A home old people remote monitoring alarm system with voice alarm and activity detection

Abstract

The application provides a home old person remote monitoring alarm system with voice alarm and activity detection, comprising an infrared monitoring module, a preprocessing module, a risk assessment module, a fall detection module, an alarm module and a mobile control terminal, whether the old person falls in the activity detection process is found by analyzing the factors of the old person falling, the fall risk factor of multiple fall factors and the movement change characteristics related to the fall are trained by a deep learning algorithm model, and the fall risk of the current target is comprehensively evaluated by analyzing the surrounding environment of the target and the movement characteristics of the target, which greatly improves the accuracy of judging the fall condition of the old person, effectively solves the problem of inaccurate detection results caused by not considering all aspects, thereby achieving the purpose of improving the accuracy of judging the fall condition of the old person, effectively solving the problem of low motion detection accuracy in the prior art, and thereby achieving the purpose of improving the target detection accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of health monitoring of the elderly, in particular to a home remote monitoring alarm system for the elderly with voice alarm and activity detection. BACKGROUND

[0002] With the intensification of the aging society problem and the miniaturization of family structure, the safety problem of the elderly has attracted widespread attention. The physiological decline of the elderly can lead to health problems such as physical disability and cognitive impairment, thereby reducing the mobility and self-care ability of the elderly. In addition, the elderly living alone or the elderly, when encountering an emergency, have difficulty in solving the problem themselves, and thus fall into a dangerous situation. In order to enable the elderly to be discovered and rescued in time after falling at home, a large amount of research is currently being conducted on the elderly fall detection and rescue system. The detection and evaluation of the fall state of the elderly are important parts of the effectiveness of the entire system. Since the health status of the elderly is different, the risk of complications after falling of the elderly with different physical conditions is different, and therefore, for the application scenario of the elderly fall rescue system, the fall state of the elderly needs to be classified and the severity of the fall under different fall categories needs to be classified. Therefore, a method for monitoring abnormal activities of the elderly falling is proposed, which can monitor the abnormal activities of the elderly falling and wrestling in real time, and when the abnormal activity of the elderly falling is detected, an alarm signal is sent in time, thereby protecting the health of the elderly.

[0003] The prior art one uses point cloud data of a 3D depth camera to model human features, detects the joint points of the human body based on the human body modeling, collects the depth information of the human body to calculate the height information of the human body, and performs fall detection.

[0004] The shortcomings of the prior art one are that the 3D depth camera is expensive and difficult to deploy in a general home environment, and the calculation amount of the point cloud data is huge, which is difficult to run offline in a general embedded device, and must be deployed in the cloud, causing the outflow of private data.

[0005] The prior art two uses a general RGB camera to collect human body RGB and depth thermal imaging data, uses a wearable device to collect acceleration sensor information of the joint points of the human body, analyzes the human body based on the joint points of the human body model to obtain the joints of the human body, and thus realizes the judgment of the fall.

[0006] The shortcomings of the prior art two are that the wearable device is inconvenient for the user's normal life, and it is difficult to wear for a long time, the user friendliness is poor, and the analysis and calculation amount of the thermal imaging data is large, which is difficult to deploy in the cloud, causing secondary leakage of user data.

[0007] The prior art has three disadvantages: the need to collect thermal imaging data and sound information, which is susceptible to environmental interference, and the difficulty in detecting the help request of the elderly when the elderly have a small voice and the background noise is large.

[0008] To this end, we propose a home elderly remote monitoring alarm system with voice alarm and activity detection. SUMMARY

[0009] The purpose of the present application is to provide a home elderly remote monitoring alarm system with voice alarm and activity detection to solve the problems raised in the background art.

[0010] To achieve the above purpose, the present application provides the following technical solution: a home elderly remote monitoring alarm system with voice alarm and activity detection, comprising an infrared monitoring module, a preprocessing module, a risk assessment module, a fall detection module, an alarm module and a mobile control terminal;

[0011] The infrared monitoring module is connected to the preprocessing module and is used to obtain thermal imaging data of the elderly activity scene; the preprocessing module is connected to the risk assessment module and the fall detection module, respectively, and is used to process the thermal imaging data of the elderly activity scene to obtain preprocessed thermal imaging data; the risk assessment module is used to assess the current fall risk of the elderly based on the preprocessed thermal imaging data, the fall detection module is used to judge whether the elderly have fallen based on the target human body of the preprocessed thermal imaging data, the alarm module is connected to the risk assessment module and the fall detection module, respectively, and the mobile control terminal is used to receive the state information of the elderly and issue a warning or a help request based on the state information of the elderly.

