Three-dimensional human body sign data analysis method and system

Abstract

The invention relates to the technical field of medical health management, in particular to a three-dimensional human body sign data analysis method and a system thereof.A data acquisition module scans a human body to obtain human body data and sends the obtained human body data to a data processing module, and the data processing module receives preprocessed data and sends the preprocessed data to a cloud server; the preprocessing module is used for denoising, filling and adjusting the preprocessed data to ensure the accuracy and stability of the data, and sending the processed data to the feature extraction module, and the extraction module is used for fusing the data to obtain a high-precision human body three-dimensional model and body surface feature angles of human body key parts; the human body three-dimensional model and the body surface feature angle are sent to the analysis module, analysis and disease diagnosis are carried out on the human body posture, and a related treatment plan is made, so that the high-precision human body three-dimensional model can be obtained, data analysis is not influenced, and an efficient treatment plan can be made.

Description

Technical Field

[0001] The present invention relates to the field of medical health management technology, and in particular to a three-dimensional human body vital sign data analysis method and system. Background Art

[0002] Three-dimensional human body signs mainly refer to the physical sign data obtained by all-round and three-dimensional measurement and analysis of the human body through three-dimensional technology. These data usually include three-dimensional morphological parameters such as length, circumference, and volume of the human body, which can more accurately reflect the morphological characteristics and health status of the human body. According to the user's physical sign data, the user's body composition, posture, dynamic and static body function can be evaluated, and various functional data can be mapped out in a three-dimensional and intuitive manner, which is convenient for formulating corresponding training plans to achieve the purpose of rehabilitation.

[0003] Currently, the existing three-dimensional human vital sign data analysis often uses methods such as three-dimensional reconstruction, contour extraction and fitting, which are easily affected by factors such as the complex curved surface of the human body, the non-rigid movement of the human body during the reconstruction process, and the large volume of the human body. As a result, the human body data obtained by three-dimensional reconstruction is prone to distortion, and a high-precision three-dimensional human body model cannot be obtained, which affects data analysis and makes it impossible to formulate an efficient treatment plan. Summary of the invention

[0004] The purpose of the present invention is to provide a three-dimensional human vital signs data analysis method and system thereof, aiming to solve the technical problem that the existing three-dimensional human vital signs data analysis often adopts three-dimensional reconstruction, contour extraction and fitting methods, which are easily affected by factors such as complex human body surfaces, non-rigid human body movement during reconstruction and large human body volume, making the human body data obtained by three-dimensional reconstruction prone to distortion and unable to obtain a high-precision three-dimensional human body model, thereby affecting data analysis and unable to formulate an efficient treatment plan.

[0005] To achieve the above purpose, the present invention provides a three-dimensional human body sign data analysis system, including a data acquisition module, a data processing module, a feature extraction module and an analysis module:

[0006] The data acquisition module is connected to the data processing module, the data processing module is connected to the feature extraction module, and the feature extraction module is connected to the analysis module;

[0007] The data acquisition module is used to scan the human body, obtain human body data, and send the obtained human body data to the data processing module;

[0008] The data processing module is used to receive human body data, pre-process the human body data, and send the pre-processed data to the feature extraction module;

[0009] The feature extraction module is used to receive the pre-processed data, extract and fuse the pre-processed data, obtain a high-precision three-dimensional human body model, and send the three-dimensional human body model to the analysis module;

[0010] The analysis module is used to analyze and evaluate the three-dimensional model of the human body and formulate relevant treatment plans.

[0011] Wherein, the data processing module includes a noise removal unit and a filling unit, the noise removal unit is connected to the data acquisition module, and the filling unit is connected to the noise removal unit;

[0012] The noise removal unit is used to filter the human body data to remove noise points that do not conform to normal distribution;

[0013] The filling unit is used to fill the missing area in the human body data.

[0014] Wherein, the data processing module further comprises an adjustment unit, and the adjustment unit is connected to the filling unit;

[0015] The adjustment unit is used to transform and adjust the coordinates of the human body data in terms of position and direction.

