A method, system, device and storage medium for constructing a human body model

Abstract

The present invention relates to the technical field of human body modeling, and provides a method, a system, a device and a storage medium for constructing a human body model. The method includes: when the user to be modeled enters the first preset position, invoking the first image sensor array to collect the first image acquisition result; performing clustering analysis on the user to be modeled to obtain the clustering result of the modeling area; traversing the clustering result of the modeling area and invoking the first image acquisition result to obtain the outer frame modeling result; reminding the user to be modeled to enter the second preset position, invoking the second image sensor array to collect the second image acquisition result; traversing the clustering result of the modeling area and invoking the second image acquisition result to obtain the inner skeleton modeling result; constructing a human body static simulation model according to the outer frame modeling result and the inner skeleton modeling result; uploading the basic parameters of the user, and initializing the human body static simulation model to generate a human body dynamic simulation model. The technical effect of improving the fitness between the human body model and the requirements of the metaverse human body model is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of human body modeling, and in particular, to a method, system, device and storage medium for constructing a human body model. Background Art

[0002] The construction of a three-dimensional human body model has been proposed a long time ago. The general model construction process mainly involves collecting the size and position data of various parts of the human body, and then from points to lines, from lines to surfaces, from surfaces to objects, so as to realize the simulation generation of a three-dimensional human body model.

[0003] With the rise of the metaverse, the concept of digital avatars has been proposed, that is, a virtual simulation model is constructed based on a real person. Since this simulation model needs to perform various virtual movements and social activities in the metaverse later, the three-dimensional human body model constructed by the traditional method is difficult to meet the complex and diverse requirements due to its low level of refinement. How to construct a human body model that can meet the various requirements of the metaverse has become the main research direction.

[0004] The three-dimensional human body model constructed by the prior art is difficult to adapt to various dynamic activity requirements and social requirements due to its low level of refinement, resulting in a technical problem of low fitness with the requirements of the metaverse human body model. Summary of the Invention

[0005] In view of the above, the present invention provides a method, system, device and storage medium for constructing a human body model, aiming to improve the fitness of the constructed human body model with the requirements of the metaverse human body model.

[0006] To achieve the above object, in a first aspect, the present invention provides a method for constructing a human body model, wherein the method is applied to a human body model construction system, the system includes a user terminal, and the system is communicatively connected to an image sensor array. The method includes:

[0007] When the user to be modeled enters the first preset position, the first image sensor array is called to perform multi-dimensional image acquisition on the user to be modeled, and a first image acquisition result is obtained;

[0008] Perform clustering analysis on the user to be modeled to obtain a clustering result of the modeling area;

[0009] Traverse the clustering result of the modeling area and call the first image acquisition result to perform outer frame modeling, and obtain a plurality of outer frame modeling results;

[0010] Remind the user to be modeled to enter the second preset position, call the second image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain a second image acquisition result;

[0011] Traverse the clustering results of the modeling area, retrieve the second image acquisition results, and perform endoskeleton modeling to obtain multiple endoskeleton modeling results;

[0012] Construct a human static simulation model based on the multiple outer frame modeling results and the multiple endoskeleton modeling results;

[0013] Upload the user's basic parameters through the user terminal, initialize the human static simulation model, and generate a human dynamic simulation model.

[0014] To achieve the above object, in a second aspect, the present invention further provides a human body model construction system, wherein the system includes a user terminal, the system is communicatively connected to an image sensor array, and the system includes:

[0015] A first image acquisition module, configured to retrieve the first image sensor array to perform multi-dimensional image acquisition on the user to be modeled and obtain a first image acquisition result when the user to be modeled enters a first preset position;

[0016] A modeling area clustering module, configured to perform clustering analysis on the user to be modeled to obtain modeling area clustering results;

[0017] An outer frame modeling module, configured to traverse the modeling area clustering results, retrieve the first image acquisition results, and perform outer frame modeling to obtain multiple outer frame modeling results;

[0018] A second image acquisition module, configured to remind the user to be modeled to enter a second preset position, retrieve the second image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain a second image acquisition result;

[0019] An endoskeleton modeling module, configured to traverse the modeling area clustering results, retrieve the second image acquisition results, and perform endoskeleton modeling to obtain multiple endoskeleton modeling results;

[0020] A static simulation model construction module, configured to construct a human static simulation model based on the multiple outer frame modeling results and the multiple endoskeleton modeling results;

[0021] A dynamic simulation model construction module, configured to upload the user's basic parameters through the user terminal, initialize the human static simulation model, and generate a human dynamic simulation model.

[0022] To achieve the above object, in a third aspect, the present invention further provides an electronic device, where the electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a program executable by the at least one processor, and the program is executed by the at least one processor to enable the at least one processor to execute the human body model construction method described in any one of the above.

[0023] To achieve the above object, in a fourth aspect, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a human body model construction program, and when the human body model construction program is executed by a processor, the steps of the human body model construction method described in any one of the above are implemented.

