, applied in character and pattern recognition, instruments, sensors, etc., can solve the problems of low recognition accuracy, achieve high recognition accuracy, solve the problems of accuracy and speed, and reduce the effect of positioning error

Active Publication Date: 2019-11-15
SICHUAN TECH & BUSINESS UNIV
View PDF9 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is: the present invention provides a method for identifying falls of the elderly and an accompanying robot, which solves the problem of low recognition accuracy caused by the existing use of local feature extraction and detection, and realizes the problem of blurred images, video shakes and poor light. It can correctly and quickly identify the fall behavior of the elderly in such environments

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 recognizing falling of old people and accompanying robot
  • Method for recognizing falling of old people and accompanying robot
  • Method for recognizing falling of old people and accompanying robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] The traditional attitude feature extraction method of the elderly relies on the recognition of the local features of the elderly body in the image, and accurate detection is required. When the environmental noise such as light is large, the extraction of local features may be inaccurate; the attitude feature extraction method cannot obtain high-dimensional The densely sampled information in the space will lead to data loss during continuous estimation, resulting in the failure to guarantee the recognition accuracy and recognition continuity. Therefore, this application proposes an identification method to overcome the above problems, the details are as follows:

[0066] Such as figure 1 , 4 As shown, a method for identifying falls in the elderly includes the following steps:

[0067] Step 1: Collect body video data of the detected object;

[0068] Step 2: Use the YOVO algorithm to perform human body positioning through distance measurement to obtain human body image ...

Embodiment 2

[0100] Based on the method of Embodiment 1, this embodiment provides a companion robot that recognizes falls of the elderly, the details are as follows:

[0101] A companion robot that recognizes falls in the elderly includes

[0102] The collection device is used to collect video information, voice information and image information such as the behavior and posture of the detection object and send them to the GPU cluster server and database;

[0103] GPU cluster server to analyze video information, image information and voice information to obtain fall recognition results;

[0104] The database is used to store the collected video information, image information and voice information and the analyzed fall recognition results;

[0105] The processing device is used for invoking database data, receiving fall recognition results for display, and alarming.

[0106] The GPU cluster server includes a fall recognition module, and the fall recognition module includes

[0107] A form...

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 method for recognizing falling of old people and an accompanying robot, and relates to the field of falling posture recognition. The method comprises the steps: 1, collectingbody video data; 2, positioning a human body; 3, acquiring skeleton information based on the result; 4, calculating a head and foot height difference value hd, a head and foot height difference valuehp of a front frame and a rear frame, and a speed v and a shoulder width w corresponding to the head height difference value of the front frame and the rear frame according to the skeleton information; and 5, establishing a judgment formula according to the data, outputting a result, calculating a distance measurement error, judging whether the distance measurement error meets a dichotomy condition or not, if so, identifying by adopting the established neural network model, and if not, returning to the step 1. According to the method, figure extraction is carried out firstly, and then posturerecognition is carried out, and dynamic and static recognition is carried out through skeleton information, so that the problem of low recognition accuracy caused by local feature extraction and detection in the prior art is solved, and the falling behavior of the old people can be correctly and rapidly recognized.

Description

technical field [0001] The invention relates to the field of fall posture recognition, in particular to a method for recognizing falls of an elderly person and an accompanying robot. Background technique [0002] With the continuous development and progress of my country's science and technology and medical care, my country's "aging" population is growing simultaneously, and the elderly care has become a social problem. So far, my country's aging population has far exceeded the world average. According to the prediction results of the United Nations, the National Population and Family Planning Commission, the National Committee on Aging and some scholars on the future aging development trend of China, the elderly population in my country will increase by about 10 million annually from 2018 to 2035. At present, the rate of elderly empty-nest families in my country's mass cities has reached 70%. This data is deteriorating sharply. However, China's elderly care industry is s...

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): G06K9/00B25J11/00A61B5/11
CPCA61B5/1117A61B5/1128B25J11/009G06V40/20G06V20/10
Inventor 王敏陈蕊汪依帆
Owner SICHUAN TECH & BUSINESS 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