WO2020211255A1

WO2020211255A1 - Human body shape and physique data acquisition method, device and storage medium

Info

Publication number: WO2020211255A1
Application number: PCT/CN2019/103586
Authority: WO
Inventors: 钱根双
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-04-17
Filing date: 2019-08-30
Publication date: 2020-10-22
Also published as: CN110123331A

Abstract

A human body shape and physique data acquisition method, a device and a storage medium. The method comprises: collecting two-dimensional image information of a human body by means of a photographing device (13), the two-dimensional image information comprising image information of the front side, the back side, the side surface, the top of the head and the sole of the human body (S110); obtaining corresponding human body 3D distribution feature information by means of the two-dimensional image information and a corresponding correction scale coefficient, wherein the correction scale coefficient is obtained based on a deep neural network model (S120); and determining shape parameter data of each part of the human body according to the human body 3D distribution feature information, and determining physique data of the human body according to the shape parameter data (S130). The method can collect and analyze human health data and shape data, and obtain the current health status of the human body according to the existing health standards.

Description

Human body shape and physique data collection method, device and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on April 17, 2019, the application number is 201910308190.6, and the invention title is "Human Body and Physical Data Collection Methods, Devices, and Storage Media", the entire content of which is incorporated by reference Incorporated in this application.

Technical field

This application relates to the field of image recognition technology, and in particular to a method and device for collecting human body shape and physical fitness data, and a computer non-volatile readable storage medium.

Background technique

With the improvement of living standards and the gradual attention to the concept of health preservation, physical examination and fitness have gradually entered thousands of households in recent years. However, the current medical examination systems on the market have relatively single functions, or have many functions but complicated operations, and only professional and technical personnel can operate them. Moreover, the results given by the general physical examination system are all measured parameters, and it is generally difficult for ordinary users to obtain the analysis results and current health status through each number.

For example, in the traditional physical examination process, the collection of physical examination data of the human body is usually limited to the measurement of health data such as height, weight, and body fat, while the measurement of data on other parts of the human body, such as body measurements and body proportions, requires manual inspection by medical staff. , Resulting in slow detection speed, low efficiency, and even non-detection of such data.

Summary of the invention

This application provides a method and device for collecting human body shape and physique data, and a computer non-volatile readable storage medium, the main purpose of which is to collect two-dimensional image information of the human body through a photographing device, and to mark all positions to be measured based on the two-dimensional image information The plane data value of, combined with the corresponding correction scale factor, finally obtain the actual body data and physical data of the human body.

In the first aspect, this application provides a method for collecting human body shape and physical fitness data, which is applied to an electronic device, and the method includes:

Collecting two-dimensional image information of the human body by a photographing device, where the two-dimensional image information includes image information of the front, back, side, top of the head, and soles of the human body;

Acquire corresponding human body 3D distribution feature information through the two-dimensional image information and the corresponding correction scale factor; wherein the correction scale factor is acquired based on a deep neural network model;

The body parameter data of each part of the human body is determined according to the 3D distribution feature information of the human body, and the body fitness data of the human body is determined according to the body parameter data.

In a second aspect, the present application also provides an electronic device that includes a memory, a processor, and a photographing device. The memory includes a human body shape and a physical data collection program. The human body shape and physical data collection program are The processor executes the following steps:

Collecting two-dimensional image information of the human body by a photographing device, the two-dimensional image information including image information of the front, back, side, top of the head and soles of the human body;

In addition, in order to achieve the above object, the present application also provides a non-volatile computer readable storage medium, the computer readable storage medium includes a human body shape and a physical data collection program, and the human body shape and a physical data collection program are When the processor is executed, the steps of the above-mentioned human body shape and physical fitness data collection method are realized.

The human body shape and physique data collection method, device, and computer non-volatile readable storage medium proposed in this application are mainly intended to collect two-dimensional image information of the human body through a photographing device, so as to image various parts of the human body (two-dimensional image) , And annotate the plane data values of all the human body positions to be measured according to the portrait, combined with the corresponding correction scale coefficient, and finally obtain the actual body shape data and physical data of the human body.

