CN109409348A - A kind of determination method, apparatus, equipment and the storage medium of user's sign - Google Patents
A kind of determination method, apparatus, equipment and the storage medium of user's sign Download PDFInfo
- Publication number
- CN109409348A CN109409348A CN201811638496.XA CN201811638496A CN109409348A CN 109409348 A CN109409348 A CN 109409348A CN 201811638496 A CN201811638496 A CN 201811638496A CN 109409348 A CN109409348 A CN 109409348A
- Authority
- CN
- China
- Prior art keywords
- user
- dimensional
- practical
- sign
- manikin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Abstract
The invention discloses determination method, apparatus, equipment and the storage mediums of a kind of user's sign.This method comprises: obtaining image to be detected;By image to be detected input three-dimensional prediction model trained in advance, corresponding practical three-dimensional (3 D) manikin is obtained, which is that the standard three-dimensional manikin for corresponding to figure and movement in two dimensional image and two dimensional image is inputted deep neural network training to obtain;According to the parameter of key point each in practical three-dimensional (3 D) manikin, the actual body parameter of user is determined;User's sign is determined according to actual body parameter and standard physical parameter.The present invention passes through three-dimensional prediction model trained in advance, without repeatedly shooting human body image with different view, image to be detected directly can be converted into practical three-dimensional (3 D) manikin, and according to the parameter of each key point in practical three-dimensional (3 D) manikin, can conveniently and efficiently determine user's sign.
Description
Technical field
The present embodiments relate to data analysis technique more particularly to a kind of determination method, apparatus, the equipment of user's sign
And storage medium.
Background technique
With the continuous promotion of people's living standard, people increasingly pay attention to the situation of change of itself sign.Therefore, how
Quickly and easily determine that user's sign becomes particularly critical.
Currently, usually being analyzed by the two-dimentional artis of user in detection human body image user's sign.But due to
Human body image is a two dimensional image, and the two-dimentional artis in two dimensional image lacks depth information, it usually needs user claps
Take the photograph multiple human body images of different perspectives, and when shooting the human body image of different perspectives, be easy to produce and block so as to
The accuracy that family sign is analyzed is affected, to reduce the usage experience of user.
Summary of the invention
In view of this, the present invention provides determination method, apparatus, equipment and the storage medium of a kind of user's sign, realize
It, can convenient and efficient determining user's sign without repeatedly shooting multiple human body images with different view.
In a first aspect, the embodiment of the invention provides a kind of determination methods of user's sign, comprising:
Obtain image to be detected;
By described image to be detected input three-dimensional prediction model trained in advance, corresponding practical 3 D human body mould is obtained
Type, the three-dimensional prediction model are that the standard three-dimensional manikin of figure and movement will be corresponded in two dimensional image and two dimensional image
Input deep neural network training obtains;
According to the parameter of each key point in the practical three-dimensional (3 D) manikin, the actual body parameter of user is determined;
User's sign is determined according to the actual body parameter and standard physical parameter.
Further, user's sign includes at least one of following: user's posture, user actual body degree of enclosing letter
It ceases, the body fat information of user.
Further, the three-dimensional prediction model is that the mark of figure and movement will be corresponded in two dimensional image and two dimensional image
Quasi- three-dimensional (3 D) manikin input deep neural network training obtains, comprising:
User is acquired in the two dimensional image at same visual angle;
According in the two dimensional image figure and movement find corresponding standard three-dimensional manikin;
The two dimensional image and standard three-dimensional manikin input deep neural network are trained, corresponded to
Three-dimensional prediction model.
Further, the parameter according to each key point in the practical three-dimensional (3 D) manikin, determines the reality of user
Body parameter, comprising:
Extract the practical three-dimensional coordinate of each key point in the practical three-dimensional (3 D) manikin;
The actual body parameter of user is determined according to the practical three-dimensional coordinate of each key point;
Further, in the three-dimensional prediction model that the input of described image to be detected is trained in advance, corresponding reality is obtained
After three-dimensional (3 D) manikin, further includes:
Determine the height ratio simulated between height in the practical height obtained in advance and the practical three-dimensional (3 D) manikin;
According to simulated body degree of the enclosing letter in the height ratio, the practical height and the practical three-dimensional (3 D) manikin
Breath, determines actual body degree of the enclosing information of user.
Further, the method, further includes:
The body fat information of user is determined according to the actual weight and actual body degree of the enclosing information that obtain in advance.
Further, the method, further includes:
User's body health degree is determined according to user's body standard sign of seeking peace.
Further, the actual body parameter includes at least one of following: the practical relative position between each key point
With practical relative angle.
Second aspect, the embodiment of the invention also provides a kind of determination devices of user's sign, comprising:
First obtains module, for obtaining image to be detected;
First determining module is corresponded to for the three-dimensional prediction model that the input of described image to be detected is trained in advance
Practical three-dimensional (3 D) manikin, the three-dimensional prediction model be will correspond in two dimensional image and two dimensional image figure and act
The input deep neural network training of standard three-dimensional manikin obtains;
Second determining module determines user's for the parameter according to each key point in the practical three-dimensional (3 D) manikin
Actual body parameter;
Third determining module, for determining user's sign according to the actual body parameter and standard physical parameter.
