CN109655011B - Method and system for measuring dimension of human body modeling - Google Patents
Method and system for measuring dimension of human body modeling Download PDFInfo
- Publication number
- CN109655011B CN109655011B CN201811526665.0A CN201811526665A CN109655011B CN 109655011 B CN109655011 B CN 109655011B CN 201811526665 A CN201811526665 A CN 201811526665A CN 109655011 B CN109655011 B CN 109655011B
- Authority
- CN
- China
- Prior art keywords
- human body
- dimensional
- human
- model
- modeling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 31
- 230000036544 posture Effects 0.000 claims description 27
- 230000037237 body shape Effects 0.000 claims description 26
- 238000013136 deep learning model Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 210000000689 upper leg Anatomy 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 244000309466 calf Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000000245 forearm Anatomy 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
- G01B11/2433—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures for measuring outlines by shadow casting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G06T3/06—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Abstract
The invention provides a method and a system for measuring human body modeling dimension, wherein the method comprises the following steps: acquiring a target human body image and extracting a body surface contour of the target human body image; establishing a human body three-dimensional model according to the body surface contour; and calculating to obtain the human body dimension data of the target person according to the human body three-dimensional model and the actual height of the target person. The invention solves the problems of insufficient convenience and high cost of the existing human body modeling, can improve the convenience of human body modeling and improve the accuracy of human body dimension measurement.
Description
Technical Field
The invention relates to the technical field of intelligent network models of computers, in particular to a method and a system for measuring human body modeling dimensions.
Background
With the continuous development of computer technology, three-dimensional human body modeling is widely applied in the fields of scientific research, animation, games, clothing design, industry and the like. The existing three-dimensional modeling technology mainly scans a human body object through a human body scanner. To obtain a three-dimensional model of the human body. Wherein, the human body scanner includes: three-dimensional laser scanners, infrared scanners, speckle scanners, large industrial camera arrays, structured light depth cameras, and the like. However, these devices all have a high cost, which is hundreds of thousands or even millions. The use of these devices is limited to specific scenarios, so that measurements can only be made in a fixed environment. Therefore, the process of establishing the human body three-dimensional model has more limitations, and the human body three-dimensional model is not convenient to establish.
Disclosure of Invention
The invention provides a method and a system for measuring human body modeling dimension, which solve the problems of insufficient convenience and high cost of the existing human body modeling, can improve the convenience of human body modeling and improve the accuracy of human body dimension measurement.
In order to achieve the above purpose, the invention provides the following technical scheme:
a method of human modeling dimensional measurements, comprising:
acquiring a target human body image and extracting a body surface contour of the target human body image;
establishing a human body three-dimensional model according to the body surface contour;
and calculating to obtain the human body dimension data of the target person according to the human body three-dimensional model and the actual height of the target person.
Preferably, the establishing of the human body three-dimensional model according to the body surface contour includes:
setting a training deep learning model, wherein the training deep learning model maps the body surface contour network into three subspaces of camera parameters, human body shapes and human body postures;
establishing a human body three-dimensional template model according to the human body shape and the human body posture, and carrying out re-projection according to the human body three-dimensional template model and the camera parameters to form a projection profile;
and taking the residual error between the projection outline and the body surface outline as a loss function, and carrying out training and learning on the body surface outline by the training deep learning model according to the loss function to obtain the human body three-dimensional model.
Preferably, the establishing of the human body three-dimensional template model according to the human body shape and the human body posture includes:
training according to the human body size standard to generate various human body three-dimensional templates;
and establishing a corresponding human body three-dimensional template model according to the human body shape, the human body posture and the human body three-dimensional template.
Preferably, the calculating to obtain the human body dimension data of the target person according to the human body three-dimensional model and the actual height of the target person includes:
calculating the proportional scale of the body of the target person according to the human body three-dimensional model;
and calculating to obtain dimension data of each part of the body of the target person according to the actual height and the proportional scale.
Preferably, the acquiring the target human body image includes: at least one front human body image and one side human body image are obtained.
Preferably, the extracting the body surface contour of the target human body image includes:
extracting the original contour and the mark characteristics of the target human body image by adopting an image recognition algorithm;
and forming the body surface contour according to the original contour and the marking feature.
The invention also provides a system for measuring the human body modeling dimension, which comprises:
the human body characteristic acquisition unit is used for acquiring a target human body image and extracting a body surface contour of the target human body image;
the three-dimensional modeling unit is used for establishing a human body three-dimensional model according to the body surface outline;
and the human body dimension calculation unit is used for calculating to obtain human body dimension data of the target person according to the human body three-dimensional model and the actual height of the target person.