[0016] Wherein, the feature extraction module includes a multi-fusion dynamic reconstruction unit and a body surface feature angle extraction unit, the multi-fusion dynamic reconstruction unit is connected to the adjustment unit, and the body surface feature angle extraction unit is connected to the multi-fusion dynamic reconstruction unit;

[0017] The multi-fusion dynamic reconstruction unit is used to fuse multiple groups of human body color and depth image data from different angles to obtain a high-precision three-dimensional model of the human body;

[0018] The body surface feature angle extraction unit is used to calculate and obtain the body surface feature angles of key parts of the human body.

[0019] Wherein, the analysis module comprises a bone point position estimation unit and an auxiliary diagnosis unit, the bone point position estimation unit is connected to the body surface feature angle extraction unit, and the auxiliary diagnosis unit is connected to the body surface feature angle extraction unit;

[0020] The skeleton point position estimation unit is used to measure and analyze the data of the obtained three-dimensional human body model and analyze the human body posture;

[0021] The auxiliary diagnosis unit is used to assist doctors in diagnosing diseases, output information such as the probability and risk level of the disease, and provide decision support for doctors.

[0022] Wherein, the analysis module further comprises a condition assessment unit, and the condition assessment unit is connected to the auxiliary diagnosis unit;

[0023] The condition assessment unit is used to assess the progression of the condition.

[0024] The present invention also provides a three-dimensional human body sign data analysis method, which is applied to the three-dimensional human body sign data analysis system as described above, and comprises the following steps:

[0025] Scanning a human body through the data acquisition module to obtain human body data, and sending the obtained human body data to the data processing module;

[0026] Preprocessing the human body data using the data processing module, and sending the preprocessed data to the feature extraction module;

[0027] The feature extraction module is used to extract and fuse the preprocessed data to obtain a high-precision three-dimensional human body model, and the three-dimensional human body model is sent to the analysis module;

[0028] The analysis module is used to analyze and evaluate the three-dimensional model of the human body and formulate a relevant treatment plan.

[0029] A three-dimensional human body vital sign data analysis method and system of the present invention scans a human body through the data acquisition module to obtain human body data, and sends the obtained human body data to the data processing module. The data processing module receives pre-processed data, removes noise, fills and adjusts the pre-processed data to ensure the accuracy and stability of the data, and sends the processed data to the feature extraction module. The feature extraction module fuses the data to obtain a high-precision three-dimensional human body model and surface feature angles of key parts of the human body, and sends the three-dimensional human body model and the surface feature angles to the analysis module to analyze the human body posture and diagnose diseases, and formulate relevant treatment plans, thereby obtaining a high-precision three-dimensional human body model without affecting data analysis, and being able to formulate an efficient treatment plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention 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 invention. 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 structural schematic diagram of the three-dimensional human body vital signs data analysis system of the present invention.

[0032] Figure 2 It is a structural schematic diagram of the data processing module of the present invention.

[0033] Figure 3 It is a structural schematic diagram of the feature extraction module of the present invention.

[0034] Figure 4 It is a structural schematic diagram of the analysis module of the present invention.

[0035] Figure 5 It is a structural schematic diagram of the multi-fusion dynamic reconstruction unit of the present invention.

[0036] Figure 6 It is a step diagram of the three-dimensional human body sign data analysis method of the present invention.

[0037] In the figure: 1-data acquisition module, 2-data processing module, 3-feature extraction module, 4-analysis module, 11-infrared camera, 12-turntable, 13-control unit, 14-laser stripe projector, 21-noise removal unit, 22-filling unit, 23-adjustment unit, 31-multi-fusion dynamic reconstruction unit, 32-body surface feature angle extraction unit, 41-bone point position estimation unit, 42-auxiliary diagnosis unit, 43-disease assessment unit. DETAILED DESCRIPTION

[0038] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0039] See also Figures 1 to 5 The present invention provides a three-dimensional human body sign data analysis system, including a data acquisition module 1, a data processing module 2, a feature extraction module 3 and an analysis module 4:

[0040] The data acquisition module 1 is connected to the data processing module 2, the data processing module 2 is connected to the feature extraction module 3, and the feature extraction module 3 is connected to the analysis module 4;

[0041] The data acquisition module 1 is used to scan the human body, obtain human body data, and send the obtained human body data to the data processing module 2;

[0042] The data processing module 2 is used to receive human body data, pre-process the human body data, and send the pre-processed data to the feature extraction module 3;

[0043] The feature extraction module 3 is used to receive the pre-processed data, extract and fuse the pre-processed data, obtain a high-precision three-dimensional human body model, and send the three-dimensional human body model to the analysis module 4;

[0044] The analysis module 4 is used to analyze and evaluate the three-dimensional model of the human body and formulate relevant treatment plans.

[0045] In this embodiment, the human body is scanned by the data acquisition module 1 to obtain human body data, and the obtained human body data is sent to the data processing module 2. The data processing module 2 receives the pre-processed data, removes noise, fills and adjusts the pre-processed data to ensure the accuracy and stability of the data, and sends the processed data to the feature extraction module 3. The feature extraction module 3 fuses the data to obtain a high-precision three-dimensional human body model and surface feature angles of key parts of the human body, and sends the three-dimensional human body model and the surface feature angles to the analysis module 4 to analyze the human body posture and diagnose diseases, and formulate relevant treatment plans, so as to obtain a high-precision three-dimensional human body model without affecting data analysis, and to formulate an efficient treatment plan.

[0046] Further, the data processing module 2 includes a noise removal unit 21 and a filling unit 22, the noise removal unit 21 is connected to the data acquisition module 1, and the filling unit 22 is connected to the noise removal unit 21;

[0047] The noise removal unit 21 is used to filter the human body data to remove noise points that do not conform to normal distribution;

[0048] The filling unit 22 is used to fill the missing area in the human body data.

[0049] Furthermore, the data processing module 2 further includes an adjustment unit 23, and the adjustment unit 23 is connected to the filling unit 22;

[0050] The adjustment unit 23 is used to transform and adjust the coordinates of the human body data in terms of position and direction.

[0051] In this embodiment, the denoising unit 21 adopts filtering and statistical methods to remove noise points that do not conform to the normal distribution from the acquired human body data, thereby reducing the impact of noise points. The data is transmitted to the filling unit 22 after denoising. The filling unit 22 adopts interpolation and surface reconstruction methods to select known points around the missing area, and performs interpolation calculations based on these positions and attributes to obtain data in the missing area, fill the missing area, and transmit the data to the adjustment unit 23 after filling. The adjustment unit 23 adopts rigid body transformation and affine transformation to transform the position and direction of the data, and performs scaling, rotation and translation to align it with the reference coordinate system, thereby improving data accuracy and completeness, and providing a reliable foundation for the feature extraction module 3.

[0052] Further, the feature extraction module 3 includes a multi-fusion dynamic reconstruction unit 31 and a body surface feature angle extraction unit 32, the multi-fusion dynamic reconstruction unit 31 is connected to the adjustment unit 23, and the body surface feature angle extraction unit 32 is connected to the multi-fusion dynamic reconstruction unit 31;

[0053] The multi-fusion dynamic reconstruction unit 31 is used to fuse multiple groups of human body color and depth image data from different angles to obtain a high-precision three-dimensional human body model;

[0054] The body surface feature angle extraction unit 32 is used to calculate and obtain the body surface feature angles of key parts of the human body.

[0055] In this embodiment, after receiving the data sent by the adjustment unit 23, the multi-fusion dynamic reconstruction unit 31 fuses multiple groups of human body color and depth image data at different angles to obtain a high-precision three-dimensional human body model. The surface feature angle extraction unit 32 obtains the surface feature angles of key parts of the human body, such as the back angle, hip angle, chest angle, etc., by calculating the three-dimensional human body model. These angles can reflect the posture and shape characteristics of the human body in different parts, thereby providing strong support for subsequent analysis.

