Self-service normalized posture monitoring system

Abstract

The invention relates to the technical field of posture evaluation, and discloses a self-service normalized posture monitoring system, which comprises a posture data acquisition self-service terminal, a health data management and analysis cloud platform and an information push and management client, the posture data acquisition self-service terminal is used for collecting posture data of a tested person, and the posture data comprises but is not limited to a human body front and whole body RGB picture, a human body side and whole body RGB picture and a back RGB-D depth image in a human body forward bending state; according to the method, operation of professional medical staff is not needed, a tested person can complete measurement in a self-service mode, the functions of evaluating scoliosis, high-low shoulders, X / O-shaped legs, cervical vertebra anteversion, cervical vertebra heeling, pelvic anteversion, pelvic heeling and the like are achieved in a one-stop mode, the posture screening cost is greatly reduced, and the screening frequency is improved; the system comprises terminal equipment, a cloud platform and a user client, realizes closed-loop data acquisition, storage, management, analysis and push, and has strong supervision and urging effects in posture health prevention and control.

Description

Technical Field

[0001] The present invention relates to the technical field of body posture assessment, and in particular to a self-service normalized body posture monitoring system. Background Art

[0002] In recent years, my country has paid more attention to the health of children and adolescents, especially focusing on common posture diseases such as scoliosis, uneven shoulders, and X / O legs.

[0003] The current posture assessment process requires professional posture testers to use traditional equipment such as measuring rulers and angle measuring instruments to conduct the assessment. The testing process is complicated, labor costs are high, and efficiency is low. It is very necessary to develop a system that can achieve high-precision, self-service normalized posture monitoring, so as to achieve high-frequency posture screening, improve screening efficiency and accuracy, and reduce screening costs.

[0004] In the patent with the authorization announcement number CN202310785060.8, a posture assessment method based on human skeleton point and action recognition is disclosed, which is evaluated through the following steps: S1, data collection: obtain basic information of the user through the intelligent strength fitness equipment, collect photos of the front, side and back of the user's whole body through the large-screen camera, and the user performs corresponding actions according to the standard physical test video prompts; S2, data preprocessing: denoise, scale, rotate and other operations are performed on the collected image or video data to improve the accuracy and efficiency of subsequent processing. Action recognition and posture assessment are realized through computer vision and deep learning technology, which abandons the traditional on-site coach observation and guidance methods, improves the evaluation efficiency, and can also collect images or video data of users in real time during exercise, perform action recognition and posture assessment in real time, and perform posture assessment according to the specific situation of the user, which is helpful for more accurate assessment of the user's posture. However, the above posture assessment method is still subject to the influence of body clothing, and no further collection actions and evaluation methods are designed for posture types such as scoliosis. At the same time, the equipment does not retain the measurement data of each measurement, and it is impossible to perform normalized posture data monitoring and analysis.

[0005] In the patent with the authorization announcement number CN201920018132.5, a human posture assessor is disclosed, which is provided with a bracket set on the ground; an optical depth camera fixed to the top of the bracket by a horizontal fixed frame, and an adjustment knob is provided at the connection between the horizontal fixed frame and the bracket; a computer connected to the optical depth camera signal; a large-screen display connected to the computer signal; and a round table for human standing arranged in front of the bracket; wherein the evaluation angle of the optical depth camera is adjusted by the adjustment knob. According to the utility model, not only can the posture and joint activity of the human body be detected, but also problem analysis, rehabilitation suggestions and corresponding rehabilitation actions can be further provided for certain health defects detected by the detection object, and a human posture assessor with higher accuracy that meets the specific customer posture analysis is provided. The device does not have a cloud platform, and cannot realize data monitoring and analysis and early warning functions, and the function is relatively single. For this reason, a self-service normalized posture monitoring system is proposed. Summary of the invention

[0006] The purpose of the present invention is to provide a self-service normalized body posture monitoring system to solve the problems raised in the above background technology.

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a self-service normalized posture monitoring system, comprising a posture data collection self-service terminal, a health data management and analysis cloud platform, and an information push and management client;

[0008] The posture data collection self-service terminal is used to collect the posture data of the subject, and the posture data includes but is not limited to: a full-body RGB photo of the front of the human body, a full-body RGB photo of the side of the human body, and an RGB-D depth image of the back of the human body in a forward bending state;

[0009] The health data management and analysis cloud platform is used for the storage, management and analysis of health data, and for evaluating and predicting the body condition and trend of the subjects through big data analysis;

[0010] The information push and management client is used to present the body data and related content of the subject, and can push the detected results together with future risk warning information to the end user. The user can also maintain and manage the information through the client.