[0012] The preprocessing module includes a data acquisition unit, a data collection system, a data upload system and a data storage warehouse.

[0013] The risk assessment module includes a data analysis system, a result determination system and a threshold import system.

[0014] The fall detection module includes an abnormal alarm system, a data retrieval system, a central control terminal and a remote connection system.

[0015] Preferably, the data acquisition unit is connected to the data collection system and is used to collect and collect the data of the on-site elderly; the data acquisition unit includes a first data acquisition module, the first data acquisition module is connected to the data collection system and is used to obtain the thermal imaging data of the daily activities of the elderly; the data acquisition unit includes a second data acquisition module, the second data acquisition module is connected to the data collection system and is used to obtain the thermal imaging data of the daily activities of the elderly.

[0016] The data collection system is connected to the data upload system and is used to arrange the collected data of the elderly and transmit it to the data upload system.

[0017] The data uploading system is connected with the data storage warehouse, and is used for uploading the old person data in the data storage warehouse;

[0018] The data storage warehouse is connected with the data calling system, and is used for storing the old person data input by the data calling system;

[0019] The data storage warehouse is connected with the data analysis system, the data analysis system is connected with the result judging system, and the data analysis system performs remote monitoring through data analysis;

[0020] The data analysis system is connected with the threshold importing system and the abnormal alarm system respectively, and is used for comparing the data analysis with the database threshold and sending an alarm;

[0021] The data analysis system is connected with the central control terminal, and is used for controlling and processing the central data information;

[0022] The central control terminal is connected with the remote connection system, and is used for remotely monitoring and processing the data information analyzed by the data analysis system;

[0023] The data analysis system is connected with the mobile control terminal, and is used for sending the data information analyzed by the data analysis system to family members through the mobile control terminal.

[0024] Preferably, the fall detection module is used for detecting whether the old person falls during the activity, and the detection method is as follows:

[0025] Step A: receiving thermal imaging data, subtracting two adjacent frames of the thermal imaging data in sequence to obtain a frame difference graph corresponding to the two adjacent frames of the thermal imaging data, and regarding non-zero pixel points in the frame difference graph as suspected moving target pixel points;

[0026] Step B: performing intersection processing on the suspected moving target pixel points in the frame difference graph and a preset moving area, and judging that a moving target is detected if there is no intersection;

[0027] Step C: calculating the moving direction and the moving speed of the moving target in the thermal imaging data by using an optical flow algorithm;

[0028] Step D: determining a moving area based on the frame difference graph and the non-zero pixel points, labeling and connecting the moving area in the continuous frame difference by using a connected domain method, and obtaining the center of mass of the moving area;

[0029] Step E: tracking the center of mass of the moving area, obtaining the pixel distance between two centers of mass, and judging that the moving target falls if the pixel distance is greater than a preset threshold; the fall detection module is used for sending an alarm signal when the risk assessment module determines that the old person falls.

[0030] Preferably, the fall detection module further comprises a difference analysis algorithm based on continuous frames to obtain the frame difference graph, and the formula of the difference analysis algorithm based on continuous frames is as follows:

[0031] D(xc,yc)=|It(xc,yc)-I(ta,xc,yc)|;

[0032] Wherein, It(xc,yc) and I(ta,xc,yc) are pixel point values of the position in the previous two frames (assuming t is the current frame, ta is the previous frame), D(xc,yc) represents the pixel value of (xc,yc) position in the frame difference map, which is equal to the absolute value of the difference between the pixel values of the same position in the previous two frames.

[0033] Preferably, the risk assessment module comprises a fall risk factor acquisition module for acquiring fall-related risk factors, taking into account falling behavior and environmental factors for the fall of the elderly, wherein the fall risk factor acquisition module is based on the thermal imaging data of the infrared monitoring module to count the motion target features within 30 seconds before the fall of the elderly within a period of time, and acquire a set of fall-related risk factors.

