CN104899919A - Modeling method and apparatus - Google Patents
Modeling method and apparatus Download PDFInfo
- Publication number
- CN104899919A CN104899919A CN201510259610.8A CN201510259610A CN104899919A CN 104899919 A CN104899919 A CN 104899919A CN 201510259610 A CN201510259610 A CN 201510259610A CN 104899919 A CN104899919 A CN 104899919A
- Authority
- CN
- China
- Prior art keywords
- body structure
- user
- pixel distance
- volume image
- amount volume
- 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
Landscapes
- Image Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to the field of automation, and discloses a modeling method and apparatus, for solving the technical problem that an error is great when a three-dimensional model of a human body is built in the prior art. The method comprises: acquiring body measurement images of a user, wherein the images comprise a front image, a side image, a left image, and a right image of the body of the user; extracting profile information of the user from the body measurement images of the user; determining shape features of the user based on the profile information of the user, and height information of the user; building a three-dimensional model of the user based on the shape features. The present invention achieves the technical effect of reducing the error degree of the built three-dimensional model of human bodies.
Description
Technical field
The present invention relates to automatic field, particularly relate to a kind of modeling method and device.
Background technology
The mode of the body characteristics of current acquisition human body mainly comprises: tape measuring, photo comparison two kinds of modes are below the respective implementation procedures of these two kinds of modes:
The first, tape measuring mode needs professional by tape measure, user to be measured to be carried out to the measurement of various piece, and then obtain the body characteristics of human body, because everyone measurement custom and mode are not quite similar, cause human dimension error larger, cannot unify, and time spent by the program is longer.
The second, first photo alignments needs the image taking the user with object of reference, then after being analyzed by professional's comparison film " estimation " go out the approximate dimensions of human body, first it need the photo taken to have object of reference, and also there is very large requirement for the angle of photo, in addition, owing to still needing artificial estimation, so error also can be caused larger.
Because the error of the body characteristics of human body measured in prior art is comparatively large, thus also cause the error of the three-dimensional model of the human body set up based on this body characteristics larger.
Summary of the invention
The invention provides a kind of modeling method and device, to solve in prior art the larger technical matters of the three-dimensional model time error of setting up human body.
First aspect, the embodiment of the present invention provides a kind of modeling method, comprising:
Obtain the amount volume image of user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg;
The profile information of described user is extracted from described amount volume image;
Height information based on described profile information and described user determines the body characteristics of described user;
The three-dimensional model of described user is set up based on described body characteristics.
Optionally, the described height information based on described profile information and described user determines the body characteristics of described user, specifically comprises:
Determine the first area at the first body structure place of described user;
The first pixel distance of the first body structure in described amount volume image is determined based on described first area;
The second pixel distance of height in described amount volume image at least based on described first pixel distance, described height information, described user determines the feature of described first body structure.
Optionally, describedly determine the first pixel distance of the first body structure in described amount volume image based on described first area, specifically comprise:
Determine that in described first area, border extreme slope value point position is the joint position of described first body structure;
Described first pixel distance is determined based on described joint position.
Optionally, describedly at least determine to be specially the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user:
The size of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance.
Optionally, describedly at least determine to be specially the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user:
The width of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the width of described first body structure and the first modeling algorithm of described first body structure; Or
Width and the thickness of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the second modeling algorithm of the width of described first body structure, thickness and described first body structure.
Optionally, be: when upper arm, underarm, wrist, thigh, knee, shank, ankle at described first body structure, described first modeling algorithm is specially: π W, and wherein W represents the width of the first body structure.
Optionally, at described first body structure be: when chest, abdomen, waist, hip, neck, described modeling algorithm is specially: π (W+L)/2, and wherein W represents the width of the first body structure, and L represents the thickness of the first body structure.
Second aspect, the embodiment of the present invention provides a kind of model building device, comprising:
Acquisition module, for obtaining the amount volume image of user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg;
Extraction module, for extracting the profile information of described user from described amount volume image;
First determination module, for determining the body characteristics of described user based on the height information of described profile information and described user;
Set up module, for setting up the three-dimensional model of described user based on described body characteristics.