Preferably, the three-dimensional modeling unit includes:
the network mapping unit is used for setting a training deep learning model, and the training deep learning model maps the body surface contour network into three subspaces of camera parameters, human body shapes and human body postures;
the human body template unit is used for establishing a human body three-dimensional template model according to the human body shape and the human body posture;
the human body projection unit is used for carrying out re-projection according to the human body three-dimensional template model and the camera parameters to form a projection outline;
and the network learning unit is used for taking the residual error between the projection outline and the body surface outline as a loss function, and the training deep learning model is used for training and learning the body surface outline according to the loss function to obtain the human body three-dimensional model.
Preferably, the human body template unit includes:
the standard template unit is used for generating various human body three-dimensional templates according to human body size standard training;
and the model establishing unit is used for establishing the corresponding human body three-dimensional template model according to the human body shape, the human body posture and the human body three-dimensional template.
Preferably, the human dimension calculating unit includes:
the proportional scale calculation unit is used for calculating the proportional scale of the body of the target person according to the human three-dimensional model;
and the body part calculating unit is used for calculating and obtaining dimension data of each part of the body of the target person according to the actual height and the proportional scale.
The invention provides a method and a system for measuring human body modeling dimension, which are characterized in that a body surface outline is extracted from a target person image, a human body three-dimensional model is established according to the body surface outline, and then human body dimension data are obtained according to the human body three-dimensional model and the actual height of a target person through calculation. The problems of inconvenience and high cost of the existing human body modeling are solved, the convenience of the human body modeling can be improved, and the accuracy of the human body dimension measurement is improved.
Drawings
In order to more clearly describe the specific embodiments of the present invention, the drawings to be used in the embodiments will be briefly described below.
FIG. 1: the invention provides a method and a flow chart for measuring the human body modeling dimension.
FIG. 2: the invention provides a schematic diagram of human body modeling dimension measurement.
Detailed Description
In order to make the technical field of the invention better understand the scheme of the embodiment of the invention, the embodiment of the invention is further described in detail with reference to the drawings and the implementation mode.
Aiming at the problems of high cost and long time spent on human body modeling at present, the invention provides a method and a system for measuring human body modeling dimension. The problems of inconvenience and high cost of the existing human body modeling are solved, the convenience of the human body modeling can be improved, and the accuracy of the human body dimension measurement is improved.
As shown in fig. 1, a method of human modeling dimensional measurement includes:
s1: acquiring a target human body image and extracting a body surface contour of the target human body image;
s2: establishing a human body three-dimensional model according to the body surface contour;
s3: and calculating to obtain the human body dimension data of the target person according to the human body three-dimensional model and the actual height of the target person.
Further, the establishing of the human body three-dimensional model according to the body surface contour comprises:
s21: setting a training deep learning model, wherein the training deep learning model maps the body surface contour network into three subspaces of camera parameters, human body shapes and human body postures;
s22: establishing a human body three-dimensional template model according to the human body shape and the human body posture, and carrying out re-projection according to the human body three-dimensional template model and the camera parameters to form a projection profile;
s23: and taking the residual error between the projection outline and the body surface outline as a loss function, and carrying out training and learning on the body surface outline by the training deep learning model according to the loss function to obtain the human body three-dimensional model.
Specifically, as shown in fig. 2, in one embodiment, first, image capturing is performed, and image capturing may be performed using a common camera, and generally, it is required to take one each of a front photograph and a side photograph of a user, and it is required that the user must take a full-length photograph, and a half-length photograph or a partial photograph is not supported in the photograph. The posture of the user is normal standing or standing with arms straightened. While also supporting other gestures or other numbers of photographs as input. No special requirements are required for scenes, light rays and dresses, and the clothes can be made according with daily conditions. Secondly, establishing a training deep learning model, constructing a first part of network by using open source frames tensorflow and ResNet, using a common human body photo as input, and mapping the input to three subspaces of camera parameters, human body shape and human body posture through the network. And secondly, taking the skeleton of the human body posture, the re-projection after the reconstruction of the human body model and the figure outline in the input photo as labels, taking the re-projection of the human body template model generated by the human body shape and the human body posture and the residual error of the figure outline in the input image as loss functions, and enabling the network to have the capability of identifying the camera parameters, the human body shape and the human body posture of the figure in the two-position photo through iteration of a large amount of data. In addition, because the body types of men and women have different characteristics, the models of men and women are trained respectively. And finally, after the three-dimensional model is obtained, calculating the length scale of the three-dimensional model and the real human body according to the actual height and by combining the model. After obtaining the dimension, the length and width of each part of the human body in the model can be measured, and then the required human body dimension is obtained, wherein the human body dimension comprises: forearm length, calf length, thigh length, upper body length, shoulder width, chest circumference, waist circumference, crotch circumference, hip circumference, thigh circumference, and the like. The method can improve the accuracy of the dimension measurement of the human body.
