Method for determining garment looseness in motion state

Abstract

The application discloses a kind of clothing loose amount determination method under motion state, belong to clothing performance evaluation technical field, including: constructing three-dimensional human body submodel and three-dimensional clothing submodel under each motion key frame in motion cycle, carry out human body feature area division, according to the overall volume of the three-dimensional human body submodel corresponding to the feature area overall model under each motion key frame, the local upper surface area, the local lower surface area and the local volume of three-dimensional human body submodel and three-dimensional clothing submodel corresponding to the feature area local model under each motion key frame, the local volume of clothing fabric corresponding to the feature area local model under each motion key frame and the height of feature area, calculate the clothing looseness required for the feature area local model under each motion key frame, determine clothing loose amount under motion state.This method can solve the problem that traditional static design method cannot accurately reflect the change of human motion form, improve the precision of clothing loose amount design under motion state.

Description

TECHNICAL FIELD

[0001] The application relates to a method for determining clothing looseness in a motion state, and belongs to the technical field of clothing performance evaluation. BACKGROUND

[0002] Clothing looseness, as a key parameter affecting the fit and activity performance of clothing, shows significant differences under static and dynamic conditions. Under static conditions, the complex undulations of the human body surface cause the clothing looseness to present a non-uniform distribution characteristic. In the motion process, due to the dynamic changes of multi-joint coordinated action and the asymmetry of motion posture, the looseness distribution presents a high time-varying and spatial non-uniformity. This dynamic characteristic not only increases the technical difficulty of accurate quantification of looseness, but also affects the heat and moisture transfer efficiency of clothing, leading to local heat accumulation or sweat retention, and even limiting the freedom of motion. Therefore, accurate characterization of dynamic looseness is of great significance for optimizing the functional design of clothing, and can promote the transformation of clothing design from traditional homogenization to partition parameterization, and provide theoretical support for the development of high-performance sports equipment.

[0003] The prior art (such as Chinese patents with publication numbers CN117313182A and CN109978837A) mainly obtains the clothing looseness based on traditional historical body shape statistical methods and two-dimensional image analysis methods. Although the statistical method based on historical body shape data can realize body shape classification and looseness prediction, it is only suitable for clothing design under static posture and cannot reflect the dynamic change characteristics of human body shape in a motion state. The fit evaluation technology relying on two-dimensional image analysis realizes the unified evaluation of visual comfort and objective fit, but is limited by the lack of information in the two-dimensional plane and cannot accurately quantify the three-dimensional spatial relationship between clothing and human body. SUMMARY

[0004] The purpose of the present application is to provide a method for determining clothing looseness in a motion state, which can solve the problem that traditional static design methods cannot accurately reflect the change of human motion form, and improve the accuracy of clothing looseness design in a motion state.

[0005] To achieve the above purpose, the present application provides the following technical scheme:

[0006] In a first aspect, the present application provides a method for determining clothing looseness in a motion state, comprising:

[0007] Based on a three-dimensional dynamic human body model and a three-dimensional dynamic clothing model, three-dimensional human body sub-models and three-dimensional clothing sub-models under each motion key frame in a motion cycle are constructed;

[0008] The three-dimensional human body sub-models and three-dimensional clothing sub-models under each motion key frame are divided into human feature regions, and a feature region overall model under each motion key frame is constructed;

[0009] the feature region integral model under each motion key frame is divided into several local domains with the gravity center as the reference central axis, and a local model of the feature region under each motion key frame is constructed;

[0010] According to the overall volume of the three-dimensional human body sub-model corresponding to the feature region integral model under each motion key frame, the local upper surface area, the local lower surface area and the local volume of the three-dimensional human body sub-model and the three-dimensional garment sub-model corresponding to the feature region local model under each motion key frame, the local volume of the garment fabric corresponding to the feature region local model under each motion key frame, and the height of the feature region, the garment looseness required by the feature region local model under each motion key frame is calculated;

[0011] According to the garment looseness required by the feature region local model under each motion key frame, the garment looseness required by the feature region integral model in the motion cycle is calculated;

[0012] According to the garment looseness required by the feature region integral model in the motion cycle, the garment sag under the motion state is determined.

[0013] In combination with the first aspect, further, the method for constructing a three-dimensional dynamic human body model comprises:

[0014] The actually measured human body shape data is input into a three-dimensional virtual fitting software to generate a three-dimensional human body model that fits the real human body shape;

[0015] The three-dimensional human body model is input into a three-dimensional modeling software to construct a skeletal system that matches the shape characteristics of the three-dimensional human body model, thereby forming a three-dimensional static human body model integrated with the skeleton;

[0016] The real human body motion trajectory data is collected by using an AI motion capture software, and skeletal joint motion data is generated;

[0017] The skeletal joint motion data is input into the three-dimensional modeling software, and the posture and joint node matching is performed between the skeletal joint motion data and the three-dimensional static human body model integrated with the skeleton, thereby generating a three-dimensional dynamic human body model with continuous action characteristics.

[0018] In combination with the first aspect, further, the method for constructing a three-dimensional dynamic garment model comprises:

[0019] The three-dimensional dynamic human body model and the drawn two-dimensional garment template are input into a three-dimensional virtual fitting software, the physical and mechanical performance properties of the virtual fabric are set, the two-dimensional garment template is fitted to the surface of the three-dimensional dynamic human body model by using virtual sewing technology, and a three-dimensional dynamic garment model with fabric reality and dynamic adaptability is generated.