[0034] Preferably, the data analysis system comprises a target detection module, a target tracking module and a target motion statistics module, wherein the target detection module extracts the feature region of the preprocessed thermal imaging data through a target detection algorithm, the target tracking module is used to track according to the feature region, and the target motion statistics module is used to analyze the motion change characteristics of the feature region within a period of time; the target tracking module tracks the feature region obtained by the target detection module, extracts the motion characteristics of the target region during tracking, and the motion characteristics include moving speed, motion distance and motion area. The target motion statistics module statistically analyzes the motion characteristics of the target region within a certain time, analyzes the moving speed characteristic score, the motion distance characteristic score and the motion area characteristic score, and then comprehensively scores the comprehensive motion change characteristics of the target region. The comprehensive score formula is as follows:

[0035] S=Σ(Si×Wi);

[0036] Wherein: S is the comprehensive score, which represents the overall evaluation of the comprehensive motion change characteristics of the target region;

[0037] Si is the score of each feature, which represents the performance of the target region in a certain motion change characteristic;

[0038] i is the number of characteristics, which represents the total number of characteristics participating in the comprehensive score;

[0039] Wi is the weight of each feature, which represents the importance of the feature in the comprehensive score.

[0040] Preferably, the data analysis system further comprises a fall risk factor processing module, which combines the fall risk factors with the motion change features obtained by the target motion statistics module, obtains comprehensive information of motion change features and different fall risk factors, calculates the fall risk score of the elderly based on the comprehensive information, and the fall risk score formula is as follows:

[0041] A=aθ+bV+cL+dArea;

[0042] Wherein: A is the fall risk score, which is a comprehensive evaluation result for quantifying the fall risk;

[0043] θ is the posture feature score of the elderly, reflecting the posture stability, coordination and other factors of the elderly at a specific time point;

[0044] V is the moving speed feature score;

[0045] L is the motion distance feature score;

[0046] Area is the motion area feature score.

[0047] Preferably, the data acquisition unit simultaneously acquires the posture, behavior and multiple continuous thermal imaging data of the elderly activity, the posture feature score includes the scores corresponding to different fall risk factors, and the posture feature score corresponds to the factor characteristics of the corresponding fall risk factors obtained by the fall risk factor acquisition module. The factor characteristics include arm posture characteristics, leg posture characteristics, body inclination characteristics and step size characteristics. By combining the factor characteristics and comparing and calculating, the posture feature score related to falls is obtained, and the formula of the posture feature score related to falls is as follows:

[0048] θ_total=θ1×k1+θ2×k2+θ3×k3+θ4×k4;

[0049] Wherein: θ1 is the arm posture feature score, reflecting the influence of arm posture or motion state on fall risk;

[0050] θ2 is the leg posture feature score, reflecting the relationship between leg posture or action and fall risk;

[0051] θ3 is the body inclination feature score, evaluating the effect of body inclination angle or posture change on fall risk;

[0052] θ4 is the step feature score, involving factors such as step stability and step size;

[0053] k1, k2, k3, k4 are weight factors corresponding to the characteristics, which determine the relative importance of each feature in the overall score.

[0054] Preferably, the alarm module comprises a voice alarm system connected with the alarm module, the voice alarm system sends a voice alarm signal according to the fall risk score level and the motion change feature, and the voice alarm system comprises:

[0055] A voice playing module is configured to perform sound feature matching according to the fall risk score level and the motion change feature to obtain the voice alarm signal.

[0056] A voice receiving module is configured to collect voice information and transmit the voice information to a voice server.

[0057] A voice judging module is configured to collect environmental noise and sound intensity and judge whether the current environment is suitable for voice alarm.

[0058] A voice optimizing module is configured to optimize the obtained voice information.

[0059] A voice encoding module is configured to compress and encode the obtained voice information.

[0060] A voice decoding module is configured to decode and restore the voice information.

[0061] A voice synthesizing module is configured to synthesize voice according to the obtained voice alarm signal and user voice data.

[0062] Compared with the prior art, the present application has the following advantages:

[0063] 1. The present application can detect whether the old person falls during the activity by analyzing the factors of the old person falling, and can comprehensively evaluate the fall risk of the target by analyzing the surrounding environment of the target and the motion feature of the target, thereby greatly improving the accuracy of judging the falling condition of the old person, effectively solving the problem of inaccurate detection results caused by not considering all aspects, and achieving the purpose of improving the accuracy of judging the falling condition of the old person.

[0064] 2. The present application trains a model through a plurality of fall risk factors of the fall factors and the motion change features related to the fall through a deep learning algorithm, so that the model is more adaptive in predicting the fall of the old person, effectively solves the problem of deviation in model prediction caused by only using the motion change feature in the prior art, and achieves the purpose of increasing the output accuracy of the model.