It should be noted that, the method for acquiring a human body image by using a common camera and generating a 3D model therefrom is similar to the method using an industrial camera array, but the method is different in that only a small number of pictures or even only one common picture is needed to generate a three-dimensional model, and the industrial camera array method requires dozens of industrial-grade high-definition pictures with fixed angles to generate the three-dimensional model. At the same time, internally used computation schemes are also differentiated. In the scheme of the industrial camera array, firstly, the SIFT, SURF, FAST and other technologies are used for extracting the feature points of each photo, the descriptors of the feature points are calculated, then the feature points are matched, and the internal and external parameters of the camera are used for estimating the spatial position of each feature point. The feature points of all the photographs are then matched into a three-dimensional point cloud. This solution requires a long calculation time (typically more than 10 minutes) and is highly susceptible to environmental, light and human wear. The invention uses a more complex deep learning model (resNet) and a human body template model, maps two-dimensional human body photo information into three subspaces of camera parameters, human body shapes and human body actions in a network, maps the information in the three subspaces of the camera parameters, the human body shapes and the human body actions into a human body three-dimensional template by a subsequent network, and finally generates the three-dimensional model by the three-dimensional human body template. Such processing is based on large data sets and statistics and greatly increases the computational speed (within 10 seconds).
The establishment of the human body three-dimensional template model according to the human body shape and the human body posture comprises the following steps: training according to the human body size standard to generate various human body three-dimensional templates; and establishing a corresponding human body three-dimensional template model according to the human body shape, the human body posture and the human body three-dimensional template.
In practical applications, the three-dimensional template of the human body uses a set of pose vectors and a set of shape vectors to control a three-dimensional model of the human body. Changing the shape vector will cause the dimensionality of the human body in the three-dimensional model of the human body to change, and changing the posture vector will cause the posture of the human body in the three-dimensional model of the human body to change. The human three-dimensional template expresses a human three-dimensional model by using limited and important characteristics. The human body three-dimensional template is used as the input end of the deep learning network, so that the feature extraction in the network is smoother, and the convergence speed is accelerated.
The method for obtaining the human body dimension data of the target person through calculation according to the human body three-dimensional model and the actual height of the target person comprises the following steps: calculating the proportional scale of the body of the target person according to the human body three-dimensional model; and calculating to obtain dimension data of each part of the body of the target person according to the actual height and the proportional scale.
The acquiring of the target human body image includes: at least one front human body image and one side human body image are obtained.
The extracting of the body surface contour of the target human body image comprises the following steps: extracting the original contour and the mark characteristics of the target human body image by adopting an image recognition algorithm; and forming the body surface contour according to the original contour and the marking feature.
The invention provides a method for measuring human body modeling dimension, which comprises the steps of extracting a body surface outline from a target person image, establishing a human body three-dimensional model according to the body surface outline, and calculating according to the human body three-dimensional model and the actual height of the target person to obtain human body dimension data. The problems of inconvenience and high cost of the existing human body modeling are solved, the convenience of the human body modeling can be improved, and the accuracy of the human body dimension measurement is improved.
The invention also provides a system for measuring the human body modeling dimension, which comprises: and the human body characteristic acquisition unit is used for acquiring a target human body image and extracting the body surface outline of the target human body image. And the three-dimensional modeling unit is used for establishing a human body three-dimensional model according to the body surface outline. And the human body dimension calculation unit is used for calculating to obtain human body dimension data of the target person according to the human body three-dimensional model and the actual height of the target person.
Further, the three-dimensional modeling unit includes: and the network mapping unit is used for setting a training deep learning model, and the training deep learning model maps the body surface contour network into three subspaces of camera parameters, human body shapes and human body postures. And the human body template unit is used for establishing a human body three-dimensional template model according to the human body shape and the human body posture. And the human body projection unit is used for carrying out re-projection according to the human body three-dimensional template model and the camera parameters to form a projection outline. And the network learning unit is used for taking the residual error between the projection outline and the body surface outline as a loss function, and the training deep learning model is used for training and learning the body surface outline according to the loss function to obtain the human body three-dimensional model.
The human body template unit includes: and the standard template unit is used for generating various human body three-dimensional templates according to the human body size standard training. And the model establishing unit is used for establishing the corresponding human body three-dimensional template model according to the human body shape, the human body posture and the human body three-dimensional template.