Optionally, described first determination module, specifically comprises:
First determining unit, for determining the first area at the first body structure place of described user;
Second determining unit, for determining the first pixel distance of the first body structure in described amount volume image based on described first area;
3rd determining unit, at least determining the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user.
Optionally, described second determining unit, specifically comprises:
First determines subelement, for determining that in described first area, border extreme slope value point position is the joint position of described first body structure;
Second determines subelement, for determining described first pixel distance based on described joint position.
Optionally, described 3rd determining unit, specifically for:
The size of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance.
Optionally, described 3rd determining unit, specifically for:
The width of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the width of described first body structure and the first modeling algorithm of described first body structure; Or
Width and the thickness of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the second modeling algorithm of the width of described first body structure, thickness and described first body structure.
Optionally, be: when upper arm, underarm, wrist, thigh, knee, shank, ankle at described first body structure, described first modeling algorithm is specially: π W, and wherein W represents the thickness of the first body structure.
Optionally, be: when chest, abdomen, waist, hip, neck at described first body structure, described second modeling algorithm is specially: π (W+L)/2, and wherein W represents the thickness of the first body structure, and L represents the width of the first body structure.
Beneficial effect of the present invention is as follows:
Due in embodiments of the present invention, first obtain the amount volume image of user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg; Then from described amount volume image, extract the profile information of described user; Then the body characteristics of described user is determined based on the height information of described profile information and described user; Finally, the three-dimensional model of described user is set up based on described body characteristics.Owing to not needing to rely on the body characteristics that professional gathers human body in the program, but directly gather the amount volume image obtaining user, thus the body characteristics of user is obtained based on amount volume image, and in the process of body characteristics obtaining user, do not need the measurement of professional person (namely its acquisition precision does not rely on manually yet), so this body characteristics is objective and accurate data, thus greatly can reduce the error degree of user's body characteristics of acquisition, and the efficiency of the body characteristics obtaining user can be improved, thus reach the technique effect of the error degree of the three-dimensional model of the user that reduction is set up, and the efficiency setting up three-dimensional model can be improved.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of modeling method in the embodiment of the present invention;
Fig. 2 a and Fig. 2 b is the schematic diagram of profile information in embodiment of the present invention modeling method;
Fig. 3 is the schematic diagram of the body characteristics determining user in embodiment of the present invention modeling method;
Fig. 4 is the structural drawing of model building device in the embodiment of the present invention.
Embodiment
The invention provides a kind of modeling method and device, to solve in prior art the larger technical matters of the three-dimensional model time error of setting up human body.
Technical scheme in the embodiment of the present application is solve above-mentioned technical matters, and general thought is as follows:
First obtain the amount volume image of user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg; Then from described amount volume image, extract the profile information of described user; Then the body characteristics of described user is determined based on the height information of described profile information and described user; Finally, the three-dimensional model of described user is set up based on described body characteristics.Owing to not needing to rely on the body characteristics that professional gathers human body in the program, but directly gather the amount volume image obtaining user, thus the body characteristics of user is obtained based on amount volume image, and in the process of body characteristics obtaining user, do not need the measurement of professional person (namely its acquisition precision does not rely on manually yet), so this body characteristics is objective and accurate data, thus greatly can reduce the error degree of user's body characteristics of acquisition, and the efficiency of the body characteristics obtaining user can be improved, thus reach the technique effect of the error degree of the three-dimensional model of the user that reduction is set up, and the efficiency setting up three-dimensional model can be improved.
In order to better understand technique scheme, below by accompanying drawing and specific embodiment, technical solution of the present invention is described in detail, the specific features being to be understood that in the embodiment of the present invention and embodiment is the detailed description to technical solution of the present invention, instead of the restriction to technical solution of the present invention, when not conflicting, the technical characteristic in the embodiment of the present invention and embodiment can combine mutually.
First aspect, the embodiment of the present invention provides a kind of modeling method, please refer to Fig. 1, comprising:
Step S101: the amount volume image obtaining user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg;
Step S102: the profile information extracting described user from described amount volume image;
Step S103: the height information based on described profile information and described user determines the body characteristics of described user;
Step S104: the three-dimensional model setting up described user based on described body characteristics.
