CN113658412A - Millimeter wave radar-based household old people behavior monitoring method and system - Google Patents
Millimeter wave radar-based household old people behavior monitoring method and system Download PDFInfo
- Publication number
- CN113658412A CN113658412A CN202110894480.0A CN202110894480A CN113658412A CN 113658412 A CN113658412 A CN 113658412A CN 202110894480 A CN202110894480 A CN 202110894480A CN 113658412 A CN113658412 A CN 113658412A
- Authority
- CN
- China
- Prior art keywords
- information
- millimeter wave
- wave radar
- monitoring
- behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0446—Sensor means for detecting worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0453—Sensor means for detecting worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
- H04W88/16—Gateway arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Emergency Management (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Cardiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physical Education & Sports Medicine (AREA)
- Physiology (AREA)
- Pulmonology (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method and a system for monitoring the behavior of a family old man based on a millimeter wave radar, wherein background information is set by a user in a self-defined manner; the millimeter wave radar module collects heartbeat information, respiratory frequency, position information and posture information of personnel and sends the information to the gateway; the gateway compares the received information with a preset threshold value, and starts a positioning and posture detection function when judging that the fluctuation is abnormal; the millimeter wave radar module carries out personnel positioning again and collects personnel posture information; generating image information by utilizing background information, positioning information, heartbeat information, respiratory frequency and posture information; selecting machine learning model parameters based on the person posture information; and importing the image information into the selected machine learning model parameters, and extracting characteristic information to perform discrimination and classification. The invention aims at the health state monitoring requirement of the household old people, can be customized in a personalized way, can monitor in a non-contact way, and has high timeliness, reliability, accuracy and effectiveness.
Description
Technical Field
The invention relates to a millimeter wave radar-based method and system for monitoring behaviors of a family elder, and belongs to the field of behavior monitoring of the Internet of things.
Background
Aging has become a tendency that society cannot avoid, the number of old people who are at home alone is gradually increased, on the other hand, in the endowment institution, the number of the old people is obviously more than the number of nursing staff, the nursing staff is difficult to immediately pay attention to the state of the old people, and serious consequences are easily caused if the old people cannot intervene and treat the old people in time when the old people suffer from sudden diseases. Although the real-time status of the elderly can be concerned about through advanced wearable devices or video monitoring devices, the real-time status of the elderly is also confronted with difficult-to-overcome problems, including that contact devices are expensive and inconvenient to wear, the elderly are easy to conflict, and privacy problems are caused by video monitoring devices, so that the scheme is difficult to be implemented on the ground. In addition, different old people have different health problems, different health states have different processing on detection information, and classification and judgment based on a single model also leads to single application scene of the traditional non-contact detection scheme.
In summary, it is urgently needed to design a non-contact monitoring system which is not easy to cause privacy problems and can be customized as required to track the health condition of the elderly in real time, so that nursing staff or other staff can conveniently and remotely monitor the basic physical condition of the elderly as required.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a method and a system for realizing personalized and non-contact monitoring service for the behavior of the elderly at home based on a millimeter wave radar aiming at the health state monitoring requirement of the elderly at home.
The technical scheme is as follows: the invention discloses a millimeter wave radar-based method for monitoring the behavior of a family elder, which comprises the following steps:
(1) setting background information by a user in a self-defined manner;
(2) the millimeter wave radar module collects heartbeat information, respiratory frequency, position information and posture information of personnel and sends the information to the gateway;
(3) the gateway compares the received information with a preset threshold value, and starts a positioning and posture detection function when judging that the fluctuation is abnormal;
(4) the millimeter wave radar module carries out personnel positioning again and collects personnel posture information;
(5) generating image information by utilizing background information, positioning information, heartbeat information, respiratory frequency and posture information;
(6) selecting machine learning model parameters based on the person posture information;
(7) and importing the image information into the selected machine learning model parameters, and extracting characteristic information to perform discrimination and classification.
In step 1, background information is a basic image frame.
In the step 2, the position information is the position of a pixel point in the image frame, the information of the letter and the breathing frequency are expressed as the gray value of the pixel point in the region, and the posture information is the range of the region of the point to be bet.
In step 5, generating image information includes the steps of:
(51) generating a basic frame diagram, namely a room layout diagram, based on the background information parameters;
(52) marking the position of a pixel central point on the basic frame diagram based on the collected positioning information;
(53) confirming a pixel area by taking a pixel central point as a center based on the acquired attitude information;
(54) converting the heartbeat or respiratory frequency into a gray value of a pixel area;
(55) and confirming the generated image.