Description of the drawings

Figure 1 is a schematic diagram of the application environment of an embodiment of the applicant's body shape and physical fitness data collection method;

FIG. 2 is a schematic diagram of a unit of an embodiment of a human body shape and physical fitness data collection program in FIG. 1;

Fig. 3 is a flowchart 1 of an embodiment of the applicant's body shape and physical data collection method;

Fig. 4 is a second flowchart of an embodiment of the applicant's body shape and physical fitness data collection method.

The realization, functional characteristics, and advantages of the purpose of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

detailed description

It should be understood that the specific embodiments described here are only used to explain the application, and are not used to limit the application.

This application provides a method for collecting human body shape and physical fitness data, which is applied to an electronic device 1. Referring to FIG. 1, it is a schematic diagram of an application environment of a preferred embodiment of the applicant's body shape and physical data collection method.

In this embodiment, the electronic device 1 may be a terminal device with arithmetic function, such as a server, a smart phone, a tablet computer, a portable computer, a desktop computer, and the like.

The electronic device 1 includes a processor 12, a memory 11, a camera 13, a network interface 14, and a communication bus 15.

The memory 11 includes at least one type of readable storage medium. The at least one type of readable storage medium may be a non-volatile storage medium such as flash memory, hard disk, multimedia card, card-type memory 11, and the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1. In other embodiments, the readable storage medium may also be the external memory 11 of the electronic device 1, such as a plug-in hard disk or a smart memory card (Smart Media Card, SMC) equipped on the electronic device 1. , Secure Digital (SD) card, Flash Card, etc.

In this embodiment, the readable storage medium of the memory 11 is generally used to store the human body shape and the physical data collection program 10, the human body image database, etc. installed in the electronic device 1. The memory 11 can also be used to temporarily store data that has been output or will be output.

In some embodiments, the processor 12 may be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run program codes or process data stored in the memory 11, such as executing human body shapes and Physical data collection program 10 etc.

The photographing device 13 may be a part of the electronic device 1 or may be independent of the electronic device 1. In some embodiments, the electronic device 1 is a terminal device with a camera such as a smart phone, a tablet computer, or a portable computer, and the photographing device 13 is the camera of the electronic device 1. In other embodiments, the electronic device 1 may be a server, and the photographing device 13 is independent of the electronic device 1 and is connected to the electronic device 1 via a network. For example, the photographing device 13 is installed in a specific place, such as a hospital. A real-time image is captured by the person to be examined, and the captured real-time image is transmitted to the processor 12 via the network.

The network interface 14 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface), and is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

The communication bus 15 is used to realize the connection and communication between these components.

FIG. 1 only shows the electronic device 1 with the components 11-15, but it should be understood that it is not required to implement all the illustrated components, and more or fewer components may be implemented instead.

Optionally, the electronic device 1 may also include a user interface. The user interface may include an input unit such as a keyboard (Keyboard), a voice input device such as a microphone (microphone) and other devices with voice recognition functions, and a voice output device such as audio, earphones, etc. Optionally, the user interface may also include a standard wired interface and a wireless interface.

Optionally, the electronic device 1 may also include a display, and the display may also be called a display screen or a display unit. In some embodiments, it may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an organic light-emitting diode (Organic Light-Emitting Diode, OLED) touch device. The display is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.

Optionally, the electronic device 1 further includes a touch sensor. The area provided by the touch sensor for the user to perform a touch operation is called a touch area. In addition, the touch sensor described here may be a resistive touch sensor, a capacitive touch sensor, or the like. Moreover, the touch sensor includes not only a contact type touch sensor, but also a proximity type touch sensor and the like. In addition, the touch sensor may be a single sensor, or may be, for example, a plurality of sensors arranged in an array.

In addition, the area of the display of the electronic device 1 may be the same as or different from the area of the touch sensor. Optionally, the display and the touch sensor are stacked to form a touch display screen. The device detects the touch operation triggered by the user based on the touch screen.

Optionally, the electronic device 1 may also include a radio frequency (RF) circuit, a sensor, an audio circuit, etc., which will not be repeated here.

In the device embodiment shown in FIG. 1, the memory 11 as a computer storage medium may include an operating system, and a human body shape and physical data collection program 10; the processor 12 executes the human body shape and physical data stored in the memory 11. The following steps are implemented in the acquisition program 10:

Among them, the photographing device 13 includes a rotatable base for the user to stand on, and a photographing camera arranged around the rotatable base. The photographing camera is connected to an external control system. The human body stands on the rotatable base, and the photographing camera is controlled by the control system to perform the human body Multi-angle shooting. Among them, the angle of the shooting camera can be adjusted according to the height of the human body to be detected.