Further, user's sign includes at least one of following: user's posture, user actual body degree of enclosing letter
It ceases, the body fat information of user.
Further, the three-dimensional prediction model is that the mark of figure and movement will be corresponded in two dimensional image and two dimensional image
Quasi- three-dimensional (3 D) manikin input deep neural network training obtains, and is specifically used for:
User is acquired in the two dimensional image at same visual angle;
According in the two dimensional image figure and movement find corresponding standard three-dimensional manikin;
The two dimensional image and standard three-dimensional manikin input deep neural network are trained, corresponded to
Three-dimensional prediction model.
Further, second determining module, comprising:
Extraction unit, for extracting the practical three-dimensional coordinate of each key point in the practical three-dimensional (3 D) manikin;
Determination unit, for determining the actual body parameter of user according to the practical three-dimensional coordinate of each key point.
Further, described device, further includes:
4th determining module, in the three-dimensional prediction model that the input of described image to be detected is trained in advance, obtaining pair
After the practical three-dimensional (3 D) manikin answered, determines the practical height obtained in advance and simulate body in the practical three-dimensional (3 D) manikin
Height ratio between height;
5th determining module, for according to the height ratio, the practical height and the practical three-dimensional (3 D) manikin
In simulated body degree of enclosing information, determine actual body degree of the enclosing information of user.
Further, described device, further includes:
6th determining module, for determining user according to the actual weight and actual body degree of the enclosing information that obtain in advance
Body fat information.
Further, described device, further includes:
7th determining module, for determining user's body health degree according to user's body standard sign of seeking peace.
Further, the actual body parameter includes at least one of following: the practical relative position between each key point
With practical relative angle.
The third aspect, the embodiment of the invention also provides a kind of user's sign locking equipments really, comprising: memory and one
A or multiple processors;
The memory, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the determination method of user's sign as described in relation to the first aspect.
Fourth aspect, it is described the embodiment of the invention also provides a kind of storage medium comprising computer executable instructions
Computer executable instructions by computer processor when being executed for executing the determination of user's sign as described in relation to the first aspect
Method.
The present invention is by obtaining image to be detected;By image to be detected input three-dimensional prediction model trained in advance, obtain
Corresponding practical three-dimensional (3 D) manikin, three-dimensional prediction model are that figure and movement will be corresponded in two dimensional image and two dimensional image
The input deep neural network training of standard three-dimensional manikin obtains;According to the ginseng of key point each in practical three-dimensional (3 D) manikin
Number, determines the actual body parameter of user;User's sign is determined according to actual body parameter and standard physical parameter.The present invention is real
Example is applied by three-dimensional prediction model trained in advance, without repeatedly shooting multiple human body images with different view, can directly by
Detection image is converted to practical three-dimensional (3 D) manikin, and according to the parameter of each key point in practical three-dimensional (3 D) manikin, i.e.,
It can conveniently and efficiently determine user's sign.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the determination method of user's sign provided in an embodiment of the present invention;
Fig. 2 is a kind of flow chart of three-dimensional prediction model generating method provided in an embodiment of the present invention;
Fig. 3 is the display signal that a kind of image to be detected provided in an embodiment of the present invention is converted to practical three-dimensional (3 D) manikin
Figure;
Fig. 4 is a kind of display schematic diagram of key point provided in an embodiment of the present invention;
Fig. 5 is the flow chart of the determination method of another user's sign provided in an embodiment of the present invention;
Fig. 6 is the flow chart of the determination method of another user's sign provided in an embodiment of the present invention;
Fig. 7 is a kind of structural block diagram of the determination device of user's sign provided in an embodiment of the present invention;
Fig. 8 is a kind of structural schematic diagram of user's sign provided in an embodiment of the present invention locking equipment really.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Fig. 1 is a kind of flow chart of the determination method of user's sign provided in an embodiment of the present invention, is provided in the present embodiment
User's sign determination method can by user's sign really locking equipment execute, locking equipment can pass through user's sign really
The mode of software and/or hardware realizes that locking equipment can be two or more physical entities compositions to user's sign really, can also
To be that a physical entity is constituted.Locking equipment can be personal computer (Personal to user's sign really in the present embodiment
Computer, PC).
With reference to Fig. 1, the determination method of user's sign specifically comprises the following steps:
S110, image to be detected is obtained.
Wherein, image to be detected is a frame human body image, and human body image is two dimensional image.It is to be understood that be detected
Image is a frame two-dimension human body image.In the actual mechanical process for obtaining image to be detected, which can be one
Framed user's visual angle or the two-dimension human body image for doing any movement.It certainly, can accurately really in order to pass through image to be detected
Determine user's sign, it is preferable that image to be detected is the two-dimension human body image at user front to be detected visual angle, meanwhile, in order to avoid
The determination result of user's sign is influenced because of the movement that user to be detected is done, it is preferable that the use to be detected in image to be detected
Family need to keep standing activities, and the arm of user to be detected naturally droops.