When the heartbeat information and the respiratory frequency are converted into the gray values of the regional pixel points, the method is completed through the following formula:
S=α*X+β*H
wherein S is a pixel value of the last generated image, X is a heartbeat value, H is a respiratory frequency, α and β are weight values, and the selection of the weight values depends on the base type.
And 6, sending the extracted characteristic information to a server through a gateway, and judging and classifying the behavior state by the server based on the historical information.
In step 6, the machine learning model comprises three levels of normal, hidden danger and abnormity, wherein the hidden danger is used for predicting possible abnormity, provides prediction information, and reminds a user of paying attention early and intervening immediately; the abnormity is an emergency situation with hidden danger prediction, and provides instant warning information.
In step 3, different reference values are selected for the threshold value based on different basic types, wherein the basic types comprise 4 types of heart diseases, cardiovascular and cerebrovascular diseases, respiratory diseases and common monitoring.
A household old man behavior monitoring system based on a millimeter wave radar comprises the millimeter wave radar, a gateway and a server, wherein the millimeter wave radar acquires heartbeat information, respiratory frequency, indoor position and attitude information of a person; the gateway extracts characteristic data according to the acquired information and transmits the characteristic data to the server; and the server judges the state by combining the continuous characteristic data in the preset time period.
Further, the millimeter wave radar-based household old man behavior monitoring system further comprises an alarm module, and according to a monitoring result, when hidden danger or abnormality occurs, an early warning prompt or an alarm prompt is sent to a user through the alarm module.
Has the advantages that: compared with the prior art, the invention has the following remarkable advantages: based on millimeter wave radar and edge computing technology, the system architecture is more reliable and efficient; the system can be customized in a personalized way, and the uploaded information data can be collected in real time, so that the timely effectiveness of the collected data is ensured; the state image data is combined with the continuous characteristic data in the preset time period to judge the state, so that the possibility of misjudgment in the judging process is avoided, and the engineering application value of the system is improved.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart of the input image generation of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in fig. 1, the method for monitoring the behavior of the elderly at home based on the millimeter wave radar of the present invention includes the following steps:
(1) setting background information by a user in a self-defined manner;
(2) the millimeter wave radar module collects heartbeat information, respiratory frequency, position information and posture information of personnel and sends the information to the gateway;
(3) the gateway compares the received information with a preset threshold value, and starts a positioning and posture detection function when judging that the fluctuation is abnormal;
(4) the millimeter wave radar module carries out personnel positioning again and collects personnel posture information;
(5) generating image information by utilizing background information, positioning information, heartbeat information, respiratory frequency and posture information;
(6) selecting machine learning model parameters based on the person posture information;
(7) and importing the image information into the selected machine learning model parameters, and extracting characteristic information to perform discrimination and classification.
In step 1, background information is a basic image frame.
In the step 2, the position information is the position of a pixel point in the image frame, the information of the letter and the breathing frequency are expressed as the gray value of the pixel point in the region, and the posture information is the range of the region of the point to be bet.
With reference to fig. 2, in step 5, generating image information includes the following steps:
(51) generating a basic frame diagram, namely a room layout diagram, based on the background information parameters;
(52) marking the position of a pixel central point on the basic frame diagram based on the collected positioning information;
(53) confirming a pixel area by taking a pixel central point as a center based on the acquired attitude information;
(54) converting the heartbeat or respiratory frequency into a gray value of a pixel area;
(55) and confirming the generated image.
When the heartbeat information and the respiratory frequency are converted into the gray values of the regional pixel points, the method is completed through the following formula:
S=α*X+β*H
wherein S is a pixel value of the last generated image, X is a heartbeat value, H is a respiratory frequency, α and β are weight values, and the selection of the weight values depends on the base type.
And 6, sending the extracted characteristic information to a server through a gateway, and judging and classifying the behavior state by the server based on the historical information.
In step 6, the machine learning model comprises three levels of normal, hidden danger and abnormity, wherein the hidden danger is used for predicting possible abnormity, provides prediction information, and reminds a user of paying attention early and intervening immediately; the abnormity is an emergency situation with hidden danger prediction, and provides instant warning information.
In step 3, different reference values are selected for the threshold value based on different basic types, wherein the basic types comprise 4 types of heart diseases, cardiovascular and cerebrovascular diseases, respiratory diseases and common monitoring.
A household old man behavior monitoring system based on a millimeter wave radar comprises the millimeter wave radar, a gateway and a server, wherein the millimeter wave radar acquires heartbeat information, respiratory frequency, indoor position and attitude information of a person; the gateway extracts characteristic data according to the acquired information and transmits the characteristic data to the server; and the server judges the state by combining the continuous characteristic data in the preset time period.
In this embodiment, old man's action monitoring system at home based on millimeter wave radar still includes the warning module, according to the monitoring result, when hidden danger or unusual appearing, sends the early warning through the warning module and reminds or reports an emergency and asks for help or increased vigilance to the user.