[0024] A human body model construction method and system proposed by the present invention perform modeling area clustering on a user to be modeled to obtain a modeling area clustering result; then, image acquisition is performed on the user to be modeled entering a first preset position, and then, based on the modeling area clustering result, the image acquisition results are sequentially retrieved for outer frame modeling; then, image acquisition is performed on the user to be modeled entering a second preset position, and then, based on the modeling area clustering result, the image acquisition results are sequentially retrieved for inner skeleton modeling; a human body static simulation model is constructed according to the inner skeleton modeling and the outer frame modeling; then, the basic parameters of the user are uploaded to initialize the human body static simulation model to generate a human body dynamic simulation model. By performing area-based modeling on the user to be modeled, the modeling fineness can be improved, and the modeling is divided into separate outer frame and inner skeleton modeling. Based on the outer frame, the modeling of the appearance can be realized, similar to traditional modeling. Based on the inner skeleton, the activity simulation between different bones of the human body model can be realized. Finally, the human body static simulation model is initialized according to the basic information of the user to realize the definition of the basic information of the human body model, making it social, and it can be adapted to various sports and social activities in the metaverse in the future. In summary, the technical effects of improving the human body model construction result and the adaptability of the metaverse human body model requirements are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flowchart schematic diagram of a preferred embodiment of a human body model construction method of the present invention;

[0026] Figure 2 It is a schematic diagram of the modeling area clustering process of a preferred embodiment of a human body model construction method of the present invention;

[0027] Figure 3 It is a schematic diagram of the outer frame modeling process of a preferred embodiment of a human body model construction method of the present invention;

[0028] Figure 4 It is a schematic diagram of the structure of a preferred embodiment of a human body model construction system of the present invention;

[0029] Figure 5 Schematic diagram of a preferred embodiment of the electronic device of the present invention.

[0030] Explanation of reference numerals: Client 001, Image sensor array 020, First image acquisition module 11, First image sensor array 021, Modeling area clustering module 12, Outer frame modeling module 13, Second image acquisition module 14, Second image sensor array 022, Inner skeleton modeling module 15, Static simulation model construction module 16, Dynamic simulation model construction module 17, Electronic device 4, Memory 41, Human body model construction program 40, Display 43, Processor 42, Network interface 44.

[0031] The implementation, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0032] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0033] Embodiment 1

[0034] The embodiment of the present invention provides a method for constructing a human body model. Referring to FIG. 1, it is a schematic flowchart of the method of an embodiment of a method for constructing a human body model of the present invention. This method can be executed by an electronic device, and the electronic device can be implemented by software and / or hardware. A method for constructing a human body model, wherein the method is applied to a human body model construction system, the system includes a client, the system is communicatively connected to an image sensor array, and the method includes the steps:

[0035] S100: When the user to be modeled enters the first preset position, call the first image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain the first image acquisition result;

[0036] Specifically, the user value to be modeled is the user for whom a metaverse digital human model will be constructed; the first preset position is the preset position for collecting the external image of the user to be modeled; the first image sensor array is a part of the image sensor array, deployed in all directions of the first preset position, for realizing the all-round image collection of the user to be modeled; the first image collection result is the result after the image of the user to be modeled located at the first preset position is collected by the first image sensor array. Further, the collected images are preferably grouped and stored according to the positions of the image sensors in the first image sensor array, and then a multi-group image set representing multiple angles and orientations is obtained, which is set to the waiting response state and waits for quick call in the later steps.

[0037] S200: Conduct cluster analysis on the user to be modeled to obtain the modeling area clustering result;

[0038] Further, as Figure 2 shown, based on the cluster analysis of the user to be modeled to obtain the modeling area clustering result, step S200 includes the steps:

[0039] S210: Construct a grid space coordinate system according to the first preset position;

[0040] S220: Input the user to be modeled into the grid space coordinate system to obtain the positioning result of the user to be modeled;

[0041] S230: Traverse the positioning result of the user to be modeled to separate the torso coordinates and obtain multiple groups of torso area positioning information;

[0042] S240: Traverse the multiple groups of torso area positioning information to generate the modeling area clustering result.

[0043] Specifically, the grid space coordinate system is a coordinate system for positioning each position of the user to be modeled. Its unit length is preferably measured in mm. Taking a plane within the first preset position as the reference plane, multiple l cubic millimeter grids are extended to construct the grid space coordinate system, thereby enabling accurate positioning of the user to be modeled. The positioning result of the user to be modeled is the positioning information after the user to be modeled is input into the grid space coordinate system. The multi-group torso area positioning information refers to the positioning information of the space grids occupied by different types of torsos. Any group of torso areas corresponds to a type of torso area, such as, for example, the head, chest, left leg, right leg, left hand, eyes, nose, etc., without limitation on the torso types. The clustering result of the modeling area refers to the result representing different modeling areas obtained by clustering based on the multi-group torso area positioning information according to the torso types. The positioning area where different torso types are located is a clustering result. By separating the torso of the user to be modeled through the clustering result of the modeling area, and since the same torso types have basically the same characteristics such as shape, volume, and function, the efficiency of constructing the human body model is higher. Separating the torso is beneficial to improving the construction efficiency of the human body model.

