CN106952333A - A kind of method and system for creating human body parameterized model - Google Patents
A kind of method and system for creating human body parameterized model Download PDFInfo
- Publication number
- CN106952333A CN106952333A CN201710079335.0A CN201710079335A CN106952333A CN 106952333 A CN106952333 A CN 106952333A CN 201710079335 A CN201710079335 A CN 201710079335A CN 106952333 A CN106952333 A CN 106952333A
- Authority
- CN
- China
- Prior art keywords
- human body
- model
- parameterized model
- database
- models
- 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.)
- Pending
Links
Classifications
-
- 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
Abstract
The present invention proposes a kind of method and system for creating human body parameterized model, comprises the following steps：S1:Set up containing height, body weight, gender information human body 3D model databases；S2:Posture, overall build and local shape parameter are determined, parameterized model is set up according to the model database.By choosing a master pattern, determine posture, overall build and local shape parameter, set up the deformation relationship between master pattern and each parameter, and pass through machine learning algorithm, the unknown parameter item in deformation relationship is solved using other sample patterns in model database, parameterized model is established.The parameterized model considers the influence of posture, entirety and partial body's feature to human body 3D models simultaneously, therefore, and more accurate human body 3D models can be reconstructed using the human parameters model creation method and system of the present invention.
Description
Technical field
The present invention relates to computer technology and technical field of image processing, and in particular to one kind creates human body parameterized model
Method and system.
Background technology
Human body three-dimensional (later abbreviation 3D) model is all played in terms of 3D printing, custom made clothing, 3D fittings, cartoon making
Important effect.Obtain human body 3D models mainly has two kinds of approach at present, and one kind is that, by microcomputer modelling, this mode is obtained
Model smooth it is true to nature, but to model personnel technical merit have higher requirement, the efficiency of modeling is relatively low；Another side
Formula is that directly human body is measured by equipment such as 3D scanners or depth cameras, and what is typically obtained in this way is a little
Cloud data, the human body 3D models that subsequently can be more satisfied with by the processing such as denoising, gridding.Latter approach is although essence
Degree is not high, but obtains that the speed of human body 3D models is fast, is increasingly becoming the conventional mode in cartoon making, 3D fittings field.
In order to improve the precision of 3D measurement models, at present frequently with a kind of mode be by setting up parameterized model, so
Measurement model is approached by deforming the methods such as iteration under the constraint of energy function using parameterized model afterwards, the parameter after deformation
Changing model and measurement model has largely similar, but smoothness, precision will be far superior to measurement model.Ginseng true to nature
Numberization model after learning to human body 3D model databases by obtaining, such as SCAPE parameterized models.
In current prior art, the foundation of parameterized model is often only capable of being directed to some specific situations, such as only with appearance
The relevant parameter model of gesture, human body 3D models are changed by changing pose parameter；Or the only parameter model relevant with build.
Good parameterized model can reflect the change of different human body feature, and SCAPE models can be described not in terms of posture, build two
With the feature of human body.But in fact, influence characteristics of human body's also has the local features, particularly body weight parameters such as sex, body weight
Feature, its influence to parameter model is not accounted for also, such as sex is identical, height is identical but body weight is different in the prior art
Two people can possess different physical characteristics, still lack a kind of can reflect the parameterized model of these information at present.
The content of the invention
The technical problem to be solved in the present invention is：Existing human parameters model can not accurately reflect human body sex, body
The problem of local features such as height, body weight, propose a kind of method and system for creating human body parameterized model.
The method of the establishment human body parameterized model of the present invention, comprises the following steps：
S1:Set up containing height, body weight, gender information human body 3D model databases；
S2:Parameterized model is set up according to the model database.
Preferably, the human body 3D models are obtained by the method measurement based on laser scanner or depth camera
's.
Preferably, the human body 3D models are comprising in height, body weight, sex and 3D point cloud model or 3D grid models
It is a kind of.
Preferably, height, body weight are close in the human body 3D model databases, and sex identical human body 3D models are at least
Two.
Preferably, it is described parameterized model is set up according to model database to comprise the following steps：
S21:One in preference pattern database is used as master pattern；
S22:Determine posture, overall build and local shape parameter, it is established that the change between master pattern and each parameter
Shape relation；
S23:The unknown parameter item in deformation relationship is solved using other sample patterns in model database.
Preferably, the unknown ginseng in other model solution deformation relationships in model database is utilized in the step S23
It is several, refer specifically to by machine learning algorithm, calculating obtains unknown parameter item.