[0056] Further, the analysis module 4 includes a skeleton point position estimation unit 41 and an auxiliary diagnosis unit 42, the skeleton point position estimation unit 41 is connected to the body surface feature angle extraction unit 32, and the auxiliary diagnosis unit 42 is connected to the body surface feature angle extraction unit 32;

[0057] The skeleton point position estimation unit 41 is used to measure and analyze the obtained three-dimensional human body model and analyze the human body posture;

[0058] The auxiliary diagnosis unit 42 is used to assist doctors in diagnosing diseases, output information such as the probability and risk level of the disease, and provide decision support for doctors.

[0059] Furthermore, the analysis module 4 further includes a condition assessment unit 43, and the condition assessment unit 43 is connected to the auxiliary diagnosis unit 42;

[0060] The disease condition assessment unit 43 is used to assess the disease condition progression.

[0061] In this embodiment, the bone point position estimation unit 41 judges the forward head tilt, round shoulders, uneven shoulders, forward and backward pelvic tilt, and long and short legs according to the obtained high-precision human body three-dimensional model and body surface feature angles, and performs posture analysis. At the same time, the auxiliary diagnosis unit 42 diagnoses the human body three-dimensional model and body surface feature angles, outputs information such as the probability and risk level of the disease, and transmits it to the condition assessment unit 43 to assess the patient's disease progression and treatment effect, provide decision support for doctors, and help doctors adjust treatment plans in a timely manner to improve treatment effects.

[0062] Furthermore, the data acquisition module 1 includes an infrared camera 11, a turntable 12 and a control unit 13;

[0063] The infrared camera 11 is used for performing non-contact scanning and measurement of the human body;

[0064] The turntable 12 is used to control the rotation and movement of the infrared camera 11 to achieve a comprehensive scan of various parts of the human body;

[0065] The control unit 13 is used to control the infrared camera 11 and the turntable 12 and store data.

[0066] The control unit 13 controls the turntable 12 so that the turntable 12 controls the infrared camera 11 to rotate and move up and down, so that the infrared camera 11 performs an all-round scan of various parts of the human body, and stores the scanned data in the control unit 13 to obtain human body data.

[0067] In this embodiment, the infrared camera 11 is controlled by the turntable 12 to rotate 360 ​​degrees to perform an all-round scan of the human body, and the scanned human body data is stored in the control unit 13, thereby ensuring the integrity of the human body data.

[0068] Furthermore, the data acquisition module 1 also includes a laser stripe projector 14;

[0069] The laser stripe projector 14 is used to project laser stripes on the surface of the human body to help the system capture the contour of the human body more accurately.

[0070] In this embodiment, the laser stripe projector 14 can be used to further measure the human body by projecting laser stripes onto the surface of the human body and collecting and analyzing the deformation or displacement information of the stripes, so as to more accurately capture the contour of the human body and accurately measure the three-dimensional size of the human body.

[0071] See also Figure 6 The present invention also provides a three-dimensional human body sign data analysis method, which is applied to the three-dimensional human body sign data analysis system as described above, and comprises the following steps:

[0072] S101: Scanning a human body through the data acquisition module 1 to obtain human body data, and sending the obtained human body data to the data processing module 2;

[0073] S102: preprocessing the human body data using the data processing module 2, and sending the preprocessed data to the feature extraction module 3;

[0074] S103: extracting and fusing the preprocessed data using the feature extraction module 3 to obtain a high-precision three-dimensional human body model, and sending the three-dimensional human body model to the analysis module 4;

[0075] S104: Analyze and evaluate the three-dimensional model of the human body using the analysis module 4, and formulate a relevant treatment plan.

[0076] In this embodiment, first, the data acquisition module 1 uses a laser scanner to scan the human body to obtain human body data, and transmits the obtained data to the data processing module 2. The data processing module 2 uses a computer, relies on software algorithms and technologies, removes noise, fills and adjusts the data to obtain complete data, and transmits the complete data to the feature extraction module 3. The feature extraction module 3 uses three-dimensional reconstruction technology to fuse the data to obtain a high-precision three-dimensional model of the human body and the surface feature angles of key parts of the human body, and sends the three-dimensional model of the human body and the surface feature angles to the analysis module 4 to analyze the human body posture and diagnose diseases, and formulate relevant treatment plans, thereby obtaining a high-precision three-dimensional model of the human body without affecting data analysis, and being able to formulate an efficient treatment plan.

[0077] What is disclosed above is only a preferred embodiment of the present invention, and it certainly cannot be used to limit the scope of rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiment and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. A three-dimensional human body sign data analysis system, characterized in that: Including data acquisition module, data processing module, feature extraction module and analysis module: The data acquisition module is connected to the data processing module, the data processing module is connected to the feature extraction module, and the feature extraction module is connected to the analysis module; The data acquisition module is used to scan the human body, obtain human body data, and send the obtained human body data to the data processing module; The data processing module is used to receive human body data, pre-process the human body data, and send the pre-processed data to the feature extraction module; The feature extraction module is used to receive the pre-processed data, extract and fuse the pre-processed data, obtain a high-precision three-dimensional human body model, and send the three-dimensional human body model to the analysis module; The analysis module is used to analyze and evaluate the three-dimensional model of the human body and formulate relevant treatment plans.

2. The three-dimensional human body vital signs data analysis system according to claim 1, characterized in that: The data processing module includes a noise removal unit and a filling unit, the noise removal unit is connected to the data acquisition module, and the filling unit is connected to the noise removal unit; The noise removal unit is used to filter the human body data to remove noise points that do not conform to normal distribution; The filling unit is used to fill the missing area in the human body data.

3. The three-dimensional human body vital signs data analysis system according to claim 2, characterized in that: The data processing module further includes an adjustment unit, and the adjustment unit is connected to the filling unit; The adjustment unit is used to transform and adjust the coordinates of the human body data in terms of position and direction.

4. The three-dimensional human body vital signs data analysis system according to claim 3, characterized in that: The feature extraction module includes a multi-fusion dynamic reconstruction unit and a body surface feature angle extraction unit, the multi-fusion dynamic reconstruction unit is connected to the adjustment unit, and the body surface feature angle extraction unit is connected to the multi-fusion dynamic reconstruction unit; The multi-fusion dynamic reconstruction unit is used to fuse multiple groups of human body color and depth image data from different angles to obtain a high-precision three-dimensional model of the human body; The body surface feature angle extraction unit is used to calculate and obtain the body surface feature angles of key parts of the human body.

5. The three-dimensional human body vital signs data analysis system according to claim 4, characterized in that: The analysis module includes a skeleton point position estimation unit and an auxiliary diagnosis unit, wherein the skeleton point position estimation unit is connected to the body surface feature angle extraction unit, and the auxiliary diagnosis unit is connected to the body surface feature angle extraction unit; The skeleton point position estimation unit is used to measure and analyze the data of the obtained three-dimensional human body model and analyze the human body posture; The auxiliary diagnosis unit is used to assist doctors in diagnosing diseases, output information such as the probability and risk level of the disease, and provide decision support for doctors.

6. The three-dimensional human body vital signs data analysis system according to claim 5, characterized in that: The analysis module further includes a condition assessment unit, which is connected to the auxiliary diagnosis unit; The condition assessment unit is used to assess the progression of the condition.

7. A three-dimensional human body sign data analysis method, applied to the three-dimensional human body sign data analysis system as claimed in claim 1, characterized in that: The following steps are involved: Scanning a human body through the data acquisition module to obtain human body data, and sending the obtained human body data to the data processing module; Preprocessing the human body data using the data processing module, and sending the preprocessed data to the feature extraction module; The feature extraction module is used to extract and fuse the preprocessed data to obtain a high-precision three-dimensional human body model, and the three-dimensional human body model is sent to the analysis module; The analysis module is used to analyze and evaluate the three-dimensional model of the human body and formulate a relevant treatment plan.

Images