Smart home security protection system based on remote monitoring

Abstract

The present invention discloses an intelligent home safety protection system based on remote monitoring, which relates to the field of home safety technology, and comprises an information collection module, an intelligent protection module, and a feedback correction module. The information collection module is used to determine the identity of an elderly person and collect the action information of the elderly person. The intelligent protection module is used to analyze the action behavior of the elderly person and alarm for abnormal action phenomena. The feedback correction module is used to set the position relationship of food taking and putting according to the compliance of the elderly person's action, and to adjust the subsequent position relationship of taking and putting food in real time according to the elderly person's action. The information collection module comprises a face recognition module, an identity labeling module, a camera unit, a voice reminder module, an action storage library, and a food storage cabinet. The face recognition module is electrically connected to the identity labeling module. The present invention has the characteristics of accurate judgment and strong pertinence.

Description

Technical Field

[0001] The present invention relates to the field of home safety technology, and in particular to an intelligent home safety protection system based on remote monitoring. Background Art

[0002] With the popularity of home-based elderly care communities, remote monitoring technology is increasingly being used in elderly care community security protection. Surveillance cameras installed in various locations at home can transmit images in real time, and intelligent algorithms can be used to analyze whether the elderly's movements are abnormal, thereby protecting the elderly's life safety and effectively saving the time cost of caregivers.

[0003] In the existing technology, only a set of fixed actions are performed by the elderly and then analyzed, or only some daily behaviors of the elderly are identified. Although the former is highly targeted, it is easy to cause the elderly to get bored. After a long time, the elderly deliberately do not do standard actions, resulting in inaccurate judgment results. The latter involves too many scenarios, resulting in a lack of targeted judgment. Therefore, it is necessary to design a smart home security protection system based on remote monitoring that is accurate and targeted. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent home security protection system based on remote monitoring to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent home security protection system based on remote monitoring, comprising an information collection module, an intelligent protection module, and a feedback correction module. The information collection module is used to determine the identity of the elderly and collect the elderly's movement information. The intelligent protection module is used to analyze the elderly's movement behavior and alarm for abnormal movement phenomena. The feedback correction module is used to set the positional relationship between food picking and putting according to the compliance of the elderly's movements, and to make real-time adjustments to the subsequent positional relationship between food picking and putting according to the elderly's movements.

[0006] According to the above technical solution, the information collection module includes a face recognition module, an identity tagging module, a camera unit, a voice reminder module, an action storage library, and a food storage cabinet. The face recognition module is electrically connected to the identity tagging module, and the camera unit is electrically connected to the action storage library. The face recognition module is used to identify the elderly in the home-based elderly care community, the identity tagging module is used to mark and confirm the identity of the elderly, the camera unit is used to shoot the place where food is taken and put, the voice reminder module is used to play voice prompts to the elderly who need to be monitored to take and put food, and call animals to the feeding place, the action storage library is used to store the actions of each elderly person taking and putting food, and the standard actions of taking and putting food, and the food storage cabinet includes a plurality of food storage drawers for storing food;

[0007] The intelligent protection module includes a storage unlocking module, a motion analysis module, a compliance determination module, and an alarm module. The motion analysis module is electrically connected to the motion storage library and the compliance determination module. The compliance determination module is electrically connected to the alarm module. The storage unlocking module is used to unlock the food storage drawer that currently needs to take food. The motion analysis module is used to analyze the actions of the elderly in taking and storing food. The compliance determination module is used to analyze the compliance of the elderly's actions with standard actions according to the motion analysis results. The alarm module is used to alarm the caregiver when it is determined that the current action is abnormal.

[0008] The feedback correction module includes a real-time position adjustment module and a pick-up and placement position setting module. The pick-up and placement position setting module is electrically connected to the motion analysis module, and the real-time position adjustment module is electrically connected to the compliance determination module. The real-time position adjustment module is used to temporarily adjust the next food picking and storage position when the elderly's current motion is inconsistent with the motion during the test. The pick-up and placement position setting module is used to preliminarily set the food picking and placement position according to the elderly's physical condition and the results of initial data collection.

[0009] According to the above technical solution, the working method of the system is:

[0010] S1. Scan the faces of all elderly people and confirm their identity information. Place food storage drawers at different locations in the homes of the elderly care community, set multiple food placement locations around the food storage cabinets, and install camera units near the food placement locations.