[0011] Preferably, the above-mentioned body data collection self-service terminal is connected to the health data management and analysis cloud platform, and the health data management and analysis cloud platform is connected to the health data management and analysis cloud platform.

[0012] Preferably, the above-mentioned health data management and analysis cloud platform analyzes and evaluates the body posture of the subject based on a human posture assessment algorithm based on human key point detection technology, a scoliosis assessment algorithm based on RGB-D depth images of the back in the human flexion state, and an obesity assessment algorithm based on human three-dimensional reconstruction technology.

[0013] Preferably, the human body posture assessment algorithm of the above-mentioned human body key point detection technology evaluates the two-dimensional posture information of various tissue parts of the human body in a relaxed state through a frontal image of the human body, and assesses posture problems such as uneven shoulders, X / O legs, cervical anteversion, cervical lateral tilt, pelvic anteversion, and pelvic lateral tilt.

[0014] Preferably, the scoliosis assessment algorithm based on the RGB-D depth image of the back in the forward flexed state uses the RGB-D depth image of the back in the forward flexed state to analyze the characteristics of the height distribution of muscles on both sides of the back of the entire human body, and then generates a scoliosis assessment result.

[0015] Preferably, the obesity assessment algorithm of the above-mentioned human body three-dimensional reconstruction technology utilizes the acquisition of human body front color images and side color images to perform three-dimensional reconstruction of the human body, and calculates data such as waist-to-hip ratio to assess the degree of human obesity.

[0016] Preferably, the above-mentioned posture data collection self-service terminal includes a display module, an identity authentication module, a voice prompt module, an RGB camera module, a depth camera module, a collection time adjustment module and an output module;

[0017] The display module is used to collect action diagrams of human body images;

[0018] The identity authentication module is used to authenticate the identity of the person being tested, and the authentication methods include but are not limited to card swiping authentication, face recognition authentication, and account password authentication;

[0019] The voice prompt module is used to remind the test subject to start and end, prepare for corresponding actions, count down, and give voice prompts when completed;

[0020] The RGB camera module is used to capture a frontal image of a person standing relaxedly with both hands at an angle of about 30 degrees to the body and a side image of a person standing relaxedly with both hands pressed against the trouser seams;

[0021] The depth camera module is used to collect depth images of a person bending forward, with the upper body bent at 90 degrees to the body, and the hands clasped together and pointing to the center of the two feet;

[0022] The collection time adjustment module is used to adjust the collection countdown interval according to the preparation actions of different groups of people;

[0023] The output module is used to automatically upload the information of the subject's ID, the front image of the human body, the side image of the human body, and the depth map of the back of the human body in the forward bending state to the health data management and analysis cloud platform.

[0024] Preferably, the above-mentioned display module includes but is not limited to a liquid crystal display screen, a LED display screen, an OLED display screen and a serial port display screen.

[0025] Preferably, the above-mentioned depth camera module includes but is not limited to a monocular structured light depth camera, a binocular structured light depth camera, and a structured light camera.

[0026] Compared with the prior art, the present invention adopts the above technical solution and has the following technical effects:

[0027] 1. The present invention does not require the operation of professional medical personnel. The subject can complete the measurement by himself, and realize the one-stop evaluation of scoliosis, high and low shoulders, X / O-shaped legs, cervical anteversion, cervical lateral tilt, pelvic anteversion, pelvic lateral tilt and other functions, which greatly reduces the cost of posture screening, increases the screening frequency, and provides a feasible and effective means for posture.

[0028] 2. The posture data collection self-service terminal of the present invention can use the human body key point detection technology and deep image processing technology to design limb movements for scoliosis assessment, and can complete posture assessment with high accuracy, speed and convenience.

[0029] 3. The present invention includes terminal equipment, a cloud platform and a user client, realizing a closed loop of data collection, storage, management, analysis and push, and has a strong supervisory and urging role in physical health prevention and control, providing a complete solution for physical health prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 It is a schematic diagram of the system of the present invention;

[0032] Figure 2 It is a schematic diagram of the structure of the acquisition device of the present invention;

[0033] Figure 3 The figure is a schematic diagram of the use process of the acquisition device of the present invention.

[0034] Explanation of reference numerals: 1. Depth camera; 2. Display screen; 3. RGB camera; 4. Mirror body; 5. Base. DETAILED DESCRIPTION

[0035] 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.

[0036] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which this application can be implemented. Therefore, they have no substantive technical significance. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical content disclosed in this application without affecting the effects and purposes that can be achieved by this application.

