CN110074788A - A kind of body data acquisition methods and device based on machine learning - Google Patents
A kind of body data acquisition methods and device based on machine learning Download PDFInfo
- Publication number
- CN110074788A CN110074788A CN201910316421.8A CN201910316421A CN110074788A CN 110074788 A CN110074788 A CN 110074788A CN 201910316421 A CN201910316421 A CN 201910316421A CN 110074788 A CN110074788 A CN 110074788A
- Authority
- CN
- China
- Prior art keywords
- human body
- model
- gauger
- machine learning
- data acquisition
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1075—Measuring physical dimensions, e.g. size of the entire body or parts thereof for measuring dimensions by non-invasive methods, e.g. for determining thickness of tissue layer
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1077—Measuring of profiles
- A61B5/1078—Measuring of profiles by moulding
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/44—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing persons
- G01G19/50—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups for weighing persons having additional measuring devices, e.g. for height
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Dentistry (AREA)
- Computer Graphics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of body data acquisition methods and device based on machine learning, wherein method includes: to obtain gauger's image and weight；By gauger's image and weight and human body 3D models coupling, output has the gauger's human body 3D model and body data information of textures.The present invention also provides a kind of body data acquisition device based on machine learning, including host and doctor's type scale；The host includes display, camera and station；The station includes identity recognition device, controller and printer, and the display, camera, identity recognition device and printer are electrically connected with the controller respectively, and the scale and the controller communicate to connect.The present invention does not do particular requirement to the clothing of people, and the body data of acquisition is not influenced by clothes, it is ensured that people precisely speculates human body posture and posture in the case where wearing ordinary clothing, the significant increase convenience of amount body.
Description
Technical field
The invention belongs to somatic data field of measuring technique, and in particular to a kind of body data acquisition based on machine learning
Method and apparatus.
Background technique
Tradition obtains human somatotype data by way of manual measurement, it is desirable that measurement people allows for contact and is measured
People cannot achieve long-range measurement, and there are a variety of errors possibility for this traditional measurement method.With the continuous hair of 3D technology
Exhibition, human body 3D scanner are also completed to develop, but use body scanning technique, it is desirable that human body is sufficiently exposed, obtains the body of people
Model, and high equipment cost, volume are big, still cannot achieve long-range measurement, and since its high price is also difficult extensively
It is general to spread in daily life.Existing somatometric instrument relies on depth device, and Function detection is not perfect, due to clothes etc.
Certain deviation can also be had by blocking.
In current area, the method for human body three-dimensional modeling that there are two main classes: the first kind is to have one group of joint, such as neck in mind
Portion, such as ancon, obtain a simple skeleton model figure of human body, this partial data does not include the body scale of analysis object
The information of information, analysis is very limited.Second class is by 3D scanning technique, using multiple groups camera, to shoot multiple side
Formula, split go out a 3D model, and the model that this method obtains can not rule out clothes, influence of the hair style to body.At present about
The information of the method analysis of human body three-dimensional modeling is very limited, can not rule out the influence of clothes, hair style to body model, obtains
Model application field is very limited.The textures that depth camera multi-angle photographic method the is taken model that then split obtains, does not have
There are body scale data, cannot be perceived for 3D and basis is provided.
Summary of the invention
The present invention provides a kind of body data acquisition methods and device based on machine learning, overcome body in the prior art
The problems such as result of volume data detection is inaccurate, and apparatus structure is complicated, inconvenient for use.
For achieving the above object, the present invention is achieved by the following scheme:
A kind of body data acquisition methods based on machine learning, comprising the following steps:
Obtain gauger's image and weight；
By gauger's image and weight and human body 3D models coupling, gauger human body 3D model of the output with textures with
And body data information.
Further, the generation method of the human body 3D model are as follows:
Random selected training crowd, shooting obtain training picture；
The key position of human body on training picture is divided into meaning of one's words region；
Key point on key position is manually marked, while the artificial natural direction for determining key position, is obtained
Training data；
Training data and standardized human body's model template are combined, training obtains human body 3D model.
Further, the key position of the human body are as follows: left side head, right side head, neck, left upper arm, lower-left arm, the right side
Lower arm, right upper arm, trunk, left hand, the right hand, left thigh, right thigh, left leg, right leg, left foot, right crus of diaphragm, wherein upper arm, under
Arm, thigh, shank are made of tow sides two parts.
Further, the key point manually marked is the key point on the edge of body and the key position of human body.
Further, standardized human body's model template are as follows:
Wherein, eachThe vertex of corresponding 3 dimension space manikins, m are standardized human body's model template
The sum on vertex, X represent the set on standardized human body's model template vertex, and standardized human body's model template is one by triangle
The 3D grid of the standard of shape composition, number of triangles is 5500~6500.
Further, gauger's image is the change in topology and DUAL PROBLEMS OF VECTOR MAPPING of human body 3D model, biaxial stress structure ψ, from
3D coordinate is to the space 2DToψ: mapping relations, u are representedj: 2D is empty
Between coordinate, xj: human body 3D model coordinate represents a vertex in 3D mesh, obtains gauger's human body 3D model and patch
The UV coordinate of figure.
Further, gauger's image is as textures, according to the UV coordinate of textures, for gauger's human body 3D model
Color textures, output have gauger's human body 3D model of textures.
A kind of body data acquisition device based on machine learning, it includes host and doctor's type scale；The host includes aobvious
Show device, camera and station；The station includes identity recognition device, controller and printer, the display, camera shooting
Head, identity recognition device and printer are electrically connected with the controller respectively, and the scale and the controller communicate to connect.
Further, the host top is provided with the display, and the camera is set to the middle part of the host,
The station is set to the lower part of the host；The identification module includes card reader and scanner.
Further, the display is touching display screen or projector.
The advantages of the present invention are: the body data acquisition methods provided by the invention based on machine learning and
Device can exclude the influence of loose clothing, hair style, accomplish the body approached in the not habited situation of human body to the full extent
Human body is carried out accurate profile separation by form under complicated background, while by the present invention in that with multiple deep neural networks,
Human testing is realized, human body semantic segmentation is carried out, from 2D picture to the mapping reconstruction of human body 3D model, is obtained with patch
The gauger's human body 3D model and body data information of figure.The present invention does not need depth of field camera or multiple groups camera, just
Getable human body 3D model corresponds to the true form of human body, provides for various industries, such as clothes, health etc. wide
Application scenarios.
The present invention provides analyze Whole Body photo by deep neural network to obtain accurate human 3d model
Common photo can be used in method, the present invention, is rapidly Human Modeling, can be in various complexity using deep neural network
In scene, human body is restored with very high precision.The principle of this method can be widely used in the field of other 2D to 3D conversion,
Thinner coordinate cutting off field, carries out face modeling, human ear modeling, the modeling of people's foot.
Inventive arrangement provides the modes of two kinds of authentications, have both facilitated acquisition data, while being also conducive to protect hidden
It is private；For device by using the body data acquisition methods based on machine learning, Function detection is more perfect, in conjunction with the number such as weight
According to providing the precise information for the body datas such as Human Height, shoulder breadth, brachium and leg be long, the suitable clothes of gauger can be provided
Model；The data of acquisition can carry out real time print, convenient and efficient.The apparatus structure is simple, easily operated, and cost is relatively low,
Convenient for promoting the use of on a large scale, it is widely portable to body-building group, body-building mechanism, custom made clothing mechanism etc..
Detailed description of the invention
Fig. 1 is the flow chart of the body data acquisition methods based on machine learning；
Fig. 2 is the schematic diagram of human body main portions label；Wherein, a is original image, and b is artificial mark head and trunk
Picture；
Fig. 3 is using the image of people as input, the schematic diagram of gauger human body 3D model of the output with textures.
Fig. 4 is the structural schematic diagram of the body data acquisition device based on machine learning；
Fig. 5 is the side view of the body data acquisition device host based on machine learning；
Wherein, 1 is host, and 11 be display, and 12 be camera, and 13 be station, and 131 be printer, and 132 be card reading
Device, 133 be scanner, and 2 be doctor's type scale.
Specific embodiment
Technical solution of the present invention is further described With reference to embodiment.
Embodiment 1
A kind of body data acquisition methods based on machine learning are present embodiments provided, the present invention utilizes training data
Labeling method Fast Labeling, carry out the division of the human body meaning of one's words, can complex background, different distance scene under, precisely rebuild
The algorithm model of body provides body data information.Fig. 1 is the flow chart of the body data acquisition methods based on machine learning,
This method comprises the following steps:
(1), gauger's image and weight are obtained.