[0011] S2. Unlock different food storage drawers one by one and ask the staff to place the stored food in different food placement positions in sequence, use a camera unit to shoot standard food taking and placing movements, and establish a standard human movement 3D model;

[0012] S3, notifying each elderly person to conduct a test on taking and putting food, photographing and analyzing the elderly person's actions of taking and putting food, establishing a three-dimensional human body action model of the elderly person, and setting the current positional relationship of the elderly person's food taking and putting according to the action conformity with the standard three-dimensional human body action model, and then conducting a test based on this positional relationship;

[0013] S4. During daily monitoring, a voice prompt is played at the specified time to remind the elderly to take and put food, and the pet is called to the feeding place at the same time. The elderly’s current actions are evaluated for compliance with the test in S3. When it is determined that there is a small abnormality in the action, the position of the next food taking and putting is temporarily adjusted, and the compliance is judged again. When it is determined that there is a large abnormality in the action, the alarm module immediately sends an alarm to the caregiver.

[0014] According to the above technical scheme, in S2, the specific method for establishing a standard human body motion three-dimensional model is: establishing a spatial three-dimensional coordinate system, calculating the position of each camera unit relative to the spatial three-dimensional coordinate system, obtaining the projection matrix of the camera, and reconstructing the three-dimensional point cloud data of the food picking and placing action images of the staff taken at multiple different angles, marking the key points of the body joints at the shoulders, elbows, wrists, knees, coccyx, and ankles of the staff, importing the marked joint coordinates into the modeling software, using the skeletal animation system to establish the joints, and establishing a natural motion trajectory through interpolation to create a standard human body motion three-dimensional model.

[0015] According to the above technical solution, in S3, the specific method for obtaining the degree of conformity of the action with the standard human action three-dimensional model is:

[0016] S3-1. When the elderly person takes food and places it at the designated location, the standard human motion 3D model of the same taking and placing location is called, and the angles between the key points of the elderly person's body joints are recorded at intervals t, and the angles are subtracted from the angles between the key points of the body joints of the standard human motion 3D model to calculate the error of the angles between the two. , and the average angle error is obtained ,in is the number of angles between key points of body joints, is the number of times t is recorded during the behavior of taking and placing food;

[0017] S3-2. Select several points where the distance needs to be recorded from the key points of the body joints and record them as distance measurement points. The distance between the elderly's distance measurement points is recorded, subtracted from the distance between the distance measurement points of the standard human motion 3D model, and the error between the two distances is calculated. , and get the average distance error ,in is the number of distances between distance measurement points;

[0018] S3-3, action compliance is ,in is the action angle weight coefficient, is the body part distance weight coefficient.

[0019] According to the above technical solution, in S3, the setting method of the position relationship between the current elderly person's food taking and putting is: during the taking and putting test, it is set to take from the bottom storage drawer to the top putting position, which is the action with the largest distance span. After the elderly person makes this action, the action compliance is calculated as , The higher the value, the closer the elderly person's physical condition is to that of a normal person. Set the vertical distance between where food is taken and put. The larger the .

[0020] According to the above technical solution, in S4, the three-dimensional model of the elderly's human body movements under the relationship between the picking and storing positions set in the test in S3 is used as a benchmark to evaluate the conformity of the three-dimensional model of the elderly's human body movements during daily monitoring with the benchmark, and the standard for determining whether the movement has a small amplitude abnormality is The standard for judging whether the action is significantly abnormal is When it is determined that there is a small abnormality in the action, the adjacent food picking position and storage position are changed, and monitoring is performed again to determine the conformity of the elderly's human body movement 3D model with the standard human body movement 3D model. , and re-judge the compliance.

[0021] According to the above technical solution, in S4, when ,and When there is a continuous decrease, reduce the time interval between the next pick-up and delivery test for this elderly person To increase the frequency of monitoring the physical condition of the elderly, specifically: ,in To take and place the test times, is the weight coefficient of the trend of decreasing conformity, is the weight coefficient of the conformity itself, The more times the value is constant and decreases continuously, the The bigger.

[0022] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention limits the action analysis of the elderly to the food delivery scene of animals, and analyzes the elderly's actions in different aspects by asking the elderly to deliver food at different specified locations. Since interacting with animals can fully mobilize the elderly's interest, the elderly are not easily bored. At the same time, by specially setting the locations for taking and delivering food, various test actions can be completed in a targeted manner, making the detection targeted. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0024] Figure 1 It is a schematic diagram of the overall module structure of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 The present invention provides a technical solution: a smart home security protection system based on remote monitoring, comprising an information collection module, an intelligent protection module, and a feedback correction module. The information collection module is used to determine the identity of the elderly and collect the action information of the elderly. The intelligent protection module is used to analyze the action behavior of the elderly and alarm for abnormal action phenomena. The feedback correction module is used to set the position relationship of food taking and putting according to the compliance of the elderly's action, and adjust the subsequent position relationship of taking and putting food in real time according to the elderly's action.

