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

Human body falling detection method based on RGBD sensor

A detection method and sensor technology, which is applied in the field of human motion recognition, can solve problems such as poor reliability, few technical features of fall detection, and sensitivity to changes in ambient light, and achieve the effect of protecting privacy

Active Publication Date: 2018-10-09
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF7 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of fall detection technology can extract fewer features and is sensitive to changes in ambient light, so the reliability is not good

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 falling detection method based on RGBD sensor
  • Human body falling detection method based on RGBD sensor
  • Human body falling detection method based on RGBD sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051]The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly. It should be emphasized that the following description is only exemplary and not intended to limit the scope of the invention and its application.

[0052] refer to figure 1 , in one embodiment, the fall detection method based on RGBD sensor includes: color camera calibration and depth camera stereo calibration, spatial three-dimensional structure information extraction, joint point location based on convolutional neural network, joint point static and dynamic feature extraction, fall Judgment classification training and prediction. This example uses Microsoft's KinectV2 as the RGBD sensor.

[0053] Among them, stereo camera calibration includes: ...

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 falling detection method based on an RGBD sensor. The human body falling detection method based on the RGBD sensor comprises the steps of carrying out internal and external camera parameter calibration correction on the RGBD sensor; adopting a calibration step for the RGBD video sequence, extracting the three-dimensional structural information of an active space environment; extracting a joint point on the basis of a multi-stage convolution neural network, so as to obtain a set of three-dimensional coordinate positions of human body joint points; extracting the three-dimensional structure information, static information and dynamic information of the human body joint points to serve as features for describing action behaviors of the human body and to comprehensively analyze whether abnormal falling behaviors occur or not. The falling detection method can accurately and conveniently monitor the three-dimensional movement states of an aged people anddetermining whether falling occurs or not. The intelligent RGBD sensor can be used for accurately identify and track the activity of the aged people without affecting the daily life of the aged people. Meanwhile, the deep imaging features are utilized, so that the privacy of the old is well protected.

Description

technical field [0001] The invention relates to human body action recognition, in particular to a human body fall detection method based on an RGBD sensor. Background technique [0002] Statistics show that my country is gradually entering the stage of an aging society, and how to effectively monitor the safety of the elderly has become an urgent problem to be solved. Falls are the most common safety problem encountered by the elderly in their daily lives. According to the statistics of the World Health Organization, falls are currently the second leading cause of accidental death and unintentional injury death in the world. About 460,000 people die every year due to fall injuries Among them, the proportion of fall injuries in low-income and middle-income countries is more than 80%, and the number of hospital admissions due to fall injuries is as high as 37 million each year. [0003] Falls of the elderly are often accompanied by symptoms such as fractures, soft tissue inju...

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): G08B21/04G06K9/00G06K9/62
CPCG08B21/043G08B21/0476G06V40/103G06F18/2411
Inventor 袁克虹申代友
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
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