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

Home scene-oriented old people abnormal behavior detection method

A detection method and technology for the elderly, applied in the field of computer vision, can solve the problems of combined analysis, serious delay, and disconnection of multi-person behaviors, so as to improve practicability, eliminate missed judgments, and reduce false positive and false positive rates. Effect

Active Publication Date: 2021-01-15
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the popular products currently on the market are applied on the server side. Although the accuracy rate has been improved, the time delay is serious, and most of them have separated the relationship between the behaviors of multiple people in the same image, making effective combination analysis impossible.

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
  • Home scene-oriented old people abnormal behavior detection method
  • Home scene-oriented old people abnormal behavior detection method
  • Home scene-oriented old people abnormal behavior detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In order to illustrate the technical solution of the present invention more clearly, the technical solution of the present invention is described in further detail below in conjunction with the accompanying drawings:

[0020] Such as figure 1 As mentioned above, the specific steps of the abnormal behavior detection method for the elderly in the home scene include the following:

[0021] Step (1.1), several cameras are arranged in different directions in each room of the residence;

[0022] Step (1.2), obtaining various life videos of the elderly in the residence from several installed cameras;

[0023] Step (1.3), training a single-person behavior recognition CNN neural network, through which the input of various life videos of the elderly is identified and features are extracted; then according to the changes in the characteristics of the elderly when they are performing abnormal behaviors, extract their abnormal behaviors when the characteristic value;

[0024] Ste...

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 home scene-oriented old people abnormal behavior detection method. The invention belongs to the technical field of computer vision. The method comprises the following specific steps: 1, arranging a plurality of cameras in each room; 2, acquiring various life videos of the elderly in the residence; 3, training a single-person behavior recognition CNN neural network, and extracting feature values of the elderly during abnormal behaviors according to character feature changes of the elderly during the abnormal behaviors; 4, performing network training on the acquired various life videos at different angles; and 5, carrying out feature fusion and judgment on the feature values, and notifying family members of the elderly. The invention has the advantages that the method has a more comprehensive observation visual field, behaviors of the elderly can be comprehensively detected, and multiple features of abnormal behaviors of the elderly are observed and combined atthe same time. In the aspect of judging the abnormal behaviors of the old people, the misjudgment rate and the misjudgment rate are reduced, meanwhile, the situation of missed judgment is almost avoided, and the monitoring practicability is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for detecting abnormal behaviors of the elderly facing home scenes. Background technique [0002] Since the 1990s, a large number of scholars have devoted themselves to the research of behavior analysis. Traditional behavior analysis technology has been significantly developed and achieved many results. Behavior analysis technology is also playing an important role in more and more fields. . Moving target detection is the basis of behavior analysis. Only when a moving target is detected in video data or image data can further behavior analysis be performed. Moving object detection is to first detect the human body information from the image data, and then segment the human body foreground from the image to obtain the human body motion information. After the moving object detection and segmentation of the human body area, it is necessary to extract the human bod...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/20G06V2201/07G06N3/045G06F18/253G06F18/24G06F18/214Y02P90/02
Inventor 张晖夏望舒赵海涛孙雁飞朱洪波
Owner NANJING UNIV OF POSTS & TELECOMM
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