Method for determining looseness of clothes in motion state

Abstract

The invention discloses a method for determining clothing looseness in a motion state, which belongs to the technical field of clothing performance evaluation, and comprises the following steps: constructing a three-dimensional human body sub-model and a three-dimensional clothing sub-model under each motion key frame in a motion period, and carrying out human body feature region division to obtain a three-dimensional human body sub-model and a three-dimensional clothing sub-model; 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, and 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, calculating the overall volume of the three-dimensional human body sub-model; according to the local volume of the garment fabric and the height of the feature region corresponding to the feature region local model under each motion key frame, calculating the garment looseness required by the feature region local model under each motion key frame, and determining the garment looseness under the motion state. The method can solve the problem that a traditional static design method cannot accurately reflect human body motion form changes, and improves the precision of clothing looseness design in a motion state.

Description

Technical Field

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

[0002] Garment bulk, a key parameter affecting clothing fit and performance, exhibits significant differences between static and dynamic conditions. Under static conditions, the complex fluctuations of the human body's surface morphology lead to a non-uniform distribution of garment bulk. During exercise, however, the dynamic changes in multi-joint coordinated movements and the asymmetry of movement postures make the bulk distribution highly time-varying and spatially non-uniform. This dynamic characteristic not only increases the technical difficulty of accurately quantifying bulk, but also affects the heat and moisture transfer efficiency of clothing, leading to localized heat accumulation or sweat retention, and even restricting freedom of movement. Therefore, the precise characterization of dynamic bulk is of great significance for optimizing clothing functional design. It can promote the transformation of clothing design from traditional homogenization to zoning parameterization, and provide theoretical support for the development of high-performance sports equipment.

[0003] Existing technologies (such as Chinese patents with publication numbers CN117313182A and CN109978837A) are mainly based on traditional historical body shape statistics and two-dimensional image analysis methods to obtain the looseness of clothing. Although the statistical method based on historical body shape data can realize body shape classification and looseness prediction, it is only applicable to clothing design in static postures and cannot reflect the dynamic changes in human body shape in motion. Although the fit evaluation technology relying on two-dimensional image analysis realizes the unified evaluation of visual comfort and objective fit, it is limited by the lack of information on the two-dimensional plane and it is difficult to accurately quantify the three-dimensional spatial relationship between clothing and the human body. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for determining the looseness of clothing in a moving state, which can solve the problem that traditional static design methods cannot accurately reflect the changes in human body movement morphology and improve the accuracy of clothing looseness design in a moving state.

[0005] In order to achieve the above object, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for determining the looseness of clothing in a moving state, comprising: Based on the 3D dynamic human body model and the 3D dynamic clothing model, a 3D human body sub-model and a 3D clothing sub-model are constructed under each motion key frame in the motion cycle; Divide the 3D human body sub-model and 3D clothing sub-model under each motion key frame into human body feature regions, and construct an overall model of the feature regions under each motion key frame; The overall model of the feature region under each motion key frame is divided into several local domains with the center of gravity as the reference axis, and the local model of the feature region under each motion key frame is constructed; Calculate the required clothing looseness of the local model of the feature region under each motion key frame based on the overall volume of the 3D human body sub-model corresponding to the overall model of the feature region under each motion key frame, the local upper surface area, local lower surface area, and local volume of the 3D human body sub-model and the 3D clothing sub-model corresponding to the local model of the feature region under each motion key frame, the local volume of the clothing fabric corresponding to the local model of the feature region under each motion key frame, and the height of the feature region; According to the clothing looseness required by the local model of the feature area under each motion key frame, the clothing looseness required by the overall model of the feature area in the motion cycle is calculated; The looseness of the clothing in the motion state is determined according to the clothing looseness required by the overall model of the characteristic area during the motion cycle.

[0006] In combination with the first aspect, further, a method for constructing a three-dimensional dynamic human body model includes: Input the measured human body shape data into the 3D virtual fitting software to generate a 3D human body model that fits the real human body shape; Inputting the three-dimensional human body model into three-dimensional modeling software, constructing a skeletal system that matches the morphological characteristics of the three-dimensional human body model, and forming a three-dimensional static human body model with integrated bones; Use AI motion capture software to collect real human motion trajectory data and generate skeletal joint motion data; The skeletal joint motion data is input into the 3D modeling software, and the posture and joint points are matched with the 3D static human body model with integrated skeleton to generate a 3D dynamic human body model with continuous motion characteristics.

[0007] In combination with the first aspect, further, the method for constructing a three-dimensional dynamic clothing model includes: The three-dimensional dynamic human body model and the drawn two-dimensional clothing sample are input into the three-dimensional virtual fitting software, the physical and mechanical properties of the virtual fabric are set, and the two-dimensional clothing sample is attached to the surface of the three-dimensional dynamic human body model using virtual stitching technology to generate a three-dimensional dynamic clothing model with fabric authenticity and dynamic adaptability.

[0008] In combination with the first aspect, further, based on the three-dimensional dynamic human body model and the three-dimensional dynamic clothing model, constructing the three-dimensional human body sub-model and the three-dimensional clothing sub-model under each motion key frame in the motion cycle includes: The 3D virtual fitting software is used to perform spatiotemporal discretization on the 3D dynamic human body model and the 3D dynamic clothing model, and the motion cycle is decomposed into several motion key frames. For each motion keyframe, a paired 3D human body sub-model and 3D clothing sub-model are extracted synchronously.