[0020] Building upon the first aspect, further, based on the 3D dynamic human body model and the 3D dynamic clothing model, the construction of 3D human body sub-models and 3D clothing sub-models at each motion keyframe within the motion cycle includes:

[0021] Using 3D virtual fitting software, spatiotemporal discretization processing is performed on 3D dynamic human body models and 3D dynamic clothing models, decomposing the motion cycle into several motion keyframes;

[0022] For each motion keyframe, the paired 3D human body sub-model and 3D clothing sub-model are extracted synchronously.

[0023] Building upon the first aspect, further, the 3D human body sub-model and 3D clothing sub-model under each motion keyframe are divided into human feature regions, and an overall feature region model under each motion keyframe is constructed, including:

[0024] For each motion keyframe, the 3D human body sub-model and the 3D clothing sub-model are aligned using reverse modeling software to construct the human body clothing sub-model under that motion keyframe.

[0025] Based on human anatomical features, the human clothing sub-model under each motion keyframe is divided into human feature regions. The height of the feature regions is set according to the physiological height of each part of the human body. A positioning plane is constructed along the height direction of the feature regions. A clipping plane is set at the boundary of the feature regions. Redundant parts that exceed the boundary of the feature regions are deleted, generating an overall model of the feature regions under each motion keyframe that conforms to human anatomical features.

[0026] Building upon the first aspect, further, the overall model of the feature region under each motion keyframe is divided into several local domains with the centroid as the reference axis. The local model of the feature region under each motion keyframe includes:

[0027] For the overall model of the feature region under each motion keyframe, the overall model of the feature region is divided into 4 local regions orthogonally along the sagittal and coronal planes using the centroid of the overall model of the feature region as the reference axis, and the dual-plane segmentation method is used to form the local model of the feature region under each motion keyframe.

[0028] In conjunction with the first aspect, the formula for calculating the required clothing looseness for the local model of the feature region under each motion keyframe is as follows:

[0029] ;

[0030] in, Indicates the first The first motion keyframe The required clothing looseness for a local model of a feature region , They represent the first the local upper surface area and the local lower surface area of the three-dimensional human sub-model corresponding to the local model of the the local upper surface area and the local lower surface area of the three-dimensional garment sub-model corresponding to the local model of the the overall volume of the three-dimensional human sub-model corresponding to the overall model of the feature region under the the local volume of the three-dimensional human sub-model, the three-dimensional garment sub-model and the garment fabric corresponding to the local model of the the height of the feature region.

[0031] According to the garment looseness required by the local model of the feature region under each motion key frame, the garment looseness required by the overall model of the feature region under each motion key frame is calculated.

[0032] According to the garment looseness required by the local model of the feature region under each motion key frame, the garment looseness required by the overall model of the feature region under each motion key frame is calculated.

[0033] According to the garment looseness required by the overall model of the feature region under each motion key frame, the garment looseness required by the overall model of the feature region in the motion cycle is calculated.

[0034] The calculation formula of the garment looseness required by the overall model of the feature region under each motion key frame is:

[0035] ;

[0036] wherein, the garment looseness required by the overall model of the feature region under the the garment looseness required by the local model of the each overall model of the feature region is divided into 4 local models of the feature region.

[0037] The calculation formula of the garment looseness required by the overall model of the feature region in the motion cycle is:

[0038] ​​​​​​​​​​​​ ;

[0039] wherein, represents the garment looseness required by the feature region overall model in the motion cycle, represents the total number of motion key frames in the motion cycle.

[0040] In combination with the first aspect, further, the calculation formula of the garment looseness in the motion state is:

[0041] ;

[0042] wherein, represents the garment looseness in the motion state, represents the garment looseness required by the feature region overall model in the motion cycle.

[0043] The second aspect, the present application provides a kind of garment looseness determination device in motion state, comprising:

[0044] Model construction module, for based on three-dimensional dynamic human body model and three-dimensional dynamic garment model, constructs three-dimensional human body submodel and three-dimensional garment submodel under each motion key frame in motion cycle;The three-dimensional human body submodel and three-dimensional garment submodel under each motion key frame are divided into human body feature region, and the feature region overall model under each motion key frame is constructed;The feature region overall model under each motion key frame is divided into several local domains with gravity as reference central axis, and the feature region local model under each motion key frame is constructed;

[0045] Looseness calculation module, for according to the overall volume of the three-dimensional human body submodel corresponding to the feature region overall model under each motion key frame, the local upper surface area, the local lower surface area and the local volume of the three-dimensional human body submodel and the three-dimensional garment submodel corresponding to the feature region local model under each motion key frame, the local volume of the garment fabric corresponding to the feature region local model under each motion key frame, and the height of feature region, the garment looseness required by the feature region local model under each motion key frame is calculated;According to the garment looseness required by the feature region local model under each motion key frame, the garment looseness required by the feature region overall model in the motion cycle is calculated;

[0046] Garment looseness determination module, for according to the garment looseness required by the feature region overall model in the motion cycle, determine the garment looseness in the motion state.

[0047] The third aspect, the present application provides a kind of computer equipment, comprising:

[0048] Storage medium, for storing computer program;

[0049] A processor is configured to execute the computer program to implement the method for determining the garment ease in the motion state according to the first aspect.

[0050] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method for determining the garment ease in the motion state according to the first aspect.

[0051] In a fifth aspect, the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the method for determining the garment ease in the motion state according to the first aspect.