Specifically, using the image of monocular cam shooting gauger, and obtain gauger's weight.
(2), by gauger's image and weight and human body 3D models coupling, output has gauger's human body 3D model of textures
And body data information.
Wherein, the generation method of human body 3D model is as follows:
A, random selected training crowd, shooting obtain training picture.
Specifically, random selected training crowd, carries out taking pictures under various scenes to it, the image that shooting is obtained is made
For training picture.
B, the key position of human body on training picture is divided into meaning of one's words region.
Specifically, the key position of human body on training picture is divided into 24 meaning of one's words regions, key position includes a left side
Side head, right side head, neck, left upper arm, right upper arm, lower-left arm, bottom right arm, trunk, left hand, the right hand, left thigh, the right side are big
Leg, left leg, right leg, left foot, right crus of diaphragm；Wherein, upper arm, lower arm, thigh, shank are made of tow sides two parts.
C, the key point on key position is manually marked, while the artificial natural direction for determining key position, is obtained
To training data.
Specifically, as shown in Fig. 2, on training picture, to the edge (not being the edge of clothes) of artificial mark body
It selects key point to be labeled on the key position of human body, while according to the joint position in key position, determining position
Natural direction, such as left upper arm and human body separate angle, and accumulation obtains a large amount of training data.
D, training data and standardized human body's model template are combined, training obtains human body 3D model.
Wherein, standardized human body's model template are as follows:
Wherein, eachThe vertex of corresponding 3 dimension space manikins, m are standardized human body's model template
The sum on vertex, X represent the set on standardized human body's model template vertex；Standardized human body's model template is one by triangle
The 3D grid of the standard of shape composition, wherein number of triangles is 6000.
Gauger's image is combined with the human body 3D model of generation, can export gauger's human body 3D model with textures
And body data information, it is specific as follows:
What is inputted when defining machine learning model is the image of gauger, and the feature captured from image may be implemented one group
The point-to-point mapping of 2D and 3D is completed in mapping, from this group mapping, available gauger's human body 3D model, i.e. depth model,
And the UV coordinate of textures.
The image of the gauger obtained in input step (5), picture is rgb format, can be the human figure of free position
Piece；Gauger's human body is the change in topology and DUAL PROBLEMS OF VECTOR MAPPING of human body 3D model.Biaxial stress structure ψ, from 3D coordinate to the space 2DToWherein, mapping relations, u ψ: are representedj: from object to be measured human body
The 2D space coordinate obtained on picture, xj: human body 3D model coordinate represents a vertex in 3Dmesh.The manikin of 3D
Template be by many triangulars at, the stretching of triangle, rotation, the variation for being displaced corresponding human body, extract one group of topology to
Amount mapping, represents these variations.
It is the 3D model of gauger's human body according to the UV coordinate of textures directly using gauger's human body picture as textures
Color textures, output have gauger's human body 3D model of textures, see Fig. 3.This step is to carry out textures, UV to the 3D model of completion
It is the coordinate of textures, it is thus necessary to determine that the corresponding relationship of each pixel and 3D on photo, U and V can be trained individually, it is therefore intended that
Reduce the complexity calculated.
Based on training data, the foundation of model above relies on a convolutional neural networks (CNN) to complete.Of the invention
Purpose is some region each pixel-map on picture to target template, certainly also includes the picture for being not belonging to human body
Element, mapping can generate an empty output, can be ignored.This is that typical returns calculates.
The human body 3D model generated in the present invention can be recycled, as long as input measurement person's picture, in conjunction with external data
Weight is analyzed according to machine vision, the human body size under various varying environments is detected, with the clothes model in database
Match, export the clothes model for being suitble to gauger, is a kind of mode that body data most rapidly, quick, inexpensive obtains.
Fig. 4-Fig. 5 is please referred to, the embodiments of the present invention also provide the body data acquisition device based on machine learning, packets
Host 1 and doctor's type scale 2 are included, the doctor's type scale 2 is separate structure with host 1.
The host 1 includes display 11, camera 12 and station 13.The display 11 is touching display screen,
The display 11 is set to the top of the host 1, and the camera 12 is set to the centre of the host 1, the operation
Platform 13 is set to the lower part of the host 1.The station 13 includes identity recognition device, controller and printer 131.It is described
Controller is set to inside the station 13, and the controller is filled with the display 11, camera 12, identification respectively
Set and be electrically connected with printer 131, the scale 2 is communicated to connect with the controller, the scale 2 by bluetooth or
WIFI is connect with the doctor's type scale 2.The identity recognition device includes card reader 132 and scanner 133, the card reader 132
Set on the centre of the station 13, identification China second-generation identity card is supported；The scanner 133 is set to the station 13
Right side can obtain the identity information of gauger by scanning the two-dimensional code.The left side of the station 13 is equipped with printer 131,
For printing the sign examining report generated.
When using present invention selection clothes model, China second-generation identity card can be used first and be placed in the card reader 132
Upper carry out identification, if identity card inconvenient to use, especially group personnel need to select clothes model, such as company person
Work or school student can encode personnel in inside, two dimensional code are made, is scanned the two-dimensional code with the scanner 133
Identification is carried out, in addition identity information can also be inputted by touching display screen and directly be logged in.Identification or
After directly logging in, the controller can obtain personally identifiable information.Weight number is obtained on the doctor's type scale 2 of gauger station
According to weight data is transferred to controller by bluetooth or WIFI by the doctor's type scale 2, if measurement object understands the true of oneself
Entity weight can input weight numerical value by touching display screen direct labor；Gauger is directed at the camera 12, at this time institute
The image that the camera 12 captures can be shown by stating touching display screen, and gauger is according to the prompt of the touching display screen
With require to adjust oneself posture, after adjusting, the camera 12 is taken pictures, and is shot gauger one respectively and is opened positive photograph
It is shone with a side.The controller handles the image for obtaining gauger and weight information, the specifically used prior art
In analyzed by deep neural network the method that Whole Body photo obtains accurate human 3d model obtain height, shoulder breadth and
The body datas information such as brachium, the controller is according to the clothes to match in database in body data information selection control
Model, is then transferred to the printer 131, and printing obtains the sign examining report with personally identifiable information, including measurement
The body data information (including height, shoulder breadth and brachium etc.) of person, and suitable clothes model.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than is limited；Although referring to aforementioned reality
Applying example, invention is explained in detail, for those of ordinary skill in the art, still can be to aforementioned implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these are modified or replace
It changes, the spirit and scope for claimed technical solution of the invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of body data acquisition methods based on machine learning, it is characterised in that: the following steps are included:
Obtain gauger's image and weight；
By gauger's image and weight and human body 3D models coupling, output has the gauger's human body 3D model and body of textures
Data information.
2. the body data acquisition methods according to claim 1 based on machine learning, it is characterised in that: the human body 3D
The generation method of model are as follows:
Random selected training crowd, shooting obtain training picture；
The key position of human body on training picture is divided into meaning of one's words region；
Key point on key position is manually marked, while the artificial natural direction for determining key position, is trained
Data；
Training data and standardized human body's model template are combined, training obtains human body 3D model.
3. the body data acquisition methods according to claim 2 based on machine learning, it is characterised in that: the human body
Key position are as follows: left side head, right side head, neck, left upper arm, lower-left arm, bottom right arm, right upper arm, trunk, left hand, the right hand,
Left thigh, right thigh, left leg, right leg, left foot, right crus of diaphragm, wherein upper arm, lower arm, thigh, shank are all by tow sides
Two parts are constituted.
4. the body data acquisition methods according to claim 2 based on machine learning, it is characterised in that: the artificial mark
The key point of note is the key point on the edge of body and the key position of human body.
5. the body data acquisition methods according to claim 2 based on machine learning, it is characterised in that: the standard people
Body Model template are as follows:
Wherein, eachThe vertex of corresponding 3 dimension space manikins, m are standardized human body's model template vertex
Sum, X represents the set on standardized human body's model template vertex, and standardized human body's model template is one by triangle sets
At standard 3D grid, number of triangles is 5500~6500.
6. the body data acquisition methods according to claim 2 based on machine learning, it is characterised in that: the gauger
Image is the change in topology and DUAL PROBLEMS OF VECTOR MAPPING of human body 3D model, biaxial stress structure ψ, from 3D coordinate to the space 2DToψ: mapping relations, u are representedj: 2D space coordinate, xj: human body 3D model coordinate, generation
A vertex in table 3D mesh, obtains the UV coordinate of gauger's human body 3D model and textures.
7. the body data acquisition methods according to claim 6 based on machine learning, it is characterised in that: the gauger
Image is as textures, according to the UV coordinate of textures, colours textures for gauger's human body 3D model, output has the gauger of textures
Human body 3D model.
8. a kind of body data acquisition device based on machine learning, it is characterised in that: it includes host and doctor's type scale；The master
Machine includes display, camera and station；The station includes identity recognition device, controller and printer, described aobvious
Show that device, camera, identity recognition device and printer are electrically connected with the controller respectively, the scale and the controller
Communication connection.
9. the body data acquisition device according to claim 8 based on machine learning, it is characterised in that: on the host
Portion is provided with the display, and the camera is set to the middle part of the host, and the station is set to the host
Lower part；The identification module includes card reader and scanner.
10. the body data acquisition device according to claim 8 based on machine learning, it is characterised in that: the display
Device is touching display screen or projector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910316421.8A CN110074788B (en) | 2019-04-18 | 2019-04-18 | Body data acquisition method and device based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910316421.8A CN110074788B (en) | 2019-04-18 | 2019-04-18 | Body data acquisition method and device based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110074788A true CN110074788A (en) | 2019-08-02 |
| CN110074788B CN110074788B (en) | 2020-03-17 |
Family
ID=67415721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910316421.8A Active CN110074788B (en) | 2019-04-18 | 2019-04-18 | Body data acquisition method and device based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110074788B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110411308A (en) * | 2019-08-14 | 2019-11-05 | 浙江德尔达医疗科技有限公司 | A kind of accuracy checking method of customized type 3D printing model |
| CN110782482A (en) * | 2019-10-21 | 2020-02-11 | 深圳市网心科技有限公司 | Motion evaluation method and device, computer equipment and storage medium |
| CN111311732A (en) * | 2020-04-26 | 2020-06-19 | 中国人民解放军国防科技大学 | 3D human body grid obtaining method and device |
| CN112733804A (en) * | 2021-01-29 | 2021-04-30 | 闽江学院 | Camera device for measuring human body parameters |
| CN112819881A (en) * | 2021-01-29 | 2021-05-18 | 福州靠谱云科技有限公司 | Human body measuring method |
| CN113112321A (en) * | 2021-03-10 | 2021-07-13 | 深兰科技（上海）有限公司 | Intelligent energy body method, device, electronic equipment and storage medium |
| CN118078258A (en) * | 2024-03-06 | 2024-05-28 | 广东启悦未来科技股份有限公司 | Human body parameter detection method, device and storage medium thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002259474A (en) * | 2001-03-05 | 2002-09-13 | Oojisu Soken:Kk | Method and device for generating human body model, computer program and recording medium |
| US20160155262A1 (en) * | 2013-09-23 | 2016-06-02 | Beihang University | Method of constructing 3d clothing model based on a single image |
| CN105653742A (en) * | 2014-11-10 | 2016-06-08 | 江苏中佑石油机械科技有限责任公司 | Clothes model building method in three-dimension simulation fitting system |
| CN107545598A (en) * | 2017-07-31 | 2018-01-05 | 深圳市蒜泥科技有限公司 | A kind of human 3d model synthesis and body data acquisition methods |
| CN107705355A (en) * | 2017-09-08 | 2018-02-16 | 郭睿 | A kind of 3D human body modeling methods and device based on plurality of pictures |
| CN107924579A (en) * | 2015-08-14 | 2018-04-17 | 麦特尔有限公司 | The method for generating personalization 3D head models or 3D body models |
-
2019
- 2019-04-18 CN CN201910316421.8A patent/CN110074788B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002259474A (en) * | 2001-03-05 | 2002-09-13 | Oojisu Soken:Kk | Method and device for generating human body model, computer program and recording medium |
| US20160155262A1 (en) * | 2013-09-23 | 2016-06-02 | Beihang University | Method of constructing 3d clothing model based on a single image |
| CN105653742A (en) * | 2014-11-10 | 2016-06-08 | 江苏中佑石油机械科技有限责任公司 | Clothes model building method in three-dimension simulation fitting system |
| CN107924579A (en) * | 2015-08-14 | 2018-04-17 | 麦特尔有限公司 | The method for generating personalization 3D head models or 3D body models |
| CN107545598A (en) * | 2017-07-31 | 2018-01-05 | 深圳市蒜泥科技有限公司 | A kind of human 3d model synthesis and body data acquisition methods |
| CN107705355A (en) * | 2017-09-08 | 2018-02-16 | 郭睿 | A kind of 3D human body modeling methods and device based on plurality of pictures |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110411308A (en) * | 2019-08-14 | 2019-11-05 | 浙江德尔达医疗科技有限公司 | A kind of accuracy checking method of customized type 3D printing model |
| CN110411308B (en) * | 2019-08-14 | 2021-08-24 | 浙江德尔达医疗科技有限公司 | Precision detection method for customized 3D printing model |
| CN110782482A (en) * | 2019-10-21 | 2020-02-11 | 深圳市网心科技有限公司 | Motion evaluation method and device, computer equipment and storage medium |
| CN111311732A (en) * | 2020-04-26 | 2020-06-19 | 中国人民解放军国防科技大学 | 3D human body grid obtaining method and device |
| CN112733804A (en) * | 2021-01-29 | 2021-04-30 | 闽江学院 | Camera device for measuring human body parameters |
| CN112819881A (en) * | 2021-01-29 | 2021-05-18 | 福州靠谱云科技有限公司 | Human body measuring method |
| CN112819881B (en) * | 2021-01-29 | 2023-10-31 | 福州靠谱云科技有限公司 | Human body measuring method |
| CN113112321A (en) * | 2021-03-10 | 2021-07-13 | 深兰科技（上海）有限公司 | Intelligent energy body method, device, electronic equipment and storage medium |
| CN118078258A (en) * | 2024-03-06 | 2024-05-28 | 广东启悦未来科技股份有限公司 | Human body parameter detection method, device and storage medium thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110074788B (en) | 2020-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110074788A (en) | A kind of body data acquisition methods and device based on machine learning | |
| US11010896B2 (en) | Methods and systems for generating 3D datasets to train deep learning networks for measurements estimation | |
| Bogo et al. | FAUST: Dataset and evaluation for 3D mesh registration | |
| CN104376594B (en) | Three-dimensional face modeling method and device | |
| Cheng et al. | Parametric modeling of 3D human body shape—A survey | |
| CN105631861B (en) | Restore the method for 3 D human body posture from unmarked monocular image in conjunction with height map | |
| CN107924579A (en) | The method for generating personalization 3D head models or 3D body models | |
| CN104240289B (en) | Three-dimensional digitalization reconstruction method and system based on single camera | |
| CN103356163B (en) | Based on fixation point measuring device and the method thereof of video image and artificial neural network | |
| US20150347833A1 (en) | Noncontact Biometrics with Small Footprint | |
| CN107016721A (en) | The modeling method of human 3d model | |
| US11798299B2 (en) | Methods and systems for generating 3D datasets to train deep learning networks for measurements estimation | |
| CN106920277A (en) | Simulation beauty and shaping effect visualizes the method and system of online scope of freedom carving | |
| CN107041585A (en) | The measuring method of human dimension | |
| CN101882326A (en) | Three-dimensional craniofacial reconstruction method based on overall facial structure shape data of Chinese people | |
| CN109655011B (en) | Method and system for measuring dimension of human body modeling | |
| CN105139007B (en) | Man face characteristic point positioning method and device | |
| CN106780713A (en) | A kind of three-dimensional face modeling method and system based on single width photo | |
| CN112016497A (en) | Single-view Taijiquan action analysis and assessment system based on artificial intelligence | |
| CN109903377A (en) | A kind of three-dimensional face modeling method and system without phase unwrapping | |
| CN108564619A (en) | A kind of sense of reality three-dimensional facial reconstruction method based on two photos | |
| Kaashki et al. | Deep learning-based automated extraction of anthropometric measurements from a single 3-D scan | |
| Pan et al. | Establishing point correspondence of 3d faces via sparse facial deformable model | |
| CN111274944A (en) | Three-dimensional face reconstruction method based on single image | |
| CN110477921B (en) | Height measurement method based on skeleton broken line Ridge regression |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 266000 802, Building 3, Publishing Building, No. 182, Haier Road, Laoshan District, Qingdao, Shandong Patentee after: Shandong Bihai Clothing Co.,Ltd. Address before: 266000 Intersection of Taiguang Road and Yangchun Road, Jiangshan Town, Laixi City, Qingdao, Shandong Province Patentee before: MENGDUO TECHNOLOGY Co.,Ltd. |