[0044] Further, based on traversing the positioning result of the user to be modeled to perform torso coordinate separation and obtain multi-group torso area positioning information, step S230 includes the steps of:

[0045] S231: Traverse the positioning result of the user to be modeled to perform primary torso coordinate separation and obtain primary torso area positioning information;

[0046] S232: Traverse the primary torso area positioning information and extract multi-group torso contour positioning coordinates;

[0047] S233: Traverse and connect the multi-group torso contour positioning coordinates to generate multiple torso contour three-dimensional diagrams;

[0048] S234: Traverse the multiple torso contour three-dimensional diagrams to extract size features and obtain multi-group size feature sets;

[0049] S235: Traverse the multi-group size feature sets to perform secondary torso coordinate separation on the multiple torso contour three-dimensional diagrams and obtain the multi-group torso area positioning information.

[0050] Specifically, the first-level torso area positioning information is the area positioning information of the grid occupied by the relatively upper torso types. Exemplarily, such as the area positioning information of the grids occupied by torso types such as the head, neck, back, chest, abdomen, pelvis, perineum, and limbs; the multiple torso contour stereograms are stereograms obtained by traversing the first-level torso area positioning information and preliminarily tracing the contour lines of the torso within the area based on the occupied grid. Taking the head as an example without limitation: the head can be represented by a cube formed by the area of the occupied grid, and the two ears can be represented by two small cubes formed by the occupied grid. The two small cubes are symmetrically deployed on both sides of a large cube, and other head organs are traced based on the same principle, and then the contour stereogram of the head is obtained. Use the same method to traverse torso types such as the neck, back, chest, abdomen, pelvis, perineum, and limbs to obtain multiple torso contour stereograms.

[0051] The multiple sets of size feature sets are size features corresponding to the multiple torso contour solids Figure 1 One-to-one. Any set of size feature sets corresponds to a torso contour stereogram, and the same set of size feature sets is grouped and stored according to the feature position. The torso contour stereogram can be regarded as composed of multiple regular cubes or other shaped stereograms, and the size features of different cubes or other shaped stereograms at similar positions vary greatly. Therefore, according to the multiple sets of size feature sets, the second-level torso coordinate separation can be performed on the multiple torso contour stereograms. Exemplarily, for torso types such as the neck, back, chest, abdomen, pelvis, perineum, and limbs, further separation is performed according to the size features, and then more refined grid area positioning information occupied by torso types such as eyes, nose, fingers, ears, eyebrows, etc. is obtained, denoted as multiple sets of torso area positioning information, thereby realizing the refined division of the human torso, facilitating the subsequent differential separation modeling according to different torso types, and achieving the technical effect of improving the human body modeling efficiency.

[0052] S300: Traverse the clustering results of the modeling area to retrieve the first image acquisition results for outer frame modeling, and obtain multiple outer frame modeling results;

[0053] Furthermore, as Figure 3 shown, based on traversing the clustering results of the modeling area to retrieve the first image acquisition results for outer frame modeling and obtaining multiple outer frame modeling results, step S300 includes the steps:

[0054] S310: Traverse the clustering results of the modeling area to retrieve the first image acquisition results for feature extraction, and generate multiple sets of torso geometric features and multiple sets of torso color features;

[0055] S320: Traverse the multiple sets of torso geometric features to construct multiple torso geometric models;

[0056] S330: Traverse multiple sets of torso color features to render the multiple torso geometric models, and obtain the modeling results of the multiple outer frames.

[0057] Specifically, multiple sets of torso geometric features refer to the information of geometric features representing the torso of the user to be modeled that corresponds one-to-one with the categories in the clustering result of the modeling area. Exemplarily, such as: size features at millimeter-level different positions of the left ear: thickness, length, width, shape features and other geometric feature information; multiple sets of torso color features refer to the data representing the color features of the user's torso that corresponds one-to-one with the categories in the clustering result of the modeling area. Exemplarily, such as: feature data such as color type, color position, and color depth. The above features are all the results obtained by traversing the clustering result of the modeling area and extracting the corresponding areas in the first image acquisition result for feature extraction. Since the acquisition process of the first image acquisition result and the positioning reference used in the clustering result of the modeling area are both the grid space coordinate system, accurate image calling can be achieved.

[0058] Determine the positioning information of the grid occupied by the areas of different torso types through the clustering result of the modeling area, and then extract the image acquisition result of this part according to the positioning information of the grid. Preferably, feature analysis is realized through an image feature extractor constructed based on a deep convolutional neural network. The image feature extractor uses multiple sets of human body image information as input data, and multiple sets of corresponding torso geometric feature record data and torso color feature record data as output identification information, and is supervised and trained based on the deep convolutional neural network. After convergence, it is used to evaluate the torso features extracted from the first image acquisition result.