[0065] 3. The present application outputs a comprehensive score and a corresponding score of the fall risk factor through the model, and then compares it with the set threshold value to determine the comprehensive risk score of the old person, thereby improving the accuracy of the output result, and the threshold value of the fall risk factor and the comprehensive motion change feature is set by the user import system, which divides the comprehensive risk score into several levels, and triggers the voice alarm system to alarm the target when the score level exceeds the set threshold value.

[0066] 4. The application is based on the difference analysis algorithm of continuous frames, including motion detection and optical flow method, by comprehensively applying motion detection and optical flow method, the accuracy of motion detection is improved, effectively solve the problem of low motion detection accuracy in the prior art, so as to achieve the purpose of improving the target detection accuracy. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments of the application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the protection scope of the application.

[0068] The embodiment provides a technical scheme: a home old person remote monitoring alarm system with voice alarm and activity detection, comprising an infrared monitoring module, a preprocessing module, a risk assessment module, a fall detection module, an alarm module and a mobile control terminal.

[0069] The infrared monitoring module is connected with the preprocessing module, and is used to acquire the thermal imaging data of the old person activity scene. The infrared thermal imaging technology can accurately capture the position of the heat source and judge the thermal properties of the object. Compared with the traditional manual inspection method, the infrared detection can greatly improve the detection efficiency and accuracy, and avoid missed detection and false detection. The preprocessing module is connected with the risk assessment module and the fall detection module, respectively, and is used to process the thermal imaging data of the old person activity scene to obtain preprocessed thermal imaging data. The risk assessment module is used to assess the current fall risk of the old person based on the preprocessed thermal imaging data. The fall detection module is used to judge whether the old person falls based on the target human body of the preprocessed thermal imaging data. The alarm module is connected with the risk assessment module and the fall detection module, respectively. The mobile control terminal is used to receive the state information of the old person, and send an early warning or a help based on the state information of the old person.

[0070] The preprocessing module comprises a data acquisition unit, a data collection system, a data uploading system and a data storage warehouse.

[0071] The risk assessment module comprises a data analysis system, a result determination system and a threshold import system.

[0072] The fall detection module comprises an abnormal alarm system, a data retrieval system, a central control terminal and a remote connection system.

[0073] The data acquisition unit is connected with the data collection system and is used for collecting and gathering the data of the old people in the field; the data acquisition unit comprises a first data acquisition module, which is connected with the data collection system and is used for acquiring the thermal imaging data of the daily activities of the old people; the data acquisition unit comprises a second data acquisition module, which is connected with the data collection system and is used for acquiring the thermal imaging data of the daily activities of the old people;

[0074] The data collection system is connected with the data uploading system and is used for transmitting the collected data of the old people to the data uploading system after the data is sorted;

[0075] The data uploading system is connected with the data storage warehouse and is used for uploading the data of the old people in the data storage warehouse;

[0076] The data storage warehouse is connected with the data calling system and is used for storing the data of the old people input by the data calling system;

[0077] The data storage warehouse is connected with the data analysis system, the data analysis system is connected with the result determining system, and the data analysis system performs remote monitoring through data analysis;

[0078] The data analysis system is connected with the threshold importing system and the abnormal alarm system respectively and is used for comparing the data analysis with the database threshold and sending an alarm;

[0079] The data analysis system is connected with the central control terminal and is used for controlling and processing the central data information;

[0080] The central control terminal is connected with the remote connection system and is used for remotely monitoring and processing the data information analyzed by the data analysis system;

[0081] The data analysis system is connected with the mobile control terminal and is used for sending the data information analyzed by the data analysis system to the family members through the mobile control terminal.

[0082] The fall detection module is used for detecting whether the old people fall during the activities, and the detection method is as follows:

[0083] Step A: receiving the thermal imaging data, subtracting the continuous adjacent two frames of thermal imaging data in the thermal imaging data to obtain the frame difference graph corresponding to the adjacent two frames of thermal imaging data, and the non-zero pixel points in the frame difference graph are the suspected moving target pixel points;

[0084] Step B: performing intersection processing on the suspected moving target pixel points in the frame difference graph and the preset moving area, and if there is no intersection, it is judged that the moving target is detected;

[0085] Step C: calculating the moving direction and moving speed of the moving target in the thermal imaging data by using the optical flow algorithm;

[0086] Step D: determining the motion region based on the frame difference map and non-zero pixel points, connecting the motion region in the continuous frame difference through the connected domain method to obtain the centroid of the motion region;

[0087] Step E: tracking the centroid of the motion region to obtain the pixel distance between the two centroids, and if the pixel distance is greater than a preset threshold, determining that the motion target falls; the fall detection module is used to send an alarm signal when the risk assessment module determines that the old person falls.