The invention provides an interactive interface for service customization operation for users through real-time data acquisition, processing, analysis and discrimination, provides different service types such as heart diseases, cardiovascular and cerebrovascular diseases, solitary old people, respiratory diseases, common monitoring, multi-class personnel monitoring and the like, provides a more reliable, efficient and open system architecture based on edge computing and software definition technology, and improves the robustness and the engineering application value of the system.
Claims (10)
1. A household old man behavior monitoring method based on a millimeter wave radar is characterized by comprising the following steps:
(1) setting background information by a user in a self-defined manner;
(2) the millimeter wave radar module collects heartbeat information, respiratory frequency, position information and posture information of personnel and sends the information to the gateway;
(3) the gateway compares the received information with a preset threshold value, and starts a positioning and posture detection function when judging that the fluctuation is abnormal;
(4) the millimeter wave radar module carries out personnel positioning again and collects personnel posture information;
(5) generating image information by utilizing background information, positioning information, heartbeat information, respiratory frequency and posture information;
(6) selecting machine learning model parameters based on the person posture information;
(7) and importing the image information into the selected machine learning model parameters, and extracting characteristic information to perform discrimination and classification.
2. The millimeter wave radar-based method for monitoring the behavior of elderly people living in home according to claim 1, wherein in the step 1, background information is a basic image frame.
3. The millimeter wave radar-based method for monitoring the behavior of the elderly living in the home according to claim 1, wherein the position information in the step 2 is the position of a pixel point in the image frame, the information of the letter and the breathing frequency are represented by gray values of pixel points in the area, and the posture information is the range of the area where the user wants to bet on the point.
4. The millimeter wave radar-based method for monitoring the behavior of elderly people living in home according to claim 1, wherein the step 5 of generating image information comprises the steps of:
(51) generating a basic frame diagram, namely a room layout diagram, based on the background information parameters;
(52) marking the position of a pixel central point on the basic frame diagram based on the collected positioning information;
(53) confirming a pixel area by taking a pixel central point as a center based on the acquired attitude information;
(54) converting the heartbeat or respiratory frequency into a gray value of a pixel area;
(55) and confirming the generated image.
5. The millimeter wave radar-based method for monitoring the behavior of the elderly living in the home according to claim 4, wherein the conversion of the heartbeat information and the breathing frequency into the gray values of the regional pixel points is performed according to the following formula:
S=α*X+β*H
wherein S is a pixel value of the last generated image, X is a heartbeat value, H is a respiratory frequency, α and β are weight values, and the selection of the weight values depends on the base type.
6. The millimeter wave radar-based method for monitoring the behavior of the elderly living in the home according to claim 1, wherein the extracted feature information is sent to a server through a gateway, and the server discriminates and classifies the behavior state based on historical information.
7. The millimeter wave radar-based method for monitoring the behavior of the elderly living in the home according to claim 1, wherein in the step 6, the machine learning model comprises three levels of normal, hidden danger and abnormal, and the level of the hidden danger corresponds to the advance notice of the occurrence of the abnormal and provides prediction information; the abnormality level corresponds to an emergency alert that an abnormality has occurred.
8. The millimeter wave radar-based method for monitoring the behavior of the elderly living in the home according to claim 1, wherein in the step 3, the threshold value is selected from different reference values based on different basic types, wherein the basic types include heart diseases, cardiovascular and cerebrovascular diseases, respiratory diseases and general monitoring 4 types.
9. A household old man behavior monitoring system based on a millimeter wave radar is characterized by comprising the millimeter wave radar, a gateway and a server, wherein the millimeter wave radar acquires heartbeat information, respiratory frequency, indoor position and posture information of personnel; the gateway extracts characteristic data according to the acquired information and transmits the characteristic data to the server; and the server judges the state by combining the continuous characteristic data in the preset time period.