The step of obtaining the correction scale factor includes: creating a human body image database, and collecting the scale factor between the two-dimensional image data in the database and the corresponding parameters of each part of the actual human body, and then obtaining the correction scale factor of each part of the human body. The correction scale factor varies according to different parts of the human body and different angles, such as sideways correction scale factor, front correction scale factor, head correction scale factor, shoulder correction scale factor, chest correction scale factor, etc.

In addition, with the assistance of the rotatable base, the human body can be photographed at various angles every 15 degrees or 30 degrees, until the human body rotates 360 degrees, so as to obtain the image information of the human body at various angles to improve 3D The accuracy of the characteristic information.

When obtaining the correction scale coefficient based on the deep neural network model, the steps of obtaining the correction scale coefficient may include:

1. Create a convolutional neural network model, and initialize the parameters of the convolutional neural network model through the pre-training model.

2. Input the image in the human body image database into the initialized convolutional neural network model for training, extract the feature information in the image, and obtain the two-dimensional image data corresponding to the image.

3. Obtain the correction scale coefficient according to the two-dimensional image data and the corresponding size parameters of each part of the actual human body. The proportional coefficient between the two-dimensional image data and the corresponding parameters of each part of the actual human body is the correction proportional coefficient.

In the process of acquiring two-dimensional image data based on two-dimensional image analysis, the front human body image area, the back human body image area, the side human body image area, etc. can be identified in a variety of ways.

Method 1: Train the human front detector, side detector, and back detector by extracting typical human features (such as gradient features, edge features), and then apply the human front detector, side detector, and back detector in the scale and position space The device separately judges the front body image, the side body image and the back body image of the human body, and then detects the front body image area, the back body image area, and the side body image area in the front body image. In addition, a human frontal detector can also be constructed by combining the features of gradient direction histogram and support vector machine.

Method 2: Detect different parts of the front of the human body, and then use the geometric relationship between the parts to construct a human front detector. For example, divide the front of the human body into multiple parts: head, upper chest, lower chest, waist, buttocks, legs, left arm, right arm, and construct a human body side detector based on these eight parts. The constructed human frontal detector recognizes the frontal human body image area based on these eight parts from the frontal full-body image.

Furthermore, the two-dimensional image data of the human body can be determined according to the front body image area, the side body image area, and the back body image area.

In addition, the 3D distribution feature information of the human body includes the three-dimensional shape information of the human body and various feature points distributed on the three-dimensional shape. The feature points include head vertices, hand/foot distribution points, and various joint points of the human body. The feature points can be set according to The shape parameter data to be measured is determined, that is, we can measure the shape parameter data through the feature points.

As a specific example, the body parameter data includes basic parameters and scale parameters: among them, the basic parameters include: body height, weight, arm length, leg length, shoulder width, palm size, sole size, head size, bust, waist, and hip And neck circumference data, etc.; the ratio parameters are obtained according to the basic parameters, and the ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio and head-to-shoulder ratio data.

Finally, the step of determining the body mass data of the human body according to the body parameter data includes: obtaining the body mass index according to the body parameter data, and the calculation formula of the body mass index is:

BMI=G÷H ²

Among them, BMI is body mass index; G is body weight; H is body height.

It should be noted that the human body shape and physique data collection method provided in this application also includes traditional measurement steps. The body's height, weight, grip strength, blood pressure, heart rate, blood oxygen and other indicators are collected through traditional measurement devices.

In order to facilitate the storage and analysis of the collected data, it is also possible to record the personal information of the person to be tested before the data is collected. Specifically, the fingerprint of the person to be tested is first collected to authenticate the user's identity, and then parameter information such as the age and gender of the person to be tested is input into the human body data collection program 10, and the information is displayed to the test person for confirmation, and then The collection, analysis and processing of various indicators or parameters of the human body are realized through the human body data collection program, and the acquired data is displayed and stored in real time, which is convenient for testers to establish health files and later review.

The above test parameters may include: height, weight, grip strength, blood pressure, heart rate, blood oxygen, measurements, human body upper and lower body ratio, head to body ratio, head to neck ratio and head to shoulder ratio, body mass index BMI (for body shape analysis), etc.

And then through the calculation of body mass index BMI and grip strength BMI, a comprehensive body shape analysis and upper limb strength to evaluate the health of the examinee. At the same time, according to the measured values of blood pressure and grip strength, refer to the corresponding standards for men and women of different age groups, estimate the age of the examinee, and compare their actual age to obtain the degree of aging. If the estimated age is greater than the actual age, it means that the aging rate is faster and the physical fitness declines quickly; on the contrary, it means that the aging rate is slower and the physical fitness is maintained better.

The electronic device 1 proposed in the above embodiment can collect and analyze human health and physical data in a comprehensive and rapid manner, and learn the current health status of the human body according to existing health standards, and realize the effect of one-time, automated, and comprehensive physical examination, and user experience it is good.

In other embodiments, the human body shape and physical data collection program 10 can also be divided into one or more units, and one or more units are stored in the memory 11 and executed by the processor 12 to complete the application. The unit referred to in this application refers to a series of computer program instruction segments that can complete specific functions. Referring to FIG. 2, it is the program unit of the preferred embodiment of the human body shape and physical fitness data collection program 10 in FIG. 1.

The body shape and physical fitness data collection program 10 can be divided into:

The photographing unit 110 is used to collect two-dimensional image information of the human body in various positions and multiple angles.

The 3D distribution feature determining unit 120 obtains corresponding human body 3D distribution feature information through the two-dimensional image information collected by the photographing unit and the corresponding correction scale coefficient.

The recognition unit 130 determines the parameter data of various parts of the human body to be collected according to the 3D distribution feature information of the human body, and obtains the data of the upper and lower body ratio, the head-body ratio, the head-neck ratio, and the head-to-shoulder ratio.

The display unit 140 displays the above-mentioned human body upper and lower body ratio, head to body ratio, head to neck ratio, and head to shoulder ratio data in real time.

In addition, it also includes a correction scale coefficient acquisition unit and a traditional measurement unit; the traditional measurement unit is used to collect the body's height, weight, grip strength, blood pressure, heart rate, blood oxygen and other indicators.

In addition, this application also provides a method for collecting human body shape and physical fitness data. Referring to FIG. 3, FIG. 3 is the first flow chart of a specific embodiment of the applicant's body shape and physique data collection method. The method can be executed by a device, and the device can be implemented by software and/or hardware.

In this embodiment, the method for collecting human body shape and physical fitness data includes the following steps:

Step S110: Collect two-dimensional image information of the human body through the photographing device. The two-dimensional image information includes image information of the front, back, side, top of the head and soles of the human body.

Among them, the photographing device 13 includes a rotatable base for the user to stand on and a plurality of photographing cameras arranged around the rotatable base. The photographing cameras are connected to an external control system. The human body stands on the rotatable base and rotates at any angle through the control system. Control the shooting camera to take multi-angle shooting of the human body to be detected, and obtain the human body two-dimensional image information. Among them, the angle of the shooting camera can be adjusted according to the height of the human body to be detected to obtain image information of multiple parts of the human body such as the front, back, side, top of the head, and soles of the human body.

In addition, with the assistance of the rotatable base, the human body can be photographed at various angles every 15 degrees or 30 degrees, until the human body rotates 360 degrees, so as to obtain the image information of the human body at various angles to improve 3D The accuracy of feature distribution information.

Among them, the 3D distribution feature information of the human body includes the three-dimensional shape information of the human body and various feature points distributed on the three-dimensional shape. The feature points include head vertices, hand/foot distribution points, and various joint points of the human body. The feature points can be set according to The shape parameter data to be measured is determined, that is, we can measure the shape parameter data through the feature points.

Step S120: Obtain corresponding human body 3D distribution feature information through the two-dimensional image information and the corresponding correction scale factor; wherein the correction scale factor is acquired based on a deep neural network model.

Method 1: Train the human body front detector, side detector, and back detector by extracting the typical features of the human body (such as gradient feature, edge feature), and then apply the human body, side detector, and back detector to the scale and position space respectively. The front body image, the side body image, and the back body image of the human body are judged, and then the front body image area, the back body image area, and the side body image area in the front body image are detected. In addition, a human frontal detector can also be constructed by combining the features of the gradient direction histogram and the support vector machine.