[0009] In combination with the first aspect, further dividing the 3D human body sub-model and the 3D clothing sub-model under each motion key frame into human body feature regions and constructing an overall model of the feature regions under each motion key frame includes: For each motion keyframe, the 3D human body sub-model and the 3D clothing sub-model are aligned using inverse modeling software to construct the human clothing sub-model under the motion keyframe; Based on the human anatomical characteristics, the human clothing sub-model under each motion key frame is divided into human feature areas. The height of the feature area 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 area, and a clipping plane is set at the boundary of the feature area. The redundant parts beyond the boundary of the feature area are deleted to generate an overall model of the feature area under each motion key frame that conforms to the human anatomical characteristics.

[0010] In combination with the first aspect, further, the overall model of the feature region under each motion key frame is divided into a plurality of local domains with the center of gravity as the reference axis, and the local model of the feature region under each motion key frame is constructed, including: For the overall model of the feature region under each motion key frame, the center of gravity of the overall model of the feature region is used as the reference central axis, and the dual-plane segmentation method is used to orthogonally divide the overall model of the feature region along the sagittal plane and the coronal plane into four local regions to form the local model of the feature region under each motion key frame.

[0011] In combination with the first aspect, further, the calculation formula for the clothing looseness required by the local model of the feature area under each motion key frame is: ; in, Indicates the The first motion keyframe The clothing looseness required by the local model of the feature area, 、 Respectively represent The first motion keyframe The local upper surface area and the local lower surface area of ​​the 3D human body sub-model corresponding to the local model of the feature region, 、 Respectively represent The first motion keyframe The local upper surface area and the local lower surface area of ​​the 3D clothing sub-model corresponding to the local model of the feature area, Indicates the The overall volume of the 3D human body sub-model corresponding to the overall model of the feature area under the motion key frame, 、 、 Respectively represent 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 the feature area, Indicates the height of the feature area.

[0012] In combination with the first aspect, further, according to the clothing looseness required by the local model of the feature area under each motion key frame, calculating the clothing looseness required by the overall model of the feature area in the motion cycle includes: Calculate the clothing looseness required by the overall model of the feature region under each motion key frame according to the clothing looseness required by the local model of the feature region under each motion key frame; Calculate the clothing looseness required by the overall model of the feature area in the motion cycle according to the clothing looseness required by the overall model of the feature area under each motion key frame; The calculation formula for the clothing looseness required by the overall model of the feature area under each motion key frame is: ; in, Indicates the The clothing looseness required by the overall model of the feature area under the motion key frame, Indicates the The first motion keyframe The clothing looseness required by the local model of the feature area, Indicates that the overall model of each feature region is divided into four feature region local models; The calculation formula for the clothing looseness required by the overall model of the characteristic area during the movement cycle is: ; in, Indicates the clothing looseness required by the overall model of the feature area during the motion cycle, Indicates the total number of motion keyframes in the motion cycle.

[0013] Combined with the first aspect, further, the calculation formula for the looseness of clothing in the exercise state is: ; in, Indicates the amount of looseness in clothing during exercise. Indicates the clothing looseness required by the overall model of the feature area during the motion cycle.

[0014] In a second aspect, the present invention provides a device for determining the looseness of clothing in a moving state, comprising: The model construction module is used to construct a 3D human body sub-model and a 3D clothing sub-model under each motion key frame within the motion cycle based on the 3D dynamic human body model and the 3D dynamic clothing model; divide the 3D human body sub-model and the 3D clothing sub-model under each motion key frame into human feature regions and construct an overall model of the feature region under each motion key frame; divide the overall model of the feature region under each motion key frame into several local domains with the center of gravity as the reference axis and construct a local model of the feature region under each motion key frame; The looseness calculation module is used to calculate the clothing looseness required by the local model of the characteristic region under each motion key frame based on the overall volume of the three-dimensional human body sub-model corresponding to the overall model of the characteristic region under each motion key frame, the local upper surface area, local lower surface area and local volume of the three-dimensional human body sub-model and the three-dimensional clothing sub-model corresponding to the local model of the characteristic region under each motion key frame, the local volume of the clothing fabric corresponding to the local model of the characteristic region under each motion key frame, and the height of the characteristic region; based on the clothing looseness required by the local model of the characteristic region under each motion key frame, calculate the clothing looseness required by the overall model of the characteristic region within the motion cycle; The clothing looseness determination module is used to determine the looseness of clothing in the motion state according to the clothing looseness required by the overall model of the characteristic area in the motion cycle.

[0015] In a third aspect, the present invention provides a computer device, comprising: Storage medium for storing computer programs; A processor is used to execute the computer program to implement the method for determining the looseness of clothing in a moving state described in the first aspect.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining the looseness of clothing in a moving state described in the first aspect.

[0017] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method for determining the looseness of clothing in a moving state described in the first aspect.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The method for determining the looseness of clothing in motion provided by the present invention is based on a three-dimensional dynamic human body model and a three-dimensional dynamic clothing model, combined with motion key frame analysis, to capture the real-time interaction state between the human body and clothing during the motion cycle. It can solve the problems that traditional static determination methods cannot accurately reflect the changes in human motion morphology and lack a scientific quantitative basis for looseness distribution.