The human dimension calculation unit includes: and the proportional scale calculation unit is used for calculating the proportional scale of the body of the target person according to the human three-dimensional model. And the body part calculating unit is used for calculating and obtaining dimension data of each part of the body of the target person according to the actual height and the proportional scale.
The invention provides a system for measuring human body modeling dimension, which extracts a body surface contour from a target figure image through a human body characteristic acquisition unit, establishes a human body three-dimensional model according to the body surface contour through a three-dimensional modeling unit, and calculates to obtain human body dimension data according to the human body three-dimensional model and the actual height of the target figure through a human body dimension calculation unit. The problems of inconvenience and high cost of the existing human body modeling are solved, the convenience of the human body modeling can be improved, and the accuracy of the human body dimension measurement is improved.
The construction, features and functions of the present invention have been described in detail with reference to the embodiments shown in the drawings, but the present invention is not limited to the embodiments shown in the drawings, and all equivalent embodiments modified or modified by the spirit and scope of the present invention should be protected without departing from the spirit of the present invention.
Claims (8)
1. A method of human modeling dimensional measurements, comprising:
acquiring a target human body image and extracting a body surface contour of the target human body image;
establishing a human body three-dimensional model according to the body surface contour;
calculating to obtain human body dimension data of the target person according to the human body three-dimensional model and the actual height of the target person;
wherein, according to the body surface outline, establishing a human body three-dimensional model comprises the following steps:
setting a training deep learning model, wherein the training deep learning model maps the body surface contour network into three subspaces of camera parameters, human body shapes and human body postures;
establishing a human body three-dimensional template model according to the human body shape and the human body posture, and carrying out re-projection according to the human body three-dimensional template model and the camera parameters to form a projection profile;
and taking the residual error between the projection outline and the body surface outline as a loss function, and carrying out training and learning on the body surface outline by the training deep learning model according to the loss function to obtain the human body three-dimensional model.
2. The method for modeling dimensions according to claim 1, wherein said building a three-dimensional template model of a human body from said human body shape and said human body pose comprises:
training according to the human body size standard to generate various human body three-dimensional templates;
and establishing a corresponding human body three-dimensional template model according to the human body shape, the human body posture and the human body three-dimensional template.
3. The method of claim 1, wherein the calculating human dimension data of the target person according to the human three-dimensional model and the actual height of the target person comprises:
calculating the proportional scale of the body of the target person according to the human body three-dimensional model;
and calculating to obtain dimension data of each part of the body of the target person according to the actual height and the proportional scale.
4. The method of human modeling dimensional measurements according to claim 1, wherein said obtaining a target human image comprises: at least one front human body image and one side human body image are obtained.
5. The method for modeling human dimensions as recited in claim 4, wherein said extracting a body surface contour of said target human image comprises:
extracting the original contour and the mark characteristics of the target human body image by adopting an image recognition algorithm;
and forming the body surface contour according to the original contour and the marking feature.
6. A system for modeling dimensional measurements in a human body, comprising:
the human body characteristic acquisition unit is used for acquiring a target human body image and extracting a body surface contour of the target human body image;
the three-dimensional modeling unit is used for establishing a human body three-dimensional model according to the body surface outline;
the human body dimension calculation unit is used for calculating human body dimension data of the target person according to the human body three-dimensional model and the actual height of the target person;
wherein the three-dimensional modeling unit includes:
the network mapping unit is used for setting a training deep learning model, and the training deep learning model maps the body surface contour network into three subspaces of camera parameters, human body shapes and human body postures;
the human body template unit is used for establishing a human body three-dimensional template model according to the human body shape and the human body posture;
the human body projection unit is used for carrying out re-projection according to the human body three-dimensional template model and the camera parameters to form a projection outline;
and the network learning unit is used for taking the residual error between the projection outline and the body surface outline as a loss function, and the training deep learning model is used for training and learning the body surface outline according to the loss function to obtain the human body three-dimensional model.
7. The system of human modeling dimensional measurements according to claim 6, wherein said human template unit comprises:
the standard template unit is used for generating various human body three-dimensional templates according to human body size standard training;
and the model establishing unit is used for establishing the corresponding human body three-dimensional template model according to the human body shape, the human body posture and the human body three-dimensional template.