[0059] Multiple torso geometric models refer to traversing multiple sets of torso geometric features to construct three-dimensional simulation models of the outer shapes of different torsos. Compared with the three-dimensional stereo diagrams of torso contours, they are no longer the splicing of multiple regular three-dimensional images, but three-dimensional simulation models with detailed torso dimensions; multiple outer frame modeling results refer to the detailed modeling results of the human body shape obtained by color rendering multiple torso geometric models according to multiple sets of torso color features, including the torso such as the neck, back, chest, abdomen, pelvis, perineum, and limbs, as well as multiple modeling results of the detailed torso components on the neck, back, chest, abdomen, pelvis, perineum, and limbs.

[0060] By performing refined modeling on the torso of the clustering result of the modeling area, the feature extractor constructed based on the convolutional neural network can ensure the accuracy of feature information, further ensure the dimensional accuracy of the torso, and ensure the reduction degree of the human body model.

[0061] Further, based on the traversal of the multiple sets of torso geometric features, multiple torso geometric models are constructed. Step S320 includes the steps:

[0062] S321: Obtain a first direction and a second direction, where the first direction and the second direction are perpendicular to each other;

[0063] S322: Perform a first-level arrangement on the torso geometric features according to the first direction to obtain a first-level arrangement result;

[0064] S323: Perform a second-level arrangement on the first-level arrangement result according to the second direction to obtain a second-level arrangement result;

[0065] S324: Traverse the second-level arrangement result and connect it in the first direction to obtain a first-level connection result;

[0066] S325: Traverse the first-level connection result and connect it in the second direction to obtain a second-level connection result;

[0067] S326: Add the second-level connection result to the multiple torso geometric models.

[0068] Specifically, the first direction and the second direction are two mutually perpendicular directions; the first-level arrangement result is the position information of a certain group of torso geometric features along the first direction, and the result obtained by arranging in the first direction; the second-level arrangement result is the result obtained by arranging the position in the second direction by sweeping the first-level arrangement result within the spatial domain along the second direction; the first-direction arrangement obtains the position set of the torso frame outline in the first direction, and the second-direction arrangement obtains the position set of the torso frame outline in the second direction; further, the first-level connection result refers to the position set of the torso geometric features in the same direction of the second-level arrangement result, and the result obtained by connecting the head and tail based on the closest positions. At this time, the first-level connection result is a plurality of contour surfaces in the first direction with an interval of 0-1 mm in the second direction. The second-level connection result refers to the result obtained by connecting the head and tail of the first-level connection result based on the closest positions in the second direction, thereby obtaining a geometric model of a torso, adding it to the multiple torso geometric models, setting it to the state of waiting for response, and waiting for subsequent rapid calls. By building the geometric model of the torso according to the rule from point to surface to volume, the efficiency is relatively high and the refinement degree is relatively high.

[0069] S400: Remind the user to be modeled to enter the second preset position, call the second image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain a second image acquisition result;

[0070] Specifically, the second preset position is the area for scanning the skeletal image of the user to be modeled, and its positioning method is exactly the same as that of the first preset position. Therefore, the skeletal image can be quickly called based on the clustering result of the modeling area. The second image sensor array refers to the image acquisition device belonging to the image sensor array and deployed at the second preset position for scanning the skeletal image of the user to be modeled. The second image acquisition result refers to the image set obtained by collecting images of the user to be modeled at the second preset position by calling the second image sensor array from multiple directions, which is set to the waiting response state and waits to be called later.

[0071] S500: Traverse the clustering result of the modeling area, call the second image acquisition result for inner skeletal modeling, and obtain multiple inner skeletal modeling results;

[0072] Further, based on traversing the clustering result of the modeling area and calling the second image acquisition result for inner skeletal modeling to obtain multiple inner skeletal modeling results, step S500 includes the steps:

[0073] S510: Traverse the clustering result of the modeling area, call the second image acquisition result for skeletal feature extraction, and obtain multiple sets of skeletal geometric features and multiple sets of skeletal joint features. Among them, the skeletal joint features include skeletal joint position features and skeletal joint range of motion features;

[0074] S520: According to the skeletal joint position features, traverse the multiple sets of skeletal geometric features for skeletal separation, and obtain multiple sets of skeletal separation results;

[0075] S530: Traverse the multiple sets of skeletal separation results and construct multiple sets of multiple skeletal geometric models;

[0076] S540: According to the skeletal joint range of motion features, traverse the multiple sets of multiple skeletal geometric models for adjustment, and obtain the multiple inner skeletal modeling results.

[0077] Specifically, multiple sets of skeletal geometric features refer to the data sets of skeletal geometric features in different clustering regions representing the clustering result of the modeling area, including but not limited to: size features, shape features, and positioning features. Multiple sets of skeletal joint features refer to the skeletal joint types, joint position features, and skeletal joint range of motion features in different clustering regions representing the clustering result of the modeling area. The feature extraction of the skeletal image is preferably completed using a skeletal feature extractor constructed based on a convolutional neural network. The skeletal feature extractor constructed based on a convolutional neural network is determined through supervised training based on multiple sets of: the skeletal image acquisition result as input data, and the skeletal geometric feature record data and skeletal joint feature record data as output identification information.