[0019] By adopting feature area partition modeling and multi-dimensional geometric parameter calculation, the local model of the feature area under the motion key frame is extracted, and according to the multi-dimensional parameters such as volume and surface area of ​​the three-dimensional human body sub-model and three-dimensional clothing sub-model corresponding to the overall model of the feature area and the local model of the feature area under each motion key frame, the clothing looseness required by the local model of the feature area under each motion key frame is calculated, and the clothing looseness distribution in each motion stage is dynamically optimized. This can realize scientific quantitative design, improve the accuracy of clothing looseness design under motion state, reduce the reliance on physical sample iteration, and realize precise design optimization of comfort and functionality of sportswear. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of a method for determining the looseness of clothing in a sports state provided by an embodiment of the present invention; Figure 2 14 is a schematic diagram of a human clothing sub-model under 14 high-leg-raising motion key frames provided by an embodiment of the present invention; Figure 3 : This is a schematic diagram of the overall model of the hip feature area under a high-leg-raising motion keyframe provided by an embodiment of the present invention, wherein A is a 3D human body sub-model corresponding to the overall model of the hip feature area under the high-leg-raising motion keyframe, B is a 3D clothing sub-model corresponding to the overall model of the hip feature area under the high-leg-raising motion keyframe, and C is the overall model of the hip feature area under the high-leg-raising motion keyframe; Figure 4 1 is a schematic diagram of a local model of four hip feature areas under a high-leg-raising motion key frame provided by an embodiment of the present invention; Figure 5 This is a schematic diagram of the clothing looseness required for the local models of the four hip feature areas, namely the left front, right front, left back, and right back, under the 14 high-leg-raising movement key frames provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention will be further described in detail below in conjunction with specific implementation methods.

[0022] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0023] An embodiment of the present invention provides a method for determining the looseness of clothing in a moving state, comprising: Based on the 3D dynamic human body model and the 3D dynamic clothing model, a 3D human body sub-model and a 3D clothing sub-model are constructed under each motion key frame in the motion cycle; Divide the 3D human body sub-model and 3D clothing sub-model under each motion key frame into human body feature regions, and construct an overall model of the feature regions under each motion key frame; The overall model of the feature region under each motion key frame is divided into several local domains with the center of gravity as the reference axis, and the local model of the feature region under each motion key frame is constructed; Calculate the required clothing looseness of the local model of the feature region under each motion key frame based on the overall volume of the 3D human body sub-model corresponding to the overall model of the feature region under each motion key frame, the local upper surface area, local lower surface area, and local volume of the 3D human body sub-model and the 3D clothing sub-model corresponding to the local model of the feature region under each motion key frame, the local volume of the clothing fabric corresponding to the local model of the feature region under each motion key frame, and the height of the feature region; According to the clothing looseness required by the local model of the feature area under each motion key frame, the clothing looseness required by the overall model of the feature area in the motion cycle is calculated; The looseness of the clothing in the motion state is determined according to the clothing looseness required by the overall model of the characteristic area during the motion cycle.

[0024] The method for determining the looseness of clothing in motion provided by an embodiment of the present invention is based on a three-dimensional dynamic human body model and a three-dimensional dynamic clothing model. By disassembling motion key frames, the dynamic changes of looseness are captured, and a complete technical chain of dynamic modeling-key frame extraction-partition calculation-looseness output is established. It breaks through the limitations of traditional static measurement methods and can accurately capture the real-time deformation characteristics of various parts of the human body during motion. The use of feature area partition modeling and multi-dimensional geometric parameter calculation can further improve the design accuracy of clothing looseness in motion, and quantify the clothing design looseness required for each feature area of ​​clothing in motion with high precision, providing a scientific basis for digital clothing development. Compared with the traditional optimization process that relies on repeated trial and error of physical samples, the present invention significantly improves design efficiency, is particularly suitable for the precise development of high-performance sports equipment, and has important engineering application value.

[0025] Figure 1 This is a flow chart of a method for determining the amount of loose clothing in a sports state provided by an embodiment of the present invention. This flow chart only shows the logical sequence of the method of this embodiment. Different methods can be used without conflict. Figure 1 The steps shown or described are accomplished in the order shown.

[0026] The method for determining the looseness of clothing in a moving state provided by an embodiment of the present invention can be applied to a terminal and can be executed by a device for determining the looseness of clothing in a moving state. The device can be implemented by software and / or hardware, and the device can be integrated into a terminal, for example: any tablet computer or computer device with communication function.

[0027] In one possible embodiment, the method for constructing a three-dimensional dynamic human body model specifically includes the following steps: Step 1: Input the measured human body shape data into the 3D virtual fitting software to generate a 3D human body model that fits the real human body shape; 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.

[0028] In this embodiment, the architecture of the three-dimensional virtual fitting software includes a human body parametric modeling engine. The human body parametric modeling engine generates a digital three-dimensional human body model with an editable topological structure by inputting real human body morphological data. This technology measures real human body morphological data, focusing on collecting data on key parts such as height, shoulders and neck, chest and back, waist and hips, and inputs the real human body morphological data into the human model of the virtual fitting software to obtain a digital three-dimensional human body model.