[0037] Example

[0038] See also Figure 1-3 ,The present invention provides a technical solution: a self-service normalized posture monitoring system, including a posture data collection self-service terminal, a health data management and analysis cloud platform, and an information push and management client;

[0039] A posture data collection self-service terminal is used to collect the posture data of the subject, and the posture data includes but is not limited to: a full-body RGB photo of the front of the human body, a full-body RGB photo of the side of the human body, and an RGB-D depth image of the back of the human body in a forward bending state;

[0040] Health data management and analysis cloud platform, used for storage, management and analysis of health data, and evaluation and prediction of the body status and trend of the subjects through big data analysis; health data management and analysis cloud platform can also manage the self-service terminals for body data collection, including but not limited to equipment status monitoring, remote update, information sending, etc.;

[0041] The information push and management client is used to present the body data and related content of the subject. It can push the test results and future risk warning information to the end user. The user can also maintain and manage the information through the client.

[0042] The posture data collection self-service terminal is connected to the health data management and analysis cloud platform, and the health data management and analysis cloud platform is connected to the health data management and analysis cloud platform.

[0043] The health data management and analysis cloud platform analyzes and evaluates the body posture of the subject through the human body posture assessment algorithm based on human key point detection technology, the scoliosis assessment algorithm based on the RGB-D depth image of the back in the forward bending state, and the obesity assessment algorithm based on human body three-dimensional reconstruction technology.

[0044] The human body posture assessment algorithm based on the human body key point detection technology evaluates the two-dimensional posture information of various tissue parts of the human body in a relaxed state through a frontal image of the human body, and assesses posture problems such as uneven shoulders, X / O legs, cervical anteversion, cervical lateral tilt, pelvic anteversion, and pelvic lateral tilt.

[0045] The scoliosis assessment algorithm based on the RGB-D depth image of the back in the forward bending state uses the RGB-D depth image of the back in the forward bending state to analyze the characteristics of the high and low distribution of muscles on both sides of the back of the entire human body, and then generates the assessment result of scoliosis.

[0046] The obesity assessment algorithm of the human body 3D reconstruction technology uses the collected frontal color images and side color images of the human body to perform 3D reconstruction of the human body, and calculates data such as waist-to-hip ratio to assess the degree of human obesity.

[0047] The body data collection self-service terminal includes a display module, an identity authentication module, a voice prompt module, an RGB camera module, a depth camera module, a collection time adjustment module and an output module;

[0048] A display module, used for collecting action diagrams of human body images;

[0049] Identity authentication module, used to authenticate the identity of the person being tested. Authentication methods include but are not limited to card swiping authentication, face recognition authentication, and account password authentication;

[0050] Voice prompt module, used to remind the testee to start and end, prepare for corresponding actions, count down, and give voice prompts when completed;

[0051] RGB camera module, used to collect frontal images of a person standing relaxedly with both hands at an angle of about 30 degrees to the body and side images of a person standing relaxedly with both hands pressed against the trouser seams;

[0052] Depth camera module, used to collect depth images of a person bending forward, with the upper body bent at 90 degrees to the body, and the hands clasped together pointing to the center of the two feet;

[0053] The collection time adjustment module is used to adjust the collection countdown interval according to the preparation actions of different groups of people;

[0054] The output module is used to automatically upload the information of the subject's ID, human front image, human side image, and depth map of the back in the forward bending state to the health data management and analysis cloud platform.

[0055] Display modules include but are not limited to LCD screens, LED screens, OLED screens, and serial port screens.

[0056] Depth camera modules include but are not limited to monocular structured light depth cameras, binocular structured light depth cameras, and structured light cameras.

[0057] The posture data collection self-service terminal is a collection device, with a mirror body 4 installed on the base 5, a depth camera 1 installed on the mirror body 4, a display screen 2 installed on the mirror body 4 below the depth camera 1, and an RGB camera 3 installed on the mirror body 4 below the display screen 2. The depth camera is installed on the top of the device, tilted and fixed at a 45° angle downward, with an adjustable angle, and is used to collect images of the lower back of the human body in forward bending movements; the display screen is used for interaction with the subject and displaying functions such as pictures; the RGB camera is used to collect full-body photos of the human body from the front and side; the base and the body are connected through screw holes, and the height of the device is adjustable; the mirror body makes it convenient for the subject to observe his or her body posture;

[0058] Function of collecting front human body pictures. The posture data collection self-service terminal uses the front RGB camera 3 to collect full-body RGB photos of the human body. The human body stands in a relaxed state, with arms slightly spread out at a 30° angle to the body, and the standing position is 1.2-1.5m away from the front surface of the device. The person to be tested faces the device and waits for the voice prompt countdown to collect the full-body front image of the human body;