[0052] Compared with the prior art, the present application has the following beneficial effects:

[0053] The method for determining the garment ease in the motion state provided by the present application can capture the real-time interaction state between the human body and the garment in the motion cycle based on the three-dimensional dynamic human body model and the three-dimensional dynamic garment model and in combination with the motion key frame analysis, and can solve the problems that the traditional static determination method cannot accurately reflect the change of the human body motion form and the lack of scientific quantitative basis for the ease distribution.

[0054] The feature region partition modeling and the multi-dimensional geometric parameter calculation are adopted to extract the local model of the feature region under the motion key frame, and the volume, the surface area and other multi-dimensional parameters of the three-dimensional human body sub-model and the three-dimensional garment sub-model corresponding to the feature region overall model and the feature region local model under each motion key frame are calculated to calculate the garment ease required by the feature region local model under each motion key frame, dynamically optimize the ease distribution of the garment in each motion stage, and realize the scientific quantitative design, improve the precision of the ease design of the garment in the motion state, reduce the dependence on the physical sample iteration, and realize the precise design and optimization of the comfort and functionality of the sports garment. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 is a flow chart of the method for determining the garment ease in the motion state provided by the embodiment of the present application;

[0056] Figure 2 is a schematic diagram of the human body dressing sub-model under 14 high leg motion key frames provided by the embodiment of the present application;

[0057] Figure 3 is a schematic diagram of the hip feature region overall model under one high leg motion key frame provided by the embodiment of the present application, wherein A is a three-dimensional human body sub-model corresponding to the hip feature region overall model under the high leg motion key frame, B is a three-dimensional garment sub-model corresponding to the hip feature region overall model under the high leg motion key frame, and C is the hip feature region overall model under the high leg motion key frame;

[0058] Figure 4is a 4-hip feature region local model schematic diagram under 1 high leg lifting motion key frame provided by the embodiment of the application;

[0059] Figure 5 is a garment looseness schematic diagram required by 4 left front, right front, left rear and right rear hip feature region local models under 14 high leg lifting motion key frames provided by the embodiment of the application. DETAILED DESCRIPTION

[0060] The technical solutions of the application will be further described in detail below with reference to specific embodiments.

[0061] Embodiments of the application are described in detail below, and examples of the embodiments are shown in the drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are only used to explain the application, and cannot be understood as a limitation on the application. The technical features in the embodiments of the application and the embodiments can be combined with each other without conflict.

[0062] The embodiment of the application provides a garment looseness determination method in a motion state, comprising:

[0063] Based on a three-dimensional dynamic human body model and a three-dimensional dynamic garment model, three-dimensional human body sub-models and three-dimensional garment sub-models under each motion key frame in a motion cycle are constructed;

[0064] Human feature region division is performed on the three-dimensional human body sub-models and the three-dimensional garment sub-models under each motion key frame, and a feature region overall model under each motion key frame is constructed;

[0065] The feature region overall model under each motion key frame is divided into a plurality of local domains with a gravity center as a reference central axis, and a feature region local model under each motion key frame is constructed;

[0066] According to the overall volume of the three-dimensional human body sub-model corresponding to the feature region overall model under each motion key frame, the local upper surface area, the local lower surface area and the local volume of the three-dimensional human body sub-model and the three-dimensional garment sub-model corresponding to the feature region local model under each motion key frame, the local volume of the garment fabric corresponding to the feature region local model under each motion key frame, and the height of the feature region, the garment looseness required by the feature region local model under each motion key frame is calculated;

[0067] According to the garment looseness required by the feature region local model under each motion key frame, the garment looseness required by the feature region overall model in the motion cycle is calculated;

[0068] According to the garment looseness required by the feature region overall model in the motion cycle, the garment looseness in the motion state is determined.

[0069] The garment ease determination method in a motion state provided by the embodiment of the present application is based on a three-dimensional dynamic human body model and a three-dimensional dynamic garment model, and the dynamic change of the ease is captured by disassembling the motion key frame, a complete technical chain of dynamic modeling-key frame extraction-partition calculation-ease output is established, the limitation of the traditional static measurement method is broken through, and the real-time deformation characteristics of each part of the human body in the motion process can be accurately captured. The feature region partition modeling and multi-dimensional geometric parameter calculation can further improve the design accuracy of the garment ease in the motion state, and the garment design ease required by each feature region of the garment in the motion state is quantified with high precision, thereby providing a scientific basis for digital garment development. Compared with the traditional optimization process which depends on the repeated trial and error of the physical sample clothes, the design efficiency is significantly improved, and the method is especially suitable for the accurate development of high-performance sports equipment, and has important engineering application value.

[0070] Figure 1 The flowchart is a garment ease determination method in a motion state provided by the embodiment of the present application, and only the logical order of the method of the embodiment is shown. The steps shown or described can be completed in an order different from that shown in the figure on the premise that they do not conflict with each other. Figure 1

[0071] The garment ease determination method in a motion state provided by the embodiment of the present application can be applied to a terminal, and can be executed by a garment ease determination device in a motion state. The device can be realized in the form of software and / or hardware, and can be integrated in the terminal, for example, any tablet computer or computer device with a communication function.

[0072] In one possible embodiment, the method for constructing a three-dimensional dynamic human body model specifically includes the following steps:

[0073] Step 1: input the measured human body shape data into a three-dimensional virtual fitting software to generate a three-dimensional human body model that fits the real human body shape.

[0074] Specifically, the measured human body shape data is input into the human body model parameter module of the three-dimensional virtual fitting software to generate a three-dimensional human body model that fits the real human body shape.

[0075] In the embodiment, the architecture of the three-dimensional virtual fitting software includes a human body parameterized modeling engine. The human body parameterized modeling engine generates a topological structure editable digital three-dimensional human body model by inputting real human body shape data. The technology measures real human body shape data, focuses on collecting data of key parts such as height, shoulder neck, chest back, waist hip, and the like, inputs the real human body shape data into a virtual fitting software mannequin to obtain a digital three-dimensional human body model.

[0076] ​Step 2: input the three-dimensional human model into a three-dimensional modeling software, build a skeletal system matching the morphological characteristics of the three-dimensional human model, and form a three-dimensional static human model integrated with the skeleton;

[0077] Step 3: collect real human motion trajectory data using AI motion capture software, and generate skeletal joint motion data;

[0078] Specifically, real human motion trajectory data is collected using AI motion capture software. In an open background, the action video of the target human body is shot by a fixed camera, and the action video is input into the AI motion capture software to generate skeletal joint motion data.

[0079] In this embodiment, the AI motion capture technology is a three-dimensional space motion measurement technology based on multi-modal sensing technology. Its core principle is to track the position and rotation information of the key points (such as joints and bones) of the target in three-dimensional space through the device, and then map the data to a virtual character or model. Through advanced deep learning algorithms for real-time analysis and recognition of video data, accurate recognition and monitoring of human actions can be achieved.

[0080] The use of AI motion capture technology to obtain real human motion trajectory data to construct a human skeletal model in a motion state includes: using a specially designed garment integrated with a miniature inertial measurement unit (IMU) to collect displacement and rotation data during the movement of the model through an inertial motion capture system. The collected action file is wirelessly transmitted to a three-dimensional modeling software, and after noise reduction, smoothing and correction, a human skeletal model in a motion state containing skeletal structure, time sequence and three-dimensional spatial coordinates of each bone is constructed. The mapping list ensures one-to-one correspondence of the bone names, and the data of the animation skeleton is transmitted to the driver bone.

[0081] Step 4: input the skeletal joint motion data into the three-dimensional modeling software, match the posture and joint nodes with the three-dimensional static human model integrated with the skeleton, and generate a three-dimensional dynamic human model with continuous action characteristics.

[0082] In this embodiment, the core architecture of the three-dimensional modeling software integrates modeling, rendering, animation, simulation and post-production modules, especially the character animation control tools based on skeletal system, inverse dynamics (IK), forward dynamics (FK) and physical engine. The three-dimensional modeling software can construct a skeletal architecture in the three-dimensional human model, control the skeletal joint nodes, and realize walking, posture changes and other functions of the three-dimensional human model.

[0083] The skeleton binding of the constructed human body model in motion state and the three-dimensional human body model specifically includes: matching the spatial size and proportion of the motion capture skeleton model to the three-dimensional human body model skeleton by using a three-dimensional modeling software; and associating the motion skeleton to the three-dimensional human body model skeleton node to drive the motion thereof by using a skeleton system combined with a constraint, a driver and a skeleton controller, to generate a three-dimensional dynamic human body model.

[0084] In one possible embodiment, the method for constructing a three-dimensional dynamic clothing model includes: inputting the three-dimensional dynamic human body model and the drawn two-dimensional clothing pattern into a three-dimensional virtual fitting software, setting the physical and mechanical performance attributes of the virtual fabric, and fitting the two-dimensional clothing pattern to the surface of the three-dimensional dynamic human body model by using a virtual sewing technology to generate a three-dimensional dynamic clothing model with fabric authenticity and dynamic adaptability.

[0085] Specifically, the three-dimensional dynamic human body model and the drawn two-dimensional clothing pattern are input into the three-dimensional virtual fitting software, the physical and mechanical performance attributes of the virtual fabric are set by using the fabric simulation function of the three-dimensional virtual fitting software, and the two-dimensional clothing pattern is fitted to the surface of the three-dimensional dynamic human body model by using a virtual sewing technology to complete the conversion of the clothing from a plane to a solid, and finally generate a three-dimensional dynamic clothing model with fabric authenticity and dynamic adaptability.

[0086] In this embodiment, the architecture of the three-dimensional virtual fitting software includes a human body parameterized modeling engine, a size driving system, a fabric physical simulator, a dynamic rendering pipeline and an adaptability evaluation module. The human body parameterized modeling engine generates a topologically structured editable digital three-dimensional human body model by inputting real human body shape data. The size driving system dynamically binds the clothing pattern parameters and the human body model to realize size-driven model deformation. The fabric physical simulator integrates nonlinear stretching, bending stiffness and friction coefficient to simulate the clothing-human interactive mechanical behavior. The dynamic rendering pipeline generates high-fidelity dressing visualization effects based on real-time ray tracing technology. The adaptability evaluation module quantifies the local pressure distribution and gap parameters. Through the architecture of the three-dimensional virtual fitting software, the whole process of digital reconstruction from two-dimensional pattern making to three-dimensional dynamic dressing effect simulation can be realized, the different motion postures of the human body can be simulated in real time, and the continuous change image of the clothing shape of the human body after dressing under the dynamic state can be generated.

[0087] In one possible embodiment, based on the three-dimensional dynamic human body model and the three-dimensional dynamic clothing model, the three-dimensional human body sub-model and the three-dimensional clothing sub-model under each motion key frame in a motion cycle are constructed, specifically including the following steps:

[0088] Step 1: performing space-time discretization processing on the three-dimensional dynamic human body model and the three-dimensional dynamic clothing model by using the three-dimensional virtual fitting software to divide the motion cycle into a plurality of motion key frames;

[0089] Step 2: For each motion key frame, synchronously extract the paired three-dimensional human body sub-model and three-dimensional garment sub-model.

[0090] In one possible embodiment, the human body feature region division is performed on the three-dimensional human body sub-model and the three-dimensional garment sub-model under each motion key frame, and the feature region overall model under each motion key frame is constructed, which specifically includes the following steps:

[0091] Step 1: For each motion key frame, the three-dimensional human body sub-model and the three-dimensional garment sub-model are aligned by using the reverse modeling software to construct the human body dressing sub-model under the motion key frame.

[0092] In this embodiment, the reverse modeling software includes high-precision point cloud processing, parameterized surface reconstruction and optimization, cross-platform data output and other modules. The three-dimensional human body sub-model and the three-dimensional garment sub-model are spatially aligned by high-precision point cloud processing to generate the human body dressing sub-model; the encapsulation of the model is completed by surface reconstruction and optimization; the core function of the reverse modeling software is to efficiently process three-dimensional scanning data, accurately reconstruct and optimize the editable CAD model, and realize the parameterized conversion of physical objects to digital design reverse engineering.

[0093] Step 2: Based on the human anatomy features, the human body feature region division is performed on the human body dressing sub-model under each motion key frame, the height of the feature region is set according to the physiological height of each part of the human body, the positioning plane is constructed along the height direction of the feature region, the cutting plane is set at the boundary of the feature region, the redundant part beyond the boundary of the feature region is deleted, and the feature region overall model under each motion key frame conforming to the human anatomy features is generated.

[0094] In one possible embodiment, the feature region overall model under each motion key frame is divided into several local domains with the barycenter as the reference axis, and the feature region local model under each motion key frame is constructed, which includes: for each feature region overall model under each motion key frame, taking the barycenter of the feature region overall model as the reference axis, the feature region overall model is orthogonally divided into four local regions along the sagittal plane and the coronal plane by using the double-plane segmentation method to construct the feature region local model under each motion key frame.

[0095] Specifically, for each feature region overall model under each motion key frame, according to different parts of the human body, muscle stretching patterns and garment fabric sliding trajectories, taking the barycenter of the feature region overall model as the reference axis, the feature region overall model is orthogonally divided into four local regions along the sagittal plane and the coronal plane by using the double-plane segmentation method to construct the feature region local model under each motion key frame.

[0096] In this embodiment, the calculation formula of the garment looseness required by the feature region local model under each motion key frame is:

[0097] ;

[0098] in, Indicates the first The first motion keyframe The required clothing looseness for each feature region's local model, in mm. , They represent the first The first motion keyframe The local upper and lower surface areas of the 3D human sub-model corresponding to each feature region, in mm. 2 , , They represent the first The first motion keyframe The local upper and lower surface areas of the 3D clothing sub-model corresponding to each feature region, in mm. 2 , Indicates the first The overall volume of the 3D human sub-model corresponding to the overall model of the feature region under each motion keyframe, in mm. 3 , , , They represent the first The first motion keyframe The local volume of the 3D human body sub-model, 3D clothing sub-model, and clothing fabric corresponding to the local model of each feature region, in mm. 3 , This indicates the height of the feature region, in mm.

[0099] In this embodiment, calculating the clothing looseness required for the overall model of the feature region within the motion cycle based on the clothing looseness required for the local model of the feature region under each motion keyframe specifically includes the following steps:

[0100] Step 1: Calculate the clothing looseness required for the overall model of the feature region under each motion keyframe based on the clothing looseness required for the local model of the feature region under each motion keyframe.

[0101] Specifically, the formula for calculating the clothing looseness required for the overall model of the feature regions in each motion keyframe is as follows:

[0102] ;

[0103] in, Indicates the first a garment looseness required by the feature region global model under each motion key frame, in mm, indicates that each feature region global model is divided into 4 feature region local models.

[0104] Step 2: According to the garment looseness required by the feature region global model under each motion key frame, calculate the garment looseness required by the feature region global model in the motion cycle.

[0105] Specifically, the calculation formula of the garment looseness required by the feature region global model in the motion cycle is:

[0106] ;

[0107] wherein, indicates the garment looseness required by the feature region global model in the motion cycle, in mm, indicates the total number of motion key frames in the motion cycle.

[0108] In this embodiment, the calculation formula of the garment looseness in the motion state is:

[0109] ;

[0110] wherein, indicates the garment looseness in the motion state, in mm.

[0111] The garment looseness determination method in the motion state provided by the embodiment of the present application realizes full-process digitalization relying on three-dimensional software and AI motion capture technology, from dynamic modeling, key frame extraction to looseness calculation, significantly improves the design efficiency and accuracy, reduces the repeated modification cost of physical sample clothes, breaks through the limitations of traditional static design, and provides a quantifiable and reusable technical path for functional optimization of thermal and moisture intelligent adjusting clothes and sports clothes.

[0112] The embodiment of the present application provides a garment looseness determination method in the motion state, which specifically comprises the following steps:

[0113] Step 1: Based on the constructed high-leg three-dimensional dynamic human body model and high-leg three-dimensional dynamic garment model, construct three-dimensional human body sub-models and three-dimensional garment sub-models under 14 high-leg motion key frames in the high-leg motion cycle;

[0114] In this embodiment, the measured human body shape data is input into the human model parameter module of the three-dimensional virtual fitting software to generate a high-kicking three-dimensional human body model that fits the real human body shape; the high-kicking three-dimensional human body model is input into a three-dimensional modeling software to construct a skeletal system that matches the shape characteristics of the high-kicking three-dimensional human body model, forming a three-dimensional static human body model integrated with the skeleton; since high-kicking is a periodic motion, the real motion trajectory data of the human body in the high-kicking motion cycle (high-kicking action selects frames 1, 3, 5, 11, 15, 17, 18, 19, 21, 23, 29, 33, 35, 36, a total of 14 frames, as high-kicking motion key frames) is obtained based on the AI motion capture technology to construct a human body skeletal model in the high-kicking state, and the constructed human body skeletal model in the high-kicking state is matched with the high-kicking three-dimensional human body model to construct a high-kicking three-dimensional dynamic human body model.

[0115] In this embodiment, the drawn two-dimensional garment template is tried on the high-kicking three-dimensional dynamic human body model through fabric simulation and virtual sewing functions, and then the high-kicking three-dimensional dynamic human body model in the simulation process is removed to generate a high-kicking three-dimensional dynamic garment model.

[0116] In this embodiment, the three-dimensional dynamic human body model and the three-dimensional dynamic garment model are disassembled into 14 high-kicking motion key frames in the high-kicking motion cycle, from which three-dimensional human body sub-models and three-dimensional garment sub-models under the 14 high-kicking motion key frames in the high-kicking motion cycle are respectively derived.

[0117] Step two: divide the three-dimensional human body sub-models and three-dimensional garment sub-models under the 14 high-kicking motion key frames into human feature area, and construct the hip feature area overall model under the 14 high-kicking motion key frames;

[0118] In this embodiment, the three-dimensional human body sub-models and three-dimensional garment sub-models under the 14 high-kicking motion key frames are registered through spatial coordinate registration to obtain the human body dressing sub-model under the 14 high-kicking motion key frames as shown in Figure 2 Next, the region with a longitudinal height of 210 mm of the hip is selected as the hip feature area, and the registered human body dressing sub-model under the 14 high-kicking motion key frames is precisely cut using a cutting tool, the upper and lower bottom surfaces of the human body dressing sub-model under the 14 high-kicking motion key frames are cut along the positioning plane of the height of the hip feature area, and the remaining regions are separated and deleted, only the hip feature area part is retained, and the hip feature area overall model under the 14 high-kicking motion key frames is constructed. The hip feature area overall model under 1 high-kicking motion key frame is as shown in Figure 3 Figure 3 ​In the embodiment, A is a three-dimensional human body sub-model corresponding to the hip feature region overall model under the high leg lifting motion key frame, B is a three-dimensional garment sub-model corresponding to the hip feature region overall model under the high leg lifting motion key frame, and C is the hip feature region overall model under the high leg lifting motion key frame.

[0119] Step three: the hip feature region overall model under the 14 high leg lifting motion key frames is divided into four local domains based on the gravity as the reference central axis, and the hip feature region local model under the 14 high leg lifting motion key frames is constructed;

[0120] In the embodiment, the hip feature region overall model under the 14 high leg lifting motion key frames is refined into four local domains of the left front, right front, left rear and right rear hip feature regions based on the gravity as the reference central axis, according to the hip feature, muscle stretching shape and garment fabric sliding track, and the left front, right front, left rear and right rear hip feature region local models are generated as shown in FIG. 4. Figure 4

[0121] Step four: according to the overall volume of the three-dimensional human body sub-model corresponding to the hip feature region overall model under the 14 high leg lifting motion key frames, the local upper surface area, local lower surface area and local volume of the three-dimensional human body sub-model and the three-dimensional garment sub-model corresponding to the hip feature region local model (left front, right front, left rear and right rear) under the 14 high leg lifting motion key frames, the local volume of the garment fabric corresponding to the hip feature region local model (left front, right front, left rear and right rear) under the 14 high leg lifting motion key frames, and the height of the hip feature region, the garment looseness required by the hip feature region local model (left front, right front, left rear and right rear) under the 14 high leg lifting motion key frames is calculated.

[0122] In the embodiment, the measurement data of the related parameters of the three-dimensional human body sub-model and the three-dimensional garment sub-model corresponding to the hip feature region under the 14 high leg lifting motion key frames is shown in Table 1.

[0123] Table 1: measurement data of related parameters of three-dimensional human body sub-model and three-dimensional garment sub-model corresponding to hip feature region under 14 high leg lifting motion key frames

[0124] .

[0125] In Table 1, respectively correspond to the left front, right front, left rear and right rear hip feature region local models.

[0126] Step five: according to the garment looseness required by the hip feature region local model (left front, right front, left rear and right rear) under the 14 high leg lifting motion key frames, the garment looseness required by the hip feature region overall model in the high leg lifting motion cycle is calculated.​

[0127] In this embodiment, the garment looseness required by the overall model of the hip feature region under the 14 high-leg movement key frames is calculated according to the garment looseness required by the local models of the hip feature region (left front, right front, left rear and right rear) under the 14 high-leg movement key frames, and the garment looseness required by the overall model of the hip feature region in the high-leg movement period is calculated according to the garment looseness required by the overall model of the hip feature region under the 14 high-leg movement key frames.

[0128] Step six: determining the garment looseness in the high-leg movement state according to the garment looseness required by the overall model of the hip feature region in the high-leg movement period.

[0129] In this embodiment, the calculation results of the garment looseness and the garment looseness are shown in Table 2, and the garment looseness required by the local models of the left front, right front, left rear and right rear hip feature regions under the 14 high-leg movement key frames is shown in Table 2. Figure 5

[0130] Table 2: Calculation results of garment looseness and garment looseness

[0131] .

[0132] In Table 2, corresponding to the left front, right front, left rear and right rear four hip feature region local models.

[0133] As shown in Table 2, the garment looseness required by the hip feature region under the 14 high-leg movement key frames has obvious differences, which shows that the embodiment can effectively plan the garment looseness required in the movement process, and provide more detailed data support for the garment looseness design.

[0134] The embodiment of the application provides a garment looseness determination device in a movement state, which comprises:

[0135] The model construction module is configured to construct three-dimensional human body sub-models and three-dimensional garment sub-models under each movement key frame in a movement period based on a three-dimensional dynamic human body model and a three-dimensional dynamic garment model, divide the three-dimensional human body sub-models and the three-dimensional garment sub-models under each movement key frame into human feature regions, construct overall feature region models under each movement key frame, and divide the overall feature region models under each movement key frame into a plurality of local domains with the gravity center as a reference central axis to construct local feature region models under each movement key frame.

[0136] ​The looseness calculation module is configured to calculate the garment looseness required by the local model of the feature region at each motion key frame according to the overall volume of the three-dimensional human body sub-model corresponding to the overall model of the feature region at each motion key frame, the local upper surface area, the local lower surface area and the local volume of the three-dimensional human body sub-model and the three-dimensional garment sub-model corresponding to the local model of the feature region at each motion key frame, the local volume of the garment fabric corresponding to the local model of the feature region at each motion key frame, and the height of the feature region; and calculate the garment looseness required by the overall model of the feature region in the motion cycle according to the garment looseness required by the local model of the feature region at each motion key frame.

[0137] The garment looseness determination module is configured to determine the garment looseness in the motion state according to the garment looseness required by the overall model of the feature region in the motion cycle.

[0138] The garment looseness determination device in the motion state provided by the embodiment of the present application can execute the garment looseness determination method in the motion state provided by the embodiment of the present application, and has the function modules and beneficial effects corresponding to the execution method.

[0139] The embodiment of the present application provides a computer device, comprising:

[0140] The storage medium is configured to store the computer program.

[0141] The processor is configured to execute the computer program to implement the garment looseness determination method in the motion state provided by the embodiment of the present application.

[0142] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the garment looseness determination method in the motion state provided by the embodiment of the present application.

[0143] The embodiment of the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the garment looseness determination method in the motion state provided by the embodiment of the present application.

[0144] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0145] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flows and / or block diagram block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart

[0146] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flows and / or block diagram block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart

[0147] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flows and / or block diagram block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps of the flowchart

[0148] The above merely provides the preferred embodiment of the present application, and it should be noted that for those skilled in the art, some improvements and modifications can be made without departing from the technical principles of the present application, and these improvements and modifications should also be considered as falling within the protection scope of the present application.

Claims

1. A method of determining a garment slack in a motion state, characterized by, The application comprises the following steps: Based on a three-dimensional dynamic human body model and a three-dimensional dynamic clothing model, three-dimensional human body sub-models and three-dimensional clothing sub-models under each key frame in a movement cycle are constructed; Human body feature region division is performed on the three-dimensional human body sub-models and the three-dimensional clothing sub-models under each key frame, and a feature region overall model under each key frame is constructed; The feature region overall model under each key frame is divided into a plurality of local domains based on the gravity as a reference central axis, and a feature region local model under each key frame is constructed; According to the overall volume of the three-dimensional human body sub-model corresponding to the feature region overall model under each key frame, the local upper surface area, the local lower surface area and the local volume of the three-dimensional human body sub-model and the three-dimensional clothing sub-model corresponding to the feature region local model under each key frame, the local volume of the clothing fabric corresponding to the feature region local model under each key frame, and the height of the feature region, the clothing looseness required by the feature region local model under each key frame is calculated; According to the clothing looseness required by the feature region local model under each key frame, the clothing looseness required by the feature region overall model in the movement cycle is calculated; According to the clothing looseness required by the feature region overall model in the movement cycle, the clothing slackness in the movement state is determined; The calculation formula of the clothing looseness required by the feature region local model under each key frame is: ； wherein, represents the garment looseness required by the local model of the th feature region under the th motion key frame, , respectively represent the local upper surface area and the local lower surface area of the three-dimensional human sub-model corresponding to the local model of the th feature region under the th motion key frame, , respectively represent the local upper surface area and the local lower surface area of the three-dimensional garment sub-model corresponding to the local model of the th feature region under the th motion key frame, represents the overall volume of the three-dimensional human sub-model corresponding to the overall model of the feature region under the th motion key frame, , , respectively represent the local volume of the three-dimensional human sub-model, the three-dimensional garment sub-model, and the garment fabric corresponding to the local model of the th feature region under the th motion key frame, represents the height of the feature region.

2. The method of claim 1, wherein The construction method of the three-dimensional dynamic human body model comprises the following steps: Human body shape data actually measured is input into three-dimensional virtual fitting software to generate a three-dimensional human body model that fits the actual human body shape; The three-dimensional human body model is input into three-dimensional modeling software to construct a skeleton system that matches the shape characteristics of the three-dimensional human body model, thereby forming a three-dimensional static human body model integrated with the skeleton; Real human body movement trajectory data is collected by using AI motion capture software, and skeleton joint movement data is generated; The skeleton joint movement data is input into the three-dimensional modeling software to match the posture and joint nodes with the three-dimensional static human body model integrated with the skeleton, thereby generating a three-dimensional dynamic human body model with continuous action characteristics.

3. The method of claim 1, wherein The construction method of the three-dimensional dynamic clothing model comprises the following steps: The three-dimensional dynamic human body model and the drawn two-dimensional clothing template are input into three-dimensional virtual fitting software, the physical and mechanical performance properties of the virtual fabric are set, the two-dimensional clothing template is fitted to the surface of the three-dimensional dynamic human body model by using virtual sewing technology, and a three-dimensional dynamic clothing model with fabric reality and dynamic adaptability is generated.

4. The method of claim 1, wherein Based on the three-dimensional dynamic human body model and the three-dimensional dynamic clothing model, three-dimensional human body sub-models and three-dimensional clothing sub-models under each key frame in a movement cycle are constructed, which comprises the following steps: The three-dimensional virtual fitting software is used to perform space-time discretization processing on the three-dimensional dynamic human body model and the three-dimensional dynamic clothing model, and the movement cycle is divided into a plurality of key frames; For each key frame, the paired three-dimensional human body sub-model and the three-dimensional clothing sub-model are synchronously extracted.

5. The method of claim 1, wherein Human body feature region division is performed on the three-dimensional human body sub-models and the three-dimensional clothing sub-models under each key frame, and a feature region overall model under each key frame is constructed, which comprises the following steps: For each motion key frame, a three-dimensional human body sub-model and a three-dimensional clothing sub-model are aligned by using reverse modeling software to construct a human body clothing sub-model under the motion key frame; Based on human anatomy features, the human body clothing sub-model under each motion key frame is divided into human feature regions, the height of the feature region is set according to the physiological height of each part of the human body, a positioning plane is constructed along the height direction of the feature region, a cutting plane is set at the boundary of the feature region, the redundant part beyond the boundary of the feature region is deleted, and a feature region overall model under each motion key frame conforming to the human anatomy features is generated.

6. The method of claim 1, wherein The feature region overall model under each motion key frame is divided into a plurality of local domains along the gravity center as the reference central axis to construct a feature region local model under each motion key frame, including: For the feature region overall model under each motion key frame, the feature region overall model is orthogonally divided into four local regions along the sagittal plane and the coronal plane by using a two-plane segmentation method with the gravity center of the feature region overall model as the reference central axis to construct the feature region local model under each motion key frame.

7. The method of claim 1, wherein According to the clothing looseness required by the feature region local model under each motion key frame, the clothing looseness required by the feature region overall model in the motion cycle is calculated, including: According to the clothing looseness required by the feature region local model under each motion key frame, the clothing looseness required by the feature region overall model under each motion key frame is calculated; According to the clothing looseness required by the feature region overall model under each motion key frame, the clothing looseness required by the feature region overall model in the motion cycle is calculated; The calculation formula of the clothing looseness required by the feature region overall model under each motion key frame is: ； wherein, represents the garment looseness required by the feature region global model under the th motion key frame, represents the garment looseness required by the th feature region local model under the th motion key frame, represents that each feature region global model is divided into 4 feature region local models; The calculation formula of the clothing looseness required by the feature region overall model in the motion cycle is: ； wherein, represents the garment looseness required by the overall model of the feature region within the motion cycle, represents the total number of key frames of the motion within the motion cycle.

8. The method of claim 1, wherein, The calculation formula of the clothing looseness in the motion state is: ； wherein, represents the garment looseness in the motion state, represents the garment looseness required by the overall model of the feature region in the motion cycle.

9. A device for determining the amount of looseness of a garment in a motion state, characterized by including: The model construction module is configured to construct, based on the three-dimensional dynamic human body model and the three-dimensional dynamic clothing model, the three-dimensional human body sub-model and the three-dimensional clothing sub-model under each motion key frame in the motion cycle; The human body feature region division is performed on the three-dimensional human body sub-model and the three-dimensional clothing sub-model under each motion key frame to construct the feature region overall model under each motion key frame; the feature region overall model under each motion key frame is divided into a plurality of local domains along the gravity center as the reference central axis to construct the feature region local model under each motion key frame; The looseness calculation module is configured to calculate, according to the overall volume of the three-dimensional human body sub-model corresponding to the feature region overall model under each motion key frame, the local upper surface area, the local lower surface area and the local volume of the three-dimensional human body sub-model and the three-dimensional clothing sub-model corresponding to the feature region local model under each motion key frame, the local volume of the clothing fabric corresponding to the feature region local model under each motion key frame, and the height of the feature region, the clothing looseness required by the feature region local model under each motion key frame; and calculate, according to the clothing looseness required by the feature region local model under each motion key frame, the clothing looseness required by the feature region overall model in the motion cycle. The garment slack determination module is configured to determine the garment slack in the motion state according to the garment looseness required by the overall model of the feature region in the motion cycle. The calculation formula of the garment looseness required by the local model of the feature region under each motion key frame is: ； in, Indicates the first The first motion keyframe The required clothing looseness for a local model of a feature region , They represent the first The first motion keyframe The local upper surface area and local lower surface area of ​​the 3D human body sub-model corresponding to the local model of each feature region. , They represent the first The first motion keyframe The local upper surface area and local lower surface area of ​​the 3D clothing sub-model corresponding to the local model of each feature region. Indicates the first The overall volume of the 3D human sub-model corresponding to the overall model of the feature region under each motion keyframe. , , They represent the first The first motion keyframe The local volume of the 3D human body sub-model, 3D clothing sub-model, and clothing fabric corresponding to the local model of each feature region. Indicates the height of the feature region.

Images