In step S101, in specific implementation process, user can pass through other equipment collection acquisition amount volume images, then the model building device that modeling method is applied is sent it to, or can directly by model building device collection acquisition amount volume image, gather acquisition amount volume image for which kind of mode of employing, the embodiment of the present invention is not itemizing, and is not restricted.
In step S102, gray threshold can be utilized to carry out binary conversion treatment to image, human body is plucked out from photo, and then determine the profile information of user.
For example, Otsu method can be adopted to find threshold value, and specific algorithm is as follows:
A. calculating probability histogram P
pHs (i), i=0,1 ..., 255;
B. gray average μ is calculated
r;
C. calculate gray scale class average μ (k), analogous column diagram and
k=0,1 ..., 255;
D. class Separation Indexes corresponding to gray scale k is calculated
The pixel change that usual characteristic is moved towards along image border is mild, and the change of the pixel of vertical direction is violent..Select thresholding method, modal form is that gray scale is set as two state of value, and to image F (j, k), its thresholding output is:
T in formula
ifor thresholding.
Image is made to be made up of object and background two parts.The background gray level probability distribution density corresponding with object is respectively P
1and P (F)
2(F), area ratio is respectively P
1and P
2(P
1+ P
2=1).The mixing probability distributing density function of its normal distribution in Gauss's situation is P (β, F
i), wherein β is μ
i, σ
i, P
i, the Multidimensional Parametric Vectors that (i=1,2) aliquot is formed. in general, above-mentioned parameter is unknown, can estimate to obtain from image histogram.If actual histogram h (F
i) represent, P (β, F
i) and h (F
i) between square error be:
When E is minimum, separate P (β, F
i) obtain μ, the parameters such as σ, P, and then successfully obtain the profile information of manikin, as shown in Figure 2 a and 2 b, be front view and the side view of the profile information of manikin, label shown in Fig. 2 a and Fig. 2 b is joint position, specifically has 1,2,3 ... 21,22 etc.
In step S103, the height information based on described profile information and described user determines the body characteristics of described user, please refer to Fig. 3, comprising:
Step S301: the first area determining the first body structure place of described user;
Step S302: determine the first pixel distance of the first body structure in described amount volume image based on described first area;
Step S303: the second pixel distance of height in described amount volume image at least based on described first pixel distance, described height information, described user determines the feature of described first body structure.
In step S301, different based on the first body structure, the first area at the first body structure place is also different, and such as: if the first body structure is shoulder, then first area is that in front view (FV), vertical number percent is near 0.81 place; If the first body structure is chest, then first area is front view (FV), vertical number percent is near 0.75 place in outboard profile (left hand view or right part of flg); If the first body structure is abdomen, then first area is arranged in front view (FV), the vertical number percent of outboard profile is near 0.58 place; If the first body structure is hip, then first area is arranged in front view (FV), the vertical number percent of outboard profile is near 0.53 place; If the first body structure is neck, then first area is arranged in front view (FV), the vertical number percent of outboard profile is near 0.86 place etc., and be positioned at which kind of region for first area, the embodiment of the present invention no longer itemizes, and is not restricted.
For the first body structure for chest, then first obtaining vertical number percent in front view (FV), outboard profile is as first area near 0.75 place.
In step S302, describedly determine the first pixel distance of the first body structure in described amount volume image based on described first area, specifically comprise:
Determine that in described first area, border extreme slope value point position is the joint position of described first body structure;
Described first pixel distance is determined based on described joint position.
For the first body structure for shoulder, then first can determine that in first area, extreme slope value point in border is the joint position of left shoulder joint position and right shoulder; Then, directly the distance measured between these two joint positions just can obtain the first pixel distance.When being other positions for the first body structure, determine that the mode of the first pixel citing is similar with it, so do not repeat them here.
In step S303, based on the difference of the first body structure, and then determine that the feature of the first body structure is also different, three kinds of enumerating below are wherein introduced, and certainly, in specific implementation process, are not limited to following three kinds of situations.
The first, describedly at least determine to be specially the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user:
The size of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance.