Step S130: Determine the body parameter data of each part of the human body according to the 3D distribution feature information of the human body, and determine the physical data of the human body according to the body parameter data.

For a specific example, the body parameter data includes basic parameters and scale parameters: among them, the basic parameters include: body height, weight, arm length, leg length, shoulder width, palm size, foot size, head size, bust, waist, and hip And neck circumference data, etc.; the ratio parameters are obtained according to the basic parameters, and the ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio and head-to-shoulder ratio data.

BMI=G÷H ²

Among them, BMI is the body mass index; G is the body weight and the unit can be Kg; H is the body height and the unit can be m.

The above test parameters may include: height, weight, grip strength, blood pressure, heart rate, blood oxygen, measurements, upper and lower body ratio, head-to-body ratio, head-neck ratio and head-to-shoulder ratio, body mass index BMI (for body shape analysis), etc.

As a specific embodiment, FIG. 4 shows the second process of the embodiment of the applicant's body shape and physique data collection method.

As shown in Figure 4, the Applicant's body shape and physical data collection method further includes the following steps:

S210: Perform fingerprint collection and information entry for the person to be tested.

S220: Collect two-dimensional image information of the human body from various angles through the cooperation of the shooting device and the rotating base.

S230: Obtain the 3D distribution feature information of the human body through the above-mentioned human body two-dimensional image information and the corresponding correction scale coefficient.

S240: Determine parameter data of various parts of the human body according to the 3D distribution feature information of the human body.

S250: Obtain human body measurements, upper and lower body ratio, head to body ratio, head to neck ratio, and head to shoulder ratio data according to the parameter data.

S260: Save, analyze and process the above data to obtain the health status of the tester.

The human body shape and physique data collection method proposed in the above embodiment obtains the 3D distribution feature information of the human body through the camera and the correction ratio coefficient, and then determines the shape parameter data and physique data of each part of the human body according to the 3D distribution feature information, the body shape and the physique The data is relatively comprehensive, the test operation is simple, and the scope of application is wide.

In addition, an embodiment of the present application also proposes a computer-readable storage medium that includes a human body shape and a physical data collection program, and the following operations are implemented when the human body shape and physical data collection program is executed by a processor :

Preferably, the step of obtaining the correction scale coefficient based on a deep neural network model includes:

Create a convolutional neural network model, and initialize the parameters of the convolutional neural network model through the pre-training model;

Input the image in the human body image database into the initialized convolutional neural network model for training, extract feature information in the image, and obtain two-dimensional image data corresponding to the image;

The correction scale coefficient is obtained according to the two-dimensional image data and the corresponding size parameters of each part of the actual human body.

Preferably, the body parameter data includes basic parameters and scale parameters: wherein,

The basic parameters include: human body height, weight, arm length, leg length, shoulder width, palm size, foot size, head size, bust, waist, hip and neck data;

The ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio, and head-to-shoulder ratio data.

Preferably, the step of determining the physical data of the human body according to the physical parameter data includes:

The body mass index is obtained according to the body shape parameter data, and the calculation formula of the body mass index is:

BMI=G÷H ²

Among them, BMI is the body mass index; G is the body weight in Kg; H is the body height in m.

Preferably, the correction ratio includes a sideways correction ratio, a front correction ratio, a head correction ratio, a shoulder correction ratio, and a chest correction ratio.

The specific implementation of the computer-readable storage medium of the present application is substantially the same as the specific implementation of the above-mentioned human body shape and physical data collection method, and electronic device, and will not be repeated here.

It should be noted that in this article, the terms "including", "including" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements, It also includes other elements that are not explicitly listed, or elements inherent to the process, device, article, or method. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, device, article or method that includes the element.

The serial numbers of the foregoing embodiments of the present application are for description only, and do not represent the superiority of the embodiments. Through the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present application.

The above are only preferred embodiments of this application, and do not limit the scope of this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of this application, or directly or indirectly used in other related technical fields , The same reason is included in the scope of patent protection of this application.