[0027] The information collection module includes a face recognition module, an identity tagging module, a camera unit, a voice reminder module, an action storage library, and a food storage cabinet. The face recognition module is electrically connected to the identity tagging module, and the camera unit is electrically connected to the action storage library. The face recognition module is used to identify the elderly in the home-based elderly care community. The identity tagging module is used to tag and confirm the identity of the elderly. The camera unit is used to shoot the place where food is taken and put. The voice reminder module is used to play voice prompts to the elderly who need to be monitored to take and put food, and call animals to the feeding place. The action storage library is used to store the actions of each elderly person taking and putting food, as well as the standard actions of taking and putting food. The food storage cabinet includes a plurality of food storage drawers for storing food;

[0028] The intelligent protection module includes a storage unlocking module, a motion analysis module, a compliance determination module, and an alarm module. The motion analysis module is electrically connected to the motion storage library and the compliance determination module. The compliance determination module is electrically connected to the alarm module. The storage unlocking module is used to unlock the food storage drawer that currently needs to take food. The motion analysis module is used to analyze the actions of the elderly in taking and storing food. The compliance determination module is used to analyze the compliance of the elderly's actions with standard actions according to the motion analysis results. The alarm module is used to alarm the caregiver when it is determined that the current action is abnormal.

[0029] The feedback correction module includes a real-time position adjustment module and a pick-and-place position setting module. The pick-and-place position setting module is electrically connected to the motion analysis module, and the real-time position adjustment module is electrically connected to the compliance determination module. The real-time position adjustment module is used to temporarily adjust the next food picking and storage position when the elderly's current motion does not conform to the motion during the test. The pick-and-place position setting module is used to preliminarily set the food picking and placement position according to the elderly's physical condition and the results of the initial data collection.

[0030] The system works as follows:

[0031] S1. Scan the faces of all elderly people and confirm their identity information. Place food storage drawers at different locations in the homes of the elderly care community, set multiple food placement locations around the food storage cabinets, and install camera units near the food placement locations.

[0032] S2. Unlock different food storage drawers one by one and ask the staff to place the stored food in different food placement positions in sequence, use a camera unit to shoot standard food taking and placing movements, and establish a standard human movement 3D model;

[0033] S3, notifying each elderly person to conduct a test on taking and putting food, photographing and analyzing the elderly person's actions of taking and putting food, establishing a three-dimensional human body action model of the elderly person, and setting the current positional relationship of the elderly person's food taking and putting according to the action conformity with the standard three-dimensional human body action model, and then conducting a test based on this positional relationship;

[0034] S4: During daily monitoring, a voice prompt is played at the specified time to remind the elderly to take and put food, and the pet is called to the feeding place at the same time. The elderly’s current action is evaluated for compliance with the test in S3. When it is determined that there is a small abnormality in the action, the position of the next food taking and putting is temporarily adjusted, and the compliance is judged again. When it is determined that there is a large abnormality in the action, the alarm module immediately sends an alarm to the caregiver;

[0035] In S2, the specific method for establishing the standard human motion three-dimensional model is as follows: establish a spatial three-dimensional coordinate system, calculate the position of each camera unit relative to the spatial three-dimensional coordinate system, obtain the projection matrix of the camera, and reconstruct the three-dimensional point cloud data of the food picking and placing action images of the staff taken at multiple different angles, mark the key points of the body joints at the shoulders, elbows, wrists, knees, coccyx, and ankles of the staff, import the marked joint coordinates into the modeling software, use the skeletal animation system to establish the joints, and establish the natural motion trajectory through interpolation to create a standard human motion three-dimensional model;

[0036] In S3, the specific method for obtaining the motion conformity with the standard human motion three-dimensional model is as follows:

[0037] S3-1. When the elderly person takes food and places it at the designated location, the standard human motion 3D model of the same taking and placing location is called, and the angles between the key points of the elderly person's body joints are recorded at intervals t, and the angles are subtracted from the angles between the key points of the body joints of the standard human motion 3D model to calculate the error of the angles between the two. , and the average angle error is obtained ,in is the number of angles between key points of body joints, is the number of times t is recorded during the behavior of taking and placing food;

