Modeling method, device, system and storage medium of three-dimensional human body model

Abstract

The present application provides a modeling method, device, system and storage medium for a three-dimensional human body model. The modeling method includes: obtaining the actual human body parameters of the user, scaling the standard human body three-dimensional model according to the actual human body parameters, and obtaining an initial human body three-dimensional model that matches the human body features of the user; obtaining the human body image of the user, and determining the first distance of each pair of associated actual body surface feature points in the human body image; determining the target position of each reference body surface feature point and reference bone point in the initial human body three-dimensional model according to the first distance of each pair of associated actual body surface feature points; adjusting each reference body surface feature point and reference bone point in the initial human body three-dimensional model to the corresponding target position, and obtaining a customized three-dimensional human body model of the user. The modeling method can be executed by an electronic device by itself. Compared with manual modeling, the modeling method is fast and efficient, and the generated three-dimensional human body model has a higher matching degree with the user's body shape.

Description

Technical Field

[0001] The present application relates to the technical field of three-dimensional human body models. Specifically, the present application relates to a modeling method, device, system and storage medium for a three-dimensional human body model. Background Art

[0002] With the development of three-dimensional digital human technology, more and more industries (such as smart medical care or games) need to provide users with customized three-dimensional human models to enhance user experience.

[0003] In the prior art, a three-dimensional human body model is generally generated for a user through manual modeling. This modeling method requires a lot of manual work and has low modeling efficiency. In addition, the three-dimensional human body model generated by manual modeling has a low degree of match with the user's actual body shape features, lacks realism, and cannot significantly improve the user experience. Summary of the invention

[0004] In view of the shortcomings of existing methods, the present application proposes a modeling method, device, system and storage medium for a three-dimensional human body model to solve the technical problems of low efficiency of existing three-dimensional human body modeling methods or low matching degree between the three-dimensional human body model and the user's real body shape characteristics.

[0005] In a first aspect, the present application provides a method for modeling a three-dimensional human body model, comprising:

[0006] Acquire the actual human body parameters of the user, and scale the standard human body 3D model according to the actual human body parameters to obtain an initial human body 3D model that matches the user's human body features;

[0007] Acquire a human body image of the user, and determine a first distance between each pair of associated actual body surface feature points in the human body image;

[0008] Determine the target position of each reference body surface feature point and reference bone point in the initial human body three-dimensional model according to the first distance of each pair of associated actual body surface feature points;

[0009] Each reference body surface feature point and reference bone point in the initial human body 3D model is adjusted to the corresponding target position to obtain a user's customized 3D human body model.

[0010] In a second aspect, the present application provides a modeling device for a three-dimensional human body model, comprising:

[0011] The initial adjustment module is used to obtain the actual human body parameters of the user, and scale the standard human body 3D model according to the actual human body parameters to obtain an initial human body 3D model that matches the user's human body features;

[0012] A distance determination and adjustment module, used to obtain a human body image of a user and determine a first distance between each pair of associated actual body surface feature points in the human body image;

[0013] A point position determination module, used to determine the target position of each reference body surface feature point and reference bone point in the initial human body three-dimensional model according to the first distance of each pair of associated actual body surface feature points;

[0014] The target adjustment module is used to adjust each reference body surface feature point and reference bone point in the initial human body three-dimensional model to the corresponding target position to obtain a user's customized three-dimensional human body model.

[0015] In a third aspect, the present application provides an electronic device, including:

[0016] Processor; and

[0017] The memory is configured to store machine-readable instructions, and when the instructions are executed by the processor, the processor executes the modeling method of the three-dimensional human body model provided in the present application.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the modeling method of a three-dimensional human body model provided by the present application.

[0019] The beneficial technical effects brought about by the technical solution provided by the embodiment of the present application include:

[0020] In the embodiment of the present application, in the process of executing the modeling method of the human body model of the present application, the standard human body three-dimensional model is first used as the basis, and the standard human body three-dimensional model is automatically scaled according to the actual human body parameters of the user to generate an initial human body three-dimensional model that is similar to the user's body shape. The above steps make the positions of the feature points and bone points of the standard human body three-dimensional model match their expected target positions, reduce the amount of calculation in subsequent steps, and help to improve the processing speed.

[0021] Afterwards, the position information of the actual feature points of the user's body image is automatically identified, and the initial three-dimensional body model is adjusted more accurately based on the position information of the actual feature points of the user's body image, so that the initial three-dimensional body model is further close to the user's real body shape characteristics, and finally a customized three-dimensional body model with a higher degree of match with the user's real body shape is generated.

[0022] The above-mentioned three-dimensional human body modeling method can be executed by the electronic device itself. Compared with the manual modeling method, the modeling method of the present application is faster and more efficient, and the generated three-dimensional human body model has a higher degree of matching with the user's body shape.

[0023] Additional aspects and advantages of the present application will be partially given in the following description, which will become apparent from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0025] Figure 1 A schematic diagram of a standard three-dimensional human body model provided in an embodiment of the present application;

[0026] Figure 2 A schematic diagram of a flow chart of a method for modeling a three-dimensional human body model provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of a flow chart of another method for modeling a three-dimensional human body model provided in an embodiment of the present application;

[0028] Figure 4 A schematic diagram of the distribution of actual body surface feature points of a human body image of a user provided in an embodiment of the present application;

[0029] Figure 5 A schematic diagram of a state in which a standard three-dimensional human body model provided in an embodiment of the present application is converted into a reference three-dimensional human body model;

[0030] Figure 6 A schematic diagram of a state where a reference three-dimensional human body model provided in an embodiment of the present application is converted into a customized three-dimensional human body model;

[0031] Figure 7 A flowchart of an extended method of "calculating the spatial distance between each pair of associated actual body surface feature points B3 in a reference three-dimensional coordinate system and using the spatial distance as the first distance" provided in an embodiment of the present application;

[0032] Figure 8 A schematic diagram of a framework of a modeling device for a three-dimensional human body model provided in an embodiment of the present application;

[0033] Fig. 9 A schematic diagram of the framework of another modeling device for a three-dimensional human body model provided in an embodiment of the present application;

[0034] Fig.10 A schematic diagram of a framework of another modeling device for a three-dimensional human body model provided in an embodiment of the present application;

[0035] Fig.11 A schematic diagram of a framework of an electronic device provided in an embodiment of the present application;

[0036] Fig.12A schematic diagram of the framework of another electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The present application is described in detail below, and examples of embodiments of the present application are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar components or components with the same or similar functions. In addition, if the detailed description of the known technology is unnecessary for the features of the present application shown, it will be omitted. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0038] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0039] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0040] like Figure 1 As shown, the standard human body 3D model is a digital human body model, which includes bone points marked on the skeleton and body surface feature points marked on the surface of the human body. The bone points are generally marked on the key axis of human body movement, such as the nodes at the ends of the human skeleton, and the body surface feature points can be marked on the surface of the human body near the bone points. By changing the positions of the bone points and body surface feature points in the standard human body 3D model, the body shape (such as height, weight, and body shape), posture, and movement of the standard human body 3D model can be changed.