Claims

A method for collecting human body shape and physical fitness data, applied to an electronic device, characterized in that the method includes:

Collecting two-dimensional image information of the human body by a photographing device, the two-dimensional image information including image information of the front, back, side, top of the head and soles of the human body;

Acquire corresponding human body 3D distribution feature information through the two-dimensional image information and the corresponding correction scale factor; wherein the correction scale factor is acquired based on a deep neural network model;

The body parameter data of each part of the human body is determined according to the 3D distribution feature information of the human body, and the body fitness data of the human body is determined according to the body parameter data.
The method for collecting human body shape and physique data according to claim 1, wherein the step of acquiring the correction scale coefficient based on a deep neural network model comprises:

Create a convolutional neural network model, and initialize the parameters of the convolutional neural network model through the pre-training model;

Input the image in the human body image database into the initialized convolutional neural network model for training, extract feature information in the image, and obtain two-dimensional image data corresponding to the image;

The correction scale coefficient is obtained according to the two-dimensional image data and the corresponding size parameters of each part of the actual human body.
The method for collecting human body shape and physique data according to claim 2, wherein the process of obtaining two-dimensional image data corresponding to the image comprises:

Take the typical characteristics of the human body and train the front detector, side detector, and back detector;

Through the front detector, side detector, and back detector, the front full body image, side full body image, and back full body image of the human body are judged respectively, and the front body image area, side full body image area and back full body image area are detected respectively ；

The two-dimensional image data is determined based on the front body image area, the side body image area, and the back body image area.
The method for collecting human body shape and physique data according to claim 3, wherein:

The typical features include: human body gradient features, edge features, and gradient direction histogram features.
The human body shape and physique data collection method according to claim 1, wherein the correction scale factor comprises a sideways correction scale factor, a front correction scale factor, a head correction scale factor, a shoulder correction scale factor, and a chest correction scale factor. coefficient;

The body parameter data includes basic parameters and proportional parameters: among them,

The basic parameters include: human body height, weight, arm length, leg length, shoulder width, palm size, foot size, head size, bust, waist, hip and neck data;

The ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio, and head-to-shoulder ratio data.
The human body shape and physique data collection method according to claim 2, wherein the correction scale factor includes a sideways correction scale factor, a front correction scale factor, a head correction scale factor, a shoulder correction scale factor, and a chest correction scale factor. coefficient;

The body parameter data includes basic parameters and proportional parameters: among them,

The basic parameters include: human body height, weight, arm length, leg length, shoulder width, palm size, foot size, head size, bust, waist, hip and neck data;

The ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio, and head-to-shoulder ratio data.
The human body shape and physique data collection method according to claim 3, wherein the correction scale factor includes a sideways correction scale factor, a front correction scale factor, a head correction scale factor, a shoulder correction scale factor, and a chest correction scale factor. coefficient;

The body parameter data includes basic parameters and proportional parameters: among them,

The basic parameters include: human body height, weight, arm length, leg length, shoulder width, palm size, foot size, head size, bust, waist, hip and neck data;

The ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio, and head-to-shoulder ratio data.
The human body shape and physique data collection method according to claim 4, wherein the correction scale factor comprises a sideways correction scale factor, a front correction scale factor, a head correction scale factor, a shoulder correction scale factor, and a chest correction scale factor. coefficient;

The body parameter data includes basic parameters and proportional parameters: among them,

The basic parameters include: human body height, weight, arm length, leg length, shoulder width, palm size, foot size, head size, bust, waist, hip and neck data;

The ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio, and head-to-shoulder ratio data.
The method for collecting human body shape and physique data according to claim 1, wherein:

The 3D distribution feature information of the human body includes three-dimensional shape information of the human body and feature points distributed on the three-dimensional shape;

The characteristic points include head vertices, hand/foot distribution points, and joint points of the human body.
An electronic device, characterized in that the electronic device includes a memory, a processor, and a photographing device, the memory includes a human body shape and a physical data collection program, and the human body shape and a physical data collection program are executed by the processor When implementing the following steps:

Collecting two-dimensional image information of the human body by a photographing device, the two-dimensional image information including image information of the front, back, side, top of the head and soles of the human body;

Acquire corresponding human body 3D distribution feature information through the two-dimensional image information and the corresponding correction scale factor; wherein the correction scale factor is acquired based on a deep neural network model;