[0088] The fall detection module further comprises a continuous frame difference analysis algorithm for obtaining the frame difference map, and the formula of the continuous frame difference analysis algorithm is:

[0089] D(xc,yc)=|It(xc,yc)-I(ta,xc,yc)|;

[0090] Wherein, It(xc,yc) and I(ta,xc,yc) are pixel point values of the position in the previous and subsequent two frames (assuming t is the current frame and ta is the previous frame), and D(xc,yc) represents the pixel value of the position (xc,yc) in the frame difference map, which is equal to the absolute value of the difference between the pixel values of the same position in the previous and subsequent two frames.

[0091] The risk assessment module comprises a fall risk factor acquisition module, which is used to acquire the risk factors related to falling, and for the old people falling, the falling behavior and environmental factors are considered, wherein the fall risk factor acquisition module is based on the thermal imaging data of the infrared monitoring module to count the motion target features within 30 seconds before falling of the old people within a period of time, and acquire the risk factor set related to falling.

[0092] The data analysis system comprises a target detection module, a target tracking module and a target motion statistical module, wherein the target detection module extracts the feature region of the preprocessed thermal imaging data through a target detection algorithm, the target tracking module is used to track according to the feature region, and the target motion statistical module is used to analyze the motion change characteristics of the feature region within a period of time; the target tracking module tracks the feature region obtained by the target detection module, extracts the motion characteristics of the target region in the tracking process, and the motion characteristics include moving speed, motion distance and motion area, the target motion statistical module statistically analyzes the motion characteristics of the target region within a certain time, analyzes the moving speed characteristic score, the motion distance characteristic score and the motion area characteristic score, and then comprehensively scores the comprehensive motion change characteristics of the target region, and the comprehensive score formula is as follows:

[0093] S=Σ(Si×Wi);

[0094] Wherein: S is the comprehensive score, indicating the overall evaluation of the comprehensive motion change characteristics of the target region;

[0095] Si is the score of each feature, representing the performance of the target area on a certain specific motion change feature;

[0096] i is the number of features, indicating the total number of features participating in the comprehensive score;

[0097] Wi is the weight of each feature, indicating the importance of the feature in the comprehensive score.

[0098] The data analysis system further comprises a fall risk factor processing module, which combines the fall risk factors with the motion change features obtained by the target motion statistics module, obtains comprehensive information of motion change features and different fall risk factors, and calculates an old person fall risk score based on the comprehensive information, the fall risk score formula being as follows:

[0099] A=aθ+bV+cL+dArea;

[0100] Wherein: A is a fall risk score, which is a comprehensive evaluation result for quantifying the fall risk;

[0101] θ is an old person posture feature score, reflecting the posture stability, coordination and other factors of the old person at a specific time point;

[0102] V is a moving speed feature score;

[0103] L is a motion distance feature score;

[0104] Area is a motion area feature score.

[0105] The data acquisition unit simultaneously collects the posture, behavior and multiple continuous thermal imaging data of the old person activity, the posture feature score includes the scores corresponding to different fall risk factors, and the posture feature score corresponds to the factor characteristics of the corresponding fall risk factors obtained by the fall risk factor acquisition module, the factor characteristics include arm posture characteristics, leg posture characteristics, body inclination characteristics and step size characteristics, combined with the factor characteristics, the posture feature score related to falls is obtained by comparison and comprehensive calculation, the posture feature score related to falls is as follows:

[0106] θ_total=θ1×k1+θ2×k2+θ3×k3+θ4×k4;

[0107] Wherein: θ1 is an arm posture feature score, reflecting the influence of arm posture or motion state on fall risk;

[0108] θ2 is a leg posture feature score, reflecting the relationship between leg posture or action and fall risk;

[0109] θ3 is a body tilt feature score, evaluating the effect of body tilt angle or posture change on the risk of falling;

[0110] θ4 is a step feature score, involving factors such as step stability, step size, etc.

[0111] k1, k2, k3, k4 are weight factors corresponding to the features, which determine the relative importance of each feature in the overall score.