[0059] Function of collecting human side pictures. The posture data collection self-service terminal uses the front RGB camera 3 to collect RGB photos of the human side. The standing position is 1.2-1.5m away from the front surface of the device, with the left side of the person to be tested facing the device vertically, standing relaxed, with both hands close to the trouser seams. Wait for the voice prompt countdown to collect the full-body front image of the human body;

[0060] Collect the depth image of the human body in the forward state. The posture data collection self-service terminal uses the depth camera 1 on the top of the device to collect the RGB-D depth image of the human body from the side. The standing position is 1.2-1.5m away from the front surface of the device. The person to be tested faces the device with his back, relaxes his body, puts his feet together, bends at a 90-degree angle between his body and legs, puts his hands together and points to the center of his feet, and his head and upper body are in a straight line, showing a standard human forward bending action. Wait for the voice prompt countdown to collect the back image of the human body in the forward bending state.

[0061] Testing process: After clicking Start Test, the device enters the continuous data collection phase. First, personal identity authentication is performed. You can choose to scan a code or swipe a card for identification. After the identity authentication is completed, it will prompt that the identity authentication is successful and enter the collection phase.

[0062] 1. The system prompts the human body frontal image acquisition action;

[0063] After completing the identity authentication, the preparation for collecting the frontal image of the human body begins. At this time, the subject is prompted to complete the preparation action through voice instructions and animations displayed on the screen (animation of the subject standing in the corresponding position and completing the corresponding action, the human body stands relaxed, and the hands are about 30 degrees to the body);

[0064] 2. RGB camera 3 takes photos to collect the front image of the human body;

[0065] 3. After completing the corresponding preparation actions, image acquisition is performed. After the acquisition is completed, an external sound prompts that the human body front image data acquisition is completed;

[0066] 4. System prompts: The system prompts the human body side image acquisition action;

[0067] Through voice instructions, an animation is displayed on the main screen (an animation of the subject standing in the corresponding position and completing the corresponding movements, with the human body standing relaxed and the hands pressed against the trouser seams);

[0068] 5. RGB camera 3 takes photos to collect side images of the human body;

[0069] 6. After completing the corresponding preparation actions, image acquisition is performed. After the acquisition is completed, an external voice prompts that the human body side image data acquisition is completed;

[0070] 7. System prompts: The system prompts the back image acquisition action under the human body's forward bending action;

[0071] Through voice instructions, an animation is displayed on the main screen (animation of the subject standing in the corresponding position and completing the corresponding action, human body forward bending action, upper body bending at 90° with the body, hands clasped together and pointing to the center of the two feet);

[0072] 8. The depth camera 1 collects a depth image of the human body in a forward bending state;

[0073] After completing the corresponding preparatory movements, the image is collected. After the collection is completed, an external sound prompts that the back image collection in the forward bending movement of the human body is completed;

[0074] 9. The collection is completed and the data is uploaded;

[0075] 10. The human posture assessment algorithm based on human key point detection technology deployed on the health data management and analysis cloud platform uses the frontal image of the human body collected by the posture data collection self-service terminal to evaluate the two-dimensional posture information of various tissues and parts of the human body in a relaxed state, and then evaluates posture problems such as high and low shoulders, X / O legs, cervical anteversion, cervical lateral tilt, pelvic anteversion, and pelvic lateral tilt. The human body three-dimensional reconstruction algorithm based on multi-view uses the collected front and side color images of the human body to reconstruct the human body in three dimensions, and calculates data such as waist-to-hip ratio to evaluate the degree of human obesity. The scoliosis assessment algorithm based on the RGB-D depth image of the back of the human body in the forward bending state uses the RGB-D depth image of the back of the human body in the forward bending state to analyze the characteristics of the high and low distribution of muscles on both sides of the back of the entire human body, and evaluates the results of scoliosis;

[0076] 11. The health data management and analysis cloud platform stores, manages and analyzes the above data, evaluates and predicts the body status and trends of the subjects through big data analysis. The results are sent to the information push and management client. Users can view the measured data and analysis results through the client.

[0077] The subjects use the posture data collection self-service terminal to collect the data required for the evaluation algorithm, upload the data to the health data management and analysis cloud platform through the network, and use the algorithms and data analysis capabilities deployed on the health data management and analysis cloud platform to achieve evaluation and data management, storage, analysis and other functions for posture problems including scoliosis, high and low shoulders, X / O legs, cervical anteversion, cervical lateral tilt, pelvic anteversion, pelvic lateral tilt, obesity, etc. Finally, the detected results and future risk warning information are pushed to the end user through the information push and management client to create a data closed loop. The three parts are organically combined to achieve high-frequency, high-efficiency, low-cost, and high-precision normalized posture data collection and analysis, and strong intervention reminder functions to achieve more effective posture monitoring purposes.