[0038] S3-2. Select several points where the distance needs to be recorded from the key points of the body joints and record them as distance measurement points. The distance between the elderly's distance measurement points is recorded, subtracted from the distance between the distance measurement points of the standard human motion 3D model, and the error between the two distances is calculated. , and get the average distance error ,in is the number of distances between distance measurement points;

[0039] S3-3, action compliance is ,in is the action angle weight coefficient, is the distance weight coefficient of body parts;

[0040] In S3, the setting method of the current position relationship of the elderly's food taking and putting is: in the taking and putting test, it is set to take from the bottom storage drawer to the top putting position. This is the action with the largest distance span. After the elderly makes this action, the action compliance is calculated as , The higher the value, the closer the elderly person's physical condition is to that of a normal person. Set the vertical distance between where food is taken and put. The larger the ;

[0041] In S4, the three-dimensional model of the elderly's human body movements under the relationship between the picking up and storing positions set in the test in S3 is used as the benchmark to evaluate the conformity of the three-dimensional model of the elderly's human body movements during daily monitoring with the benchmark. The standard for determining whether there is a small abnormality in the movement is The standard for judging whether the action is significantly abnormal is When it is determined that there is a small abnormality in the action, the adjacent food picking position and storage position are changed, and monitoring is performed again to determine the conformity of the elderly's human body movement 3D model with the standard human body movement 3D model. , and re-judge the compliance;

[0042] In S4, when ,and When there is a continuous decrease, reduce the time interval between the next pick-up and delivery test for this elderly person To increase the frequency of monitoring the physical condition of the elderly, specifically: ,in To take and place the test times, is the weight coefficient of the trend of decreasing conformity, is the weight coefficient of the conformity itself, The more times the value is constant and decreases continuously, the The greater the number of consecutive decreases, the greater the probability of the elderly becoming physically disabled, and more frequent testing is needed. It will become smaller and smaller, so its weight will decrease accordingly, and the more obvious the trend of decreasing conformity is, the greater the weight of the changing trend will be.

[0043] Since each elderly person's physical health is different, if the same action is followed with the same degree of difficulty, some elderly people may not be able to complete the action, and it is impossible to judge whether there is any abnormality in the elderly's actions. Therefore, in the process of collecting data on the elderly, by analyzing the elderly's actions, the positional relationship of food taking and putting is set according to the conformity of the actions, and the subsequent detection time interval is adjusted in real time according to the elderly's actions to determine whether there is any abnormality, thereby improving the accuracy of detection.

[0044] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0045] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Smart home security protection system based on remote monitoring, characterized by: It includes an information collection module, an intelligent protection module, and a feedback correction module. The information collection module is used to determine the identity of the elderly and collect the movement information of the elderly. The intelligent protection module is used to analyze the movement behavior of the elderly and alarm for abnormal movement. The feedback correction module is used to set the position relationship of food taking and putting according to the compliance of the elderly's movement, and adjust the subsequent position relationship of taking and putting food in real time according to the elderly's movement. The system works as follows: S1. Scan the faces of all elderly people and confirm their identity information. Place food storage drawers at different locations in the homes of the elderly care community, set multiple food placement locations around the food storage cabinets, and install camera units near the food placement locations. S2. Unlock different food storage drawers one by one and ask the staff to place the stored food in different food placement positions in sequence, use a camera unit to shoot standard food taking and placing movements, and establish a standard human movement 3D model; S3, notifying each elderly person to conduct a test on taking and putting food, photographing and analyzing the elderly person's actions of taking and putting food, establishing a three-dimensional human body action model of the elderly person, and setting the current positional relationship of the elderly person's food taking and putting according to the action conformity with the standard three-dimensional human body action model, and then conducting a test based on this positional relationship; S4: During daily monitoring, a voice prompt is played at the specified time to remind the elderly to take and put food, and the pet is called to the feeding place at the same time. The elderly’s current action is evaluated for compliance with the test in S3. When it is determined that there is a small abnormality in the action, the position of the next food taking and putting is temporarily adjusted, and the compliance is judged again. When it is determined that there is a large abnormality in the action, the alarm module immediately sends an alarm to the caregiver; In S2, the specific method for establishing the standard human body motion three-dimensional model is: establishing a spatial three-dimensional coordinate system, calculating the position of each camera unit relative to the spatial three-dimensional coordinate system, obtaining the projection matrix of the camera, and reconstructing the three-dimensional point cloud data of the food picking and placing action images of the staff taken at multiple different angles, marking the key points of the body joints on the shoulders, elbows, wrists, knees, coccyx, and ankles of the staff, importing the marked joint coordinates into the modeling software, using the skeletal animation system to establish the joints, and establishing the natural motion trajectory through interpolation to create a standard human body motion three-dimensional model.