[0078] The results of separating multiple groups of bones refer to the results obtained by traversing the bone joint position features and multiple groups of bone geometric features, separating the bone geometric features. After separation, there are multiple data sets, and one bone geometric feature data set corresponds to a single bone. Multiple groups of multiple bone geometric models refer to the results after constructing geometric simulation models by traversing the results of separating multiple groups of bones. The construction process of the bone geometric model is exactly the same as the construction principle of the torso geometric model, so it will not be elaborated here. Further, the results of modeling multiple inner bones refer to the results of obtaining multiple inner bone modeling results with movable ranges after connecting bones by traversing any group of multiple bone geometric models in multiple groups of multiple bone geometric models according to the bone joint movement range features. By modeling the results of multiple inner bone modeling, the simulation movement process of each joint of the human digital model can be realized, and the plasticity of the subsequent simulation model is improved.

[0079] S600: Construct a human static simulation model according to the multiple outer frame modeling results and the multiple inner bone modeling results;

[0080] S700: Initialize the human static simulation model by uploading user basic parameters through the user terminal to generate a human dynamic simulation model.

[0081] Further, based on uploading user basic parameters through the user terminal to initialize the human simulation model to generate a human dynamic simulation model, step S700 includes the steps:

[0082] S710: Upload user occupation parameter information, age parameter information, and gender parameter information through the user terminal;

[0083] S720: Upload user specialty parameter information through the user terminal;

[0084] S730: Upload user social relationship parameter information through the user terminal;

[0085] S740: Add the occupation parameter information, the age parameter information, the gender parameter information, the specialty parameter information, and the social relationship parameter information into the user basic parameters.

[0086] Specifically, a human body static simulation model refers to the result of combining multiple outer frame modeling results and multiple inner skeleton modeling results to form a static modeling result with a relatively high simulation degree for the user to be modeled. Due to the role of multiple inner skeleton modeling results, the human body static simulation model has activity plasticity; a human body dynamic simulation model refers to the result obtained after initializing the human body static simulation model by adding basic parameters such as the user's occupation parameter information, age parameter information, gender parameter information, specialty parameter information, and social relationship parameter information. The user to be modeled can customize and set the user's basic parameters through the user terminal, thereby realizing the personalized setting of the human body dynamic simulation model.

[0087] In summary, a human body model construction method and system provided by an embodiment of the present invention have at least the following technical effects:

[0088] 1. A human body model construction method and system proposed by the present invention perform modeling area clustering on the user to be modeled to obtain a modeling area clustering result; then collect images of the user to be modeled entering the first preset position, and then sequentially retrieve the image collection results based on the modeling area clustering result for outer frame modeling; then collect images of the user to be modeled entering the second preset position, and then sequentially retrieve the image collection results based on the modeling area clustering result for inner skeleton modeling; construct a human body static simulation model based on the inner skeleton modeling and the outer frame modeling; then upload the user's basic parameters to initialize the human body static simulation model to generate a human body dynamic simulation model. By performing regional modeling on the user to be modeled, the fineness of modeling can be improved, and the modeling is divided into separate outer frame and inner skeleton modeling. Based on the outer frame, the modeling of the appearance can be realized, similar to traditional modeling. Based on the inner skeleton, the activity simulation between different bones of the human body model can be realized. Finally, the human body static simulation model is initialized according to the user's basic information, realizing the definition of the basic information of the human body model, making it social, and being adaptable to various sports and social activities in the metaverse in the future. In summary, the technical effect of improving the construction result of the human body model and the adaptability to the needs of the metaverse human body model is achieved.

[0089] 2. Compared with the traditional single modeling, the human body model construction result of the embodiment of the present application has stronger intelligence and plasticity, which is more conducive to subsequent expansion and the adjustment of the diversification of the human body model functions.

[0090] Embodiment 2

[0091] In this embodiment, as Figure 4 shown, a human body model construction system provided by an embodiment of the present invention is shown, wherein the system includes a user terminal 001, the system is communicatively connected to an image sensor array 020, and the system includes:

[0092] The first image acquisition module 11 is configured to, when the user to be modeled enters the first preset position, retrieve the first image sensor array 021 to perform multi-dimensional image acquisition on the user to be modeled, and obtain a first image acquisition result;

[0093] The modeling area clustering module 12 is configured to perform clustering analysis on the user to be modeled, and obtain a modeling area clustering result;

[0094] The outer frame modeling module 13 is configured to traverse the modeling area clustering result, retrieve the first image acquisition result, and perform outer frame modeling to obtain a plurality of outer frame modeling results;

[0095] The second image acquisition module 14 is configured to remind the user to be modeled to enter the second preset position, retrieve the second image sensor array 022 to perform multi-dimensional image acquisition on the user to be modeled, and obtain a second image acquisition result;

[0096] The inner skeleton modeling module 15 is configured to traverse the modeling area clustering result, retrieve the second image acquisition result, and perform inner skeleton modeling to obtain a plurality of inner skeleton modeling results;

[0097] The static simulation model construction module 16 is configured to construct a human body static simulation model according to the plurality of outer frame modeling results and the plurality of inner skeleton modeling results;

[0098] The dynamic simulation model construction module 17 is configured to upload user basic parameters through the user terminal 001, initialize the human body static simulation model, and generate a human body dynamic simulation model.