[0041] The initial human body 3D model and customized 3D human body model mentioned below are obtained by changing the positions of the bone points and body surface feature points in the standard human body 3D model. For the sake of distinction, the bone points and body surface feature points of the standard human body 3D model are respectively recorded as standard bone points A1 and standard body surface feature points B1; the bone points and body surface feature points of the reference human body 3D model are respectively recorded as reference bone points A2 and reference body surface feature points B2; the bone points and body surface feature points of the customized 3D human body model are respectively recorded as customized bone points A4 and customized body surface feature points B4.

[0042] The actual body surface feature points B3 in the user's body image are various position points on the body surface identified based on the user's real body image.

[0043] The electronic device 500 provided in the present application can be used as the executor of the modeling method of a three-dimensional human body model. The following content will take the electronic device 500 as an example of the executor, and the specific embodiments will explain in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems.

[0044] The present application embodiment provides a method for modeling a three-dimensional human body model, and the flow chart of the method is as follows: Figure 2 As shown, including:

[0045] S101: Acquire actual body parameters of the user.

[0046] The user's actual body parameters can represent the user's real body shape characteristics (such as height, weight, etc.), and the actual body parameters can include the user's actual height value, arm length value, leg length value, shoulder width value, chest circumference, waist circumference and hip circumference, etc.

[0047] In one embodiment of the present application, step S101 includes: obtaining the actual height value of the user as an actual human body parameter.

[0048] S102: scaling the standard human body 3D model according to actual human body parameters to obtain an initial human body 3D model that matches the user's human body features, and then executing step S105.

[0049] In step S102, the standard human body 3D model is scaled, which may be to adjust the positions of the skeleton points and body surface feature points in the standard human body 3D model, thereby changing the shape of the standard human body 3D model, thereby obtaining an initial human body 3D model.

[0050] In steps S101 and S102, the standard human body 3D model is first used as a basis, and the standard human body 3D model is automatically scaled according to the actual human body parameters of the user to generate an initial human body 3D model that is similar to the user's body shape. The above steps make the positions of the feature points and bone points of the standard human body 3D model match their expected target positions, reduce the amount of calculation in subsequent steps, and help improve the processing speed.

[0051] In one embodiment of the present application, when the actual human body parameter of the user is the actual height value, step S102 includes: determining an initial scaling ratio based on the actual height value and the defined height value of the standard human body three-dimensional model; scaling the standard human body three-dimensional model according to the initial scaling ratio to obtain an initial human body three-dimensional model that matches the user's human body height characteristics.

[0052] S103: Acquire a body image of the user.

[0053] In step S103, the user's body image may include at least one of a front image, a side image, and a back image of the user, and may also include images of the user at other angles.

[0054] S104: Determine a first distance between each pair of associated actual body surface feature points B3 in the human body image.

[0055] In one embodiment of the present application, step S104 includes: using the recognition model to identify multiple actual body surface feature points B3 in the human body image; calculating the spatial distance between each pair of associated actual body surface feature points B3 in the reference three-dimensional coordinate system, and using the spatial distance as the first distance.

[0056] It should be noted that each actual body surface feature point B3 is associated with at least one other actual body surface feature point B3. Two adjacent actual body surface feature points B3 may constitute a pair of associated actual body surface feature points B3.

[0057] by Figure 4 For example, the two actual body surface feature points B3 at the right wrist in the figure can constitute a pair of associated actual body surface feature points B3, and the spatial distance L between the two actual body surface feature points B3 can be used as the first distance between the two actual body surface feature points B3.

[0058] S105: Determine the target position of each reference body surface feature point B2 and reference bone point A2 in the initial human body three-dimensional model according to the first distance of each pair of associated actual body surface feature points B3.

[0059] In step S105, the positions of the reference surface feature points B2 and the reference bone points A2 in the initial human 3D model are further corrected based on the positions of the actual surface feature points B3 on the user's human body image to obtain the target positions of the reference surface feature points B2 and the reference bone points A2.

[0060] In one embodiment of the present application, step S105 includes:

[0061] Determine a target scaling ratio of each pair of associated reference body surface feature points B2 according to a first distance of each pair of associated actual body surface feature points B3 and a defined distance of a pair of associated reference body surface feature points B2 corresponding to each pair of associated actual body surface feature points B3;

[0062] Determine the target position of each reference body surface feature point B2 according to the target scaling ratio of each pair of associated reference body surface feature points B2;

[0063] The target position of each reference body surface feature point B2 is determined according to the target position of each reference body surface feature point B2 and the preset position conversion relationship between the reference bone point A2 and the reference body surface feature point B2.

[0064] S106: Adjust each reference body surface feature point B2 and reference bone point A2 in the initial human body three-dimensional model to a corresponding target position to obtain a customized three-dimensional human body model of the user.

[0065] In steps S103 to S106, the position information of the actual feature points of the user's body image is first automatically identified, and the initial three-dimensional human body model is adjusted more accurately based on the position information of the actual feature points of the user's body image, so that the initial three-dimensional human body model is further close to the user's real body shape features, and finally a customized three-dimensional human body model with a higher degree of match with the user's real body shape is generated, thereby improving the realism of the customized three-dimensional human body model.

[0066] In one embodiment of the present application, before step S102, the method further includes: obtaining a standard human 3D model matching the category information from a human 3D model library according to the category information of the user. The category information includes at least one of gender, race and age.

[0067] Optionally, the modeling method of a three-dimensional human body model provided in an embodiment of the present application further includes: controlling the display unit 503 to display at least one of a standard three-dimensional human body model, a human body image, an initial three-dimensional human body model, and a customized three-dimensional human body model.

[0068] Optionally, after obtaining the customized three-dimensional human body model of the user, it also includes: judging whether the preset body part of the user has an abnormal posture based on the standard posture information of the preset body part and the customized three-dimensional human body model of the user, and if so, displaying the abnormal posture information of the preset body part of the user.

[0069] In the embodiment of the present application, in the process of executing the modeling method of the human body model of the present application, the standard human body three-dimensional model is first used as the basis, and the standard human body three-dimensional model is automatically scaled according to the actual human body parameters of the user to generate an initial human body three-dimensional model that is similar to the user's body shape. The above steps make the positions of the feature points and bone points of the standard human body three-dimensional model match their expected target positions, reduce the amount of calculation in subsequent steps, and help to improve the processing speed.

[0070] Afterwards, the position information of the actual feature points of the user's body image is automatically identified, and the initial three-dimensional body model is adjusted more accurately based on the position information of the actual feature points of the user's body image, so that the initial three-dimensional body model is further close to the user's real body shape characteristics, and finally a customized three-dimensional body model with a higher degree of match with the user's real body shape is generated.

[0071] The above-mentioned three-dimensional human body modeling method can be executed by the electronic device itself. Compared with the manual modeling method, the modeling method of the present application is faster and more efficient, and the generated three-dimensional human body model has a higher degree of matching with the user's body shape.

[0072] The present application also provides another method for modeling a three-dimensional human body model. The flowchart of the method is as follows: Figure 3 As shown, including:

[0073] S201: Acquire the actual height value of the user as an actual human body parameter.

[0074] It should be noted that the user's actual body parameters can represent the user's real body shape characteristics (such as height, weight, etc.), and the actual body parameters can include the user's actual height, arm length, leg length, shoulder width, chest circumference, waist circumference and hip circumference, etc.

[0075] Since the height value is a relatively intuitive and significant body shape feature, only the actual height value is selected as the actual body parameter of the user, which can also prove that the initial human body three-dimensional model obtained in the subsequent steps is very close to the body shape feature of the user.

[0076] Optionally, the electronic device 500 has an information input unit, and the actual human body parameters (such as actual height value) of the user are input through the input unit, so that the electronic device 500 obtains the actual human body parameters of the user. The output mode supported by the information input unit of the electronic device 500 can be determined according to actual design needs, such as supporting touch input or voice input, etc. The specific type of the information input unit will be further introduced in the subsequent content.

[0077] Optionally, the electronic device 500 can be communicatively connected with other devices (such as other electronic devices 500 or servers), and the other devices store the user's actual body parameters (such as actual height value). The electronic device 500 sends a request to the other devices, and the other devices send the user's actual body parameters to the electronic device 500 according to the request, so that the electronic device 500 obtains the user's actual body parameters.

[0078] In one embodiment of the present application, before step 201, the method further includes: obtaining a standard human 3D model matching the category information from a human 3D model library according to the category information of the user. The category information includes at least one of gender, race and age.

[0079] The inventor of the present application has found that users with different category information (gender, race and age) have greatly different body shape features, so a variety of standard human 3D models can be stored in the human 3D model library, and users can be divided into different user groups according to the category information, and each user group corresponds to a standard human 3D model. Therefore, a standard human 3D model can be obtained according to the user's category information, which is more compatible with the user's body shape features, which can help reduce the amount of calculation in subsequent steps.

[0080] S202: Determine an initial scaling ratio according to the actual height value and the height value defined by the standard human three-dimensional model.

[0081] In one embodiment of the present application, assuming that the actual height of the user is 1.6 meters and the defined height of the standard human 3D model is 1.8 meters, the quotient obtained by dividing the actual height of the user by the defined height of the standard human 3D model is approximately equal to 0.89, so 0.89 can be used as the initial scaling ratio. Of course, other calculation methods can also be used to calculate the actual height of the user and the defined height of the standard human 3D model to obtain the initial scaling ratio.

[0082] Optionally, in step S201 and / or step S202, the display unit 503 of the electronic device 500 may display a standard human body three-dimensional model.

[0083] S203: scaling the standard human body three-dimensional model according to the initial scaling ratio to obtain an initial human body three-dimensional model that matches the user's body height characteristics, and then executing step S207.

[0084] like Figure 4 As shown, scaling the standard human body 3D model can be performed by adjusting the positions of the skeletal points and body surface feature points in the standard human body 3D model, thereby changing the body shape of the standard human body 3D model, thereby obtaining an initial human body 3D model. When the actual height value of the user is used as an actual human body parameter, the defined height value of the initial human body 3D model should be consistent with the actual height value of the user.

[0085] In one embodiment of the present application, step S203 includes:

[0086] (a1) According to the initial scaling ratio, the distance between adjacent standard body surface feature points B1 and the distance between adjacent standard bone points A1 in the standard human body three-dimensional model are scaled.

[0087] (a2) The scaled standard human body 3D model is used as the initial human body 3D model, so that the standard body surface feature point B1 becomes the reference body surface feature point B2, and the standard bone point A1 becomes the standard bone point A1.

[0088] In the process of executing steps S201 and S203, the standard human body three-dimensional model is firstly used as the basis, and the standard human body three-dimensional model is automatically scaled according to the height value of the user to generate an initial human body three-dimensional model that is similar to the user's body shape. Since the height value is a relatively intuitive and significant body shape feature, only the actual height value is selected as the actual body parameter of the user, which can also prove that the initial human body three-dimensional model obtained in the subsequent steps is very close to the body shape feature of the user, which can reduce the type and number of actual body parameters that need to be obtained, and the positions of the reference body surface feature points and reference bone points of the initial human body three-dimensional model are more precisely the expected target positions, which reduces the amount of calculation in the subsequent steps and helps to improve the processing speed.

[0089] Optionally, in step S203, the display unit 503 of the electronic device 500 may display the standard human body 3D model and the initial human body 3D model.

[0090] S204: Acquire a human body image of the user.

[0091] In one embodiment of the present application, the electronic device 500 obtains the front view, side view and back view of the user's body.

[0092] Optionally, the electronic device 500 has a camera function. When executing step S204, the electronic device 500 turns on the camera function to shoot the user and obtains the user's body image.

[0093] Optionally, the electronic device 500 stores a body image of the user in advance, and when executing step S103 , the electronic device 500 directly calls the body image of the user.

[0094] Optionally, the electronic device 500 can be communicatively connected with other devices (such as other electronic devices 500 or servers), and the other devices store the user's body image. The electronic device 500 sends a request to the other devices, and the other devices send the user's body image stored to the electronic device 500 based on the request, so that the electronic device 500 obtains the user's body image.

[0095] Optionally, during step S204, the display unit 503 of the electronic device 500 may display the user's human body image, and may also simultaneously display the initial 22 human body three-dimensional model.

[0096] S205: Using the recognition model to identify multiple actual body surface feature points B3 in the human body image.

[0097] like Figure 5 As shown, a plurality of actual body surface feature points B3 in the human body image can be represented by circles in the figure.

[0098] The recognition model has the function of image recognition, which can process, analyze and understand images to identify targets and objects of various different patterns.

[0099] The recognition model in this field can be trained by machine learning. The training process can generally include: preparing a large number of (e.g., 100,000) human body images in advance, manually marking the actual body surface feature points B3 of each human body image, and training a neural network by identifying the actual body surface feature points B3 of a large number of human body images. The specific training process will not be repeated here.

[0100] S206: Calculate the spatial distance between each pair of associated actual body surface feature points B3 in the reference three-dimensional coordinate system, and use the spatial distance as the first distance.

[0101] In the embodiment of the present application, the reference three-dimensional coordinate system can be defined according to actual needs, and the world coordinate system or the local coordinate system can also be used as the reference three-dimensional coordinate system. The first distance of each pair of associated actual body surface feature points B3 is actually the actual distance of each pair of associated actual body surface feature points B3 on the user's real body.

[0102] S207: Determine a target scaling ratio of each pair of associated reference body surface feature points B2 according to the first distance of each pair of associated actual body surface feature points B3 and the defined distance of a pair of associated reference body surface feature points B2 corresponding to each pair of associated actual body surface feature points B3.

[0103] Take a pair of associated actual body surface feature points B3 at the right wrist of the user's human body image as an example. The pair of associated actual body surface feature points B3 at the right wrist of the user's human body image corresponds to a pair of associated reference body surface feature points B2 at the right wrist of the initial human 3D model.

[0104] Assume that the first distance between a pair of associated actual body surface feature points B3 at the right wrist of the user's human body image is 0.05 meters, and the defined distance between a pair of associated reference body surface feature points B2 at the right wrist of the initial human body three-dimensional model is 0.06 meters. After dividing the first distance by the defined distance, the quotient obtained is approximately equal to 0.83, so 0.83 can be used as the target scaling ratio. Of course, other calculation methods can also be used to calculate the first distance and the defined distance to obtain the target scaling ratio.

[0105] S208: Determine the target position of each reference body surface feature point B2 according to the target scaling ratio of each pair of associated reference body surface feature points B2.

[0106] It should be noted that both the standard human body three-dimensional model and the initial human body three-dimensional model are established in a virtual three-dimensional coordinate system. The coordinates of the reference body surface feature point B2 and the reference body bone point in the initial human body three-dimensional model in the virtual three-dimensional coordinate system are known, and the positions of the reference body surface feature point B2 and the reference body bone point can be expressed by coordinates.

[0107] Taking a pair of associated reference body surface feature points B2 at the right wrist of the initial human body three-dimensional model as an example, assuming that the definition distance of the pair of associated reference body surface feature points B2 is 0.06 meters as mentioned above, and the target scaling ratio is 0.83. Determining the target position of a pair of associated reference body surface feature points B2 at the right wrist of the initial human body three-dimensional model is actually to determine the new coordinates of the pair of reference body surface feature points B2, so that the distance between the pair of reference body surface feature points B2 with the new coordinates is shortened to 0.83 times of the original distance, and the position represented by the new coordinates of each reference body surface feature point B2 is used as the target position.

[0108] S209: Determine the target position of each reference bone point A2 according to the target position of each reference body surface feature point B2 and the preset position conversion relationship between the reference bone point A2 and the reference body surface feature point B2.

[0109] A reference body surface feature point B2 is arranged near each reference bone point A2. In the virtual three-dimensional coordinate system, there is a preset conversion relationship between the coordinates of the reference bone point A2 and the coordinates of the reference body surface feature point B2.

[0110] According to the new coordinates of the reference body surface feature point B2 in the virtual three-dimensional coordinate system determined in the above steps, the new coordinates of the reference bone point A2 in the virtual three-dimensional coordinate system are determined, and the position represented by the new coordinates of the reference bone point A2 in the virtual three-dimensional coordinate system is used as the target position.

[0111] In one embodiment of the present application, step S209 includes: determining the center point position of the two reference bone points A2 on both sides of each reference bone point A2 based on the target positions of the two reference bone points A2 on both sides of each reference bone point A2, and using the center point position as the target position of each reference bone point A2.

[0112] At least two reference body surface feature points B2 are arranged near each reference bone point A2, two of which are symmetrically distributed on both sides of the reference body surface feature point B2.

[0113] For a reference bone point A2, the coordinates of the center points of the two symmetrical reference surface feature points B2 on both sides of the reference bone point A2 in the virtual three-dimensional coordinate system are determined, and the position represented by the coordinates of the center points in the virtual three-dimensional coordinate system is taken as the target position of a reference bone point A2.

[0114] Optionally, in at least one of steps S204 to S209 , the display unit 503 of the electronic device 500 may display the user's body image and / or actual body surface feature points B3 on the body image.

[0115] Optionally, in at least one of steps S204 to S209 , the display unit 503 of the electronic device 500 may display an initial three-dimensional human body model.

[0116] S210: Adjust each reference body surface feature point B2 and reference bone point A2 in the initial human body three-dimensional model to a corresponding target position to obtain a customized three-dimensional human body model of the user.

[0117] like Figure 6 As shown, each reference body surface feature point B2 and reference bone point A2 in the initial three-dimensional human body model is adjusted to the corresponding target position to obtain a customized body surface feature point B4 and a customized reference bone point A4 in the customized three-dimensional human body model.

[0118] In steps S208 and S209, the coordinates of the target positions of the reference body surface feature points B2 and the reference bone points A2 of the initial human body three-dimensional model in the virtual three-dimensional coordinate system have been determined. In step S210, the current coordinates of each reference body surface feature point B2 and the reference bone point A2 are adjusted to the coordinates of the corresponding target position, so that each reference body surface feature point B2 and the reference bone point A2 are moved to the corresponding target position.

[0119] Optionally, in step S205, the display unit 503 of the electronic device 500 may display the initial three-dimensional human body model and the customized three-dimensional human body model.

[0120] In the process of executing steps S204 to S210, the position information of the actual feature points of the user's body image is first automatically identified, and the positions of the reference surface feature points and reference bone points of the initial human three-dimensional model are adjusted more accurately based on the position information of the actual feature points of the user's body image, so that the initial three-dimensional human body model is further close to the user's real body shape features, and finally a customized three-dimensional human body model with a higher degree of match with the user's real body shape is generated, thereby improving the realism of the customized three-dimensional human body model.

[0121] After step S210 is executed, the modeling method of the three-dimensional human body model provided in the embodiment of the present application can be ended, or, after step S210 is executed, step S211 is continued to be executed.

[0122] S211: judging whether the preset body part of the user has an abnormal posture according to the standard posture information of the preset body part and the customized three-dimensional human body model of the user, and if so, displaying the abnormal posture information of the preset body part of the user.

[0123] It should be noted that the preset body parts include at least the head, back, shoulders, spine, pelvis, legs and knees, etc. Abnormal postures include at least forward head tilt, side head tilt, hunchback, uneven shoulders, scoliosis, pelvic tilt, knee hyperextension, O-shaped legs, X-shaped legs, etc.

[0124] Taking the preset body part as the spine as an example, based on the standard spine information of the spine and the user's customized three-dimensional human body model, it is determined whether the user's spine has a scoliosis problem. If so, the scoliosis information of the user's spine is displayed. The scoliosis information can be the severity level of scoliosis, the scoliosis angle information of the scoliosis, etc.

[0125] Taking the preset body part as the shoulder as an example, based on the standard posture information of the shoulder and the user's customized 3D human body model, it is determined whether the user's two shoulders have uneven shoulders. If so, the uneven shoulder information of the user's shoulders is displayed. The uneven shoulder information can include the severity level of the uneven shoulders, the tilt angle information of the uneven shoulder information, etc.

[0126] In one embodiment of the present application, the method of displaying abnormal body posture information of a preset body part of the user may at least include: the electronic device 500 displays the abnormal body posture information in the form of pictures and texts, and the electronic device 500 plays the abnormal body posture information in the form of voice.

[0127] Optionally, when the electronic device 500 displays the abnormal posture information in the form of graphics and text, the abnormal posture information and the customized three-dimensional human body model can be displayed on the same interface. For example, the abnormal posture information is displayed around the customized three-dimensional human body model.

[0128] Optionally, when the electronic device 500 displays the abnormal posture information in the form of graphics and text, the abnormal posture information can also be displayed separately in an interface.

[0129] It should be noted that the process of determining whether other preset body parts have abnormal posture may be similar to the above-mentioned determination principle of the spine and shoulders, and will not be described in detail here.

[0130] This application uses a customized three-dimensional human body model to characterize the characteristics of the user's real body, and identifies whether the user has an abnormal posture by judging whether the customized three-dimensional human body model has an abnormal posture. The detection process can be completed by the electronic device 500 itself, and the detection of abnormal posture can be completed without the participation of professionals, which is conducive to the promotion and use of technology. The detection operation of the electronic device 500 can improve the detection efficiency of abnormal posture, reduce the interference of subjective factors in the process of manual detection of abnormal posture, and help improve the detection accuracy.

[0131] In one embodiment of the present application, step S211 includes:

[0132] (b1) Compare the standard positional relationship between the surface feature points and / or bone points in the preset body part with the actual positional relationship between the customized surface feature points B4 and / or customized bone points A4 in the user's customized three-dimensional human body model to obtain a first comparison result.

[0133] The standard posture information of the preset body part may include the standard position relationship between the body surface feature points and / or bone points in the preset body part in step (b1).

[0134] Taking the preset body part as the spine as an example, the standard posture information of the spine may be the standard positional relationship between the bone points in the spine.

[0135] Specifically, the standard positional relationship between the skeletal points in the spine can be reflected by the bending angle of the line connecting the skeletal points in the spine. The bending angle of the line connecting the skeletal points in the standard spine can be recorded as the standard spine bending angle, and the standard spine bending angle can be used as the standard posture information of the spine. The standard spine bending angle can be an angle range or a specific angle value.

[0136] The bending angle of the line connecting the bone points in the standard spine is compared with the bending angle of the line connecting the customized bone points A4 in the spine in the user's customized three-dimensional human body model to obtain a first comparison result.

[0137] (b2) determining whether a preset body part of the user has an abnormal posture according to the first comparison result.

[0138] Taking the preset body part as the spine as an example, if the first comparison result is "the bending angle of the line connecting the customized bone point A4 in the spine in the user's customized three-dimensional human body model exceeds the range of the standard spine bending angle", it is determined that the user's spine has a scoliosis problem; if the first comparison result is "the bending angle of the line connecting the customized bone point A4 in the spine in the user's customized three-dimensional human body model does not exceed the range of the standard spine bending angle", it is determined that the user's spine does not have a scoliosis problem.

[0139] In one embodiment of the present application, after determining that the user's preset body part has an abnormal posture according to the first comparison result, the severity level of the abnormal posture of the preset body part can be further determined. For example, the bending angle of the line connecting the customized bone points A4 in the spine of the user's customized three-dimensional human body model is subtracted from the standard spine bending angle, and the severity level of scoliosis is determined according to the difference obtained.

[0140] The above steps (b1) and (b2) mainly take the spine as an example to provide a more specific and exemplary introduction to the process of determining whether a preset body part has a posture abnormality. The process of determining whether other preset body parts have a posture abnormality can be similar to the above-mentioned principle of determining the spine, and will not be repeated here.

[0141] After step S211 is executed, the modeling method of the three-dimensional human body model provided in the embodiment of the present application can be ended, or, after step S211 is executed, step S212 is continued to be executed.

[0142] S212: Displaying corresponding health advice information according to the preset body part of the user with abnormal posture and abnormal posture information.

[0143] In one embodiment of the present application, health advice information is pre-stored in the advice information library, and a mapping relationship is established between preset body parts and the health advice information. When it is determined that a preset body part of the user has an abnormal posture, the corresponding health advice information is called from the advice information library according to the mapping relationship and displayed through the electronic device 500.

[0144] In one embodiment of the present application, the severity level of the abnormal posture of the preset body part can also be determined. The preset body part, the severity level of the abnormal posture and the health advice information have a mapping relationship. When it is determined that a preset body part of the user has an abnormal posture and the severity level of the abnormal posture, the corresponding health advice information is called in the advice information library according to the mapping relationship and displayed through the electronic device 500.

[0145] In one embodiment of the present application, the method of displaying the health advice information may at least include: the electronic device 500 displays the health advice information in the form of pictures and texts, and the electronic device 500 plays the health advice information in the form of voice.

[0146] Optionally, when the electronic device 500 displays the health advice information in the form of graphics and text, the health advice information and the customized three-dimensional human body model can be displayed on the same interface. For example, the health advice information is displayed around the customized three-dimensional human body model.

[0147] Optionally, when the electronic device 500 displays abnormal body posture information in the form of graphics and text, it can also display the health advice information separately in an interface.

[0148] The present application embodiment further provides an extended method of step S206 (i.e., calculating the spatial distance between each pair of associated actual body surface feature points B3 in the reference three-dimensional coordinate system). The flow chart of the extended method is shown in FIG. Figure 7 As shown, including:

[0149] S301: Determine the position of each actual body surface feature point B3 in the reference plane coordinate system.

[0150] A reference plane coordinate system may be established in the two-dimensional plane where the user's human body image is located, and the position of each actual body surface feature point B3 in the reference plane coordinate system may be represented by a two-dimensional coordinate.

[0151] S302: Convert the position of each actual body surface feature point B3 in the reference plane coordinate system into the position of each actual body surface feature point B3 in the reference three-dimensional coordinate system.

[0152] In one embodiment of the application, step S302 includes:

[0153] (b1) Determine a reference distance based on the user's actual body parameters.

[0154] In one embodiment of the present application, the actual height of the user is used as the actual parameter of the human body, and the reference distance is determined according to the actual height.

[0155] (b2) Determine the position of each actual body surface feature point B3 in the reference three-dimensional coordinate system based on the reference distance and the position of each actual body surface feature point B3 in the reference plane coordinate system.

[0156] The two-dimensional coordinate representation of the position of each actual body surface feature point B3 in the reference plane coordinate system can be converted into the coordinates of each actual body surface feature point B3 in the reference three-dimensional coordinate system according to the reference distance.

[0157] S303: Calculate the spatial distance between each pair of associated actual body surface feature points B3 in the reference three-dimensional coordinate system according to the position of each actual body surface feature point B3 in the reference three-dimensional coordinate system.

[0158] The position of the actual body surface feature point B3 in the reference three-dimensional plane coordinate system can be represented by the three-dimensional coordinates of the actual body surface feature point B3 in the reference three-dimensional plane coordinate system. According to the three-dimensional coordinates of each pair of associated actual body surface feature points B3 in the reference three-dimensional coordinate system, the spatial distance between the two actual body surface feature points B3 in the reference three-dimensional coordinate system can be calculated.

[0159] Based on the same inventive concept, the embodiment of the present application also provides a modeling device 400 for a three-dimensional human body model. The structural framework diagram of the modeling device 400 is shown in FIG. Figure 8 As shown, it includes an initial adjustment module 401 , a distance determination adjustment module 402 , a point determination module 403 and a target adjustment module 404 .

[0160] The initial adjustment module 401 is used to obtain the actual human body parameters of the user, and scale the standard human body 3D model according to the actual human body parameters to obtain an initial human body 3D model that matches the user's human body features.

[0161] The distance determination and adjustment module 402 is used to obtain a human body image of the user and determine a first distance between each pair of associated actual body surface feature points B3 in the human body image.

[0162] The point position determination module 403 is used to determine the target position of each reference body surface feature point B2 and reference bone point A2 in the initial human body three-dimensional model according to the first distance of each pair of associated actual body surface feature points B3.

[0163] The target adjustment module 404 is used to adjust each reference body surface feature point B2 and reference bone point A2 in the initial human body three-dimensional model to a corresponding target position to obtain a customized three-dimensional human body model of the user.

[0164] In one embodiment of the present application, the initial adjustment module 401 is also used to: obtain the actual height value of the user as an actual human body parameter; determine the initial scaling ratio based on the actual height value and the defined height value of the standard human body three-dimensional model; scale the standard human body three-dimensional model according to the initial scaling ratio to obtain an initial human body three-dimensional model that matches the user's human body height characteristics.

[0165] In one embodiment of the present application, the initial adjustment module 401 is also used to: scale the distance between adjacent standard body surface feature points B1 and the distance between adjacent standard bone points A1 in the standard human three-dimensional model according to the initial scaling ratio; use the scaled standard human three-dimensional model as the initial human three-dimensional model, so that the standard body surface feature point B1 becomes the reference body surface feature point B2, and the standard bone point A1 becomes the standard bone point A1.

[0166] In one embodiment of the present application, the initial adjustment module 401 is also used to: before scaling the standard human body three-dimensional model according to actual human body parameters, obtain a standard human body three-dimensional model that matches the category information in the human body three-dimensional model library according to the user's category information; the category information includes at least one of gender, race and age.

[0167] In one embodiment of the present application, the distance determination and adjustment module 402 is also used to: use the recognition model to identify multiple actual body surface feature points B3 in the human body image; calculate the spatial distance between each pair of associated actual body surface feature points B3 in the reference three-dimensional coordinate system, and use the spatial distance as the first distance.

[0168] In one embodiment of the present application, the distance determination and adjustment module 402 is also used to: determine the position of each actual body surface feature point B3 in the reference plane coordinate system; convert the position of each actual body surface feature point B3 in the reference plane coordinate system into the position of each actual body surface feature point B3 in the reference three-dimensional coordinate system; and calculate the spatial distance in the reference three-dimensional coordinate system of each pair of associated actual body surface feature points B3 based on the position of each actual body surface feature point B3 in the reference three-dimensional coordinate system.

[0169] In one embodiment of the present application, the distance determination and adjustment module 402 is also used to: determine a reference distance based on the actual body parameters of the user; determine the position of each actual body surface feature point B3 in the reference three-dimensional coordinate system based on the reference distance and the position of each actual body surface feature point B3 in the reference plane coordinate system.

[0170] In one embodiment of the present application, the point position determination module 403 is also used to: determine the target scaling ratio of each pair of associated reference surface feature points B2 based on the first distance of each pair of associated actual surface feature points B3 and the defined distance of a pair of associated reference surface feature points B2 corresponding to each pair of associated actual surface feature points B3; determine the target position of each reference surface feature point B2 based on the target scaling ratio of each pair of associated reference surface feature points B2; determine the target position of each reference surface feature point A2 based on the target position of each reference surface feature point B2 and the preset position conversion relationship between the reference bone point A2 and the reference surface feature point B2.

[0171] In one embodiment of the present application, the point position determination module 403 is also used to: determine the center point position of the two reference bone points A2 on both sides of each reference bone point A2 according to the target positions of the two reference bone points A2 on both sides of each reference bone point A2, and use the center point position as the target position of each reference bone point A2.

[0172] The present application embodiment also provides another modeling device 400 for a three-dimensional human body model. The structural framework diagram of the modeling device 400 is shown in FIG. Fig. 9 As shown, in addition to the above-mentioned initial adjustment module 401, distance determination adjustment module 402, point determination module 403 and target adjustment module 404, it also includes a display execution module 405. The display execution module 405 is used to control the display unit 503 to display at least one of the standard human body 3D model, human body image, initial human body 3D model and customized 3D human body model.

[0173] The present application embodiment also provides another modeling device 400 for a three-dimensional human body model. The structural framework diagram of the modeling device 400 is shown in FIG. Fig.10 As shown, in addition to the above-mentioned initial adjustment module 401, distance determination adjustment module 402, point determination module 403, target adjustment module 404 and display execution module 405, it also includes an abnormal posture determination module 406.

[0174] The abnormal posture determination module 406 is used to determine whether the user's preset body part has an abnormal posture based on the standard posture information of the preset body part and the user's customized three-dimensional human body model, and if so, display the abnormal posture information of the user's preset body part.

[0175] The abnormal posture determination module 406 is also used to compare the standard position relationship between the surface feature points and / or bone points in the preset body part with the actual position relationship between the customized surface feature points B4 and / or customized bone points A4 in the user's customized three-dimensional human body model to obtain a first comparison result, and determine whether the preset body part of the user has an abnormal posture based on the first comparison result.

[0176] The abnormal posture determination module 406 is further used to display corresponding health advice information according to the preset body parts of the user with abnormal posture and abnormal posture information.

[0177] The modeling device 400 of the three-dimensional human body model provided in the embodiment of the present application has the same inventive concept and the same beneficial effects as the modeling method of the three-dimensional human body model in the previous embodiments. The contents not shown in detail in the modeling device 400 of the three-dimensional human body model can be referred to the previous embodiments and will not be repeated here.

[0178] Based on the same inventive concept, the embodiment of the present application further provides an electronic device 500, the structural framework diagram of the electronic device 500 is as shown in FIG. Fig.11 As shown, it includes a processor 501 and a memory 502 .

[0179] The memory 502 is configured to store machine-readable instructions. When the instructions are executed by the processor 501, the processor 501 executes any one of the three-dimensional human body modeling methods provided in the above embodiments of the present application.

[0180] Optionally, the electronic device 500 further includes a bus and a communication unit, and the processor 501, the memory 502 and the communication unit are all electrically connected to the bus.

[0181] Processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0182] The memory 502 can be a ROM (Read-Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (random access memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0183] The bus may include a path to transmit information between the above components. The bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The communication unit may be used to receive and send signals.

[0184] The present application embodiment also provides another electronic device 500. The structural framework diagram of the electronic device 500 is shown in FIG. Fig.12 As shown, in addition to the above-mentioned processor 501 , memory 502 , bus and communication unit, it also includes a display unit 503 .

[0185] The display unit 503 is electrically connected to the processor 501 , and is used to display at least one of a standard three-dimensional human body model, a human body image, an initial three-dimensional human body model, and a customized three-dimensional human body model.

[0186] The display unit 503 may also be used to display information input by the user or information provided to the user and various menus of the electronic device 500. The display unit 503 may include a display panel, and optionally, the display panel may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0187] Optionally, the electronic device 500 has an information input unit, and the actual human body parameters (such as actual height value) of the user are input through the input unit, so that the electronic device 500 obtains the actual human body parameters of the user. The output mode supported by the information input unit of the electronic device 500 can be determined according to actual design needs, such as supporting touch input or voice input, etc. The specific type of the information input unit will be further introduced in the subsequent content.

[0188] The information input unit of the electronic device 500 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the electronic device 500. Specifically, the input unit may include a touch panel and other input devices. The touch panel, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on or near the touch panel using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel may include a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 501, and can receive and execute commands sent by the processor 501. In addition, the touch panel can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel, the input unit may also include other input devices. Specifically, other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and a microphone.

[0189] The electronic device provided in the embodiments of the present application may be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), or other electronic devices. The embodiments of the present application do not impose any restrictions on the specific type of the display device.

[0190] The electronic device 500 provided in the embodiment of the present application has the same inventive concept and the same beneficial effects as the modeling method of the three-dimensional human body model in the previous embodiments. The contents not shown in detail in the electronic device 500 can be referred to the previous embodiments and will not be repeated here.

[0191] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor 501, the modeling method of the three-dimensional human body model provided in the above embodiments of the present application is implemented.

[0192] The computer readable medium includes, but is not limited to, any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM, RAM, EPROM (Erasable Programmable Read-Only Memory), EEPROM, flash memory, magnetic card or optical card. In other words, the readable medium includes any medium that can store or transmit information in a readable form by a device (e.g., a computer).

[0193] The computer-readable storage medium provided in the embodiment of the present application has the same inventive concept and the same beneficial effects as the modeling method of the three-dimensional human body model in the previous embodiments. The contents not shown in detail in the computer-readable storage medium can be referred to the previous embodiments and will not be repeated here.

[0194] The application of the embodiments of the present application has at least the following beneficial effects:

[0195] 1. In the embodiment of the present application, in the process of executing the modeling method of the human body model of the present application, the standard human body three-dimensional model is first used as the basis, and the standard human body three-dimensional model is automatically scaled according to the actual human body parameters of the user to generate an initial human body three-dimensional model that is similar to the user's body shape. The above steps make the positions of the feature points and bone points of the standard human body three-dimensional model match their expected target positions, reduce the amount of calculation in subsequent steps, and help to improve the processing speed.

[0196] Afterwards, the position information of the actual feature points of the user's body image is automatically identified, and the initial three-dimensional body model is adjusted more accurately based on the position information of the actual feature points of the user's body image, so that the initial three-dimensional body model is further close to the user's real body shape characteristics, and finally a customized three-dimensional body model with a higher degree of match with the user's real body shape is generated.

[0197] The above-mentioned three-dimensional human body modeling method can be executed by the electronic device itself. Compared with the manual modeling method, the modeling method of the present application is faster and more efficient, and the generated three-dimensional human body model has a higher degree of matching with the user's body shape.

[0198] 2. In the embodiment of the present application, a customized three-dimensional human body model is used to represent the characteristics of the user's real body. By judging whether the customized three-dimensional human body model has an abnormal posture, it is possible to identify whether the user has an abnormal posture. The detection process can be completed by the electronic device itself, and the detection of abnormal posture can be completed without the participation of professionals, which is conducive to the promotion and use of technology. The detection operation of the electronic device can improve the detection efficiency of abnormal posture, reduce the interference of subjective factors in the process of manual detection of abnormal posture, and help improve the detection accuracy.

[0199] Those skilled in the art will appreciate that the various operations, methods, steps, measures, and schemes in the processes discussed in this application may be alternated, altered, combined, or deleted. Further, other steps, measures, and schemes in the various operations, methods, and processes discussed in this application may also be alternated, altered, rearranged, decomposed, combined, or deleted. Further, the steps, measures, and schemes in the prior art that are similar to those disclosed in this application may also be alternated, altered, rearranged, decomposed, combined, or deleted.