[0029] Step 2: Input the 3D human body model into the 3D modeling software to construct a skeletal system that matches the morphological characteristics of the 3D human body model, thereby forming a 3D static human body model with integrated skeleton; Step 3: Use AI motion capture software to collect real human motion trajectory data and generate skeletal joint motion data; Specifically, AI motion capture software is used to collect real human motion trajectory data. Against an open background, a fixed-position camera is used to shoot a motion video of the target human body, and the motion video is input into the AI ​​motion capture software to generate skeletal joint motion data.

[0030] In this embodiment, AI motion capture technology is a three-dimensional motion measurement technique based on multimodal sensing technology. Its core principle is to track the position and rotation of key points (such as joints and bones) in three-dimensional space through the device, and then map this data to the virtual character or model. Advanced deep learning algorithms analyze and recognize video data in real time, enabling accurate recognition and monitoring of human movements.

[0031] Using AI motion capture technology to capture real-world human motion trajectory data and construct a human skeleton model in motion involves using a custom suit with an integrated micro-inertial measurement unit (IMU) to capture the model's displacement and rotation data through an inertial motion capture system. The captured motion files are wirelessly transmitted to 3D modeling software. After noise reduction, smoothing, and correction, a human skeleton model in motion is constructed, including the skeletal structure, time series, and 3D spatial coordinates of each bone. A mapping list ensures one-to-one correspondence between bone names, and the data for the animated bones is then transferred to the driver bones.

[0032] Step 4: Input the skeletal joint motion data into the 3D modeling software, match the posture and joint points with the 3D static human body model with integrated skeleton, and generate a 3D dynamic human body model with continuous motion characteristics.

[0033] In this embodiment, the core architecture of the 3D modeling software integrates modeling, rendering, animation, simulation, and post-production compositing modules, specifically character animation control tools based on a skeletal system, inverse kinematics (IK), forward kinematics (FK), and a physics engine. This 3D modeling software can construct a skeletal structure within a 3D human model and, by controlling the skeletal joints, enable the 3D human model to move and change postures.

[0034] The skeleton binding of the constructed human skeleton model in motion state with the three-dimensional human body model specifically includes: using three-dimensional modeling software to match the spatial size and proportion of the motion capture skeleton model to the three-dimensional human body model skeleton; using the skeleton system combined with constraints, drivers and skeleton controllers to associate the motion skeleton with the three-dimensional human body model skeleton nodes to drive its movement, thereby generating a three-dimensional dynamic human body model.

[0035] In one possible embodiment, a method for constructing a three-dimensional dynamic clothing model includes: inputting a three-dimensional dynamic human body model and a drawn two-dimensional clothing sample into three-dimensional virtual fitting software, setting the physical and mechanical properties of the virtual fabric, and using virtual stitching technology to fit the two-dimensional clothing sample to the surface of the three-dimensional dynamic human body model to generate a three-dimensional dynamic clothing model with fabric authenticity and dynamic adaptability.

[0036] Specifically, the three-dimensional dynamic human body model and the drawn two-dimensional clothing sample are input into the three-dimensional virtual fitting software, and the physical and mechanical properties of the virtual fabric are set using the fabric simulation function of the three-dimensional virtual fitting software. Then, the two-dimensional clothing sample is fitted to the surface of the three-dimensional dynamic human body model using virtual stitching technology to complete the transformation of the clothing from plane to three-dimensional, and finally a three-dimensional dynamic clothing model with fabric authenticity and dynamic adaptability is generated.

[0037] In this embodiment, the architecture of the 3D virtual fitting software includes a human body parametric modeling engine, a dimension-driven system, a fabric physics simulator, a dynamic rendering pipeline, and a fit assessment module. The human body parametric modeling engine generates a topologically editable digital 3D human body model by inputting real human body morphological data. The dimension-driven system dynamically binds garment cutting parameters to the human body model to achieve dimension-driven model deformation. The fabric physics simulator integrates nonlinear stretching, bending stiffness, and friction coefficient to simulate the mechanical behavior of clothing-human interaction. The dynamic rendering pipeline generates high-fidelity dressing visualization effects based on real-time ray tracing technology. The fit assessment module quantifies local pressure distribution and gap parameters. Through the architecture of the 3D virtual fitting software, the entire process from 2D sample production to 3D dynamic dressing effect simulation can be digitally reconstructed, simulating different human motion postures in real time and generating dynamic images of the continuously changing clothing shape after the human body is dressed.

[0038] In one possible embodiment, based on the 3D dynamic human body model and the 3D dynamic clothing model, constructing the 3D human body sub-model and the 3D clothing sub-model at each motion key frame in the motion cycle specifically includes the following steps: Step 1: Use 3D virtual fitting software to perform spatiotemporal discretization on the 3D dynamic human body model and the 3D dynamic clothing model, and decompose the motion cycle into several motion key frames; Step 2: For each motion keyframe, synchronously extract the paired 3D human body sub-model and 3D clothing sub-model.

