CN209403650U - It is a kind of for obtaining the tight of human body surface data - Google Patents
It is a kind of for obtaining the tight of human body surface data Download PDFInfo
- Publication number
- CN209403650U CN209403650U CN201822124482.8U CN201822124482U CN209403650U CN 209403650 U CN209403650 U CN 209403650U CN 201822124482 U CN201822124482 U CN 201822124482U CN 209403650 U CN209403650 U CN 209403650U
- Authority
- CN
- China
- Prior art keywords
- tight
- code tag
- human body
- point
- body surface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000001737 promoting effect Effects 0.000 abstract description 3
- 238000012795 verification Methods 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 11
- 239000011159 matrix material Substances 0.000 description 10
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The utility model discloses a kind of for obtaining the tight of human body surface data, the regularly arranged code tag having for identification on the tight, the code tag includes the multiple encoded points being uniformly arranged in the circumferential direction, the encoded point is black or white, and the arrangement mode of the black and white encoded point in each code tag is unique.The advantages of tight provided by the utility model for being used to obtain human body surface data, is: by tight surface layout code tag, convenient for carrying out recognition and verification to image, the clothes that user only needs to wear customization, which take pictures, can be obtained the body surface data of oneself, in online shopping, businessman can obtain the accurate body data of user, it is convenient for custom made clothing, it is easy to operate, convenient for promoting.
Description
Technical field
The utility model relates to human body surface data acquisition technology fields, more particularly to one kind is for obtaining human body surface number
According to tight.
Background technique
Present more and more people are done shopping by network, but in online shopping or customization clothes, are often existed uncertain
The whether suitable problem of suit length, the data that user oneself provides may not meet the requirement of businessman, cause to exist when shopping
Certain obstacle.
Utility model content
The technical problem to be solved by the utility model is to provide a kind of for obtaining the tight of human body surface data,
User, which only passes through, wears the image that tight obtains whole body different angle, and businessman is obtained with the surface data of user.
The utility model is to solve above-mentioned technical problem by the following technical programs:
It is a kind of for obtaining the tight of human body surface data, the regularly arranged coding having for identification on the tight
Label, the code tag include the multiple encoded points being uniformly arranged in the circumferential direction, and the encoded point is black or white, Mei Gebian
The arrangement mode of black and white encoded point in code label is different.
Preferably, background of the code tag on tight is white, at least one in encoded point is black.
Preferably, the center location of the code tag is provided with an anchor point, and the anchor point area is greater than encoded point
Area.
Preferably, there is round blank to form annulus among anchor point.
Preferably, the anchor point and encoded point and code tag appearance profile are circle.
The advantages of tight provided by the utility model for being used to obtain human body surface data, is: by tight table
Code tag is arranged in face, and convenient for carrying out recognition and verification to image, the clothes that user only needs to wear customization, which is taken pictures, to be obtained
Derived from oneself body surface data, in online shopping, businessman can obtain the accurate body data of user, be convenient for custom made clothing,
It is easy to operate, convenient for promoting.
Detailed description of the invention
Fig. 1 is the schematic diagram of tight provided by the embodiments of the present invention；
Fig. 2 is the schematic diagram of code tag provided by the embodiments of the present invention.
Specific embodiment
For the purpose of this utility model, technical solution and advantage is more clearly understood, below in conjunction with specific embodiment, and
Referring to attached drawing, the utility model is described in further detail.
With reference to Fig. 1, a kind of for obtaining the tight of human body surface data, the tight 1 is regularly arranged to be had for knowing
Other code tag 2, the code tag 2 include the multiple encoded points 21 being uniformly arranged in the circumferential direction, and the encoded point 21 is arranged
For black or white, the permutation and combination method of the black and white encoded point 21 on each code tag 2 is unique.
Using tight 1 provided in this embodiment obtain human body surface data method the following steps are included:
Step 1: user wears the tight 1 for being covered with code tag 2, obtains the figure of different perspectives when user wears the clothes
Picture；
In conjunction with Fig. 2, for the ease of identification, background of the code tag 2 on tight 1 is set as white, thus in image
In be only capable of seeing that black encoded point 21, each code tag 2 at least have a black encoded point 21.
For the ease of determining the position of code tag 2, the center location for the circumference that encoded point 21 surrounds is additionally provided with centainly
The area in site 22, the anchor point 22 is greater than 21 area of encoded point, in order to further increase positioning accuracy, in anchor point 22
The intermediate anchor point 22 that circular ring shape is also formed with a round blank.
The general image that different angle is obtained by camera or mobile phone photograph can allow user to change angle and carry out when taking pictures
Shooting can also be shot simultaneously in different angle；Due to that can have angle tilt, the pattern meeting of code tag 2 when shooting
It is distorted, for the ease of processing, the outer profile of anchor point 22 and encoded point 21 and code tag 2 selects circular pattern, circle
Shape can be distorted when visual angle tilts as ellipse, carry out only needing to consider 5 parameters when Mathematical treatment i.e. to can define description ellipse, and
It can easily realize that ellipse fitting is calculated by least square method.
Step 2: image is pre-processed；
Processing method includes that unused colour information, algorithm of histogram equalization enhancing image effect are removed in gray processing processing
Fruit, median filtering algorithm remove the cluster of the prominent pattern edge profile of the pattern of useless noise, binary conversion treatment, region-growing method
Thought realizes image segmentation and merging, finally uses and empties internal algorithm extraction profile.
Above-mentioned processing method is the method having disclosed in the prior art, and those skilled in the art select to have as needed
The method of body, details are not described herein again.
Step 3: rejecting unavailable code tag 2；
Reject the method for unavailable code tag 2 the following steps are included:
Ellipse fitting:
In image physical coordinates system, there are following relationships for ellipse:
Zero is taken to obtain each parameter derivation in above formula:
In combination with constraint condition A+C=1, obtain:
Wherein, ucenter,vcenter, a, b, θ is respectively the elliptical centre coordinate fitted, long axis, short axle and inclination angle；
Circularity monitoring:
Circularity characterizes function is defined as:
L=2 π b+4 (a-b)
Area=π × a × b
Wherein, L indicates that perimeter, Area indicate the area of a circle, when cllipse is greater than preset threshold value, rejects the coding mark
Label 2；
Residual error verifying:
After carrying out ellipse fitting to code tag 2, for any point (x, y) on elliptical edge, meet following relationship:
Xx=(x-ucenter)cosθ+(y-vcenter)sinθ*(x-ucenter)cosθ+(y-vcenter)sinθ
Yy=(x-ucenter)sinθ+(y-vcenter)cosθ*(x-ucenter)sinθ+(y-vcenter)cosθ
Residual error between the actual observation value and regression estimates value of point (x, y) on ellipse are as follows:
Num is the pixel quantity on elliptical edge profile, and the residual sum for needing to calculate all marginal points corresponding obtains
Respective regression criterion；Introduce threshold residual value fError(max), if fError> fError(max), then the code tag 2 is rejected.
Step 4: identification available code label 2 judges whether image meets condition；
It is unit circle, affine transformation formula by 2 affine transformation of code tag of ellipse are as follows:
Wherein, X is the point coordinate before affine transformation on ellipse, X0It is elliptical center point coordinate, a, b are elliptical respectively
Long axis and minor axis length, α are elliptical rotation angle, and X " is the coordinate of the point after affine transformation on unit circle；
For the code tag 2 with N number of encoded point 21, on the code tag 2 to become unit circle by affine transformation
Any black encoded point 21 be starting point, according to clockwise or counterclockwise sequence, using 22 center of anchor point as the center of circle everyEncoded point 21 is read as bit, if the average gray of all pixels of the encoded point 21 of this
Value is greater than threshold value, i.e. encoded point 21 is black, then is encoded to 1, is encoded to 0 if encoded point 21 is white, reads one week and obtain
The binary numeral of the code tag 2；Then using former starting point clockwise or counterclockwise angle delta θ as new starting
Point re-reads the binary numeral of the code tag 2, repeats n times, obtains N number of two with each encoded point 21 for starting point
System number string, using wherein the smallest binary numeral as the decoded value of the code tag 2.It can according to need when judging
Binary numeral is changed to the decimal system.
It is verified by identification, therefore, to assure that at least there are 8 identical efficient coding labels 2 in the image of adjacent angular,
Otherwise it is assumed that image is unsatisfactory for requiring, the image of the angle need to be provided again.
Step 5: the 22 center two-dimensional pixel coordinate of anchor point of calculation code label 2；
The central point pixel two-dimensional coordinate of code tag 2 is extracted using intensity-weighted centroid method, and its essence is calculate original image
As the first moment of circular hole, obtain:
Wherein, (x0,y0) it is 22 centre coordinate of anchor point, f (x, y) is characterized the gray scale of pixel (x, y) in a region
Value, after the binaryzation gray proces of step 2, f (x, y)=255, m, n is the row of 22 area pixel of anchor point of code tag 2
Several and columns, P are characterized the quantity of region all pixels point, P=i × j.
Step 6: 2 anchor point of code tag, 22 center pixel two-dimensional coordinate being converted into human body and is corresponded in world coordinate system
Three-dimensional coordinate；
For the image of satisfactory adjacent view, the positioning of the code tag 2 according to its constraint condition that matches each other
22 center two-dimensional coordinates of point are respectively p1、p2, two-dimensional coordinate is respectively as follows:
Then according to Epipolar geometry principle, every group of corresponding points meet
Basis matrix F is calculated using 8 algorithms of normalization,
By p1And p2(1) formula of substitution obtains:
Above formula is unfolded, obtains:
u2u1f11+u2v1f12+u2f13+v2u1f21+v2v1f22+v2f23+u1f31+v1f32+f33=0 (3)
At this point, stating constraint equation if there is n closes glyph, then (3) formula can be rewritten as follows:
When n takes at 8, with least square method, (4) formula is solved, in order to avoid there is extra useless solution, increases constraint item
PartI.e. the derivation of equation (4) is minimum, while meeting F normalization, and basis matrix F is calculated.
Using at least continuous 7 row of human body surface image zooming-out × 7 column 2 array of code tag as calibrating template, coding
Plan range between label 2 is when making tight 1 it has been determined that in the corresponding region of calibrating template and camera image plane
When substantially parallel, ignore Z axis error, obtains template angle point 3D coordinate, found out, led in the 2D coordinate step 5 of corresponding angle point
At least 5 images crossed referring to continuous adjacent calculate camera internal reference matrix As because camera imaging Epipolar geometry constraint condition at
It is vertical:
The linear algorithm of camera internal reference matrix A is as follows:
By 2D point coordinate (xi,yi) and corresponding 3D point coordinate (Xi,Yi,Zi) above formula is substituted into respectively, over-determined systems are solved,
It obtains
Camera internal reference matrix A can be obtained after decomposition；
In addition, internal reference matrix meets following relationship:
E=ATFA
Essential matrix E is obtained by calculation, unusual decomposition is carried out to essential matrix E:
E=UDVT=U (D1D2)VT=(UD1UT)(UD2VT)
Wherein,
It obtains,
[t]x=UD1UT
R=UD2VT
Wherein, t and R is camera external parameter matrix；
Calculate projection matrix M:
M2=A × [R t]
Wherein R and t is Camera extrinsic；Projection relation of the two-dimensional image vegetarian refreshments coordinate p to three-dimensional space point coordinate P are as follows:
Expansion obtains:
It arranges and is obtained about X, Y, the linear equation of Z by expansion:
Three-dimensional space can be found out by least square methodThe three-dimensional coordinate of point.
Step 7: calculating human body surface data using three-dimensional coordinate.
1. for the length dimension of non-close: the corresponding body position three dimensional space coordinate of direct location coding label 2 leads to
Euclidean distance solution is crossed,
Wherein Pi=(Xi,Yi,Zi) and Pj=(Xj,Yj,Zj) be two tested points of human body surface three-dimensional space three-dimensional space
Coordinate points；
2.: for closed curve length dimension:
1) choosing the code tag 2 that n are substantially on same cross section is initial code tag set, utilizes minimum two
Multiplication fits a human body Space Cross Section, fit equation are as follows:
Ax+By+Cz+D=0
Human body cross section be not it is parallel with Z axis, so C ≠ 0；Therefore equation deforms are as follows:
Z=a0x+a1y+a2
(xi,yi,zi) i=0,1,2 ..., n-1
Wherein, n >=5；Parameter a is obtained by calculation0,a1,a2, fit human body cross section expression formula；
2) find and close on the code tag 2 in section, the 22 centre coordinate p=(x, y, z) of anchor point of the code tag 2 with cut
The vertical range in face is less than preset threshold value or inclination angle is less than preset threshold value, i.e.,
Dist (p, cross section)≤T (or θ)
Section edges curve matching code tag set can be added in the code tag 2, until the number of code tag 2 in set
Amount fitting human body cross-sectional edge two-dimensional curve enough；It is obtained on the curve using cubic spline interpolation calculation method the Fitting Calculation
To the cross-sectional edge length of curve；Calculative curve is divided into n parts, is quasi- not higher than multinomial three times on every part
Close function
S(xj)=yj
Wherein, (xj,yj), j=1,2 ..., n are the coordinate value put on curve；
And every part of fitting function is all satisfied Second Order Continuous derivative constraints condition, by calculating every part of S (xj) value, add up institute
There are n partsBoth girth is obtained.
When in use, businessman only needs to provide tight disclosed in the present embodiment for client, and client can voluntarily clap
It according to human body image is obtained, and is uploaded to given server and is calculated, to obtain accurate human body surface data, businessman can be with
It is the customized clothes of user according to data, it might even be possible to directly pass tight to user fastly, greatly facilitate customized clothes
Online shopping business, and the manufacturing cost of tight itself is lower, will not additionally increase businessman's cost, convenient for promoting the use of.
Claims (5)
1. a kind of for obtaining the tight of human body surface data, it is characterised in that: regularly arranged on the tight to be used for
The code tag of identification, the code tag include the multiple encoded points being uniformly arranged in the circumferential direction, the encoded point be black or
The arrangement mode of white, the black and white encoded point in each code tag is unique.
2. according to claim 1 a kind of for obtaining the tight of human body surface data, it is characterised in that: the coding
For background of the label on tight to be white, at least one in encoded point is black.
3. according to claim 1 a kind of for obtaining the tight of human body surface data, it is characterised in that: the coding
The center location of label is provided with an anchor point, and the anchor point area is greater than encoded point area.
4. according to claim 3 a kind of for obtaining the tight of human body surface data, it is characterised in that: in anchor point
Between there is round blank to form annulus.
5. according to claim 3 a kind of for obtaining the tight of human body surface data, it is characterised in that: the positioning
Point and encoded point and code tag appearance profile are circle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201822124482.8U CN209403650U (en) | 2018-12-18 | 2018-12-18 | It is a kind of for obtaining the tight of human body surface data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201822124482.8U CN209403650U (en) | 2018-12-18 | 2018-12-18 | It is a kind of for obtaining the tight of human body surface data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN209403650U true CN209403650U (en) | 2019-09-20 |
Family
ID=67938688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201822124482.8U Active CN209403650U (en) | 2018-12-18 | 2018-12-18 | It is a kind of for obtaining the tight of human body surface data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN209403650U (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111144988A (en) * | 2019-12-27 | 2020-05-12 | 中国石油大学(华东) | Body measuring clothes and body size measuring method thereof |
| CN111721197A (en) * | 2020-05-14 | 2020-09-29 | 南京工程学院 | Body model measuring device and method based on binocular stereo |
| CN112205698A (en) * | 2020-09-11 | 2021-01-12 | 集美大学 | Human body three-dimensional information acquisition method and device |
| CN112504188A (en) * | 2020-11-19 | 2021-03-16 | 东风汽车集团有限公司 | Method for generating human body model and device for measuring human body size |
-
2018
- 2018-12-18 CN CN201822124482.8U patent/CN209403650U/en active Active
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111144988A (en) * | 2019-12-27 | 2020-05-12 | 中国石油大学(华东) | Body measuring clothes and body size measuring method thereof |
| CN111721197A (en) * | 2020-05-14 | 2020-09-29 | 南京工程学院 | Body model measuring device and method based on binocular stereo |
| CN112205698A (en) * | 2020-09-11 | 2021-01-12 | 集美大学 | Human body three-dimensional information acquisition method and device |
| CN112205698B (en) * | 2020-09-11 | 2022-09-20 | 集美大学 | Human body three-dimensional information acquisition method and device |
| CN112504188A (en) * | 2020-11-19 | 2021-03-16 | 东风汽车集团有限公司 | Method for generating human body model and device for measuring human body size |
| CN112504188B (en) * | 2020-11-19 | 2021-11-23 | 东风汽车集团有限公司 | Method for generating human body model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN209403650U (en) | It is a kind of for obtaining the tight of human body surface data | |
| US11830141B2 (en) | Systems and methods for 3D facial modeling | |
| CN104915949B (en) | A kind of image matching method of combination point feature and line feature | |
| CN103210421B (en) | Article detection device and object detecting method | |
| Yamany et al. | Surface signatures: an orientation independent free-form surface representation scheme for the purpose of objects registration and matching | |
| KR20220066366A (en) | Predictive individual 3D body model | |
| CN104951940B (en) | A kind of mobile payment verification method based on personal recognition | |
| US11775781B2 (en) | Product verification in a messaging system | |
| CN106203342A (en) | Target identification method based on multi-angle local feature coupling | |
| CN106127181A (en) | One is virtual tries manicure method, system on | |
| CN109635614A (en) | A kind of contactless humanbody collecting method | |
| CN105160305B (en) | A kind of multi-modal Feature fusion of finger | |
| CN108305291B (en) | Monocular vision positioning and attitude determination method utilizing wall advertisement containing positioning two-dimensional code | |
| CN106767502A (en) | A kind of circle codification index point with start information | |
| US20210089763A1 (en) | Animal identification based on unique nose patterns | |
| CN104778491A (en) | Image code applied to information processing, as well as device and method for generating and analyzing image code | |
| CN111008935B (en) | Face image enhancement method, device, system and storage medium | |
| CN105138974B (en) | A kind of multi-modal Feature fusion of finger based on Gabor coding | |
| CN108304831B (en) | Method and device for monitoring wearing of safety helmet of worker | |
| CN109493384A (en) | Camera position and orientation estimation method, system, equipment and storage medium | |
| CN108805915A (en) | A kind of close-range image provincial characteristics matching process of anti-visual angle change | |
| US11663849B1 (en) | Transform pyramiding for fingerprint matching system and method | |
| CN106997366A (en) | Database construction method, augmented reality fusion method for tracing and terminal device | |
| CN107729904A (en) | A kind of face pore matching process based on the limitation of 3 D deformation face | |
| CN108564020A (en) | Micro- gesture identification method based on panorama 3D rendering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of utility model: A tight fitting garment for obtaining surface data of the human body Effective date of registration: 20231020 Granted publication date: 20190920 Pledgee: Shenzhen Rural Commercial Bank Co.,Ltd. Henggang Sub branch Pledgor: SHENZHEN AITECH Co.,Ltd. Registration number: Y2023980062018 |