CN115188023A

CN115188023A - Human body model construction method, system, equipment and storage medium

Info

Publication number: CN115188023A
Application number: CN202210801266.0A
Authority: CN
Inventors: 蒋亚洪; 潘永路
Original assignee: Hangzhou Youchain Times Technology Co ltd
Current assignee: Hangzhou Youchain Times Technology Co ltd
Priority date: 2022-07-08
Filing date: 2022-07-08
Publication date: 2022-10-14

Abstract

The invention relates to the technical field of human body modeling, and provides a human body model construction method, a human body model construction system, human body model construction equipment and a storage medium. The method comprises the following steps: when a user to be modeled enters a first preset position, calling a first image sensor array to acquire a first image acquisition result; clustering analysis is carried out on users to be modeled, and a clustering result of a modeling area is obtained; traversing the modeling area clustering result, calling a first image acquisition result to acquire an outer frame modeling result; reminding a user to be modeled to enter a second preset position, and calling a second image sensor array to acquire a second image acquisition result; traversing the clustering result of the modeling area to call a second image acquisition result to acquire an endoskeleton modeling result; constructing a human body static simulation model according to the outer frame modeling result and the inner skeleton modeling result; and uploading basic parameters of a user, and initializing the human body static simulation model to generate a human body dynamic simulation model. The technical effect of improving the adaptability of the human body model and the requirement of the metastic human body model is achieved.

Description

Human body model construction method, system, equipment and storage medium

Technical Field

The invention relates to the technical field of human body modeling, in particular to a human body model construction method, a human body model construction system, human body model construction equipment and a storage medium.

Background

The construction of three-dimensional human body models has been proposed in the past, and the general model construction process mainly includes collecting the size and position data of each part of the human body, and further realizing the simulation generation of the three-dimensional human body models by points, lines, surfaces and objects.

With the rise of the meta universe, the concept of digital individuation is proposed, namely, a virtual simulation model is constructed according to a real character, and because various virtual motions and social activities need to be carried out in the meta universe subsequently by the simulation model, a three-dimensional human body model constructed in a traditional mode cannot meet complex and diverse requirements due to low refinement degree, and how to construct a human body model capable of realizing various requirements needed by the meta universe becomes a main research direction.

The human body three-dimensional model constructed in the prior art is difficult to adapt to various dynamic activity requirements and social requirements due to low refinement degree, so that the technical problem of low adaptability to the requirements of the metachrosis human body model exists.

Disclosure of Invention

In view of the above, the present invention provides a human body model building method, system, device and storage medium, which aims to improve the adaptability of the built human body model and the requirement of the metastic human body model.

In order to achieve the above object, in a first aspect, the present invention provides a human body model building method, where the method is applied to a human body model building system, the system includes a user end, the system is communicatively connected to an image sensor array, and the method includes:

when a user to be modeled enters a first preset position, calling a first image sensor array to carry out multi-dimensional image acquisition on the user to be modeled, and acquiring a first image acquisition result;

performing clustering analysis on the user to be modeled to obtain a clustering result of a modeling area;

traversing the modeling area clustering result, calling the first image acquisition result to perform outer frame modeling, and acquiring a plurality of outer frame modeling results;

reminding the user to be modeled to enter a second preset position, calling a second image sensor array to carry out multi-dimensional image acquisition on the user to be modeled, and acquiring a second image acquisition result;

traversing the clustering result of the modeling area to call the second image acquisition result for inner skeleton modeling to obtain a plurality of inner skeleton modeling results;

constructing a human static simulation model according to the outer frame modeling results and the inner skeleton modeling results;

and uploading the basic parameters of the user through the user side, initializing the human body static simulation model, and generating a human body dynamic simulation model.

In order to achieve the above object, in a second aspect, the present invention further provides a human body model building system, wherein the system includes a user end, the system is communicatively connected to an image sensor array, and the system includes:

the system comprises a first image acquisition module, a second image acquisition module and a third image acquisition module, wherein the first image acquisition module is used for calling a first image sensor array to acquire a multi-dimensional image of a user to be modeled when the user to be modeled enters a first preset position, and acquiring a first image acquisition result;

the modeling area clustering module is used for carrying out clustering analysis on the user to be modeled to obtain a clustering result of a modeling area;

the outer frame modeling module is used for traversing the clustering result of the modeling area to call the first image acquisition result for outer frame modeling to acquire a plurality of outer frame modeling results;