For example, can be inputted height information voluntarily, also can be gathered by collector the height information obtaining user by user, obtain height information for which kind of mode of employing, the embodiment of the present invention no longer itemizes, and is not restricted.
Wherein, first can determine the compression factor of output volume image relative to entity human body by height information and the second pixel distance, then by the first pixel distance divided by compression factor, just can obtain the size of the first body structure.The length characteristic in the body characteristics of user can be determined, such as: brachium, leg are long etc. by the program.
The second, describedly at least determine to be specially the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user:
The width of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the thickness of described first body structure and the first modeling algorithm of described first body structure.
For example, calculate the girth being roughly circular body structure often through such scheme, being roughly circular body structure is such as: upper arm, underarm, wrist, thigh, knee, shank, ankle etc.
Wherein, first can obtain and determine the compression factor of output volume image relative to entity human body, then pass through the first pixel size divided by compression factor, just can obtain the width of the first body structure; Then carry out with circumference the girth that human body simulation (being also the first modeling algorithm) just can obtain the first body structure.
As further preferred embodiment, be: when upper arm, underarm, wrist, thigh, knee, shank, ankle at described first body structure, described first modeling algorithm is specially: π W, and wherein W represents the width of the first body structure.
Wherein, there is error in perimeter and output, adopts nonlinear least square method to be optimized result:
Wherein the final output of nonlinear system is y
k, representing the Output rusults after this iterated revision of K, is a result in the circumference calculating of the first body structure;
Q Representative errors, nonlinear least square method is minimum for criterion is to estimate a kind of method for parameter estimation of nonlinear Static model parameter with the quadratic sum of error.
The third, describedly at least determine to be specially the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user:
Width and the thickness of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the second modeling algorithm of the width of described first body structure, thickness and described first body structure.
For example, the width obtaining the first body structure can be mapped by the first pixel distance corresponding to front view (FV), the thickness obtaining the first body structure can be mapped by the first pixel distance of outboard profile (left hand view or right part of flg), also namely: the width of body structure is obtained by full face unique point pixel distance map, thickness is then obtained by side photo eigen point pixel distance map.
For example, calculate the girth being roughly oval body structure often through such scheme, being roughly oval body structure is such as: chest, abdomen, waist, hip, neck etc.
For the width specifically how determining the first body structure, owing to making introduction above, so do not repeat them here, the account form of the thickness of the first body structure and the width of the first body structure similar, just when choosing the first pixel distance, need to select the distance in side view between two joint positions.
As further preferred embodiment, at described first body structure be: when chest, abdomen, waist, hip, neck, described modeling algorithm is specially: π (W+L)/2, and wherein W represents the width of the first body structure, and L represents the thickness of the first body structure.
Because the entity girth of the first body structure can exist error with formulae discovery girth out above, nonlinear least square method is adopted to be optimized result:
Wherein the final output of nonlinear system is y
k.
In step S104, first can obtain a three-dimensional model prestored, then based on step S103 obtain user body characteristics the three-dimensional model prestored is modified, and then obtain the three-dimensional model of user.
Wherein, as follows to the code of the amendment of three-dimensional model:
Second aspect, based on same inventive concept, the embodiment of the present invention provides a kind of model building device, please refer to Fig. 4, comprising:
Acquisition module 40, for obtaining the amount volume image of user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg;
Extraction module 41, for extracting the profile information of described user from described amount volume image;
First determination module 42, for determining the body characteristics of described user based on the height information of described profile information and described user;
Set up module 43, for setting up the three-dimensional model of described user based on described body characteristics.
Optionally, described first determination module 42, specifically comprises:
First determining unit, for determining the first area at the first body structure place of described user;
Second determining unit, for determining the first pixel distance of the first body structure in described amount volume image based on described first area;
3rd determining unit, at least determining the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user.
Optionally, described second determining unit, specifically comprises:
First determines subelement, for determining that in described first area, border extreme slope value point position is the joint position of described first body structure;
Second determines subelement, for determining described first pixel distance based on described joint position.
Optionally, described 3rd determining unit, specifically for:
The size of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance.
Optionally, described 3rd determining unit, specifically for:
The width of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the width of described first body structure and the first modeling algorithm of described first body structure; Or
Width and the thickness of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the second modeling algorithm of the width of described first body structure, thickness and described first body structure.
Optionally, be: when upper arm, underarm, wrist, thigh, knee, shank, ankle at described first body structure, described first modeling algorithm is specially: π W, and wherein W represents the thickness of the first body structure.
Optionally, be: when chest, abdomen, waist, hip, neck at described first body structure, described second modeling algorithm is specially: π (W+L)/2, and wherein W represents the thickness of the first body structure, and L represents the width of the first body structure.
The one or more embodiment of the present invention, at least has following beneficial effect:
First obtain the amount volume image of user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg; Then from described amount volume image, extract the profile information of described user; Then the body characteristics of described user is determined based on the height information of described profile information and described user; Finally, the three-dimensional model of described user is set up based on described body characteristics.Owing to not needing to rely on the body characteristics that professional gathers human body in the program, but directly gather the amount volume image obtaining user, thus the body characteristics of user is obtained based on amount volume image, and in the process of body characteristics obtaining user, do not need the measurement of professional person (namely its acquisition precision does not rely on manually yet), so this body characteristics is objective and accurate data, thus greatly can reduce the error degree of user's body characteristics of acquisition, and the efficiency of the body characteristics obtaining user can be improved, thus reach the technique effect of the error degree of the three-dimensional model of the user that reduction is set up, and the efficiency setting up three-dimensional model can be improved.
Those skilled in the art should understand, embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the present invention can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disk memory, CD-ROM, optical memory etc.) of computer usable program code.
The present invention describes with reference to according to the process flow diagram of the method for the embodiment of the present invention, equipment (system) and computer program and/or block scheme.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or square frame.These computer program instructions can being provided to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computing machine or other programmable data processing device produce device for realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be loaded in computing machine or other programmable data processing device, make on computing machine or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computing machine or other programmable devices is provided for the step realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
Although describe the preferred embodiments of the present invention, those skilled in the art once obtain the basic creative concept of cicada, then can make other change and amendment to these embodiments.So claims are intended to be interpreted as comprising preferred embodiment and falling into all changes and the amendment of the scope of the invention.
Obviously, those skilled in the art can carry out various change and modification to the embodiment of the present invention and not depart from the spirit and scope of the embodiment of the present invention.Like this, if these amendments of the embodiment of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. a modeling method, is characterized in that, comprising:
Obtain the amount volume image of user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg;
The profile information of described user is extracted from described amount volume image;
Height information based on described profile information and described user determines the body characteristics of described user;
The three-dimensional model of described user is set up based on described body characteristics.
2. the method for claim 1, is characterized in that, the described height information based on described profile information and described user determines the body characteristics of described user, specifically comprises:
Determine the first area at the first body structure place of described user;
The first pixel distance of the first body structure in described amount volume image is determined based on described first area;
The second pixel distance of height in described amount volume image at least based on described first pixel distance, described height information, described user determines the feature of described first body structure.
3. method as claimed in claim 2, is characterized in that, describedly determines the first pixel distance of the first body structure in described amount volume image based on described first area, specifically comprises:
Determine that in described first area, border extreme slope value point position is the joint position of described first body structure;
Described first pixel distance is determined based on described joint position.
4. method as claimed in claim 2, it is characterized in that, describedly at least determine to be specially the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user:
The size of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance.
5. method as claimed in claim 2, it is characterized in that, describedly at least determine to be specially the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user:
The width of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the width of described first body structure and the first modeling algorithm of described first body structure; Or
Width and the thickness of described first body structure is determined based on described first pixel distance, described height information, described second pixel distance; And the girth of described first body structure is determined based on the second modeling algorithm of the width of described first body structure, thickness and described first body structure.
6. method as claimed in claim 5, it is characterized in that, at described first body structure be: when upper arm, underarm, wrist, thigh, knee, shank, ankle, described first modeling algorithm is specially: π W, and wherein W represents the width of the first body structure.
7. method as claimed in claim 5, it is characterized in that, at described first body structure be: when chest, abdomen, waist, hip, neck, described modeling algorithm is specially: π (W+L)/2, wherein W represents the width of the first body structure, and L represents the thickness of the first body structure.
8. a model building device, is characterized in that, comprising:
Acquisition module, for obtaining the amount volume image of user, described amount volume image comprises: front view (FV), outboard profile, left hand view, right part of flg;
Extraction module, for extracting the profile information of described user from described amount volume image;
First determination module, for determining the body characteristics of described user based on the height information of described profile information and described user;
Set up module, for setting up the three-dimensional model of described user based on described body characteristics.
9. device as claimed in claim 8, it is characterized in that, described first determination module, specifically comprises:
First determining unit, for determining the first area at the first body structure place of described user;
Second determining unit, for determining the first pixel distance of the first body structure in described amount volume image based on described first area;
3rd determining unit, at least determining the feature of described first body structure based on the second pixel distance of height in described amount volume image of described first pixel distance, described height information, described user.
10. device as claimed in claim 9, it is characterized in that, described second determining unit, specifically comprises:
First determines subelement, for determining that in described first area, border extreme slope value point position is the joint position of described first body structure;
Second determines subelement, for determining described first pixel distance based on described joint position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510259610.8A CN104899919A (en) | 2015-05-19 | 2015-05-19 | Modeling method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510259610.8A CN104899919A (en) | 2015-05-19 | 2015-05-19 | Modeling method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104899919A true CN104899919A (en) | 2015-09-09 |
Family
ID=54032562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510259610.8A Pending CN104899919A (en) | 2015-05-19 | 2015-05-19 | Modeling method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104899919A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260922A (en) * | 2015-10-15 | 2016-01-20 | 广东欧珀移动通信有限公司 | Commodity information matching method and commodity information matching device |
| CN107993111A (en) * | 2016-10-26 | 2018-05-04 | 深圳市衣锦未来科技有限公司 | A kind of online human body dimension measurement system |
| WO2018133691A1 (en) * | 2017-01-22 | 2018-07-26 | 北京京东尚科信息技术有限公司 | Method and device for obtaining figure parameter of user |
| CN109117449A (en) * | 2018-07-27 | 2019-01-01 | 武汉文网亿联科技有限公司 | Method based on non-linear least square calculation using models Internet bar installation rate |
| CN110188726A (en) * | 2019-06-05 | 2019-08-30 | 杭州智珺智能科技有限公司 | Online human body dimension measurement method and the amount body clothing for this method |
| CN111145207A (en) * | 2018-10-17 | 2020-05-12 | 深圳市衣锦未来科技有限公司 | On-line customization method for making clothes through photo measurement |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090028914A (en) * | 2007-09-17 | 2009-03-20 | 재단법인서울대학교산학협력재단 | Method for setting to measurement point by body region |
| CN101515374A (en) * | 2008-02-20 | 2009-08-26 | 中国科学院自动化研究所 | Individualized realistic virtual character modeling method based on images |
| CN101720992A (en) * | 2009-11-13 | 2010-06-09 | 东华大学 | Three-dimensional human body measurement method by using single camera |
| CN102842089A (en) * | 2012-07-18 | 2012-12-26 | 上海交通大学 | Network virtual fit system based on 3D actual human body model and clothes model |
| KR20140123228A (en) * | 2013-04-12 | 2014-10-22 | (주)에프엑스기어 | Apparatus and Method for providing three dimensional model which puts on clothes based on depth information |
-
2015
- 2015-05-19 CN CN201510259610.8A patent/CN104899919A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090028914A (en) * | 2007-09-17 | 2009-03-20 | 재단법인서울대학교산학협력재단 | Method for setting to measurement point by body region |
| CN101515374A (en) * | 2008-02-20 | 2009-08-26 | 中国科学院自动化研究所 | Individualized realistic virtual character modeling method based on images |
| CN101720992A (en) * | 2009-11-13 | 2010-06-09 | 东华大学 | Three-dimensional human body measurement method by using single camera |
| CN102842089A (en) * | 2012-07-18 | 2012-12-26 | 上海交通大学 | Network virtual fit system based on 3D actual human body model and clothes model |
| KR20140123228A (en) * | 2013-04-12 | 2014-10-22 | (주)에프엑스기어 | Apparatus and Method for providing three dimensional model which puts on clothes based on depth information |
Non-Patent Citations (2)
| Title |
|---|
| 吴壮志 等: "基于图像的人体参数测量***的设计与实现", 《湖南大学学报（自然科学版）》 * |
| 方金 等: "一种采用单照相机的三维人体测量方法", 《东华大学学报（自然科学版）》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260922A (en) * | 2015-10-15 | 2016-01-20 | 广东欧珀移动通信有限公司 | Commodity information matching method and commodity information matching device |
| CN107993111A (en) * | 2016-10-26 | 2018-05-04 | 深圳市衣锦未来科技有限公司 | A kind of online human body dimension measurement system |
| WO2018133691A1 (en) * | 2017-01-22 | 2018-07-26 | 北京京东尚科信息技术有限公司 | Method and device for obtaining figure parameter of user |
| CN108346156A (en) * | 2017-01-22 | 2018-07-31 | 北京京东尚科信息技术有限公司 | User's stature parameter acquiring method and device |
| US11176673B2 (en) | 2017-01-22 | 2021-11-16 | Beijing Jingdong Shangke Information Technology Co., Ltd. | Method and device for acquiring figure parameters of a user |
| CN109117449A (en) * | 2018-07-27 | 2019-01-01 | 武汉文网亿联科技有限公司 | Method based on non-linear least square calculation using models Internet bar installation rate |
| CN109117449B (en) * | 2018-07-27 | 2022-04-15 | 武汉文网亿联科技有限公司 | Method for measuring and calculating Internet bar installation rate based on nonlinear least square model |
| CN111145207A (en) * | 2018-10-17 | 2020-05-12 | 深圳市衣锦未来科技有限公司 | On-line customization method for making clothes through photo measurement |
| CN110188726A (en) * | 2019-06-05 | 2019-08-30 | 杭州智珺智能科技有限公司 | Online human body dimension measurement method and the amount body clothing for this method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104899919A (en) | Modeling method and apparatus | |
| Shephard et al. | Automatic three‐dimensional mesh generation by the finite octree technique | |
| Kumar et al. | Optical flow: a curve evolution approach | |
| CN102567973B (en) | Image denoising method based on improved shape self-adaptive window | |
| CN105069423A (en) | Human body posture detection method and device | |
| Hannah | Error detection and correction in digital terrain models | |
| Le Guyader et al. | Self-repelling snakes for topology-preserving segmentation models | |
| CN111311485B (en) | Image processing method and related device | |
| CN105335997A (en) | Complex structure point cloud processing algorithm bases on Poisson reconstruction | |
| CN111932552B (en) | Aorta modeling method and device | |
| CN106485741A (en) | A kind of method of the non-firm point set registration retaining partial structurtes | |
| CN115457056A (en) | Skeleton image segmentation method, device, equipment and storage medium | |
| CN108986020A (en) | A kind of three-dimension curved surface approximate expansion at plane adaptive approach | |
| CN117132737B (en) | Three-dimensional building model construction method, system and equipment | |
| CN102982552A (en) | Surface registration method based on ricci flow | |
| Zhu et al. | Triangulation of well-defined points as a constraint for reliable image matching | |
| CN110176021A (en) | In conjunction with the level set image segmentation method and system of the conspicuousness information of gamma correction | |
| CN114037719B (en) | Bone region determination method and device, electronic equipment and storage medium | |
| CN115311430A (en) | Training method and system of human body reconstruction model and computer equipment | |
| CN111898819B (en) | Space grid dividing method and device | |
| CN103646383A (en) | Contour non-local mean value based filtering method | |
| CN113887496A (en) | Human body posture expression method and device | |
| CN113887500A (en) | Human body semantic recognition method and device | |
| Han et al. | Adaptive image inpainting algorithm based on sample block by kriging pretreatment and facet model | |
| Lee et al. | Segmentation of medical images using a geometric deformable model and its visualization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150909 |
|
| RJ01 | Rejection of invention patent application after publication |