[0200] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0201] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0202] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for modeling a three-dimensional human body model, characterized in that: include: Acquire actual human body parameters of the user, and scale the standard human body three-dimensional model according to the actual human body parameters to obtain an initial human body three-dimensional model that matches the human body features of the user; Acquire a human body image of the user, and determine a first distance between each pair of associated actual body surface feature points in the human body image; Determining the target position of each reference body surface feature point and reference bone point in the initial human body three-dimensional model according to the first distance of each pair of associated actual body surface feature points; Each of the reference body surface feature points and reference bone points in the initial human body three-dimensional model is adjusted to a corresponding target position to obtain a customized three-dimensional human body model of the user.

2. The modeling method according to claim 1, characterized in that: The step of determining a first distance between each pair of associated actual body surface feature points in the human body image comprises: Identifying a plurality of actual body surface feature points in the human body image using a recognition model; The spatial distance between each pair of associated actual body surface feature points in the reference three-dimensional coordinate system is calculated, and the spatial distance is used as the first distance.

3. The modeling method according to claim 2, characterized in that: The calculating of the spatial distance between each pair of associated actual body surface feature points in the reference three-dimensional coordinate system comprises: Determine the position of each actual body surface feature point in the reference plane coordinate system; Converting the position of each actual body surface feature point in the reference plane coordinate system into the position of each actual body surface feature point in the reference three-dimensional coordinate system; According to the position of each actual body surface feature point in the reference three-dimensional coordinate system, the spatial distance in the reference three-dimensional coordinate system of each pair of associated actual body surface feature points is calculated.

4. The modeling method according to claim 3, characterized in that: Converting the position of each actual body surface feature point in the reference plane coordinate system into the position of each actual body surface feature point in the reference three-dimensional coordinate system includes: Determine a reference distance according to actual body parameters of the user; The position of each actual body surface feature point in the reference three-dimensional coordinate system is determined according to the reference distance and the position of each actual body surface feature point in the reference plane coordinate system.

5. The modeling method according to claim 1, characterized in that: Determining the target position of each reference body surface feature point and reference bone point in the initial human body three-dimensional model according to the first distance of each pair of associated actual body surface feature points includes: Determining a target scaling ratio of each pair of associated reference body surface feature points according to a first distance of each pair of associated actual body surface feature points and a defined distance of a pair of associated reference body surface feature points corresponding to each pair of associated actual body surface feature points; Determining a target position of each reference body surface feature point according to a target scaling ratio of each pair of associated reference body surface feature points; The target position of each reference body surface feature point is determined according to the target position of each reference body surface feature point and the preset position conversion relationship between the reference bone point and the reference body surface feature point.

6. The modeling method according to claim 5, characterized in that: The step of determining the target position of each reference bone point according to the target position of each reference body surface feature point and the preset position conversion relationship between the reference bone point and the reference body surface feature point comprises: According to the target positions of the two reference bone points on both sides of each reference bone point, the center point position of the two reference bone points on both sides of each reference bone point is determined, and the center point position is used as the target position of each reference bone point.

7. The modeling method according to claim 1, characterized in that: The obtaining of the actual human body parameter of the user includes: obtaining the actual height value of the user as the actual human body parameter; The method of scaling the standard human body three-dimensional model according to the actual parameters of the human body to obtain an initial human body three-dimensional model that matches the human body characteristics of the user includes: determining an initial scaling ratio according to the actual height value and the defined height value of the standard human body three-dimensional model; and scaling the standard human body three-dimensional model according to the initial scaling ratio to obtain an initial human body three-dimensional model that matches the human body height characteristics of the user.

8. The modeling method according to claim 7, characterized in that: The step of scaling the standard human body three-dimensional model according to the initial scaling ratio to obtain an initial human body three-dimensional model that matches the human body height feature of the user includes: According to the initial scaling ratio, scaling the distances between adjacent standard body surface feature points and the distances between adjacent standard bone points in the standard human body three-dimensional model; The scaled standard human body three-dimensional model is used as the initial human body three-dimensional model, so that the standard body surface feature points become the reference body surface feature points, and the standard skeleton points become the standard skeleton points.

9. The modeling method according to claim 1, characterized in that: Before scaling the standard human body three-dimensional model according to the actual human body parameters, the method further includes: According to the category information of the user, acquiring the standard human body three-dimensional model matching the category information in a human body three-dimensional model library; The category information includes at least one of gender, race and age.

10. The modeling method according to claim 1, characterized in that: Also includes: The display unit is controlled to display at least one of the standard three-dimensional human body model, the human body image, the initial three-dimensional human body model and the customized three-dimensional human body model.

11. The modeling method according to claim 1, characterized in that: After obtaining the customized three-dimensional human body model of the user, the method further includes: According to the standard posture information of the preset body part and the customized three-dimensional human body model of the user, it is determined whether the preset body part of the user has an abnormal posture. If so, the abnormal posture information of the preset body part of the user is displayed.

12. The modeling method according to claim 11, characterized in that: The determining, based on the standard posture information of the preset body part and the customized three-dimensional human body model of the user, whether the preset body part of the user has an abnormal posture includes: Comparing the standard positional relationship between the body surface feature points and / or the bone points in the preset body part with the actual positional relationship between the customized body surface feature points and / or the customized bone points in the customized three-dimensional human body model of the user to obtain a first comparison result; It is determined whether a preset body part of the user has an abnormal posture according to the first comparison result.

13. The modeling method according to claim 11, characterized in that: After displaying the abnormal posture information of the preset body part of the user, the method further includes: According to the preset body parts of the user with abnormal posture and abnormal posture information, corresponding health advice information is displayed.

14. A three-dimensional human body modeling device, characterized in that: include: An initial adjustment module, used to obtain actual human body parameters of the user, and scale the standard human body three-dimensional model according to the actual human body parameters to obtain an initial human body three-dimensional model that matches the human body features of the user; A distance determination and adjustment module, configured to obtain a human body image of the user and determine a first distance between each pair of associated actual body surface feature points in the human body image; A point determination module, used to determine the target position of each reference body surface feature point and reference bone point in the initial human body three-dimensional model according to the first distance of each pair of associated actual body surface feature points; The target adjustment module is used to adjust each of the reference body surface feature points and reference bone points in the initial human body three-dimensional model to a corresponding target position to obtain a customized three-dimensional human body model of the user.

15. An electronic device, characterized in that: include: processor; as well as The memory is configured to store machine-readable instructions, and when the instructions are executed by the processor, the processor executes the modeling method of the three-dimensional human body model according to any one of claims 1 to 13.

16. The electronic device according to claim 15, characterized in that: Also includes: The display unit is electrically connected to the processor and is used to display at least one of a standard three-dimensional human body model, a human body image, an initial three-dimensional human body model and a customized three-dimensional human body model.

17. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium is characterized in that when the computer program is executed by a processor, the method for modeling a three-dimensional human body model as described in any one of claims 1 to 13 is implemented.

Images