the second image acquisition module is used for reminding the user to be modeled to enter a second preset position, calling a second image sensor array to acquire a multi-dimensional image of the user to be modeled, and acquiring a second image acquisition result;

the endoskeleton modeling module is used for traversing the modeling area clustering result, calling the second image acquisition result to perform endoskeleton modeling, and acquiring a plurality of endoskeleton modeling results;

the static simulation model building module is used for building a human body static simulation model according to the outer frame modeling results and the inner skeleton modeling results;

and the dynamic simulation model building module is used for uploading user basic parameters through the user side, initializing the human body static simulation model and generating a human body dynamic simulation model.

In order to achieve the above object, in a third aspect, the present invention further provides an electronic device, wherein the electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a program executable by the at least one processor, the program being executable by the at least one processor to enable the at least one processor to perform the mannequin construction method of any one of the above.

In order to achieve the above object, in a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a human body model building program, and when the human body model building program is executed by a processor, the computer-readable storage medium implements the steps of the human body model building method according to any one of the above.

According to the human body model construction method and system, modeling region clustering is carried out on users to be modeled to obtain a modeling region clustering result; then, image acquisition is carried out on the user to be modeled, which enters the first preset position, and then image acquisition results are sequentially called to carry out outer frame modeling based on the clustering result of the modeling area; then, image acquisition is carried out on the user to be modeled, which enters a second preset position, and then image acquisition results are sequentially called to carry out endoskeleton modeling based on the clustering result of the modeling area; constructing a human body static simulation model according to the inner skeleton modeling and the outer frame modeling; and uploading the basic parameters of the user to initialize the human body static simulation model and generate the human body dynamic simulation model. The method has the advantages that the fineness of modeling can be improved by performing regional modeling on users to be modeled, the modeling is divided into the outer frame and the inner skeleton to perform separate modeling, the modeling of the appearance can be realized based on the outer frame, the method is similar to the traditional modeling, the activity simulation among different skeletons of the human body model can be realized based on the inner skeleton, finally, the human body static simulation model is initialized according to the basic information of the users, the basic information definition of the human body model is realized, the method has sociality, the later step can be suitable for various sports and social activities in the metasma, and in conclusion, the technical effect of improving the human body model construction result and the required adaptability of the metasma human body model is achieved.

Drawings

FIG. 1 is a schematic flow chart diagram of a preferred embodiment of a human body model construction method according to the invention;

FIG. 2 is a schematic diagram of a modeling region clustering process according to a preferred embodiment of the human body model construction method of the invention;

FIG. 3 is a schematic diagram of the outer frame modeling process of the preferred embodiment of the human body model construction method of the invention

FIG. 4 is a schematic structural diagram of a preferred embodiment of a mannequin construction system in accordance with the present invention;

FIG. 5 is a diagram of an electronic device according to a preferred embodiment of the invention.

Description of reference numerals: the system comprises a user terminal 001, an image sensor array 020, a first image acquisition module 11, a first image sensor array 021, a modeling area clustering module 12, an outer frame modeling module 13, a second image acquisition module 14, a second image sensor array 022, an inner skeleton modeling module 15, a static simulation model building module 16, a dynamic simulation model building module 17, an electronic device 4, a memory 41, a human body model building program 40, a display 43, a processor 42 and a network interface 44.

The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Example 1

The embodiment of the invention provides a human body model construction method. Fig. 1 is a schematic method flow diagram illustrating a human body model building method according to an embodiment of the present invention. The method may be performed by an electronic device, which may be implemented by software and/or hardware. A mannequin construction method, wherein the method is applied to a mannequin construction system, the system including a user side, the system being communicatively coupled to an image sensor array, the method comprising the steps of:

s100: when a user to be modeled enters a first preset position, calling a first image sensor array to carry out multi-dimensional image acquisition on the user to be modeled, and acquiring a first image acquisition result;

specifically, the user value to be modeled is a user to be subjected to the construction of the metauniverse digital human body model; the first preset position is a preset position for collecting the appearance image of the user to be modeled; the first image sensor array is a part of image sensors in the image sensor array, is deployed at each position of a first preset position and is used for realizing the omnibearing image acquisition of a user to be modeled; the first image acquisition result is the result of image acquisition of the user to be modeled, which is located at the first preset position, through the first image sensor array. Furthermore, the collected images are preferably stored in groups according to the positions of the image sensors in the first image sensor array, so that a plurality of groups of image sets representing a plurality of angles and orientations are obtained and set as a state to be responded, and the images are waited to be called quickly in the later step.