[0039] In one possible embodiment, dividing the 3D human body sub-model and the 3D clothing sub-model under each motion key frame into human body feature regions and constructing an overall model of the feature regions under each motion key frame specifically includes the following steps: Step 1: For each motion keyframe, use inverse modeling software to align the 3D human body sub-model with the 3D clothing sub-model to construct the human clothing sub-model under the motion keyframe; In this embodiment, the reverse modeling software includes modules such as high-precision point cloud processing, parametric surface reconstruction and optimization, and cross-platform data output. High-precision point cloud processing spatially aligns the 3D human submodel with the 3D clothing submodel to generate the human clothing submodel. Surface reconstruction and optimization complete the model packaging. The core function of the reverse modeling software is to efficiently process 3D scan data, accurately reconstruct and optimize it into an editable CAD model, and implement parametric reverse engineering to convert physical objects into digital designs.

[0040] Step 2: Based on the human anatomical characteristics, the human clothing sub-model under each motion key frame is divided into human feature areas. The height of the feature area 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 area. A clipping plane is set at the boundary of the feature area, and the redundant parts beyond the boundary of the feature area are deleted to generate an overall model of the feature area under each motion key frame that conforms to the human anatomical characteristics.

[0041] In one possible embodiment, the overall model of the feature region under each motion key frame is divided into several local domains with the center of gravity as the reference central axis, and the local model of the feature region under each motion key frame is constructed, including: for the overall model of the feature region under each motion key frame, the center of gravity of the overall model of the feature region is used as the reference central axis, and the overall model of the feature region is orthogonally divided into 4 local regions along the sagittal plane and the coronal plane using a dual-plane segmentation method to form the local model of the feature region under each motion key frame.

[0042] Specifically, for the overall model of the characteristic area under each motion key frame, according to different parts of the human body, muscle stretching shapes and sliding trajectories of clothing fabrics, the center of gravity of the overall model of the characteristic area is used as the reference central axis, and the dual-plane segmentation method is used to orthogonally divide the overall model of the characteristic area into four local areas, namely left front, left back, right front and right back, along the sagittal plane and coronal plane, forming the local model of the characteristic area under each motion key frame.

[0043] In this embodiment, the calculation formula for the clothing looseness required by the local model of the feature area under each motion key frame is: ; in, Indicates the The first motion keyframe The clothing looseness required by the local model of the feature area, in mm, 、 Respectively represent 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 the feature region, in mm 2 , 、 Respectively represent 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 the feature area, in mm 2 , Indicates the The overall volume of the 3D human body sub-model corresponding to the overall model of the feature area under the motion key frame, in mm 3 , 、 、 Respectively represent 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 the feature area, in mm 3 , Indicates the height of the feature area in mm.

[0044] In this embodiment, the calculation of the clothing looseness required by the overall model of the feature region in the motion cycle according to the clothing looseness required by the local model of the feature region under each motion key frame specifically includes the following steps: Step 1: Calculate the clothing looseness required by the overall model of the feature region under each motion key frame based on the clothing looseness required by the local model of the feature region under each motion key frame; Specifically, the calculation formula for the clothing looseness required by the overall model of the feature area under each motion key frame is: ; in, Indicates the The clothing looseness required by the overall model of the feature area under the motion key frame, in mm, Indicates that the overall model of each feature region is divided into four feature region local models.

[0045] Step 2: Calculate the clothing looseness required by the overall model of the feature area in the motion cycle based on the clothing looseness required by the overall model of the feature area under each motion key frame.

[0046] Specifically, the calculation formula for the clothing looseness required by the overall model of the characteristic area during the motion cycle is: ; in, Indicates the clothing looseness required by the overall model of the feature area during the motion cycle, in mm. Indicates the total number of motion keyframes in the motion cycle.

[0047] In this embodiment, the calculation formula for the looseness of clothing in the exercise state is: ; in, Indicates the looseness of clothing when in motion, in mm.

[0048] The method for determining the looseness of clothing in motion provided by an embodiment of the present invention relies on three-dimensional software and AI motion capture technology to achieve full-process digitization, from dynamic modeling, key frame extraction to looseness calculation, significantly improving design efficiency and accuracy, reducing the cost of repeated modification of physical samples, breaking through the limitations of traditional static design, and providing a quantifiable and reusable technical path for the functional optimization of thermal and moisture intelligent regulation clothing and sportswear.

[0049] An embodiment of the present invention provides a method for determining the looseness of clothing in a sports state, which specifically includes the following steps: Step 1: Based on the constructed high-leg-raising 3D dynamic human body model and high-leg-raising 3D dynamic clothing model, construct a 3D human body sub-model and a 3D clothing sub-model under 14 high-leg-raising motion key frames within the high-leg-raising motion cycle; In this embodiment, the measured human body morphological data is input into the human body model parameter module of the three-dimensional virtual fitting software to generate a high-leg-raising three-dimensional human body model that fits the real human body morphology; the high-leg-raising three-dimensional human body model is input into the three-dimensional modeling software to construct a skeletal system that matches the morphological characteristics of the high-leg-raising three-dimensional human body model to form a three-dimensional static human body model with integrated skeleton; since high-leg raising is a periodic movement, the real motion trajectory data of the human body during the high-leg raising movement cycle (the 1st, 3rd, 5th, 11th, 15th, 17th, 18th, 19th, 21st, 23rd, 29th, 33rd, 35th, and 36th frames, a total of 14 frames, are selected as key frames of the high-leg raising movement) are obtained based on AI motion capture technology to construct a human skeleton model in the high-leg raising state, and the constructed human skeleton model in the high-leg raising state is matched with the high-leg raising three-dimensional human body model to construct a high-leg raising three-dimensional dynamic human body model.