[0112] The alarm module includes a voice alarm system, the voice alarm system is connected with the alarm module, the voice alarm system sends a voice alarm signal according to the fall risk score level and the motion change feature, and the voice alarm system includes:

[0113] A voice playing module is configured to match sound features according to the fall risk score level and the motion change feature to obtain the voice alarm signal.

[0114] A voice receiving module is configured to collect voice information and transmit the voice information to a voice server.

[0115] A voice judging module is configured to collect environmental noise and sound intensity and determine whether the current environment is suitable for voice alarm.

[0116] A voice optimizing module is configured to optimize the obtained voice information.

[0117] A voice encoding module is configured to compress and encode the obtained voice information.

[0118] A voice decoding module is configured to decode and restore the voice information.

[0119] A voice synthesizing module is configured to synthesize voice according to the obtained voice alarm signal and in combination with user voice data.

[0120] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and variations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A home-based remote monitoring alarm system for the elderly with voice alarm and activity detection, characterized in that: The system comprises an infrared monitoring module, a preprocessing module, a risk assessment module, a fall detection module, an alarm module and a mobile control terminal. The infrared monitoring module is connected with the preprocessing module to acquire thermal imaging data of the activity scene of the old person. The preprocessing module is connected with the risk assessment module and the fall detection module to process the thermal imaging data of the activity scene of the old person and obtain preprocessed thermal imaging data; the risk assessment module assesses the current fall risk of the old person based on the preprocessed thermal imaging data, and the fall detection module judges whether the old person falls based on the target human body of the preprocessed thermal imaging data; the alarm module is connected with the risk assessment module and the fall detection module, and the mobile control terminal sends an early warning or a help based on the received state information of the old person. The preprocessing module comprises a data acquisition unit, a data collection system, a data uploading system and a data storage warehouse. The risk assessment module comprises a data analysis system, a result determination system and a threshold import system. The fall detection module comprises an abnormal alarm system, a data retrieval system, a central control terminal and a remote connection system. The risk assessment module comprises a fall risk factor acquisition module which is based on the thermal imaging data to count the motion target features of the old person within 30 seconds before falling. The data analysis system comprises a target detection module, a target tracking module and a target motion statistics module; the target detection module extracts the feature region of the preprocessed thermal imaging data; the target tracking module tracks the feature region obtained by the target detection module and extracts the motion features of the target region, wherein the motion features include the moving speed, the motion distance and the motion area; the target motion statistics module counts the motion features of the target region within a certain time, analyzes the moving speed feature score, the motion distance feature score and the motion area feature score, and comprehensively scores the comprehensive motion change features of the target region, wherein the comprehensive score formula is as follows: S=Σ(Si×Wi); S is the comprehensive score; Si is the score of each feature; i is the number of features; Wi is the weight of each feature. The data analysis system further comprises a fall risk factor processing module which combines the fall risk factors with the motion change features obtained by the target motion statistics module to obtain the comprehensive information of the motion change features and different fall risk factors, calculates the fall risk score of the old person based on the comprehensive information, and the fall risk score formula is as follows: A=aθ+bV+cL+dArea; A is the fall risk score; θ is the posture feature score of the old person; V is the moving speed feature score; L is the motion distance feature score; and Area is the motion area feature score.

2. The home based remote monitoring alarm system for old people with voice alarm and activity detection as claimed in claim 1 wherein: The data acquisition unit is connected with the data collection system to collect and collect the data of the old person on site; the data acquisition unit comprises a first data acquisition module connected with the data collection system to acquire the thermal imaging data of the daily activities of the old person; the data acquisition unit comprises a second data acquisition module connected with the data collection system to acquire the thermal imaging data of the daily activities of the old person; The data collection system is connected with the data uploading system to transmit the collected old person data to the data uploading system after sorting; The data uploading system is connected with the data storage warehouse to upload the old person data of the data storage warehouse; The data acquisition unit is connected with the data collection system to collect and collect the data of the old person on site; the data acquisition unit comprises a first data acquisition module connected with the data collection system to acquire the thermal imaging data of the daily activities of the old person; the data acquisition unit comprises a second data acquisition module connected with the data collection system to acquire the thermal imaging data of the daily activities of the old person; The data storage warehouse is connected with the data calling system, and is used for storing the old person data input by the data calling system; The data storage warehouse is connected with the data analysis system, the data analysis system is connected with the result judging system, and the data analysis system performs remote monitoring through data analysis; The data analysis system is connected with the threshold import system and the abnormal alarm system, and is used for comparing the data analysis with the database threshold and sending an alarm; The data analysis system is connected with the central control terminal, and is used for controlling and processing the central data information; The central control terminal is connected with the remote connection system, and is used for remotely monitoring and processing the data information analyzed by the data analysis system; The data analysis system is connected with the mobile control terminal, and is used for sending the data information analyzed by the data analysis system to the family members through the mobile control terminal.