2. The smart home security protection system based on remote monitoring according to claim 1 is characterized in that: In S3, the specific method for obtaining the degree of motion conformity with the standard human motion three-dimensional model is: S3-1. When the elderly person takes food and places it at the designated location, the standard human motion 3D model of the same taking and placing location is called, and the angles between the key points of the elderly person's body joints are recorded at intervals t, and the angles are subtracted from the angles between the key points of the body joints of the standard human motion 3D model to calculate the error of the angles between the two. , and the average angle error is obtained ,in is the number of types of angles between key points of body joints, is the number of times t is recorded during the behavior of taking and placing food; S3-2. Select several points where the distance needs to be recorded from the key points of the body joints and record them as distance measurement points. The distance between the elderly's distance measurement points is recorded, subtracted from the distance between the distance measurement points of the standard human motion 3D model, and the error between the two distances is calculated. , and get the average distance error ,in is the number of distances between distance measurement points; S3-3, action compliance is ,in is the action angle weight coefficient, is the body part distance weight coefficient.

3. The smart home security protection system based on remote monitoring according to claim 2 is characterized in that: In S3, the setting method of the current position relationship of the elderly person's food taking and putting is: during the taking and putting test, it is set to take from the bottom storage drawer to the top putting position, which is the action with the largest distance span. After the elderly person makes this action, the action compliance is calculated as , The higher the value, the closer the elderly person's physical condition is to that of a normal person. Set the vertical distance between where food is taken and put. The larger the .

4. The smart home security protection system based on remote monitoring according to claim 3 is characterized in that: In S4, the three-dimensional model of the elderly's human body movements under the relationship between the picking and placing positions set in the test in S3 is used as a benchmark to evaluate the conformity of the three-dimensional model of the elderly's human body movements during daily monitoring with the benchmark, and the standard for determining whether the movement has a small amplitude abnormality is The standard for judging whether the action is significantly abnormal is When it is determined that there is a small abnormality in the action, the adjacent food picking position and storage position are changed, and monitoring is performed again to determine the conformity of the elderly's human body movement 3D model with the standard human body movement 3D model. , and re-judge the compliance.

5. The smart home security protection system based on remote monitoring according to claim 4 is characterized in that: In S4, when ,and When there is a continuous decrease, reduce the time interval between the next pick-up and delivery test for this elderly person To increase the frequency of monitoring the physical condition of the elderly, specifically: ,in To take and place the test times, is the weight coefficient of the trend of decreasing conformity, is the weight coefficient of the conformity itself, The more times the value is constant and decreases continuously, the The bigger.

6. The smart home security protection system based on remote monitoring according to claim 1, characterized in that: The information collection module includes a face recognition module, an identity tagging module, a camera unit, a voice reminder module, an action storage library, and a food storage cabinet. The face recognition module is electrically connected to the identity tagging module, and the camera unit is electrically connected to the action storage library. The face recognition module is used to identify the elderly in the home-based elderly care community. The identity tagging module is used to tag and confirm the identity of the elderly. The camera unit is used to shoot the place where food is taken and put. The voice reminder module is used to play voice prompts to the elderly who need to be monitored to take and put food, and call animals to the feeding place. The action storage library is used to store the actions of each elderly person taking and putting food, as well as the standard actions of taking and putting food. The food storage cabinet includes a plurality of food storage drawers for storing food; The intelligent protection module includes a storage unlocking module, a motion analysis module, a compliance determination module, and an alarm module. The motion analysis module is electrically connected to the motion storage library and the compliance determination module. The compliance determination module is electrically connected to the alarm module. The storage unlocking module is used to unlock the food storage drawer that currently needs to take food. The motion analysis module is used to analyze the actions of the elderly in taking and storing food. The compliance determination module is used to analyze the compliance of the elderly's actions with standard actions according to the motion analysis results. The alarm module is used to alarm the caregiver when it is determined that the current action is abnormal. The feedback correction module includes a real-time position adjustment module and a pick-up and placement position setting module. The pick-up and placement position setting module is electrically connected to the motion analysis module, and the real-time position adjustment module is electrically connected to the compliance determination module. The real-time position adjustment module is used to temporarily adjust the next food picking and storage position when the elderly's current motion is inconsistent with the motion during the test. The pick-up and placement position setting module is used to preliminarily set the food picking and placement position according to the elderly's physical condition and the results of initial data collection.

Images