[0050] In this embodiment, the drawn two-dimensional clothing sample is tried on a high-leg-raising three-dimensional dynamic human body model through fabric simulation and virtual stitching functions, and then the high-leg-raising three-dimensional dynamic human body model is eliminated during the simulation process to generate a high-leg-raising three-dimensional dynamic clothing model.

[0051] In this embodiment, the three-dimensional dynamic human body model and the three-dimensional dynamic clothing model are disassembled into 14 high-leg-raising motion key frames within the high-leg-raising motion cycle, from which the three-dimensional human body sub-model and the three-dimensional clothing sub-model under the 14 high-leg-raising motion key frames within the high-leg-raising motion cycle are derived respectively.

[0052] Step 2: Divide the 3D human body sub-model and 3D clothing sub-model under the 14 high-leg-lifting motion keyframes into human body feature regions, and construct an overall model of the hip feature region under the 14 high-leg-lifting motion keyframes; In this embodiment, the 3D human body sub-model and the 3D clothing sub-model under the 14 high-leg-lifting movement key frames are registered by spatial coordinate registration to obtain the following: Figure 2The human clothing sub-models under the 14 high-leg-raising key frames shown in the figure are as follows; next, the area with a longitudinal height of 210 mm of the hips is selected as the hip feature area, and the cropping tool is used to accurately cut the human clothing sub-models under the 14 high-leg-raising key frames after registration. The upper and lower bottom surfaces of the human clothing sub-models under the 14 high-leg-raising key frames are cropped along the positioning plane of the height of the hip feature area, and the remaining areas are separated and deleted, leaving only the hip feature area part, and constructing the overall model of the hip feature area under the 14 high-leg-raising key frames. The overall model of the hip feature area under 1 high-leg-raising key frame is shown in Figure 1. Figure 3 As shown, Figure 3 In the figure, A is the three-dimensional human body sub-model corresponding to the overall model of the hip feature area under the high-leg-raising motion key frame, B is the three-dimensional clothing sub-model corresponding to the overall model of the hip feature area under the high-leg-raising motion key frame, and C is the overall model of the hip feature area under the high-leg-raising motion key frame.

[0053] Step 3: Divide the overall model of the hip feature area under the 14 high-leg-raising keyframes into four local domains based on the center of gravity as the reference axis, and construct the local model of the hip feature area under the 14 high-leg-raising keyframes; In this embodiment, the overall model of the hip feature area under the 14 high-leg-raising movement key frames is refined into four local domains of the hip feature area, namely the left front, right front, left back, and right back, based on the hip features, muscle stretching form, and clothing fabric sliding trajectory, to generate the following: Figure 4 The local models of four hip feature areas are shown: left front, right front, left back, and right back.

[0054] Step 4: Calculate the required clothing looseness of the local models of the hip feature areas (left front, right front, left back, right back) under the 14 keyframes of the high-leg-raising motion based on the overall volume of the 3D human sub-model corresponding to the overall model of the hip feature areas under the 14 keyframes of the high-leg-raising motion, the local upper surface area, local lower surface area, and local volume of the 3D human sub-model and 3D clothing sub-model corresponding to the local models of the hip feature areas (left front, right front, left back, right back) under the 14 keyframes of the high-leg-raising motion, the local volume of the clothing fabric corresponding to the local models of the hip feature areas (left front, right front, left back, right back) under the 14 keyframes of the high-leg-raising motion, and the height of the hip feature areas; In this embodiment, the measurement data of the relevant parameters of the 3D human body sub-model and the 3D clothing sub-model corresponding to the hip feature areas under the 14 high-leg-raising movement key frames are shown in Table 1.

[0055] Table 1: Measurement data of relevant parameters of the 3D human body sub-model and 3D clothing sub-model corresponding to the hip feature area under 14 high-leg movement key frames .

[0056] In Table 1, They correspond to the local models of four hip feature areas: left front, right front, left back, and right back.

[0057] Step 5: Based on the clothing looseness required by the local models of the hip feature area (left front, right front, left back, right back) under the 14 high-leg-raising movement key frames, calculate the clothing looseness required by the overall model of the hip feature area during the high-leg-raising movement cycle; In this embodiment, the clothing looseness required for the overall model of the hip feature area under the 14 high-leg-raising motion key frames is first calculated based on the clothing looseness required for the local model of the hip feature area (left front, right front, left back, right back) under the 14 high-leg-raising motion key frames. Then, the clothing looseness required for the overall model of the hip feature area under the 14 high-leg-raising motion key frames is calculated based on the clothing looseness required for the overall model of the hip feature area during the high-leg-raising motion cycle.

[0058] Step 6: Determine the amount of looseness of the clothing during the high-leg-raising exercise state based on the clothing looseness required by the overall model of the hip characteristic area during the high-leg-raising exercise cycle.