S200: performing clustering analysis on the user to be modeled to obtain a clustering result of a modeling area;

further, as shown in fig. 2, based on performing cluster analysis on the user to be modeled, a clustering result of a modeling area is obtained, and step S200 includes the steps of:

s210: constructing a grid space coordinate system according to the first preset position;

s220: inputting the user to be modeled into the grid space coordinate system to obtain a positioning result of the user to be modeled;

s230: traversing the positioning result of the user to be modeled to perform trunk coordinate separation, and acquiring a plurality of groups of trunk area positioning information;

s240: and traversing the multiple groups of trunk area positioning information to generate the modeling area clustering result.

Specifically, the grid space coordinate system is a coordinate system for positioning each position of the user to be modeled, the unit length of the grid space coordinate system is preferably measured in mm, one surface in a first preset position is taken as a reference surface, a plurality of grids of cubic millimeters are extended to construct the grid space coordinate system, and therefore the user to be modeled can be accurately positioned; the positioning result of the user to be modeled is positioning information after the user to be modeled inputs a grid space coordinate system; the plurality of sets of torso region positioning information refer to positioning information of a spatial grid occupied by different types of torso, and any one set of torso region corresponds to one type of torso region, as exemplified by: head, chest, left leg, right leg, left hand, eyes, nose, and the like, without limitation. The modeling area clustering result refers to a result representing different modeling areas, which is obtained by clustering based on trunk types according to a plurality of groups of trunk area positioning information. The positioning areas where different trunk types are located are a clustering result, the trunk separation of the user to be modeled is carried out through the modeling area clustering result, and the same trunk type has basically the same characteristics of shape, volume, function and the like, so that the efficiency of constructing the human body model is higher, and the efficiency of constructing the human body model is improved through the trunk separation.

Further, trunk coordinate separation is performed based on traversing the positioning result of the user to be modeled, and a plurality of sets of trunk area positioning information are acquired, wherein the step S230 includes the steps of:

s231: traversing the positioning result of the user to be modeled to perform primary trunk coordinate separation, and acquiring primary trunk area positioning information;

s232: traversing the first-level trunk area positioning information, and extracting a plurality of groups of trunk contour positioning coordinates;

s233: traversing the multiple groups of trunk contour positioning coordinates for connection to generate a plurality of trunk contour stereograms;

s234: traversing the plurality of trunk outline stereograms to extract size features, and acquiring a plurality of groups of size feature sets;

s235: and traversing the multiple groups of size characteristic sets to perform two-stage trunk coordinate separation on the multiple trunk outline stereograms, and acquiring the multiple groups of trunk area positioning information.

Specifically, the primary torso region location information is region location information representing an occupied grid corresponding to a relatively high torso type, and is exemplarily shown as: the region positioning information of the trunk type occupying grid, such as the head, the neck, the back, the chest, the abdomen, the basin, the perineum, the four limbs, and the like; the multiple torso contour stereograms are stereograms obtained by traversing primary torso region positioning information and performing preliminary contour line delineation on a torso in a region based on an occupied grid, and the head is taken as an example without limitation: the head can be characterized by a cube formed by the area occupying the grid, and the two ears can be characterized by two small cubes formed by the occupying grid, the two small cubes are symmetrically arranged at two sides of a large cube, and other head organs are described based on the same principle, so that the outline stereogram of the head is obtained. The same way is used for traversing the trunk types of the neck, the back, the chest, the abdomen, the basin, the perineum, the four limbs and the like to obtain a plurality of trunk outline stereograms.

The multiple sets of size feature sets are size features corresponding to the multiple torso contour stereograms one to one, any one set of size feature set corresponds to one torso contour stereogram, and the same set of size feature sets are stored in groups according to feature positions, the torso contour stereogram can be formed by splicing multiple regular cubic or other-shaped stereograms, and the size feature differences of different cubic or other-shaped stereograms at similar positions are large, so that the multiple torso contour stereograms can be subjected to two-level torso coordinate separation according to the multiple sets of size feature sets, as an example: further separation is carried out to trunk types such as neck, back, chest, belly, pelvic part, perineum, four limbs according to size characteristics, and then obtain more detailed if: grid region positioning information occupied by the trunk types such as eyes, noses, fingers, ears, eyebrows and the like is recorded as a plurality of groups of trunk region positioning information, so that the refined division of the human trunk is realized, the differential separation modeling is conveniently carried out according to different trunk types in the subsequent step, and the technical effect of improving the human body modeling efficiency is realized.