[0099] Further, the steps executed by the modeling area clustering module 12 include:

[0100] Construct a grid space coordinate system according to the first preset position;

[0101] Input the user to be modeled into the grid space coordinate system to obtain a positioning result of the user to be modeled;

[0102] Traverse the positioning result of the user to be modeled to perform trunk coordinate separation, and obtain multiple groups of trunk area positioning information;

[0103] Traverse the multiple groups of trunk area positioning information to generate the modeling area clustering result.

[0104] Furthermore, the steps executed by the modeling area clustering module 12 further include:

[0105] Traverse the positioning result of the user to be modeled to perform primary trunk coordinate separation, and obtain primary trunk area positioning information;

[0106] Traverse the first-level torso area location information and extract multiple groups of torso contour location coordinates;

[0107] Traverse and connect the multiple groups of torso contour location coordinates to generate multiple three-dimensional torso contour diagrams;

[0108] Traverse the multiple three-dimensional torso contour diagrams to extract dimensional features and obtain multiple groups of dimensional feature sets;

[0109] Traverse the multiple groups of dimensional feature sets to perform secondary torso coordinate separation on the multiple three-dimensional torso contour diagrams and obtain the multiple groups of torso area location information.

[0110] Furthermore, the steps executed by the outer frame modeling module 13 include:

[0111] Traverse the clustering results of the modeling area and retrieve the first image acquisition results for feature extraction to generate multiple groups of torso geometric features and multiple groups of torso color features;

[0112] Traverse the multiple groups of torso geometric features to construct multiple torso geometric models;

[0113] Traverse the multiple groups of torso color features to render the multiple torso geometric models and obtain the multiple outer frame modeling results.

[0114] Even further, the steps executed by the outer frame modeling module 13 further include:

[0115] Obtain a first direction and a second direction, where the first direction and the second direction are perpendicular to each other;

[0116] Perform a first-level arrangement on the torso geometric features according to the first direction to obtain a first-level arrangement result;

[0117] Perform a second-level arrangement on the first-level arrangement result according to the second direction to obtain a second-level arrangement result;

[0118] Traverse the second-level arrangement result and connect it according to the first direction to obtain a first-level connection result;

[0119] Traverse the first-level connection result and connect it according to the second direction to obtain a second-level connection result;

[0120] Add the second-level connection result to the multiple torso geometric models.

[0121] Furthermore, the steps executed by the inner skeleton modeling module 15 include:

[0122] Traverse the clustering results of the modeling area, retrieve the second image acquisition results for bone feature extraction, and obtain multiple sets of bone geometric features and multiple sets of bone joint features. Among them, the bone joint features include bone joint position features and bone joint range of motion features;

[0123] According to the bone joint position features, traverse the multiple sets of bone geometric features for bone separation to obtain multiple sets of bone separation results;

[0124] Traverse the multiple sets of bone separation results to construct multiple sets of bone geometric models;

[0125] According to the bone joint range of motion features, traverse the multiple sets of bone geometric models for adjustment to obtain the multiple inner bone modeling results.

[0126] Furthermore, the steps executed by the dynamic simulation model construction module 17 include:

[0127] Upload the user's professional parameter information, age parameter information, and gender parameter information through the user terminal;

[0128] Upload the user's specialty parameter information through the user terminal;

[0129] Upload the user's social relationship parameter information through the user terminal;

[0130] Add the professional parameter information, the age parameter information, the gender parameter information, the specialty parameter information, and the social relationship parameter information into the user's basic parameters.

[0131] Embodiment 3

[0132] Refer to Figure 5 As shown in the figure, it is a schematic diagram of a preferred embodiment of the electronic device 4 of the present invention.

[0133] The electronic device 4 includes but is not limited to: a memory 41, a processor 42, a display 43, and a network interface 44. The electronic device 4 is connected to the network through the network interface 44. Among them, the network can be an enterprise internal network (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth, Wi-Fi, a call network, or other wireless or wired networks.

[0134] Among them, the memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the electronic device 4, such as the hard disk or memory of the electronic device 4. In other embodiments, the memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, FlashCard, etc. equipped with the electronic device 4. Of course, the memory 41 may also include both the internal storage unit and the external storage device of the electronic device 4. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed in the electronic device 4, such as the program code of the human body model construction program 40. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0135] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 42 is generally used to control the overall operation of the electronic device 4, such as performing control and processing related to data interaction or communication. In this embodiment, the processor 42 is used to run the program code stored in the memory 41 or process data, such as running the program code of the human body model construction program 40.

[0136] The display 43 may be referred to as a display screen or a display unit. In some embodiments, the display 43 may be an LED display, a liquid crystal display, a touch liquid crystal display, and an organic light-emitting diode (OLED) toucher, etc. The display 43 is used to display the information processed in the electronic device 4 and to display a visual working interface.

[0137] The network interface 44 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and the network interface 44 is generally used to establish a communication connection between the electronic device 4 and other electronic devices.