3. The home based remote monitoring alarm system for old people with voice alarm and activity detection as claimed in claim 1 wherein: The fall detection module is used for detecting whether the old person falls during the activity, and the detection method is as follows: Step A: receiving the thermal imaging data, subtracting the two adjacent frames of the thermal imaging data in sequence to obtain the frame difference graph corresponding to the two adjacent frames of the thermal imaging data, and the non-zero pixel points in the frame difference graph are the suspected moving target pixel points; Step B: performing intersection processing on the suspected moving target pixel points in the frame difference graph and the preset moving area, and if there is no intersection, it is judged that the moving target is detected; Step C: calculating the moving direction and speed of the moving target in the thermal imaging data by using the optical flow algorithm; Step D: determining the moving area based on the frame difference graph and the non-zero pixel points, labeling and connecting the moving area in the continuous frame difference by using the connected domain method to obtain the centroid of the moving area; Step E: tracking the centroid of the moving area to obtain the pixel distance between the two centroids, and if the pixel distance is greater than a preset threshold, it is judged that the moving target falls; the fall detection module is used for detecting and sending an alarm signal when the old person falls according to the risk assessment module.

4. The home based remote monitoring alarm system for old people with voice alarm and activity detection as claimed in claim 3 wherein: The fall detection module further comprises a difference analysis algorithm based on continuous frames to obtain the frame difference graph, and the formula of the difference analysis algorithm based on continuous frames is as follows: D(xc,yc)=|It(xc,yc)-Ita (xc,yc)|; Wherein, It(xc,yc) and Ita (xc,yc) are pixel point values in the same position in the two continuous frames, t is the current frame, ta is the previous frame, and D(xc,yc) represents the pixel value of (xc,yc) position in the frame difference graph, which is equal to the absolute value of the difference between the pixel values of the same position in the two frames.

5. The home based remote monitoring alarm system for old people with voice alarm and activity detection as claimed in claim 1 wherein: The data acquisition unit simultaneously collects the posture, behavior and multiple continuous thermal imaging data of the old person, the posture feature score includes scores corresponding to different fall risk factors, and the posture feature score corresponds to the factor feature of the corresponding fall risk factor obtained by the fall risk factor acquisition module, the factor feature includes arm posture feature, leg posture feature, body tilt feature and step size feature, the posture feature score related to the fall is obtained by comparison and comprehensive calculation combined with the factor feature, and the posture feature score related to the fall is as follows: θ_total=θ1×k1+θ2×k2+θ3×k3+θ4×k4; Wherein: θ1 is the arm posture feature score, reflecting the influence of arm posture or motion state on the risk of falling; θ2 is the leg posture feature score, reflecting the relationship between leg posture or action and the risk of falling; θ3 is the body tilt feature score, evaluating the effect of body tilt angle or posture change on the risk of falling; θ4 is the footstep feature score, involving factors such as step stability and step size; k1, k2, k3, k4 are the weight factors of the corresponding features, which determine the relative importance of each feature in the overall score.

6. The home based remote monitoring alarm system for old people with voice alarm and activity detection as claimed in claim 1 wherein: The alarm module includes a voice alarm system, the voice alarm system is connected with the alarm module, the voice alarm system sends voice alarm signals according to the risk score level and the motion change characteristics, and the voice alarm system includes: A voice playing module is used to match the sound characteristics according to the risk score level and the motion change characteristics to obtain the voice alarm signal; A voice receiving module is used to collect voice information and transmit the voice information to a voice server; A voice judgment module is used to collect environmental noise and sound intensity to determine whether the current environment is suitable for voice alarm; A voice optimization module is used to optimize the obtained voice information; A voice encoding module is used to compress and encode the obtained voice information; A voice decoding module is used to decode and restore the voice information; A voice synthesis module is used to synthesize voice according to the obtained voice alarm signal and combined with user voice data.