10. The millimeter wave radar-based elderly home behavior monitoring system according to claim 9, further comprising an alarm module, wherein an early warning or warning prompt is sent to a user through the alarm module according to a monitoring result when a hidden danger or an abnormality occurs.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110894480.0A CN113658412A (en) | 2021-08-05 | 2021-08-05 | Millimeter wave radar-based household old people behavior monitoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110894480.0A CN113658412A (en) | 2021-08-05 | 2021-08-05 | Millimeter wave radar-based household old people behavior monitoring method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113658412A true CN113658412A (en) | 2021-11-16 |
Family
ID=78478387
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110894480.0A Withdrawn CN113658412A (en) | 2021-08-05 | 2021-08-05 | Millimeter wave radar-based household old people behavior monitoring method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113658412A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114038162A (en) * | 2021-12-29 | 2022-02-11 | 神思电子技术股份有限公司 | Vulnerable user nursing and alarming method, equipment and medium |
CN114152283A (en) * | 2021-11-24 | 2022-03-08 | 山东蓝创网络技术股份有限公司 | Family old-care nursing bed service supervision system based on stereoscopic dot matrix technology |
CN114706318A (en) * | 2022-04-18 | 2022-07-05 | 深圳亿思腾达集成股份有限公司 | Monitoring method and system based on smart home and terminal equipment |
CN114973590A (en) * | 2022-04-07 | 2022-08-30 | 深圳市科达康实业有限公司 | Indoor positioning method and system |
CN116602663A (en) * | 2023-06-02 | 2023-08-18 | 深圳市震有智联科技有限公司 | Intelligent monitoring method and system based on millimeter wave radar |
CN116703227A (en) * | 2023-06-14 | 2023-09-05 | 快住智能科技(苏州)有限公司 | Guest room management method and system based on intelligent service |
-
2021
- 2021-08-05 CN CN202110894480.0A patent/CN113658412A/en not_active Withdrawn
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114152283A (en) * | 2021-11-24 | 2022-03-08 | 山东蓝创网络技术股份有限公司 | Family old-care nursing bed service supervision system based on stereoscopic dot matrix technology |
CN114038162A (en) * | 2021-12-29 | 2022-02-11 | 神思电子技术股份有限公司 | Vulnerable user nursing and alarming method, equipment and medium |
CN114973590A (en) * | 2022-04-07 | 2022-08-30 | 深圳市科达康实业有限公司 | Indoor positioning method and system |
CN114706318A (en) * | 2022-04-18 | 2022-07-05 | 深圳亿思腾达集成股份有限公司 | Monitoring method and system based on smart home and terminal equipment |
CN116602663A (en) * | 2023-06-02 | 2023-08-18 | 深圳市震有智联科技有限公司 | Intelligent monitoring method and system based on millimeter wave radar |
CN116602663B (en) * | 2023-06-02 | 2023-12-15 | 深圳市震有智联科技有限公司 | Intelligent monitoring method and system based on millimeter wave radar |
CN116703227A (en) * | 2023-06-14 | 2023-09-05 | 快住智能科技(苏州)有限公司 | Guest room management method and system based on intelligent service |
CN116703227B (en) * | 2023-06-14 | 2024-05-03 | 快住智能科技(苏州)有限公司 | Guest room management method and system based on intelligent service |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113658412A (en) | Millimeter wave radar-based household old people behavior monitoring method and system | |
US12011259B2 (en) | Systems and methods for fall detection | |
US7612681B2 (en) | System and method for predicting fall risk for a resident | |
CN103325080B (en) | A kind of home for the aged based on technology of Internet of things intelligent safeguard system and method | |
CN110139598A (en) | Monitoring and tracking system, method, article and equipment | |
CN110197732B (en) | Remote health monitoring system, method and equipment based on multiple sensors | |
JP2009254817A (en) | System for and method of monitoring cognitive ability of person | |
CN111362089A (en) | Method and system for identifying entering of electric vehicle into lift car through artificial intelligence | |
Copetti et al. | Intelligent context-aware monitoring of hypertensive patients | |
WO2019003859A1 (en) | Monitoring system, control method therefor, and program | |
CN106821382A (en) | Monitoring of respiration diagnostic system, interference filter method and diagnostic method | |
CN113392765A (en) | Tumble detection method and system based on machine vision | |
CN117197998A (en) | Sensor integrated nursing system of thing networking | |
CN113408477A (en) | Infant sleep monitoring system, method and equipment | |
JP2021194468A (en) | Information processing device, watching system and control program | |
TWM642660U (en) | Home Behavior Analysis System | |
CN113671489A (en) | State reminding method and device, electronic equipment and computer readable storage medium | |
CN114492656A (en) | Fatigue degree monitoring system based on computer vision and sensor | |
CN117260774B (en) | Old man's robot system of accompanying and attending to based on interaction of multidimension degree intelligence | |
Watanapa et al. | Post‐Fall Intelligence Supporting Fall Severity Diagnosis Using Kinect Sensor | |
Cole et al. | Home automation to promote independent living in elderly populations | |
US20220398418A1 (en) | Machine learning based dignity preserving transformation of videos for remote monitoring | |
CN114171146B (en) | Intelligent medical monitoring method, system and readable storage medium | |
CN112617821B (en) | System and method for monitoring getting on and off of bed of old people | |
US20240157900A1 (en) | Systems and methods for accident prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211116 |
|
WW01 | Invention patent application withdrawn after publication |