[0138] Figure 5Only the electronic device 4 with components 41-44 and the human model building program 40 is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0139] Optionally, the electronic device 4 may further include a user interface, and the user interface may include a display, an input unit such as a keyboard. Optionally, the user interface may further include a standard wired interface and a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an organic light-emitting diode (OLED) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 4 and to display a visual user interface.

[0140] The electronic device 4 may further include a radio frequency (RF) circuit, a sensor, an audio circuit, etc., which will not be elaborated here.

[0141] In the above embodiment, when the processor 42 executes the human model building program 40 stored in the memory 41, the following steps may be implemented:

[0142] When the user to be modeled enters the first preset position, call the first image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain the first image acquisition result;

[0143] Perform clustering analysis on the user to be modeled, and obtain the clustering result of the modeling area;

[0144] Traverse the clustering result of the modeling area, call the first image acquisition result to perform outer frame modeling, and obtain multiple outer frame modeling results;

[0145] Remind the user to be modeled to enter the second preset position, call the second image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain the second image acquisition result;

[0146] Traverse the clustering result of the modeling area, call the second image acquisition result to perform inner skeleton modeling, and obtain multiple inner skeleton modeling results;

[0147] Construct a human static simulation model according to the multiple outer frame modeling results and the multiple inner skeleton modeling results;

[0148] Upload the user's basic parameters through the user terminal, initialize the human static simulation model, and generate a human dynamic simulation model.

[0149] The storage device may be the memory 41 of the electronic device 4, or may be other storage devices communicatively connected to the electronic device 4.

[0150] For a detailed introduction to the above steps, please refer to the above Figure 4 Regarding the structure diagram of the human body model construction system and Figure 1 Regarding the flowchart illustration of the embodiment of the human body model construction method.

[0151] In addition, an embodiment of the present invention further provides a computer-readable storage medium, which may be non-volatile or volatile. The computer-readable storage medium may be any one or any combination of a hard disk, a multimedia card, an SD card, a flash memory card, an SMC, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, and the like. The computer-readable storage medium includes a storage data area and a storage program area. The storage program area stores a human body model construction program 40. When the human body model construction program 40 is executed by a processor, the following operations are implemented:

[0152] When the user to be modeled enters the first preset position, call the first image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain the first image acquisition result;

[0153] Perform clustering analysis on the user to be modeled to obtain a clustering result of the modeling area;

[0154] Traverse the clustering result of the modeling area, call the first image acquisition result to perform outer frame modeling, and obtain a plurality of outer frame modeling results;

[0155] Remind the user to be modeled to enter the second preset position, call the second image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain the second image acquisition result;

[0156] Traverse the clustering result of the modeling area, call the second image acquisition result to perform inner skeleton modeling, and obtain a plurality of inner skeleton modeling results;

[0157] Construct a human body static simulation model according to the plurality of outer frame modeling results and the plurality of inner skeleton modeling results;

[0158] Upload the user's basic parameters through the user terminal, initialize the human body static simulation model, and generate a human body dynamic simulation model.

[0159] The specific implementation manner of the computer-readable storage medium of the present invention is substantially the same as the specific implementation manner of the above human body model construction method generation method, and will not be described herein again.

[0160] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments. And the term "including", "comprising" or any other variant thereof in this article is intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, device, article or method. Without more limitations, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, device, article or method including the element.

[0161] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, an electronic device, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0162] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for constructing a human body model, characterized in that, The method is applied to a human body model construction system, which includes a user terminal. The system is communicatively connected to an image sensor array. The method includes: When the user to be modeled enters the first preset position, the first image sensor array is called to perform multi-dimensional image acquisition on the user to be modeled, so as to obtain a first image acquisition result; Perform clustering analysis on the user to be modeled to obtain a clustering result of the modeling area, where: The specific steps of performing clustering analysis on the user to be modeled to obtain a clustering result of the modeling area include: Construct a grid space coordinate system according to the first preset position; Input the user to be modeled into the grid space coordinate system to obtain a positioning result of the user to be modeled; Separate the torso coordinates of the positioning result of the user to be modeled to obtain multiple groups of torso area positioning information; Generate the clustering result of the modeling area according to the multiple groups of torso area positioning information; The separating the torso coordinates of the positioning result of the user to be modeled to obtain multiple groups of torso area positioning information includes: Perform primary torso coordinate separation on the positioning result of the user to be modeled to obtain primary torso area positioning information; Extract multiple groups of torso contour positioning coordinates according to the primary torso area positioning information; Connect the multiple groups of torso contour positioning coordinates to generate multiple torso contour stereograms; Extract size features from the multiple torso contour stereograms to obtain multiple groups of size feature sets; Perform secondary torso coordinate separation on the multiple torso contour stereograms according to the multiple groups of size feature sets to obtain the multiple groups of torso area positioning information; Retrieve the first image acquisition result according to the clustering result of the modeling area for outer frame modeling, so as to obtain multiple outer frame modeling results; Remind the user to be modeled to enter the second preset position, call the second image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain a second image acquisition result; Retrieve the second image acquisition result according to the clustering result of the modeling area for inner skeleton modeling, so as to obtain multiple inner skeleton modeling results; Construct a human static simulation model according to the multiple outer frame modeling results and the multiple inner skeleton modeling results; Upload user basic parameters through the user terminal to initialize the human static simulation model and generate a human dynamic simulation model.