Preferably, the machine learning algorithm is referred to the sample mould of the same human body 3D models composition under different gestures
Type database, is calculated by recurrence learning algorithm and obtains master pattern and the unknown parameter item in gesture distortion relation.
Preferably, the machine learning algorithm is referred to the sample of the close different human body 3D models composition of multiple postures
Model database, is calculated by recurrence learning algorithm and obtains master pattern and the unknown parameter item in overall build deformation relationship.
Preferably, the machine learning algorithm is referred to so that height, body weight be close and the multiple different human bodies of sex identical
The sample pattern database of 3D models composition, is calculated by recurrence learning algorithm and obtains master pattern and local build deformation relationship
In unknown parameter item.
Based on the method for creating human body parameterized model, what the present invention also proposed a kind of establishment human body parameterized model is
System, including memory, for depositing program；Processor, runs described program, for controlling the establishment human body parametrization mould
The method that the system of type performs above-mentioned establishment human body parameterized model.
In addition, the present invention also proposes a kind of computer-readable recording medium for including computer program, the computer journey
Sequence is operable to the method for making computer perform above-mentioned establishment human body parameterized model.
Compared with prior art, beneficial effects of the present invention are：
The invention provides a kind of method and system for creating human body parameterized model, initially set up comprising height, body weight
And the human body 3D model databases of sex, it is then determined that posture, overall build and local shape parameter, according to the model
Database parameterized model.The parameterized model considers posture, entirety and partial body's feature to human body 3D simultaneously
The influence of model, therefore, can be reconstructed more accurate using the human parameters model creation method and system of the present invention
Human body 3D models.
Further, when setting up parameterized model according to the model database, a master pattern is first chosen, by true
Determine posture, overall build and local shape parameter, it is established that the deformation relationship between master pattern and each parameter, and pass through machine
Device learning algorithm, solves the unknown parameter item in deformation relationship using other sample patterns in model database, sets up parameter
Change model, the parameterized model considers the influence of posture, entirety and partial body's feature to human body 3D models simultaneously, because
This, more accurate human body 3D models can be reconstructed using the human parameters model creation method and system of the present invention.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of human parameters model creation method in the specific embodiment of the invention.
Fig. 2 is that the flow for setting up parameterized model method according to model database in the specific embodiment of the invention is illustrated
Figure.
Embodiment
With reference to embodiment and compare accompanying drawing the present invention is described in further details.Present invention specific implementation
The method that human body parameterized model is created in mode, as shown in figure 1, comprising the following steps：S1:Set up human body 3D model datas
Storehouse；S2:Parameterized model is set up according to model database.Wherein, human body 3D model databases are set up in step S1, include obtaining again
The step such as human body 3D point cloud or grid model, height measurement, measured body weight and sex acquisition is taken, above-mentioned steps will be entered below
Row is described in detail one by one.
1st, the method for creating the net model of human body
S1:Set up human body 3D model databases
The species that human body 3D model databases are models in the premise for obtaining human parameters model, database is set up also
Have influence on the quality of final argument model.
The quantity of 3D models is as more as possible in model database, data will as far as possible comprehensively, not only comprising Human Height,
Body weight, gender information, also comprising the human body 3D model datas under different gestures same human bodies, multiple different human bodies are in close appearance
Human body 3D model datas under gesture, multiple heights, body weight be close and sex identical different human body 3D model datas, is respectively intended to
Difference of the human body under different gestures is reacted, difference and different human body of the different human body on build are in local detail feature
Difference.
In this embodiment, the 3D models in database are in addition to itself 3D point cloud or grid model, also
Including height, body weight and gender information.Thus, setting up model database mainly includes human body 3D model measurements, height measurement, body
Remeasurement and the several aspects of gender identity.
Human body 3D model measurement methods
The method based on laser scanner and based on depth camera is roughly divided into currently used for the 3D methods measured.Laser
The high precision of scanner, but involve great expense, the speed of scanning is also relatively slow, is mainly used in the 3D surveys to some small-sized rigid objects
Amount；Method based on depth camera is to choose in human body measurement method conventional at present, present embodiment to be based on depth phase
The method of machine, further chooses and is based on the trigon depth camera of structure light, the measurement for human body 3D models.
Can be used in other embodiments and be based on laser scanner, or using based on time flight method or
The depth camera of Binocular Vision Principle carrys out the measurement for human body 3D models.
Encoded normal structure is projected into space using laser-projector based on the trigon depth camera of structure light
The difference of target depth is modulated normal structure light pattern in light pattern, space, is obtained by the related scheduling algorithm of image
The difference of structure light image and normal structure light pattern after modulation, the difference and target depth are set up according to structure light trigonometry
Between relation can solve the depth image of whole object space.
Usually, it is difficult to whole human body informations are obtained by piece image, it is necessary to obtain the depth at each position of human body
Image is spent, then obtains overall human body 3D point cloud data after being merged by registration algorithm.The 3D points obtained by depth camera
Cloud data typically can not be directly as human body 3D model datas, in addition it is also necessary to the step of being pre-processed by some.Usually, including
Image segmentation, denoising, gridding, set up the steps such as corresponding relation.
Image segmentation.It is general in the depth image that thus depth camera is obtained also to include other back ofs the body in addition to human body parts
Scape composition, the step of background necessitates is removed using image segmentation algorithm.Due to the uniqueness of depth image data, i.e., its is each
A kind of depth distance for the object that pixel value is represented, simple image segmentation algorithm --- threshold method just can effectively remove the back of the body
Scape.Specifically, i.e., the threshold value of human body and background can reasonably be differentiated by setting, the pixel value for belonging to background parts is returned
Zero (or taking maximum), retains the pixel value for belonging to human body.
Image denoising.Because the 3D point cloud data of acquisition are inevitable that noise (i.e. outlier) is present, while by
Hole occurs in blocking between human body, and the flatness of cloud data is also poor in addition.Therefore, the purpose of image denoising
On the one hand outlier is removed, on the other hand to carry out smooth and holes filling to cloud data is handled.
Gridding.In specific application, such as deformation transfer, cartoon making of model etc., only for the processing of a cloud
It is complex, thus correlation between points do not reflected in 3D point cloud.And 3D network models are then retaining
Topological relation between a cloud is added again while point cloud, and particularly in deformation process, 3D grid models have larger excellent
Gesture.Therefore, it is necessary to which 3D point cloud model meshes are melted into 3D grid models.The form of grid can be triangle, polygon etc.,
Conventional is triangle grid model.
Set up corresponding relation.The build and posture of different people are all otherwise varied, therefore the 3D point cloud obtained by depth camera
Also had any different on data bulk, bigger difficulty is had in the processing below.It is necessary when setting up database just to all
Human body 3D models set up corresponding relation.Specifically, the higher 3D point cloud data of a width quality are first chosen as reference.For working as
Preceding human body 3D models, using rigid registration or non-rigid registration algorithm, set up corresponding relation between points therebetween,
And the corresponding relation is also served as to a part for current human's 3D models.
Body weight is measured
The body weight of each human body is measured using doctor's type scale, body weight is obtained.
Height is measured
Accurate way will be used in present embodiment.Skeleton is carried out to 3D human body data clouds first to carry
Take, or 3D human body segmentations are obtained into multiple semantic components (head, upper body, leg) after then the length of various pieces is added
The height of human body.
In other embodiments, it is possible to use traditional dimensional measurement mode carries out height measurement, can also be straight
Connect using 3D human bodies point cloud or grid data to measure height.It should be noted that when human body is in different gestures, it is impossible to one
In general Stature estimation is carried out using the peak and the difference of minimum point in point cloud or grid data.
Sex is obtained
A kind of method of automatic identification is used in present embodiment.The coloured image of human body 3D models is utilized, is carried
The coloured image of face is taken, is inputted in housebroken gender sorter and is judged.According to the species of grader, processing
Mode is also had any different, and is usually carried out principal component analysis (PCA) to the coloured image of face first, can be lifted recognition efficiency.
In other embodiments, artificial setting can be carried out under artificially auxiliary situation.
S2:Parameterized model is set up according to model database
Have after the comprehensive human body 3D model databases of information, parametrization mould can be set up by machine learning algorithm
Type.Parameter in present embodiment included in parameterized model needs that human posture, overall build and office can be reflected
The feature of portion's build.In other words, if having the posture of a certain human body, build substantially and local shape parameter, so that it may
To be created that and the intimate consistent human body 3D models of the human body according to the creation method of the parameterized model.
The method of parameterized model is set up in present embodiment according to model database, as shown in Fig. 2 mainly have with
Lower step：S21:Selection standard model；S22:Posture and shape parameter are determined, the deformation set up between master pattern and each parameter
Relation；S23:Solve the unknown parameter item in deformation relationship.Wherein, posture and shape parameter are determined in step S22, is specifically referred to
The angle between pose parameter, including frame position and different skeleton positions is determined, and determines overall build and local build
Parameter；Step S23:The unknown parameter item in deformation relationship is solved, is specifically included in calculating master pattern and gesture distortion relation
Unknown parameter item, calculate master pattern and the unknown parameter item in overall build deformation relationship and calculate master pattern and office
Unknown parameter item in portion's build deformation relationship.Above-mentioned steps will one by one be described in detail below.
S21:Selection standard model
One in preference pattern database is used as master pattern.Because the version in model database is more, and
The quality of data also can be uneven.Any model can be chosen in principle as master pattern, but as should choose normal as possible
Posture, it is well-proportioned and human body 3D models that model data is intact are as master pattern.
The purpose that master pattern is chosen is the standard form as distorted pattern, by the change parameter for subsequently setting up correlation
Number, so as to obtain the human body 3D models under other postures, build using the master pattern and deformation parameter, no matter the people
Whether body 3D models are in model database.
S22:Posture and shape parameter are determined, the deformation relationship set up between master pattern and each parameter
Determine posture, overall build and local shape parameter, it is established that the deformation between master pattern and each parameter is closed
System.Shape parameter is used for reflecting the feature of specific build.The species of shape parameter can also have a variety of.In present embodiment
In, the shape parameter of posture is framework information：Including the angle between frame position and different skeleton positions；Overall build ginseng
Number is the low-dimensional matrix parameter for overall human body 3D models obtain after dimensionality reduction using principal component analysis (PCA)；Local volume
The low-dimensional matrix parameter that shape parameter to each human body obtain after dimensionality reduction also with principal component analysis.
In other embodiments, each shape parameter can also have other expression-forms.
Next the deformation relationship set up between master pattern and each parameter is needed.Deformation to model is substantially to mould
Each summit of type or grid are deformed, using triangular mesh as basic deformation unit in the present invention.
The deformation of triangular mesh mainly includes translation, rotation, scaling, and these deformation matrixs are also by posture, overall body
What type and local shape parameter were determined.Such as pose parameter can go out the section by the position and angle-determining of the end node of skeleton two
Translation, rotation and the scaled matrix of skeleton, these matrixes are applied to all on the corresponding human body 3D models of the section skeleton
Grid, you can to complete the gesture distortion operation to the department pattern.
S23:Solve the unknown parameter item in deformation relationship
The unknown parameter item in deformation relationship is solved using other sample patterns in model database.Posture, overall body
Type and local shape parameter often can not directly determine the deformation of each grid on master pattern, still suffer from some unknown
Parameter item.The effect that these unknown parameter items are is to determine how master pattern is deformed according to each shape parameter.Unknown ginseng
Several calculating be used as sample often through machine learning algorithm by the use of other human bodies 3D models in human body 3D model databases
This storehouse, these unknown parameter items are determined using recurrence learning algorithm.
Generally, the step for, solves dependent variable by known independent variable (master pattern) and dependent variable (Sample Storehouse)
The process of coefficient (unknown parameter item) between independent variable.
When calculating different unknown parameter items, the selection of Sample Storehouse also has difference.Specifically：
It is with the same human body under different gestures when calculating the unknown parameter item in master pattern and gesture distortion relation
Model composition sample database.
It is close not with multiple postures when calculating the unknown parameter item in master pattern and overall build deformation relationship
Sample database is constituted with human body 3D models.
When calculating master pattern with unknown parameter item in local build deformation relationship, be with height, body weight it is close and
The multiple different human body 3D models composition sample databases of sex identical.
2nd, the system for creating the net model of human body
In this embodiment, the system for creating human body parameterized model, including memory, for depositing program；
Processor, runs described program, for controlling the system for creating human body parameterized model to perform above-mentioned establishment human body ginseng
The method of numberization model.
In other embodiments, the system for creating human body parameterized model can also include computer to be a kind of
The computer-readable recording medium of program, the computer program is operable to make computer perform above-mentioned establishment human body parametrization
The method of model.
Present embodiment provides a kind of method and system for creating human body parameterized model, initially sets up comprising body
The human body 3D model databases of high, body weight and sex, it is then determined that posture, overall build and local shape parameter, according to
The model database sets up parameterized model.The parameterized model considers posture, entirety and partial body's feature simultaneously
Influence to human body 3D models, therefore, can be with using the human parameters model creation method and system of present embodiment
Reconstruct more accurate human body 3D models.