The body parameter data of each part of the human body is determined according to the 3D distribution feature information of the human body, and the body fitness data of the human body is determined according to the body parameter data.
The electronic device according to claim 10, wherein the step of obtaining the correction scale coefficient based on a deep neural network model comprises:

Create a convolutional neural network model, and initialize the parameters of the convolutional neural network model through the pre-training model;

Input the image in the human body image database into the initialized convolutional neural network model for training, extract feature information in the image, and obtain two-dimensional image data corresponding to the image;

The correction scale coefficient is obtained according to the two-dimensional image data and the corresponding size parameters of each part of the actual human body.
The electronic device according to claim 11, wherein:

The process of obtaining two-dimensional image data corresponding to the image includes:

Take the typical characteristics of the human body and train the front detector, side detector, and back detector;

Through the front detector, side detector, and back detector, the front full body image, side full body image, and back full body image of the human body are judged respectively, and the front body image area, side full body image area and back full body image area are detected respectively ；

The two-dimensional image data is determined based on the front body image area, the side body image area, and the back body image area.
The electronic device according to claim 12, wherein:

The typical features include: human body gradient features, edge features, and gradient direction histogram features.
The electronic device according to claim 10, wherein:

The correction proportional coefficients include sideways correction proportional coefficients, front correction proportional coefficients, head correction proportional coefficients, shoulder correction proportional coefficients, and chest correction proportional coefficients;

The body parameter data includes basic parameters and proportional parameters: among them,

The basic parameters include: human body height, weight, arm length, leg length, shoulder width, palm size, foot size, head size, bust, waist, hip and neck data;

The ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio, and head-to-shoulder ratio data.
A computer non-volatile readable storage medium, wherein the computer readable storage medium includes a human body shape and a physical data collection program, and when the human body shape and a physical data collection program is executed by a processor, the following is achieved step:

Collecting two-dimensional image information of the human body by a photographing device, the two-dimensional image information including image information of the front, back, side, top of the head and soles of the human body;

Acquire corresponding human body 3D distribution feature information through the two-dimensional image information and the corresponding correction scale factor; wherein the correction scale factor is acquired based on a deep neural network model;

The body parameter data of each part of the human body is determined according to the 3D distribution feature information of the human body, and the body fitness data of the human body is determined according to the body parameter data.
The computer non-volatile readable storage medium according to claim 15, wherein the step of obtaining the correction scale factor based on a deep neural network model comprises:

Create a convolutional neural network model, and initialize the parameters of the convolutional neural network model through the pre-training model;

Input the image in the human body image database into the initialized convolutional neural network model for training, extract feature information in the image, and obtain two-dimensional image data corresponding to the image;

The correction scale coefficient is obtained according to the two-dimensional image data and the corresponding size parameters of each part of the actual human body.
The computer non-volatile readable storage medium according to claim 16, wherein the process of obtaining two-dimensional image data corresponding to the image comprises:

Take the typical characteristics of the human body and train the front detector, side detector, and back detector;

Through the front detector, side detector, and back detector, the front full body image, side full body image, and back full body image of the human body are judged respectively, and the front body image area, side full body image area and back full body image area are detected respectively ；

The two-dimensional image data is determined based on the front body image area, the side body image area, and the back body image area.
The computer non-volatile readable storage medium according to claim 17, wherein the typical characteristics include: human body gradient characteristics, edge characteristics, and gradient direction histogram characteristics.
The computer non-volatile readable storage medium according to claim 15, wherein the correction scale factor comprises a sideways correction scale factor, a frontal correction scale factor, a head correction scale factor, a shoulder correction scale factor, and a chest Correction scale factor;

The body parameter data includes basic parameters and proportional parameters: among them,

The basic parameters include: human body height, weight, arm length, leg length, shoulder width, palm size, foot size, head size, bust, waist, hip and neck data;

The ratio parameters include: upper and lower body ratio, head-body ratio, head-neck ratio, and head-to-shoulder ratio data.
The computer non-volatile readable storage medium according to claim 15, wherein the 3D distribution characteristic information of the human body includes three-dimensional shape information of the human body and characteristic points distributed on the three-dimensional shape;

The characteristic points include head vertices, hand/foot distribution points, and joint points of the human body.