2. The method according to claim 1, wherein The retrieving the first image acquisition result according to the clustering result of the modeling area for outer frame modeling, so as to obtain multiple outer frame modeling results includes: Retrieve the first image acquisition result according to the clustering result of the modeling area for feature extraction, so as to generate multiple groups of torso geometric features and multiple groups of torso color features; Construct multiple torso geometric models according to the multiple groups of torso geometric features; Render the multiple torso geometric models according to the multiple groups of torso color features to obtain the multiple outer frame modeling results.

3. The method according to claim 2, wherein The constructing multiple torso geometric models according to the multiple groups of torso geometric features includes: Obtain a first direction and a second direction, where the first direction and the second direction are perpendicular to each other; Perform a primary arrangement on the torso geometric features according to the first direction to obtain a primary arrangement result; Perform a secondary arrangement on the primary arrangement result according to the second direction to obtain a secondary arrangement result; Connect the secondary arrangement result according to the first direction to obtain a primary connection result; Connect the primary connection result according to the second direction to obtain a secondary connection result; Add the secondary connection result to the multiple torso geometric models.

4. The method according to claim 1, wherein The step of retrieving the second image acquisition result according to the modeling area clustering result for endoskeleton modeling to obtain multiple endoskeleton modeling results includes: Retrieve the second image acquisition result according to the modeling area clustering result for bone feature extraction to obtain multiple sets of bone geometric features and multiple sets of bone joint features, where the bone joint features include bone joint position features and bone joint range of motion features; Separate the multiple sets of bone geometric features according to the bone joint position features to obtain multiple sets of bone separation results; Construct multiple sets of bone geometric models according to the multiple sets of bone separation results; Adjust the multiple sets of bone geometric models according to the bone joint range of motion features to obtain the multiple endoskeleton modeling results.

5. The method according to claim 4, wherein The step of initializing the human body simulation model by uploading user basic parameters through the user terminal to generate a human body dynamic simulation model includes: The user basic parameters include occupational parameter information, age parameter information, gender parameter information, specialty parameter information, and social relationship parameter information; Add the occupational parameter information, the age parameter information, the gender parameter information, the specialty parameter information, and the social relationship parameter information to the user basic parameters.

6. A human body model construction system, characterized in that The system includes a user terminal, and the system is communicatively connected to an image sensor array. The system includes: A first image acquisition module, configured to retrieve a first image sensor array to perform multi-dimensional image acquisition on the user to be modeled when the user to be modeled enters a first preset position, so as to obtain a first image acquisition result; A modeling area clustering module, configured to perform clustering analysis on the user to be modeled to obtain a modeling area clustering result, where: The specific steps of performing clustering analysis on the user to be modeled to obtain a modeling area clustering result include: Construct a grid space coordinate system according to the first preset position; Input the user to be modeled into the grid space coordinate system to obtain a positioning result of the user to be modeled; Perform torso coordinate separation on the positioning result of the user to be modeled to obtain multiple sets of torso area positioning information; Generate the modeling area clustering result according to the multiple sets of torso area positioning information; The step of performing torso coordinate separation on the positioning result of the user to be modeled to obtain multiple sets of torso area positioning information includes: Perform primary torso coordinate separation on the positioning result of the user to be modeled to obtain primary torso area positioning information; Extract multiple sets of torso contour positioning coordinates according to the primary torso area positioning information; Connect the multiple sets of torso contour positioning coordinates to generate multiple torso contour stereograms; Extract dimensional features from the multiple three-dimensional trunk contour diagrams to obtain multiple sets of dimensional feature sets; Perform secondary trunk coordinate separation on the multiple three-dimensional trunk contour diagrams according to the multiple sets of dimensional feature sets to obtain the multiple sets of trunk region positioning information; An outer frame modeling module, configured to retrieve the first image acquisition result according to the modeling region clustering result for outer frame modeling, so as to obtain multiple outer frame modeling results; A second image acquisition module, configured to remind the user to be modeled to enter a second preset position, retrieve a second image sensor array to perform multi-dimensional image acquisition on the user to be modeled, and obtain a second image acquisition result; An inner bone modeling module, configured to retrieve the second image acquisition result according to the modeling region clustering result for inner bone modeling, so as to obtain multiple inner bone modeling results; A static simulation model construction module, configured to construct a human body static simulation model according to the multiple outer frame modeling results and the multiple inner bone modeling results; A dynamic simulation model construction module, configured to upload user basic parameters through a user terminal, initialize the human body static simulation model, and generate a human body dynamic simulation model.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a program executable by the at least one processor, and the program is executed by the at least one processor, so that the at least one processor can execute the steps of the human body model construction method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a human body model construction program, and when the human body model construction program is executed by a processor, the steps of the human body model construction method according to any one of claims 1 to 5 are implemented.

Images