8. The system for human modeling dimensional measurements according to claim 7, wherein the human dimension calculation unit comprises:
the proportional scale calculation unit is used for calculating the proportional scale of the body of the target person according to the human three-dimensional model;
and the body part calculating unit is used for calculating and obtaining dimension data of each part of the body of the target person according to the actual height and the proportional scale.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811526665.0A CN109655011B (en) | 2018-12-13 | 2018-12-13 | Method and system for measuring dimension of human body modeling |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811526665.0A CN109655011B (en) | 2018-12-13 | 2018-12-13 | Method and system for measuring dimension of human body modeling |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109655011A CN109655011A (en) | 2019-04-19 |
CN109655011B true CN109655011B (en) | 2021-04-23 |
Family
ID=66113062
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811526665.0A Active CN109655011B (en) | 2018-12-13 | 2018-12-13 | Method and system for measuring dimension of human body modeling |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109655011B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110307788B (en) * | 2019-07-12 | 2021-05-11 | 清华大学 | Multi-depth camera human body parameter measuring method and device |
CN111784824A (en) * | 2020-07-06 | 2020-10-16 | 许忠慧 | Human body three-dimensional modeling and measuring method based on computer vision intelligent technology |
CN112258538A (en) * | 2020-10-29 | 2021-01-22 | 深兰科技(上海)有限公司 | Method and device for acquiring three-dimensional data of human body |
CN112401369A (en) * | 2020-11-23 | 2021-02-26 | 叠境数字科技(上海)有限公司 | Body parameter measuring method, system, equipment, chip and medium based on human body reconstruction |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101639349B (en) * | 2009-08-25 | 2011-11-09 | 东华大学 | Full-automatic measuring method for three-dimensional (3D) manikin |
CN102646245A (en) * | 2012-03-29 | 2012-08-22 | 柳一鸣 | Clothing fitting, clothing selecting and clothing tailoring system based on the internet |
US20140015929A1 (en) * | 2012-07-12 | 2014-01-16 | Sony Corporation | Three dimensional scanning with patterned covering |
US9710964B2 (en) * | 2014-01-23 | 2017-07-18 | Max-Planck-Gesellschaft Zur Foerderung Der Wissenschaften E.V. | Method for providing a three dimensional body model |
CN107292948B (en) * | 2016-04-12 | 2021-03-26 | 香港理工大学 | Human body modeling method and device and electronic equipment |
CN107016721A (en) * | 2017-03-07 | 2017-08-04 | 上海优裁信息技术有限公司 | The modeling method of human 3d model |
CN108305229A (en) * | 2018-01-29 | 2018-07-20 | 深圳市唯特视科技有限公司 | A kind of multiple view method for reconstructing based on deep learning profile network |
-
2018
- 2018-12-13 CN CN201811526665.0A patent/CN109655011B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN109655011A (en) | 2019-04-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109655011B (en) | Method and system for measuring dimension of human body modeling | |
CN109636831B (en) | Method for estimating three-dimensional human body posture and hand information | |
CN106600626B (en) | Three-dimensional human motion capture method and system | |
CN104794722A (en) | Dressed human body three-dimensional bare body model calculation method through single Kinect | |
CN111932678B (en) | Multi-view real-time human motion, gesture, expression and texture reconstruction system | |
Bednarik et al. | Learning to reconstruct texture-less deformable surfaces from a single view | |
CN106952335B (en) | Method and system for establishing human body model library | |
CN107016721A (en) | The modeling method of human 3d model | |
CN111862299A (en) | Human body three-dimensional model construction method and device, robot and storage medium | |
Hu et al. | 3DBodyNet: fast reconstruction of 3D animatable human body shape from a single commodity depth camera | |
Kwok et al. | Volumetric template fitting for human body reconstruction from incomplete data | |
CN110074788A (en) | A kind of body data acquisition methods and device based on machine learning | |
Chang et al. | Poselifter: Absolute 3d human pose lifting network from a single noisy 2d human pose | |
US20180094917A1 (en) | Three-dimensional measuring system and measuring method with multiple measuring modes | |
Kaashki et al. | Deep learning-based automated extraction of anthropometric measurements from a single 3-D scan | |
CN112233222A (en) | Human body parametric three-dimensional model deformation method based on neural network joint point estimation | |
CN108010122B (en) | Method and system for reconstructing and measuring three-dimensional model of human body | |
Song et al. | Data-driven 3-D human body customization with a mobile device | |
Bang et al. | Estimating garment patterns from static scan data | |
JP2022544353A (en) | A method for estimating naked body shape from hidden body scans | |
CN106933976B (en) | Method for establishing human body 3D net model and application thereof in 3D fitting | |
Darujati et al. | Facial motion capture with 3D active appearance models | |
CN109801326A (en) | It is a kind of for obtaining the image measuring method of human somatotype data | |
Liu | A mean field annealing approach to accurate free form shape matching | |
Yang et al. | Human bas-relief generation from a single photograph |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |