CN106952334A - The creation method of the net model of human body and three-dimensional fitting system - Google Patents
The creation method of the net model of human body and three-dimensional fitting system Download PDFInfo
- Publication number
- CN106952334A CN106952334A CN201710079459.9A CN201710079459A CN106952334A CN 106952334 A CN106952334 A CN 106952334A CN 201710079459 A CN201710079459 A CN 201710079459A CN 106952334 A CN106952334 A CN 106952334A
- Authority
- CN
- China
- Prior art keywords
- human body
- model
- net model
- net
- characteristic parameter
- 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.)
- Granted
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/16—Cloth
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides a kind of creation method of the net model of the human body based on depth camera, comprise the following steps：S1：At least two amplitude deepness images of the human body under at least two given poses are obtained using depth camera；S2：The characteristic parameter of the net model of human body is obtained from least two amplitude deepness images；S3：The net model of human body is created according to the characteristic parameter.The method that the present invention creates the net model of human body can avoid the manikin error that loose clothing is brought.In addition, based on the creation method of the net model of above-mentioned human body, the present invention also proposes a kind of three-dimensional fitting method and three-dimensional fitting system, and no matter human body wears loose clothing or compact clothing,, can in real time and 360 ° of effects for wearing the clothes of displaying using the three-dimensional fitting method or system of the present invention.
Description
Technical field
The present invention relates to optical technology and field of computer technology, and in particular to a kind of net mould of human body based on depth camera
The creation method of type and three-dimensional fitting system.
Background technology
With shopping at network, the arriving in private customization epoch, tried on from traditional solid shop/brick and mortar store-purchasing model gradually can be to net
Network tries/individual's customization-purchasing model transition on.In current prior art, network fitting remains in the two-dimensional fitting stage, although
There are many three-dimensional fitting applications, but the precision and real-time of actual fitting are still undesirable.The establishment of human 3d model is to realize
Network fitting and the premise of private customization, accurately acquiring the net model of human body helps to realize the accurate of suit length collocation
Property, while the characteristic attribute of hundreds of sign human appearances of human body can be disposably obtained using the net model of human body, so as to quilt
For realizing that the private of clothing customizes service.
It is that one kind is preferably selected that human 3d model is obtained currently with the depth camera of consumer level, on the one hand can be with
Cost-effective, the millimetre-sized measurement accuracy of another aspect consumer level depth camera also meets the requirement of the net model of human body enough.To the greatest extent
Pipe is thus, the fitting for being currently based on human 3d model still faces some problems：The accurate acquisition of the net model of human body needs human body
The clothes of compact is worn, but in most cases, measured personnel often wear loose clothes, are worn in human body wide
During loose clothing, current fitting technology can not still obtain the net model of human body exactly.
The content of the invention
The technical problem to be solved in the present invention is：Existing fitting scheme is difficult to when human body wears loose clothing exactly
Obtain the net model of human body.
In order to solve the above technical problems, the present invention proposes a kind of creation method of the net model of human body, comprise the following steps：
S1：At least two amplitude deepness images of the human body under at least two given poses are obtained using depth camera；
S2：The characteristic parameter of the net model of human body is obtained from least two amplitude deepness images；
S3：The net model of human body is created according to the characteristic parameter.
Preferably, the given pose in the step S1 refers under the given pose, the clothing of human body at least one portion
In compact condition.
Preferably, the step S2 includes：
S21：Extract the characteristic parameter at each compact position of human body in the depth image under each given pose；
S22：By recoverable force computing or the method for setting up empirical equation, by the spy at compact position under each given pose
Levy parameter person and be converted into the actual characteristic parameter of human body；
S23：The characteristic parameter of the net model of human body is used as after the actual characteristic parameter of human body after all conversions is collected.
Preferably, the recoverable force computing described in the step S22 is specifically included：
(1) cloud data at compact position under given pose is obtained, and is had after denoising and cavity filling
High-quality cloud data, and preserve the three-dimensional Euclidean coordinate information of each point, according to cloud data obtain grid model M=(V,
E), wherein, V=(v1,v2,…,vn)TThe matrix being made up of the three-dimensional coordinate on each summit in model is represented, E is represented in model
All sides；
(2) the canonical matrix S for relativeness between each in descriptive model cloud is calculated, computing formula is S=CV,
Wherein C=(I-D-1B) it is transformation matrix, I is unit matrix, and D is the element D on diagonal matrix, diagonalii=di, diFor with
Point viAdjacent vertex number, B matrixes can be expressed from the next：
(3) multiple deformation obligatory points are selected, obligatory point Euclidean coordinate new after recoverable force can be obtained by calculating, will
New constraint point coordinates is as restrictive condition and is added to transformation matrix, becomes new transformation matrix C ', finally, utilizes public affairs
Formula V '=C '-1S solves the summit Euclidean coordinate after deformation.
Preferably, the step S3 includes：
S31：Set up standardized human body's model；
S32：Change standardized human body's model to obtain the net model of human body according to the characteristic parameter of the net model of the human body.
Preferably, the depth camera in the step S1 is based on structure light trigonometry, time flight method or binocular vision
The one of which of principle.
Preferably, human depth's image in the step S1 is rotated one week around single depth camera by human body
What mode was obtained, or by using with different angular distributions human peripheral multiple depth cameras synchronously obtain.
Preferably, the method for modification standardized human body's model in the step S32 is the method based on shaft distortion principle, or
Person is the method by carrying out successive ignition to SCAPE models.
Based on the creation method of the net model of above-mentioned human body, the present invention also proposes a kind of system for setting up the net model of human body, wraps
Memory is included, for depositing program；Processor, runs described program, for controlling the system for setting up the net model of human body
Perform the above-mentioned method for setting up the net model of human body.
The present invention also proposes a kind of computer-readable recording medium for including computer program, and the computer program can be grasped
Make to make computer perform the above-mentioned method for setting up the net model of human body.
Based on the creation method of the net model of above-mentioned human body, the present invention also proposes a kind of three-dimensional fitting method, including following step
Suddenly：
T1：According to the creation method of the net model of above-mentioned human body, the net model of human body is created；
T2：Create clothing model；
T3：Clothes effect is shown after the net model of clothing model and human body is synthesized.
The present invention also proposes a kind of three-dimensional fitting system, including memory, for depositing program；Processor, operation is described
Program, for controlling the 3D dressing systems to perform above-mentioned 3D fitting methods.
The present invention also proposes a kind of computer-readable recording medium for including computer program, and the computer program can be grasped
Make to make computer perform above-mentioned 3D fitting methods.
Beneficial effects of the present invention are：The invention provides a kind of establishment side of the net model of the human body based on depth camera
Method, compared with prior art, the present invention can obtain characteristics of human body's parameter exactly by multiple given poses, then according to people
The net model of body characteristicses parameter acquiring human body, the manikin error that loose clothing is brought can be avoided using the method for the present invention.
In addition, the creation method based on the net model of above-mentioned human body, the present invention also proposes a kind of three-dimensional fitting method and three-dimensional
Dressing system, no matter human body wears loose clothing or compact clothing, uses the three-dimensional fitting method or system of the present invention, equal energy
The effect that enough real-time and 360 ° of displayings are worn the clothes.
Brief description of the drawings
Fig. 1 is the general flow chart of the net model creation method of human body in the specific embodiment of the invention.
Fig. 2 is the step S2 of the net model creation method of human body in specific embodiment of the invention sub-process figure.
Fig. 3 is the step S3 of the net model creation method of human body in specific embodiment of the invention sub-process figure.
Fig. 4 is the flow chart of three-dimensional fitting method in the specific embodiment of the invention.
Embodiment
It is further described below with reference to drawings and the specific embodiments.
1st, the creation method of the net model of human body
The creation method of the net model of human body, as shown in figure 1, comprising the following steps：S1：Human body is obtained using depth camera to exist
At least two amplitude deepness images under at least two given poses；S2：Obtain the characteristic parameter of the net model of human body；S3：Build human body
Net model.Wherein, at least two width depth of the human body under at least two given poses are obtained using depth camera in step sl
Image, described depth camera is to be based on the trigon depth camera of structure light, and described given pose refers to human body at least one
The clothing of individual part is in compact condition.Above-mentioned steps will be described in detail below.
S1：At least two amplitude deepness images of the human body under at least two given poses are obtained using depth camera
Mainly have based on structure light trigonometry, time flight method or binocular vision currently used for the camera for obtaining depth image
Feel the depth camera of principle.
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.
Depth camera based on time flight method utilizes Laser emission instrument to objective emission laser pulse, by optical pickup apparatus
Obtain pulse and record the light flight time for being transmitted into reception, the depth image of target can be calculated according to the flight time.
Depth camera based on Binocular Vision Principle, substantially similar to structure light trigonometry principle, difference is structure
Light trigonometry is actively to measure, and binocular vision is then passive measurement.Difference of the image obtained using left and right camera on parallax
Not, the depth value for further calculating target after the parallax using triangulation principle and is obtained by vision algorithm.
Each is good and bad for three kinds of depth acquisition methods, and structure light trigonometry cost is relatively low, and depth obtains efficiency high, but multiple phases
Machine can have interference when being measured to an object space simultaneously.And the depth camera cost of time flight method is higher.Binocular
The depth camera algorithm of vision is complicated, and has to the environment residing for target certain requirement.Thus, for application ring specifically
Border can suitably choose different depth cameras.
In this embodiment, the depth map of human body is obtained using based on the trigon depth camera of structure light
Picture.
In other embodiments, the depth camera based on time flight method or Binocular Vision Principle can be used
To obtain the depth image of human body.
Usually, manikin should include 360 ° of the angle of visual field.It is that this also has and the angle of visual field of single depth camera is limited
A variety of alternative human depth's image acquisitions schemes.
One is to utilize single depth camera, and tested human body allows depth camera to obtain by way of rotating one week and includes human body
The multi-amplitude deepness image of 360 ° of information.Overall the three of human body can be extracted according to multi-amplitude deepness image using image registration algorithms
Tie up cloud data.This method is difficult to the overall three-dimensional data of real-time human body and obtained, and advantage is that cost is relatively low.
Two be using being distributed in multiple depth cameras of human peripheral, by multiple depth cameras of different angles synchronously
The multi-amplitude deepness image of reflection all three-dimensional informations of human body is obtained, human body is obtained after finally being registered using multi-amplitude deepness image
Overall three dimensional point cloud.This method be substantially solved using the quantitative advantage of depth camera can not real-time carry
The problem of taking, the cost paid is that cost is higher.
In this embodiment, the quantitative selection of depth camera is not limited, and single depth camera extracts human body
The speed of feature is slower than multiple depth cameras.
The net model that human body can be accurately acquired is the basis for carrying out next step fitting, but in most situations
Under, measured personnel often wear loose clothes, and obtained three-dimensional (3 D) manikin can not accurately reflect the truth of human body, take off
Clothing or the measurement that is in tights are not the preferred plan of this problem of solution.
In addition, the registration of depth image needs to expend more computing resource, data demand is more accurate, the real-time of system
Will be poorer.There is presently no the consumer level solution for being capable of real-time acquisition human body three-dimensional block mold.
The problem of in order to solve real-time and measurement accuracy, the scheme that present embodiment is used is, from depth camera
The characteristic information of human body can be accurately reflected by being extracted in human depth's image of acquisition, be created that virtually according to characteristic information
The net model of the human body that can reflect human body three-dimensional feature.Once set up after the net model of human body, the reality subsequently during fitting
When display need not then be calculated frame by frame, need to extract human skeleton frame by frame, by the posture of the net model of skeleton driven human body with up to
To the requirement of real-time.
S2：Obtain the characteristic parameter of the net model of human body
The situation (the loose non-thick clothes of clothes) when human body wears loose clothes is considered herein, it is similarly suitable to wear compact clothing
Situation during thing.In addition, characteristics of human body here refers to characteristics of human body of the human body under normal stand posture.Human body wears loose clothing
There are many positions to be covered by clothes when taking, in body, covered position is divided to two kinds, and one kind covers to be personal, Yi Zhongwei
Non- personal covering.Human body net model of the model at personal covering (compact) position for reality, rather than personal covering are given tacit consent to herein
The model at (loose) position then differs greatly with the net model of human body.
In the step of obtaining the characteristic parameter of the net model of human body, as shown in Fig. 2 including three below sub-step again：
S21：Extract the characteristic parameter at each compact position of human body in the depth image under each given pose；S22：It is extensive by deforming
Multiple computing or the method for setting up empirical equation, are converted into human body actual by the characteristic parameter person at compact position under each given pose
Characteristic parameter；S23：Join after the actual characteristic parameter of human body after all conversions is collected as the feature of the net model of human body
Number.Above-mentioned steps will be described in detail below.
S21：Extract the characteristic parameter at each compact position of human body in the depth image under each given pose
Non- personal covering can be allowed to become personal covering by different gesture actions, such as with arms akimbo can then allow waist
Portion becomes personal and covers, lifts shank calf can be allowed to become personal and cover, lift a hand and bent over to side, can allow
Chest side becomes personal covering etc..
Thus, the posture of all characteristics of human body can be reflected by being previously set, and allowing tested human body to do posture one by one just can be with
Obtain the physical characteristic data that the net model of all human bodies needs.
Following table illustrates part posture and corresponding characteristics of human body.
| Sequence number | Posture | Personal position |
| 1 | Uprightly | Shoulder |
| 2 | With arms akimbo | Waist lateral dimension |
| 3 | Lift thigh | Thigh |
| 4 | Lift shank | Shank |
| 5 | Raise one's hand, bent over to side | Arm, chest and waist are sideways |
| 6 | Forwardly bend over | Back, buttocks |
| 7 | Square one's shoulders | Chest, belly |
| … | … |
The characteristic of human body is generally comprised：Height, shoulder height, shoulder breadth, waistline, bust, thigh and calf profile, arm geometry etc.
Deng.
Additionally include the characteristic point at each position, i.e. artis.The extraction of artis can be based on similar kinect
The algorithm that SDK middle skeletons are extracted, that is, first pass through positioning head and human body trunk, then utilize deep learning (K-Tree) algorithm
Orient other skeletal joint point positions.
S22：By recoverable force computing or the method for setting up empirical equation, by the spy at compact position under each given pose
Levy parameter person and be converted into the actual characteristic parameter of human body
In terms of the characteristic acquisition of human body, directly obtained under specific posture be characterized in can not be used directly to as
Manikin feature.Such as when human body is forwardly bent over, the back of acquisition and the feature (width, cross section etc.) of buttocks
All it is the data after deformation.The human body that can be obtained the data after deformation by recoverable force computing under normal attitude is special
Levy.Alternatively, it is also possible to by methods such as machine learning, set up a kind of simple empirical equation, to reflect under human body given pose
Characteristics of human body and the relation of actual characteristic.Both approaches are illustrated separately below, leg muscle portion when being squatted down with human body
, it is necessary to which indirect gain, which is characterized in thigh, includes the multiple of two ends (thigh top and with shank junction) exemplified by the deformation of position
The girth of cross section, it should be noted that be not to squat down completely here, is produced when having contact in order to avoid the thigh back side and shank
The not retrievable situation of raw back data.
(1) recoverable force
First, the cloud data of huckle after squatting down is obtained, and is obtained after denoising and cavity filling with higher
The cloud data of quality, and the three-dimensional Euclidean coordinate information of each point is preserved, grid model M=(V, E) is obtained according to cloud data.
Wherein, V=(v1,v2,…,vn)TThe matrix being made up of the three-dimensional coordinate on each summit in model is represented, E represents own in model
Side.
Secondly, the canonical matrix S for relativeness between each in descriptive model cloud is calculated, the canonical matrix is becoming
Do not changed during shape.Computing formula is S=CV, wherein C=(I-D-1B) be transformation matrix, I be unit matrix, D for pair
Element D on angular moment battle array, diagonalii=di, diFor with point viAdjacent vertex number, B matrixes can be expressed from the next：
Again, multiple deformation obligatory points are selected.Here according to priori, i.e. people, thigh is transversal under standing normal posture
Face is circle, and surface skin tension causes thigh transversal towards elliptical deformation when squatting down.It can be obtained by ellipse by calculating
Circle becomes round rear new obligatory point Euclidean coordinate, using new constraint point coordinates is as restrictive condition and is added to conversion square
Battle array, becomes new transformation matrix C '.Finally, formula V '=C ' is utilized-1S solves the summit Euclidean coordinate after deformation.
(2) empirical equation
Here main purpose be set up squat down after under the multiple section girths of thigh and normal stand posture girth it
Between relation.Because the leg profile of different crowd is different, deformation also can be different, thus want to obtain desired pass exactly
System, in addition it is also necessary to sampled to the crowd of different heights, body weight, sex, the situation of change of girth, utilizes machine before and after record deformation
Regression algorithm such as least square regression algorithm, logistic regression algorithm etc. in device study fit the relation before and after deformation, will
This relation empirically formula.
S23：The characteristic parameter of the net model of human body is used as after the actual characteristic parameter of human body after all conversions is collected.
S3：Build the net model of human body
The parametric modeling of human body can be regarded as by obtaining the net model of human body according to the characteristics of human body of extraction, as shown in figure 3,
Build the net model of human body includes following two sub-steps again：S31：Set up standardized human body's model；S32：According to the net mould of the human body
Characteristic parameter modification standardized human body's model of type is so as to obtain the net model of human body.Generally, it is necessary first to a standard people
Body Model, then according to obtained actual human body feature modification standardized human body model so as to obtain that the human body of actual human body can be reflected
Net model.
A kind of simple standardized human body's model can have the gridding of a certain proportion of regular shape according to priori
Manikin, conversion of being modified to standardized human body's model mainly has three kinds of situations：Length deformation, width deformation and girth
Deformation.When the characteristics of human body of acquisition feature corresponding with master pattern is inconsistent, it is necessary to carry out length, width or girth and become
Shape.Specific deformation principle is shaft distortion principle, and so-called shaft distortion principle is by point and length to be deformed on model here
Degree, width or the corresponding axle of girth set up mapping relations one by one, and when axle changes, the coordinate of corresponding deformation point also becomes
Change, model is re-created after calculating new coordinate.
There are the manikin that some precision are more increased, such as SCAPE models etc. at present.Human body is obtained by SCAPE models
The process of net model can regard the iteration again and again to SCAPE models as, that is, set up the property for weighing characteristics of human body's gap
Energy function, by the way that SCAPE models are changed again and again into iteration until performance function value reaches certain threshold range.
The net model algorithm of former human body is simple, and the real-time of system is higher, has the disadvantage that precision is poor；Latter algorithm compared with
Complexity, high precision has the disadvantage that real-time is poor, generally requires the problem of GPU parallel processing is to solve real-time.
The acquisition methods of the net model of human body are not any limitation as in this embodiment.
2nd, the system for setting up the net model of human body
In this embodiment, the system for setting up the net model of human body, including memory, for depositing program；Processing
Device, runs described program, for controlling the system for setting up the net model of human body to perform the above-mentioned side for setting up the net model of human body
Method.
In other embodiments, the system for setting up the net model of human body can also be a kind of comprising computer program
Computer-readable recording medium, the computer program is operable to make computer perform the above-mentioned side for setting up the net model of human body
Method.
3rd, application of the net model of human body in three-dimensional fitting
Three-dimensional fitting method, as shown in figure 4, comprising the following steps：T1：Create the net model of human body；T2：Create clothing mould
Type；T3：Clothes effect is shown after the net model of clothing model and human body is synthesized.
Usually, the manikin of standard stance is fitted first, this step can regard static fitting as；
Secondly the real-time fitting when actual human body postural change, can regard dynamic fitting as.Wherein dynamic fitting is actually quiet
The extension of state fitting in time.The thus next static fitting of main explanation.
The clothing simulation model of current comparative maturity is mass spring model, and setting up after clothing simulation model needs clothing
Thing is registered with the net model of human body.It is generally acknowledged that after the peak and human body at the clothing back side neck center, accordingly can be real
The preliminary registration of existing clothing and manikin；Then the local registration of various pieces is realized according to the current framework information of human body.
After Registration, calculating, laundry hits detection of the power of particle etc. can also be carried out, to simulate more real clothing
Display effect.
During follow-up real-time is shown, as long as the framework information by identifying human body, then according to the skeleton
It is that can realize real-time 3D fittings that information, which carries out local registration,.
4th, three-dimensional fitting system
In this embodiment, three-dimensional fitting system, including memory, for depositing program；Processor, runs institute
Program is stated, for controlling the 3D dressing systems to perform above-mentioned 3D fitting methods.
In other embodiments, three-dimensional fitting system can also can for a kind of computer comprising computer program
Storage medium is read, the computer program is operable to make computer perform above-mentioned 3D fitting methods.
Present embodiment provides a kind of creation method of the net model of human body based on depth camera, with prior art
Compare, present embodiment can obtain characteristics of human body's parameter exactly by multiple given poses, it is then special according to human body
The net model of parameter acquiring human body is levied, the manikin error that loose clothing is brought can be avoided using the method for the present invention.
In addition, the creation method based on the net model of above-mentioned human body, present embodiment also proposes a kind of three-dimensional fitting side
Method and three-dimensional fitting system, no matter human body wears loose clothing or compact clothing, is tried using the three-dimensional of present embodiment
Clothing method or system, can in real time and 360 ° show the effect worn the clothes.
Above content is to combine specific embodiment further description made for the present invention, it is impossible to assert this hair
Bright specific implementation is confined to these explanations.For those skilled in the art, this is not being departed from
On the premise of inventive concept, some equivalent substitutes or obvious modification can also be made, and performance or purposes are identical, should all regard
To belong to protection scope of the present invention.
Claims (12)
1. a kind of creation method of the net model of human body, comprises the following steps：
S1：At least two amplitude deepness images of the human body under at least two given poses are obtained using depth camera；
S2：The characteristic parameter of the net model of human body is obtained from least two amplitude deepness images；
S3：The net model of human body is created according to the characteristic parameter.
2. the creation method of the net model of human body according to claim 1, it is characterised in that the specific appearance in the step S1
Gesture refers to that under the given pose clothing of human body at least one portion is in compact condition.
3. the creation method of the net model of human body according to claim 2, it is characterised in that the step S2 includes：
S21：Extract the characteristic parameter at each compact position of human body in the depth image under each given pose；
S22：By recoverable force computing or the method for setting up empirical equation, the feature at compact position under each given pose is joined
Number person is converted into the actual characteristic parameter of human body；
S23：The characteristic parameter of the net model of human body is used as after the actual characteristic parameter of human body after all conversions is collected.
4. the creation method of the net model of human body according to claim 3, it is characterised in that described in the step S22
Recoverable force computing is specifically included：
(1) cloud data at compact position under given pose is obtained, and is obtained after denoising and cavity filling with high-quality
The cloud data of amount, and the three-dimensional Euclidean coordinate information of each point is preserved, grid model M=(V, E) is obtained according to cloud data, its
In, V=(v1,v2,…,vn)TThe matrix being made up of the three-dimensional coordinate on each summit in model is represented, E represents all in model
Side；
(2) the canonical matrix S for relativeness between each in descriptive model cloud is calculated, computing formula is S=CV, wherein
C=(I-D-1B) it is transformation matrix, I is unit matrix, and D is the element D on diagonal matrix, diagonalii=di, diFor with point vi
Adjacent vertex number, B matrixes can be expressed from the next：
(3) multiple deformation obligatory points are selected, obligatory point Euclidean coordinate new after recoverable force can be obtained by calculating, will be new
Point coordinates is as restrictive condition and is added to transformation matrix for constraint, becomes new transformation matrix C ', finally, utilizes formula V '
=C '-1S solves the summit Euclidean coordinate after deformation.
5. the creation method of the net model of human body according to claim 1, it is characterised in that the step S3 includes：
S31：Set up standardized human body's model；
S32：Change standardized human body's model to obtain the net model of human body according to the characteristic parameter of the net model of the human body.
6. the creation method of the net model of human body according to claim 1, it is characterised in that the human body in the step S1 is deep
Degree image is obtained by way of human body is rotated one week around single depth camera, or by using with different angles
It is distributed in multiple depth cameras synchronization acquisition of human peripheral.
7. the creation method of the net model of human body according to claim 5, it is characterised in that the modification in the step S32
The method of standardized human body's model is the method based on shaft distortion principle, or by carrying out successive ignition to SCAPE models
Method.
8. a kind of system for setting up the net model of human body, it is characterised in that including memory, for depositing program；Processor, operation
Described program, for controlling the system for setting up the net model of human body to perform the method as described in claim 1-7 is any.
9. a kind of computer-readable recording medium for including computer program, the computer program is operable to hold computer
Method of the row as described in claim 1-7 is any.
10. a kind of three-dimensional fitting method, comprises the following steps：
T1：The net model of human body is created according to any described methods of claim 1-7；
T2：Create clothing model；
T3：Clothes effect is shown after the net model of clothing model and human body is synthesized.
11. a kind of three-dimensional fitting system, it is characterised in that including memory, for depositing program；Processor, runs the journey
Sequence, for controlling the three-dimensional fitting system to perform three-dimensional fitting method as claimed in claim 10.
12. a kind of computer-readable recording medium for including computer program, the computer program is operable to make computer
Perform three-dimensional fitting method as claimed in claim 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710079459.9A CN106952334B (en) | 2017-02-14 | 2017-02-14 | The creation method and three-dimensional fitting system of the net model of human body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710079459.9A CN106952334B (en) | 2017-02-14 | 2017-02-14 | The creation method and three-dimensional fitting system of the net model of human body |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106952334A true CN106952334A (en) | 2017-07-14 |
| CN106952334B CN106952334B (en) | 2019-08-30 |
Family
ID=59466418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710079459.9A Active CN106952334B (en) | 2017-02-14 | 2017-02-14 | The creation method and three-dimensional fitting system of the net model of human body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106952334B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507269A (en) * | 2017-07-31 | 2017-12-22 | 广东欧珀移动通信有限公司 | Personalized three-dimensional model generating method, device and terminal device |
| CN107657657A (en) * | 2017-09-08 | 2018-02-02 | 明利 | A kind of three-dimensional human modeling method, device, system and storage medium |
| 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 |
| CN109035393A (en) * | 2018-07-27 | 2018-12-18 | 东方梦幻文化产业投资有限公司 | A kind of method and device for rebuilding three-dimensional animation |
| CN110322329A (en) * | 2019-07-09 | 2019-10-11 | 广州品唯软件有限公司 | A kind of method, apparatus and equipment that manikin is established |
| CN110926371A (en) * | 2019-11-19 | 2020-03-27 | 宁波舜宇仪器有限公司 | Three-dimensional surface detection method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1617174A (en) * | 2004-12-09 | 2005-05-18 | 上海交通大学 | Human limb three-dimensional model building method based on image cutline |
| CN102855470A (en) * | 2012-07-31 | 2013-01-02 | 中国科学院自动化研究所 | Estimation method of human posture based on depth image |
| CN104008571A (en) * | 2014-06-12 | 2014-08-27 | 深圳奥比中光科技有限公司 | Human body model obtaining method and network virtual fitting system based on depth camera |
| CN104240288A (en) * | 2013-06-21 | 2014-12-24 | 株式会社东芝 | Methods and systems for generating a three-dimensional representation of a subject |
| CN104992441A (en) * | 2015-07-08 | 2015-10-21 | 华中科技大学 | Real human body three-dimensional modeling method specific to personalized virtual fitting |
-
2017
- 2017-02-14 CN CN201710079459.9A patent/CN106952334B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1617174A (en) * | 2004-12-09 | 2005-05-18 | 上海交通大学 | Human limb three-dimensional model building method based on image cutline |
| CN102855470A (en) * | 2012-07-31 | 2013-01-02 | 中国科学院自动化研究所 | Estimation method of human posture based on depth image |
| CN104240288A (en) * | 2013-06-21 | 2014-12-24 | 株式会社东芝 | Methods and systems for generating a three-dimensional representation of a subject |
| CN104008571A (en) * | 2014-06-12 | 2014-08-27 | 深圳奥比中光科技有限公司 | Human body model obtaining method and network virtual fitting system based on depth camera |
| CN104992441A (en) * | 2015-07-08 | 2015-10-21 | 华中科技大学 | Real human body three-dimensional modeling method specific to personalized virtual fitting |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507269A (en) * | 2017-07-31 | 2017-12-22 | 广东欧珀移动通信有限公司 | Personalized three-dimensional model generating method, device and terminal device |
| CN107657657A (en) * | 2017-09-08 | 2018-02-02 | 明利 | A kind of three-dimensional human modeling method, device, system and storage medium |
| 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 |
| CN109035393A (en) * | 2018-07-27 | 2018-12-18 | 东方梦幻文化产业投资有限公司 | A kind of method and device for rebuilding three-dimensional animation |
| CN109035393B (en) * | 2018-07-27 | 2023-01-03 | 东方梦幻文化产业投资有限公司 | Method and device for reconstructing three-dimensional animation |
| CN110322329A (en) * | 2019-07-09 | 2019-10-11 | 广州品唯软件有限公司 | A kind of method, apparatus and equipment that manikin is established |
| CN110926371A (en) * | 2019-11-19 | 2020-03-27 | 宁波舜宇仪器有限公司 | Three-dimensional surface detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106952334B (en) | 2019-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106952334B (en) | The creation method and three-dimensional fitting system of the net model of human body | |
| US20210074005A1 (en) | Image processing method and apparatus, image device, and storage medium | |
| CN104992441B (en) | A kind of real human body three-dimensional modeling method towards individualized virtual fitting | |
| CN106952335B (en) | Method and system for establishing human body model library | |
| CN105631861B (en) | Restore the method for 3 D human body posture from unmarked monocular image in conjunction with height map | |
| CN109377557B (en) | Real-time three-dimensional face reconstruction method based on single-frame face image | |
| CN102999942B (en) | Three-dimensional face reconstruction method | |
| CN104008557B (en) | A kind of three-dimensional matching process of clothing and anthropometric dummy | |
| CN106952302B (en) | human body model automatic creation method and three-dimensional fitting system | |
| CN103106604B (en) | Based on the 3D virtual fit method of body sense technology | |
| CN108154550A (en) | Face real-time three-dimensional method for reconstructing based on RGBD cameras | |
| Zhu et al. | An efficient human model customization method based on orthogonal-view monocular photos | |
| CN108537110A (en) | Generate the device and method based on virtual reality of three-dimensional face model | |
| CN109086798A (en) | A kind of data mask method and annotation equipment | |
| CN105608746A (en) | Method for virtual realizing of reality | |
| CN104103090A (en) | Image processing method, customized human body display method and image processing system | |
| CN104915978A (en) | Realistic animation generation method based on Kinect | |
| CN110175897A (en) | A kind of 3D synthesis fitting method and system | |
| CN111932678A (en) | Multi-view real-time human motion, gesture, expression and texture reconstruction system | |
| CN107730449A (en) | A kind of method and system of human face five-sense-organ landscaping treatment | |
| WO2021098143A1 (en) | Image processing method and device, image processing apparatus, and storage medium | |
| CN107067299A (en) | Virtual fit method and system | |
| CN112102480B (en) | Image data processing method, apparatus, device and medium | |
| CN109655011B (en) | Method and system for measuring dimension of human body modeling | |
| CN110458924A (en) | A kind of three-dimensional facial model method for building up, device and electronic equipment |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: A808, Zhongdi building, industry university research base, China University of Geosciences, No.8, Yuexing Third Road, Nanshan District, Shenzhen, Guangdong 518000 Patentee after: Obi Zhongguang Technology Group Co., Ltd Address before: A808, Zhongdi building, industry university research base, China University of Geosciences, No.8, Yuexing Third Road, Nanshan District, Shenzhen, Guangdong 518000 Patentee before: SHENZHEN ORBBEC Co.,Ltd. |