S300: traversing the modeling area clustering result, calling the first image acquisition result to perform outer frame modeling, and acquiring a plurality of outer frame modeling results;

further, as shown in fig. 3, the first image acquisition result is called based on traversing the modeling area clustering result to perform outer frame modeling, so as to obtain a plurality of outer frame modeling results, and step S300 includes the steps of:

s310: traversing the modeling area clustering result, calling the first image acquisition result, and performing feature extraction to generate a plurality of groups of torso geometric features and a plurality of groups of torso color features;

s320: traversing the multiple groups of the geometric characteristics of the trunk to construct a plurality of geometric models of the trunk;

s330: and traversing multiple groups of trunk color features to render the multiple trunk geometric models, and acquiring modeling results of the multiple outer frames.

Specifically, the multiple groups of torso geometric features refer to information, corresponding to classes in the clustering result of the modeling area, that characterizes the geometric features of the torso of the user to be modeled, such as: dimensional characteristics of the left ear at different positions in millimeter scale: geometric characteristic information such as thickness, length, width, shape characteristic and the like; the multiple groups of trunk color features refer to data representing the color features of the trunk of the user, which are in one-to-one correspondence with the categories in the modeling region clustering result, such as: color type, color position, color depth, and the like. The characteristics are all results obtained after traversing the corresponding areas in the modeling area clustering results and calling the first image acquisition results to extract the characteristics, and because the acquisition process of the first image acquisition results and the positioning reference used by the modeling area clustering results are both grid space coordinate systems, accurate image calling can be realized.

The method comprises the steps of determining positioning information of areas occupied by grids of different trunk types according to a modeling area clustering result, extracting an image acquisition result of the part according to the positioning information of the grids, preferably, realizing feature analysis through an image feature extractor constructed based on a deep convolutional neural network, using multiple groups of human body image information as input data through the image feature extractor, using multiple groups of corresponding trunk geometric feature record data and trunk color feature record data as output identification information, performing supervised training based on the deep convolutional neural network, and evaluating a first image acquisition result after convergence to extract trunk features.

The plurality of torso geometric models refer to the appearance three-dimensional simulation models of different torsos constructed by traversing a plurality of groups of torso geometric characteristics, and compared with a torso contour stereogram, the torso contour stereogram is not a mosaic of a plurality of regular stereo images any more, but is the appearance three-dimensional simulation model with detailed torso dimensions; the modeling results of the outer frames refer to the modeling results of the human body with detailed appearance obtained after the color rendering is carried out on the plurality of torso geometric models according to the color features of the plurality of groups of torso, and the modeling results comprise torsos such as neck, back, chest, abdomen, basin, perineum and four limbs and a plurality of modeling results of the body composed of torsos on the neck, the back, the chest, the abdomen, the basin, the perineum and the four limbs.

Through carrying out refined modeling on the trunk of a clustering result of the modeling area, the accuracy of the characteristic information can be guaranteed by the characteristic extractor constructed based on the convolutional neural network, the size accuracy of the trunk is further guaranteed, and the reduction degree of the human body model is guaranteed.

Further, based on the traversal of the plurality of sets of torso geometric features, a plurality of torso geometric models are constructed, and step S320 includes the steps of:

s321: acquiring a first direction and a second direction, wherein the first direction and the second direction are perpendicular to each other;

s322: performing primary arrangement on the geometric characteristics of the trunk according to the first direction to obtain a primary arrangement result;

s323: performing secondary arrangement on the primary arrangement result according to the second direction to obtain a secondary arrangement result;

s324: traversing the secondary arrangement results, and connecting according to the first direction to obtain a primary connection result;

s325: traversing the primary connection result, and connecting according to the second direction to obtain a secondary connection result;

s326: adding the secondary joining results to the plurality of torso geometric models.

Specifically, the first direction and the second direction are two directions perpendicular to each other; the primary arrangement result is position information of a certain group of body geometric features along the first direction, and the arrangement result in the first direction is obtained; the secondary arrangement result is a primary arrangement result which is scanned in a spatial domain along a second direction, and a result obtained by carrying out position arrangement in the second direction; arranging in a first direction to obtain a position set of the contour of the trunk frame in the first direction, and arranging in a second direction to obtain a position set of the contour of the trunk frame in the second direction; further, the first-stage connection result refers to a position set of the second-stage arrangement result and the geometric features of the trunk in the same direction, and an end-to-end connection result is obtained based on the nearest position, the first-stage connection result is a plurality of profile surfaces in the first direction at intervals of 0-1 mm in the second direction, the second-stage connection result refers to a result obtained by performing end-to-end connection on the first-stage connection result according to the second direction and based on the nearest position, and then a geometric model of the trunk is obtained, a plurality of trunk geometric models are added, a state to be responded is set, and the next-stage quick calling is waited. The geometric model of the trunk is built according to the rules of points, faces and bodies, so that the efficiency is high, and the refinement degree is high.

S400: reminding the user to be modeled to enter a second preset position, calling a second image sensor array to carry out multi-dimensional image acquisition on the user to be modeled, and acquiring a second image acquisition result;

specifically, the second preset position is an area for scanning a skeleton image of the user to be modeled, and the positioning mode of the second preset position is completely the same as that of the first preset position, so that the skeleton image can be quickly called based on the clustering result of the modeling area; the second image sensor array refers to an image acquisition device which belongs to the image sensor array and is deployed at a second preset position and used for scanning a skeleton image of a user to be modeled; and the second image acquisition result refers to an image set obtained after image acquisition is carried out on the user to be modeled at the second preset position through the second image sensor array which takes a plurality of directions, and the image set is set to be in a state to be responded and waits for calling in the later step.

S500: traversing the clustering result of the modeling area to call the second image acquisition result for inner skeleton modeling to obtain a plurality of inner skeleton modeling results;

further, the second image acquisition result is called based on traversing the modeling area clustering result to perform endoskeleton modeling, and a plurality of endoskeleton modeling results are obtained, wherein the step S500 includes the steps of:

s510: traversing the modeling area clustering result, calling the second image acquisition result to perform bone feature extraction, and acquiring multiple groups of bone geometric features and multiple groups of bone joint features, wherein the bone joint features comprise bone joint position features and bone joint movement range features;

s520: traversing the plurality of groups of bone geometric characteristics according to the bone joint position characteristics to perform bone separation, and acquiring a plurality of groups of bone separation results;

s530: traversing the multiple groups of bone separation results to construct multiple groups of bone geometric models;

s540: and traversing the plurality of groups of skeleton geometric models according to the skeleton joint movement range characteristics for adjustment to obtain a plurality of internal skeleton modeling results.

Specifically, the multiple groups of bone geometric features refer to bone geometric feature data sets in different clustering regions for characterizing the clustering results of the modeling regions, including but not limited to: size features, shape features, positioning features; the multiple groups of bone joint features refer to bone joint types, joint position features and bone joint movement range features in different clustering regions of a clustering result of a characterization modeling region, the feature extraction of a bone image is preferably completed by using a bone feature extractor constructed based on a convolutional neural network, and the bone feature extractor constructed based on the convolutional neural network is formed by multiple groups of: the bone image acquisition result is used as input data, the bone geometric characteristic record data and the bone joint characteristic record data are used as output identification information, and the bone geometric characteristic record data and the bone joint characteristic record data are obtained by carrying out supervised training and determination based on a convolutional neural network.

The multi-group bone separation result refers to a result obtained by traversing the bone joint position features, traversing the multi-group bone geometric features and separating the bone geometric features, and the separated data sets are a plurality of data sets, wherein one bone geometric feature data set corresponds to a single bone. The multiple groups of skeleton geometric models refer to a result obtained by traversing multiple groups of skeleton separation results and constructing a geometric simulation model, and the construction process of the skeleton geometric models is completely the same as the construction principle of the torso geometric models, which is not repeated herein. Furthermore, the plurality of internal skeleton modeling results refer to a plurality of internal skeleton modeling results with a movable range obtained by traversing a plurality of bone geometric models of any one of a plurality of groups of bone geometric models according to the characteristics of the movable range of the bone joints and connecting bones. By modeling a plurality of inner skeleton modeling results, the movement process of the simulation of each joint of the human digital model can be realized, and the backward plasticity of the simulation model is improved.

S600: constructing a human body static simulation model according to the modeling results of the outer frames and the modeling results of the inner skeletons;

s700: and uploading the basic parameters of the user through the user side, initializing the human body static simulation model, and generating a human body dynamic simulation model.

Further, based on the basic user parameters uploaded by the user side, the human body simulation model is initialized to generate a dynamic human body simulation model, and step S700 includes the steps of:

s710: uploading user occupation parameter information, age parameter information and gender parameter information through the user side;

s720: uploading user characteristic parameter information through the user side;

s730: uploading user social relationship parameter information through the user side;

and S740: and adding the occupation parameter information, the age parameter information, the gender parameter information, the speciality parameter information and the social relationship parameter information into the user basic parameters.

Specifically, the human static simulation model refers to a static modeling result which is formed by splicing a plurality of outer frame modeling results and a plurality of inner skeleton modeling results and has higher simulation degree with a user to be modeled, and the human static simulation model has activity plasticity due to the function of the plurality of inner skeleton modeling results; the human body dynamic simulation model is a result obtained by adding basic parameters such as occupational parameter information, age parameter information, sex parameter information, special parameter information and social relation parameter information of a user and performing individualized initialization on the human body static simulation model, and a user to be modeled can set the basic parameters of the user in a user-defined manner through a user terminal so as to realize individualized setting of the human body dynamic simulation model.

In summary, the human body model construction method and system provided by the embodiments of the present invention at least have the following technical effects:

1. according to the human body model construction method and system, modeling region clustering is carried out on users to be modeled to obtain a modeling region clustering result; then, image acquisition is carried out on the user to be modeled, which enters the first preset position, and then image acquisition results are sequentially called to carry out outer frame modeling based on the clustering result of the modeling area; then, image acquisition is carried out on the user to be modeled, which enters a second preset position, and then image acquisition results are sequentially called to carry out endoskeleton modeling based on the clustering result of the modeling area; constructing a human body static simulation model according to the inner skeleton modeling and the outer frame modeling; and uploading the basic parameters of the user to initialize the human body static simulation model and generate the human body dynamic simulation model. The method has the advantages that the model building fineness can be improved by performing the regional model building on the user to be modeled, the external frame and the internal skeleton are divided for separate model building, the external frame based model building can be realized, the traditional model building is similar to the traditional model building, the activity simulation among different skeletons of the human body model can be realized based on the internal skeleton, finally, the human body static simulation model is initialized according to the basic information of the user, the basic information definition of the human body model is realized, the human body model has sociality, the later step can be suitable for various sports and social activities in the metasma, and in sum, the technical effect of improving the human body model building result and the required fitness of the metasma human body model is achieved.

2. Compared with the traditional method of only carrying out single modeling, the human body model building result of the embodiment of the application has stronger intelligence and plasticity, and is more beneficial to later expansion and adjustment of human body model function diversification.

Example 2

In this embodiment, as shown in fig. 4, a human body model building system provided for the embodiment of the present invention is a human body model building system, where the system includes a user terminal 001, the system is communicatively connected to an image sensor array 020, and the system includes:

the system comprises a first image acquisition module 11, a second image acquisition module and a third image acquisition module, wherein the first image acquisition module is used for calling a first image sensor array 021 to acquire a multi-dimensional image of a user to be modeled when the user to be modeled enters a first preset position, and acquiring a first image acquisition result;

the modeling area clustering module 12 is used for carrying out clustering analysis on the users to be modeled to obtain a clustering result of a modeling area;

the outer frame modeling module 13 is configured to traverse the modeling area clustering result to call the first image acquisition result for outer frame modeling, and obtain a plurality of outer frame modeling results;

the second image acquisition module 14 is configured to remind the user to be modeled of entering a second preset position, invoke 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;

the endoskeleton modeling module 15 is used for traversing the modeling area clustering result to call the second image acquisition result for endoskeleton modeling, and obtaining a plurality of endoskeleton modeling results;

a static simulation model construction module 16, configured to construct a human static simulation model according to the modeling results of the plurality of outer frames and the modeling results of the plurality of inner bones;

and the dynamic simulation model building module 17 is used for uploading the basic user parameters through the user side 001, initializing the human body static simulation model and generating the human body dynamic simulation model.

Further, the modeling area clustering module 12 performs steps including:

constructing a grid space coordinate system according to the first preset position;

inputting the user to be modeled into the grid space coordinate system to obtain a positioning result of the user to be modeled;

traversing the positioning result of the user to be modeled to perform trunk coordinate separation, and acquiring a plurality of groups of trunk area positioning information;

and traversing the multiple groups of trunk area positioning information to generate the modeling area clustering result.

Further, the modeling region clustering module 12 performs the steps further including:

traversing the positioning result of the user to be modeled to perform primary trunk coordinate separation, and acquiring primary trunk area positioning information;

traversing the first-level trunk area positioning information, and extracting a plurality of groups of trunk contour positioning coordinates;

traversing the multiple groups of trunk contour positioning coordinates for connection to generate a plurality of trunk contour stereograms;

traversing the plurality of trunk outline stereograms to extract size features, and acquiring a plurality of groups of size feature sets;

and traversing the multiple groups of size characteristic sets to perform two-stage trunk coordinate separation on the multiple trunk outline stereograms, and acquiring the multiple groups of trunk area positioning information.

Further, the outer frame modeling module 13 performs the steps including:

traversing the modeling area clustering result, calling the first image acquisition result for feature extraction, and generating a plurality of groups of torso geometric features and a plurality of groups of torso color features;

traversing the multiple groups of the geometric characteristics of the trunk to construct a plurality of geometric models of the trunk;

and traversing multiple groups of trunk color features to render the multiple trunk geometric models, and obtaining the modeling results of the multiple outer frames.

Further, the outer frame modeling module 13 performs the steps further including:

acquiring a first direction and a second direction, wherein the first direction and the second direction are perpendicular to each other;

performing primary arrangement on the geometric characteristics of the trunk according to the first direction to obtain a primary arrangement result;

performing secondary arrangement on the primary arrangement result according to the second direction to obtain a secondary arrangement result;

traversing the secondary arrangement result to connect according to the first direction to obtain a primary connection result;

traversing the primary connection result and connecting according to the second direction to obtain a secondary connection result;

adding the secondary joining results to the plurality of torso geometric models.

Further, the endoskeleton modeling module 15 performs steps including:

traversing the modeling area clustering result, calling the second image acquisition result to perform bone feature extraction, and acquiring multiple groups of bone geometric features and multiple groups of bone joint features, wherein the bone joint features comprise bone joint position features and bone joint movement range features;

traversing the multiple groups of bone geometric characteristics according to the bone joint position characteristics to carry out bone separation, and acquiring multiple groups of bone separation results;

traversing the plurality of groups of bone separation results to construct a plurality of groups of bone geometric models;

and traversing the plurality of groups of skeleton geometric models according to the skeleton joint movement range characteristics for adjustment to obtain a plurality of internal skeleton modeling results.

Further, the dynamic simulation model building module 17 executes steps including:

uploading user occupation parameter information, age parameter information and gender parameter information through the user side;

uploading user characteristic parameter information through the user side;

uploading user social relationship parameter information through the user side;

adding the occupation parameter information, the age parameter information, the gender parameter information, the speciality parameter information and the social relationship parameter information into the user basic parameters.

Example 3

Fig. 5 is a schematic diagram of an electronic device 4 according to a preferred embodiment of the invention.

The electronic device 4 includes, but is not limited to: memory 41, processor 42, display 43, and network interface 44. The electronic device 4 is connected to a network via a network interface 44. The network may be a wireless or wired network such as an Intranet (Internet), the Internet (Internet), a Global System for mobile communications (GSM), wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, bluetooth (Bluetooth), wi-Fi, or a telephony network.

The memory 41 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the electronic device 4, such as a hard disk or a 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, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are equipped with the electronic device 4. Of course, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. In this embodiment, the memory 41 is generally used for storing an operating system and various application software installed in the electronic device 4, such as program codes of the human body model building program 40. Further, the memory 41 may also be used to temporarily store various types of data that have been output or are to be output.

Processor 42 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 42 is generally used for controlling the overall operation of the electronic device 4, such as performing data interaction or communication related control and processing. In this embodiment, the processor 42 is configured to run the program code stored in the memory 41 or process data, for example, run the program code of the human body model building program 40.

The display 43 may be referred to as a display screen or display unit. In some embodiments, the display 43 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch screen, or the like. The display 43 is used for displaying information processed in the electronic device 4 and for displaying a visual work interface.

The network interface 44 may optionally include a standard wired interface, a wireless interface (e.g., a WI-FI interface), and the network interface 44 is typically used to establish a communication link between the electronic device 4 and other electronic devices.

FIG. 5 shows only electronic device 4 having components 41-44 and mannequin building program 40, but it should be understood that not all of the shown components are required and that more or fewer components may be implemented instead.

Optionally, the electronic device 4 may further include a user interface, the user interface may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further include a standard wired interface and a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device 4 and for displaying a visualized user interface.

The electronic device 4 may further include Radio Frequency (RF) circuits, sensors, audio circuits, and so on, which are not described in detail herein.

In the above embodiment, the processor 42, when executing the human model building program 40 stored in the memory 41, may implement the following steps:

The storage device may be the memory 41 of the electronic device 4, or may be another storage device communicatively connected to the electronic device 4.

For the detailed description of the above steps, please refer to the above description of fig. 4 for the structure diagram of the human body model building system and fig. 1 for the flowchart of the embodiment of the human body model building method.

In addition, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium may be non-volatile or volatile. The computer readable storage medium may be any one or any combination of hard disks, multimedia cards, SD cards, flash memory cards, SMCs, read Only Memories (ROMs), erasable Programmable Read Only Memories (EPROMs), portable compact disc read only memories (CD-ROMs), USB memories, etc. The computer readable storage medium includes a data storage area and a program storage area, the program storage area stores a human body model building program 40, and the human body model building program 40 implements the following operations when executed by a processor:

constructing a human body static simulation model according to the modeling results of the outer frames and the modeling results of the inner skeletons;

The specific implementation of the computer-readable storage medium of the present invention is substantially the same as the specific implementation of the human body model building method generation method, and is not described herein again.

It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one of 8230, and" comprising 8230does not exclude the presence of additional like elements in a process, apparatus, article, or method comprising the element.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (which may be a mobile phone, a computer, an electronic device, or a network device) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. A mannequin construction method, the method being applied to a mannequin construction system, the system including a user side, the system being communicatively coupled to an image sensor array, the method comprising:

and uploading the basic user parameters through the user side, initializing the human body static simulation model, and generating a human body dynamic simulation model.

2. The method of claim 1, wherein the performing cluster analysis on the user to be modeled to obtain a modeling region clustering result comprises:

3. The method of claim 1, wherein the traversing the user positioning result to be modeled for torso coordinate separation to obtain multiple sets of torso region positioning information comprises:

4. The method of claim 1, wherein said traversing the modeled region cluster results invokes the first image acquisition result for outer-frame modeling, obtaining a plurality of outer-frame modeling results, comprising:

traversing the multiple groups of body geometric characteristics to construct multiple body geometric models;

5. The method of claim 4, wherein said traversing said plurality of sets of torso geometric features, constructing a plurality of torso geometric models, comprises:

6. The method of claim 1, wherein said traversing said modeled region cluster results to retrieve said second image acquisition result for endoskeleton modeling, obtaining a plurality of endoskeleton modeling results, comprises:

traversing the modeling area clustering result, calling the second image acquisition result, and extracting bone features to obtain multiple groups of bone geometric features and multiple groups of bone joint features, wherein the bone joint features comprise bone joint position features and bone joint movement range features;

traversing the multiple groups of bone separation results to construct multiple groups of bone geometric models;

7. The method of claim 6, wherein the uploading user basic parameters through the user side, initializing the human body simulation model, and generating the human body dynamic simulation model comprises:

uploading user characteristic parameter information through the user side;

uploading user social relationship parameter information through the user side;

and adding the occupation parameter information, the age parameter information, the gender parameter information, the speciality parameter information and the social relationship parameter information into the user basic parameters.

8. A mannequin construction system, the system including a user side, the system communicatively coupled to an image sensor array, the system comprising:

the modeling area clustering module is used for carrying out clustering analysis on the user to be modeled to obtain a modeling area clustering result;

the endoskeleton modeling module is used for traversing the clustering result of the modeling area to call the second image acquisition result to perform endoskeleton modeling and acquire a plurality of endoskeleton modeling results;

the static simulation model building module is used for building a human body static simulation model according to the modeling results of the outer frames and the modeling results of the inner bones;

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a program executable by the at least one processor to enable the at least one processor to perform the steps of the mannequin construction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a mannequin constructing program, which when executed by a processor, implements the steps of the mannequin constructing method according to any one of claims 1 to 7.