[0078] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present invention may be combined and / or combined in various ways, even if such combinations and / or combinations are not explicitly described in the present invention. In particular, the features described in the various embodiments and / or claims of the present invention may be combined and / or combined in various ways without departing from the spirit and teachings of the present invention. All of these combinations and / or combinations fall within the scope of the present invention.

Claims

1. A self-service normalized body posture monitoring system, characterized in that: Including self-service terminal for body data collection, cloud platform for health data management and analysis, and client for information push and management; The posture data collection self-service terminal is used to collect the posture data of the subject, and the posture data includes but is not limited to: a full-body RGB photo of the front of the human body, a full-body RGB photo of the side of the human body, and an RGB-D depth image of the back of the human body in a forward bending state; The health data management and analysis cloud platform is used for the storage, management and analysis of health data, and for evaluating and predicting the body condition and trend of the subjects through big data analysis; The information push and management client is used to present the body data and related content of the subject, and can push the detected results together with future risk warning information to the end user. The user can also maintain and manage the information through the client.

2. A self-service normalized body posture monitoring system according to claim 1, characterized in that: The body data collection self-service terminal is connected to the health data management and analysis cloud platform, and the health data management and analysis cloud platform is connected to the health data management and analysis cloud platform.

3. The self-service normalized body posture monitoring system according to claim 1, characterized in that: The health data management and analysis cloud platform analyzes and evaluates the body posture of the subject using a human body posture assessment algorithm based on human body key point detection technology, a scoliosis assessment algorithm based on RGB-D depth images of the back in a human body flexion state, and an obesity assessment algorithm based on human body three-dimensional reconstruction technology.

4. The self-service normalized body posture monitoring system according to claim 3, characterized in that: The human body posture evaluation algorithm of the human body key point detection technology evaluates the two-dimensional posture information of various tissue parts of the human body in a relaxed state through a frontal image of the human body, and evaluates posture problems such as uneven shoulders, X / O legs, cervical anteversion, cervical lateral tilt, pelvic anteversion, and pelvic lateral tilt.

5. The self-service normalized body posture monitoring system according to claim 3, characterized in that: The scoliosis assessment algorithm based on the RGB-D depth image of the back in the forward bending state uses the RGB-D depth image of the back in the forward bending state to analyze the characteristics of the height distribution of muscles on both sides of the entire back spine of the human body, and then generates a scoliosis assessment result.

6. The self-service normalized body posture monitoring system according to claim 1, characterized in that: The obesity assessment algorithm of the human body three-dimensional reconstruction technology utilizes the collected front color images and side color images of the human body to perform three-dimensional reconstruction of the human body, and calculates data such as waist-to-hip ratio to assess the degree of human obesity.

7. The self-service normalized body posture monitoring system according to claim 1, characterized in that: The body data collection self-service terminal includes a display module, an identity authentication module, a voice prompt module, an RGB camera module, a depth camera module, a collection time adjustment module and an output module; The display module is used to collect action diagrams of human body images; The identity authentication module is used to authenticate the identity of the person being tested, and the authentication methods include but are not limited to card swiping authentication, face recognition authentication, and account password authentication; The voice prompt module is used to remind the test subject to start and end, prepare for corresponding actions, count down, and give voice prompts when completed; The RGB camera module is used to capture a frontal image of a person standing relaxedly with both hands at an angle of about 30 degrees to the body and a side image of a person standing relaxedly with both hands pressed against the trouser seams; The depth camera module is used to collect depth images of a person bending forward, with the upper body bent at 90 degrees to the body, and the hands clasped together and pointing to the center of the two feet; The collection time adjustment module is used to adjust the collection countdown interval according to the preparation actions of different groups of people; The output module is used to automatically upload the information of the subject's ID, the front image of the human body, the side image of the human body, and the depth map of the back of the human body in the forward bending state to the health data management and analysis cloud platform.

8. The self-service normalized body posture monitoring system according to claim 7, characterized in that: The display module includes but is not limited to a liquid crystal display, an LED display, an OLED display and a serial port display.

9. The self-service normalized body posture monitoring system according to claim 7, characterized in that: The depth camera module includes but is not limited to a monocular structured light depth camera, a binocular structured light depth camera, and a structured light camera.

Images