Further, when setting up parameterized model according to the model database, a master pattern is first chosen, by true
Determine posture, overall build and local shape parameter, it is established that the deformation relationship between master pattern and each parameter, and pass through machine
Device learning algorithm, solves the unknown parameter item in deformation relationship using other sample patterns in model database, sets up parameter
Change model, the parameterized model considers the influence of posture, entirety and partial body's feature to human body 3D models simultaneously, because
This, more accurate human body 3D can be reconstructed using the human parameters model creation method and system of present embodiment
Model.
Above content is to combine specific preferred embodiment further description made for the present invention, it is impossible to assert
The specific implementation of the present invention is confined to these explanations.For those skilled in the art, do not taking off
On the premise of from present inventive concept, some equivalent substitutes or obvious modification can also be made, and performance or purposes are identical, all should
When being considered as belonging to protection scope of the present invention.
Claims (10)
1. a kind of method for creating human body parameterized model, it is characterised in that comprise the following steps：
S1:Set up containing height, body weight, gender information human body 3D model databases；
S2:Posture, overall build and local shape parameter are determined, parameterized model is set up according to the model database.
2. the method according to claim 1 for creating human body parameterized model, it is characterised in that set up in the step S1
Human body 3D model databases containing height, body weight, gender information are referred to the human body 3D moulds of different heights, body weight and sex
Type is stored in a database.
3. the method according to claim 1 for creating human body parameterized model, it is characterised in that human body in the step S1
Height, body weight are close in 3D model databases, at least two, sex identical human body 3D models.
4. the method according to claim 1 for creating human body parameterized model, it is characterised in that basis in the step S2
Model database sets up parameterized model, specifically includes following steps：
S21:One in preference pattern database is used as master pattern；
S22:Determine posture, overall build and local shape parameter, it is established that the deformation between master pattern and each parameter is closed
System；
S23:The unknown parameter item in deformation relationship is solved using other sample patterns in model database.
5. the method according to claim 4 for creating human body parameterized model, it is characterised in that sharp in the step S23
The unknown parameter item in deformation relationship is solved with other sample patterns in model database, is referred specifically to by machine learning
Algorithm, calculating obtains unknown parameter item.
6. the method according to claim 5 for creating human body parameterized model, it is characterised in that the machine learning algorithm
Refer to, with the sample pattern database of the same human body 3D models composition under different gestures, calculating by recurrence learning algorithm
To the unknown parameter item in master pattern and gesture distortion relation.
7. the method according to claim 5 for creating human body parameterized model, it is characterised in that the machine learning algorithm
Refer to, with the sample pattern database of the close different human body 3D models composition of multiple postures, calculating by recurrence learning algorithm
Obtain master pattern and the unknown parameter item in overall build deformation relationship.
8. the method according to claim 5 for creating human body parameterized model, it is characterised in that the machine learning algorithm
Refer to, so that height, body weight be close and sample pattern databases of the multiple different human body 3D models compositions of sex identical, passing through
Recurrence learning algorithm, which is calculated, obtains master pattern and the unknown parameter item in local build deformation relationship.
9. a kind of system for creating human body parameterized model, it is characterised in that including memory, for depositing program；Processor,
Described program is run, for controlling the system for creating human body parameterized model to perform as described in claim 1-8 is any
Method.
10. a kind of computer-readable recording medium for including computer program, the computer program is operable to make computer
Perform the method as described in claim 1-8 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710079335.0A CN106952333A (en) | 2017-02-14 | 2017-02-14 | A kind of method and system for creating human body parameterized model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710079335.0A CN106952333A (en) | 2017-02-14 | 2017-02-14 | A kind of method and system for creating human body parameterized model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106952333A true CN106952333A (en) | 2017-07-14 |
Family
ID=59465857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710079335.0A Pending CN106952333A (en) | 2017-02-14 | 2017-02-14 | A kind of method and system for creating human body parameterized model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106952333A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053437A (en) * | 2017-11-29 | 2018-05-18 | 深圳奥比中光科技有限公司 | Three-dimensional model acquiring method and device based on figure |
| CN110662484A (en) * | 2018-04-20 | 2020-01-07 | 智能身型 | System and method for whole body measurement extraction |
| WO2020078292A1 (en) * | 2018-10-17 | 2020-04-23 | Midea Group Co., Ltd. | System and method for generating acupuncture points and pressure point maps |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194105A (en) * | 2010-03-19 | 2011-09-21 | 微软公司 | Proxy training data for human body tracking |
| CN102982578A (en) * | 2012-10-31 | 2013-03-20 | 北京航空航天大学 | Estimation method for dressed body 3D model in single character image |
| CN103268629A (en) * | 2013-06-03 | 2013-08-28 | 程志全 | Mark-point-free real-time restoration method of three-dimensional human form and gesture |
| WO2016061341A1 (en) * | 2014-10-17 | 2016-04-21 | Ebay Inc. | Fast 3d model fitting and anthropometrics |
-
2017
- 2017-02-14 CN CN201710079335.0A patent/CN106952333A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194105A (en) * | 2010-03-19 | 2011-09-21 | 微软公司 | Proxy training data for human body tracking |
| CN102982578A (en) * | 2012-10-31 | 2013-03-20 | 北京航空航天大学 | Estimation method for dressed body 3D model in single character image |
| CN103268629A (en) * | 2013-06-03 | 2013-08-28 | 程志全 | Mark-point-free real-time restoration method of three-dimensional human form and gesture |
| WO2016061341A1 (en) * | 2014-10-17 | 2016-04-21 | Ebay Inc. | Fast 3d model fitting and anthropometrics |
| CN107111833A (en) * | 2014-10-17 | 2017-08-29 | 电子湾有限公司 | Quick 3D model adaptations and anthropological measuring |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053437A (en) * | 2017-11-29 | 2018-05-18 | 深圳奥比中光科技有限公司 | Three-dimensional model acquiring method and device based on figure |
| CN108053437B (en) * | 2017-11-29 | 2021-08-03 | 奥比中光科技集团股份有限公司 | Three-dimensional model obtaining method and device based on posture |
| CN110662484A (en) * | 2018-04-20 | 2020-01-07 | 智能身型 | System and method for whole body measurement extraction |
| WO2020078292A1 (en) * | 2018-10-17 | 2020-04-23 | Midea Group Co., Ltd. | System and method for generating acupuncture points and pressure point maps |
| US11475630B2 (en) | 2018-10-17 | 2022-10-18 | Midea Group Co., Ltd. | System and method for generating acupuncture points on reconstructed 3D human body model for physical therapy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035388B (en) | Three-dimensional face model reconstruction method and device | |
| US10796480B2 (en) | Methods of generating personalized 3D head models or 3D body models | |
| De Aguiar et al. | Automatic conversion of mesh animations into skeleton‐based animations | |
| US6664956B1 (en) | Method for generating a personalized 3-D face model | |
| CN109844818B (en) | Method for building deformable 3d model of element and related relation | |
| CN110363858A (en) | A kind of three-dimensional facial reconstruction method and system | |
| CN106709947A (en) | RGBD camera-based three-dimensional human body rapid modeling system | |
| EP0907144A2 (en) | Method for extracting a three-dimensional model from a sequence of images | |
| CN102222357B (en) | Foot-shaped three-dimensional surface reconstruction method based on image segmentation and grid subdivision | |
| CN102157013A (en) | System for fully automatically reconstructing foot-type three-dimensional surface from a plurality of images captured by a plurality of cameras simultaneously | |
| CN109003331A (en) | A kind of image reconstructing method | |
| CN106952335A (en) | Set up the method and its system in manikin storehouse | |
| CN108376421A (en) | A method of human face three-dimensional model is generated based on shape from shading method | |
| CN108898673A (en) | A kind of reconstruct foot triangle grid model processing method and system | |
| Wang et al. | High resolution tracking of non-rigid 3d motion of densely sampled data using harmonic maps | |
| CN106952333A (en) | A kind of method and system for creating human body parameterized model | |
| CN109034131A (en) | A kind of semi-automatic face key point mask method and storage medium | |
| CN109102569A (en) | A kind of reconstruct foot point cloud model processing method and system | |
| CN106933976A (en) | Set up the method for the net models of human body 3D and its application in 3D fittings | |
| CN108615256A (en) | A kind of face three-dimensional rebuilding method and device | |
| CN109032073A (en) | It is a kind of that system is constructed based on image reconstruction and foot's shoe last model of parametrization | |
| CN108898663A (en) | A kind of foot's characteristic parameter driving standard shoe tree deformation method and system | |
| CN105913492A (en) | Method for complementing object shape in RGBD image | |
| CN116958420A (en) | High-precision modeling method for three-dimensional face of digital human teacher | |
| Ye et al. | 3d morphable face model for face animation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170714 |