[0059] In this embodiment, the calculation results of clothing looseness and clothing looseness are shown in Table 2. The clothing looseness required by the local model of the four hip feature regions, namely the left front, right front, left back, and right back, under 14 high-leg movement key frames is as follows: Figure 5 shown.

[0060] Table 2: Calculation results of clothing looseness and clothing volume .

[0061] In Table 2, They correspond to the local models of four hip feature areas: left front, right front, left back, and right back.

[0062] As can be seen from Table 2, there are obvious differences in the clothing looseness required for the hip feature area under the 14 high-leg-raising movement key frames, indicating that this embodiment can effectively plan the clothing looseness required during the movement process and provide more detailed data support for clothing looseness design.

[0063] An embodiment of the present invention provides a device for determining the looseness of clothing in a moving state, comprising: The model construction module is used to construct a 3D human body sub-model and a 3D clothing sub-model under each motion key frame within the motion cycle based on the 3D dynamic human body model and the 3D dynamic clothing model; divide the 3D human body sub-model and the 3D clothing sub-model under each motion key frame into human feature regions and construct an overall model of the feature region under each motion key frame; divide the overall model of the feature region under each motion key frame into several local domains with the center of gravity as the reference axis and construct a local model of the feature region under each motion key frame; The looseness calculation module is used to calculate the clothing looseness required by the local model of the characteristic region under each motion key frame based on the overall volume of the three-dimensional human body sub-model corresponding to the overall model of the characteristic region under each motion key frame, the local upper surface area, local lower surface area and local volume of the three-dimensional human body sub-model and the three-dimensional clothing sub-model corresponding to the local model of the characteristic region under each motion key frame, the local volume of the clothing fabric corresponding to the local model of the characteristic region under each motion key frame, and the height of the characteristic region; based on the clothing looseness required by the local model of the characteristic region under each motion key frame, calculate the clothing looseness required by the overall model of the characteristic region within the motion cycle; The clothing looseness determination module is used to determine the looseness of clothing in the motion state according to the clothing looseness required by the overall model of the characteristic area in the motion cycle.

[0064] The device for determining the looseness of clothing in a moving state provided by an embodiment of the present invention can execute the method for determining the looseness of clothing in a moving state provided by an embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0065] An embodiment of the present invention provides a computer device, including: Storage medium for storing computer programs; The processor is used to execute a computer program to implement the method for determining the looseness of clothing in a moving state provided by an embodiment of the present invention.

[0066] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for determining the looseness of clothing in a moving state provided by an embodiment of the present invention is implemented.

[0067] This embodiment provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for determining the looseness of clothing in a moving state provided by the embodiment of the present invention is implemented.

[0068] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0069] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0070] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0072] The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining the looseness of clothing in a sports state, characterized in that: include: Based on the 3D dynamic human body model and the 3D dynamic clothing model, a 3D human body sub-model and a 3D clothing sub-model are constructed under each motion key frame in the motion cycle; Divide the 3D human body sub-model and 3D clothing sub-model under each motion key frame into human body feature regions, and construct an overall model of the feature regions under each motion key frame; The overall model of the feature region under each motion key frame is divided into several local domains with the center of gravity as the reference axis, and the local model of the feature region under each motion key frame is constructed; Calculate the required clothing looseness of the local model of the feature region under each motion key frame based on the overall volume of the 3D human body sub-model corresponding to the overall model of the feature region under each motion key frame, the local upper surface area, local lower surface area, and local volume of the 3D human body sub-model and the 3D clothing sub-model corresponding to the local model of the feature region under each motion key frame, the local volume of the clothing fabric corresponding to the local model of the feature region under each motion key frame, and the height of the feature region; According to the clothing looseness required by the local model of the feature area under each motion key frame, the clothing looseness required by the overall model of the feature area in the motion cycle is calculated; The looseness of the clothing in the motion state is determined according to the clothing looseness required by the overall model of the characteristic area during the motion cycle.

2. The method for determining the looseness of clothing in a sports state according to claim 1, characterized in that: The method for constructing a three-dimensional dynamic human body model includes: Input the measured human body shape data into the 3D virtual fitting software to generate a 3D human body model that fits the real human body shape; Inputting the three-dimensional human body model into three-dimensional modeling software, constructing a skeletal system that matches the morphological characteristics of the three-dimensional human body model, and forming a three-dimensional static human body model with integrated bones; Use AI motion capture software to collect real human motion trajectory data and generate skeletal joint motion data; The skeletal joint motion data is input into the 3D modeling software, and the posture and joint points are matched with the 3D static human body model with integrated skeleton to generate a 3D dynamic human body model with continuous motion characteristics.

3. The method for determining the looseness of clothing in a sports state according to claim 1, characterized in that: The construction method of the three-dimensional dynamic clothing model includes: The three-dimensional dynamic human body model and the drawn two-dimensional clothing sample are input into the three-dimensional virtual fitting software, the physical and mechanical properties of the virtual fabric are set, and the two-dimensional clothing sample is attached to the surface of the three-dimensional dynamic human body model using virtual stitching technology to generate a three-dimensional dynamic clothing model with fabric authenticity and dynamic adaptability.

4. The method for determining the looseness of clothing in a sports state according to claim 1, characterized in that: Based on the 3D dynamic human body model and the 3D dynamic clothing model, the 3D human body sub-model and the 3D clothing sub-model under each motion key frame in the motion cycle are constructed, including: The 3D virtual fitting software is used to perform spatiotemporal discretization on the 3D dynamic human body model and the 3D dynamic clothing model, and the motion cycle is decomposed into several motion key frames. For each motion keyframe, a paired 3D human body sub-model and 3D clothing sub-model are extracted synchronously.

5. The method for determining the looseness of clothing in a sports state according to claim 1, characterized in that: The 3D human body sub-model and the 3D clothing sub-model under each motion key frame are divided into human body feature regions, and the overall model of the feature regions under each motion key frame is constructed, including: For each motion keyframe, the 3D human body sub-model and the 3D clothing sub-model are aligned using inverse modeling software to construct the human clothing sub-model under the motion keyframe; Based on the human anatomical characteristics, the human clothing sub-model under each motion key frame is divided into human feature areas. The height of the feature area 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 area, and a clipping plane is set at the boundary of the feature area. The redundant parts beyond the boundary of the feature area are deleted to generate an overall model of the feature area under each motion key frame that conforms to the human anatomical characteristics.

6. The method for determining the looseness of clothing in a sports state according to claim 1, characterized in that: The overall model of the feature region under each motion key frame is divided into several local domains with the center of gravity as the reference axis. The local model of the feature region under each motion key frame is constructed including: For the overall model of the feature region under each motion key frame, the center of gravity of the overall model of the feature region is used as the reference central axis, and the dual-plane segmentation method is used to orthogonally divide the overall model of the feature region along the sagittal plane and the coronal plane into four local regions to form the local model of the feature region under each motion key frame.

7. The method for determining the looseness of clothing in a sports state according to claim 1, characterized in that: The calculation formula for the clothing looseness required by the local model of the feature area under each motion key frame is: ； in, Indicates the The first motion keyframe The clothing looseness required by the local model of the feature area, 、 Respectively represent The first motion keyframe The local upper surface area and the local lower surface area of ​​the 3D human body sub-model corresponding to the local model of the feature region, 、 Respectively represent The first motion keyframe The local upper surface area and the local lower surface area of ​​the 3D clothing sub-model corresponding to the local model of the feature area, Indicates the The overall volume of the 3D human body sub-model corresponding to the overall model of the feature area under the motion key frame, 、 、 Respectively represent 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 the feature area, Indicates the height of the feature area.

8. The method for determining the looseness of clothing in a sports state according to claim 1, characterized in that: According to the clothing looseness required by the local model of the feature area under each motion key frame, the clothing looseness required by the overall model of the feature area within the motion cycle is calculated, including: Calculate the clothing looseness required by the overall model of the feature region under each motion key frame according to the clothing looseness required by the local model of the feature region under each motion key frame; Calculate the clothing looseness required by the overall model of the feature area in the motion cycle according to the clothing looseness required by the overall model of the feature area under each motion key frame; The calculation formula for the clothing looseness required by the overall model of the feature area under each motion key frame is: ； in, Indicates the The clothing looseness required by the overall model of the feature area under the motion key frame, Indicates the The first motion keyframe The clothing looseness required by the local model of the feature area, Indicates that the overall model of each feature region is divided into four feature region local models; The calculation formula for the clothing looseness required by the overall model of the characteristic area during the movement cycle is: ； in, Indicates the clothing looseness required by the overall model of the feature area during the motion cycle, Indicates the total number of motion keyframes in the motion cycle.

9. The method for determining the looseness of clothing in a sports state according to claim 1, characterized in that: The formula for calculating the looseness of clothing in motion is: ； in, Indicates the amount of looseness in clothing during exercise. Indicates the clothing looseness required by the overall model of the feature area during the motion cycle.

10. A device for determining the looseness of clothing in a sports state, characterized in that: include: A model construction module is used to construct a 3D human body sub-model and a 3D clothing sub-model under each motion key frame in a motion cycle based on the 3D dynamic human body model and the 3D dynamic clothing model; The 3D human body sub-model and the 3D clothing sub-model under each motion key frame are divided into human feature regions, and the overall model of the feature region under each motion key frame is constructed; the overall model of the feature region under each motion key frame is divided into several local domains with the center of gravity as the reference axis, and the local model of the feature region under each motion key frame is constructed; The looseness calculation module is used to calculate the clothing looseness required by the local model of the characteristic region under each motion key frame based on the overall volume of the three-dimensional human body sub-model corresponding to the overall model of the characteristic region under each motion key frame, the local upper surface area, local lower surface area and local volume of the three-dimensional human body sub-model and the three-dimensional clothing sub-model corresponding to the local model of the characteristic region under each motion key frame, the local volume of the clothing fabric corresponding to the local model of the characteristic region under each motion key frame, and the height of the characteristic region; based on the clothing looseness required by the local model of the characteristic region under each motion key frame, calculate the clothing looseness required by the overall model of the characteristic region within the motion cycle; The clothing looseness determination module is used to determine the looseness of clothing in the motion state according to the clothing looseness required by the overall model of the characteristic area in the motion cycle.

Images