In embodiment, image to be detected can be the two-dimension human body image of shooting completion in advance.It is to be understood that be checked
The acquisition modes of altimetric image can also be downloaded by the way of directly being obtained from this map office using by network
And the mode obtained can also be used directly in such a way that mobile terminal shooting is obtained certainly.Wherein, mobile terminal can
For smart phone, ipad etc..Meanwhile the image to be detected can by configured with camera mobile terminal to user to be detected into
Row shooting obtains.Then, by it is wired or wireless connection by image to be detected be uploaded to in PC machine, the mobile terminal and PC
It can be communicatively coupled by wired or wireless way between machine.It certainly, can be by since PC machine does not have radio connection
Third-party application platform, image to be detected that mobile terminal is shot upload in PC machine, for example, third-party application platform
It can be the platforms such as wechat, QQ.
S120, the three-dimensional prediction model for training image to be detected input in advance, obtain corresponding practical 3 D human body mould
Type.
Wherein, three-dimensional prediction model is that the standard three-dimensional people of figure and movement will be corresponded in two dimensional image and two dimensional image
Body Model input deep neural network training obtains.In embodiment, Fig. 2 is a kind of three-dimensional prediction provided in an embodiment of the present invention
The flow chart of model generating method, with reference to Fig. 2, the three-dimensional prediction model generating method, it may include step S1201-S1203:
S1201, user is acquired in the two dimensional image at same visual angle.
Wherein, the two dimensional image at same visual angle, it can be understood as by the mobile terminal configured with camera to different use
Family carries out two dimensional image obtained from shooting, collecting in the same angle.In embodiment, in order to guarantee the obtained three-dimensional of training
The forecasting accuracy of prediction model can obtain a large amount of two dimensional image, and can obtain different building shape, different heights, dissimilarity
Two dimensional image of the user of other and different movements at same visual angle.Wherein, the two dimensional image of user can be divided into several visual angles,
For example, positive angle, depression angle, side view angle, looking up angle etc..In embodiment, in order to guarantee acquired X-Y scheme
Picture can accurately show corresponding user's sign, can determine acquired two dimensional image by user's sign to be determined
Visual angle.Wherein, user's sign includes at least one of following: user's posture, actual body degree of enclosing information, the body fat of user of user
Information.It should be noted that user's posture can be understood as leading to self-defect because of extraneous factors such as sitting posture, stances,
Not so-called height is fat or thin.For example, user's posture type can include: high-low shoulder, X-type leg, O-shaped leg and pelvis lean forward.Make
It is non-limiting for example, for user's posture type be high-low shoulder, X-type leg or O-shaped leg, can be directly from positive angle to X-Y scheme
As being acquired;It leans forward, directly two dimensional image can be acquired from side view angle for pelvis for user's posture type;For
Other user's posture types, can be set as the case may be.It should be noted that in the present embodiment, preferably
Ground can obtain the two dimensional image at same visual angle as training sample according to different user's posture types.Certainly, to different
When user's posture is determined, the two dimensional image at same visual angle can also be acquired as training sample.Wherein, body aesthetics packet
It includes: degree of the enclosing information of the corporal parts such as bust, waistline, hip circumference, upper-arm circumference, thigh circumference.
Certainly, in order to guarantee the accuracy for training obtained three-dimensional prediction model according to collected two dimensional image, right
Three-dimensional prediction model is trained, and the movement in the two dimensional image of acquisition needs for standard, also, can set in two dimensional image
The standard degree of movement cannot be below preset standard degree, if being lower than preset standard degree, abandon the two dimensional image.Illustratively, false
If it is required that the movement in two dimensional image is standing activities, and arm naturally droops, leg is stretched and preset standard degree is
90%.After collecting two dimensional image, the action criteria of standing activities, arm and leg in the two dimensional image is divided
Analysis, if the action criteria degree in the two dimensional image is more than 90%, just using the two dimensional image as training sample;Conversely, if being lower than
90%, then abandon the two dimensional image.
It certainly,, need to be according to not in order to adapt to the crowd of different building shape when obtaining the two dimensional image as training sample yet
Acquisition is acquired to two dimensional image with figure.Wherein, figure can be divided into high, short, fat, thin etc..When getting two dimensional image,
It can be according to the fat or thin two dimensional image for obtaining same visual angle of height as training sample.Simultaneously, it is contemplated that because gender reason causes to use
The difference of family sign can also obtain two dimensional image according to gender, using as corresponding training sample.
S1202, corresponding standard three-dimensional manikin is found according to the body-building movement in two dimensional image.
Wherein, standard three-dimensional manikin can be understood as three-dimensional (3 D) manikin corresponding to standard operation.In embodiment
In, different user is being got after the two dimensional image of the same movement at same visual angle, is being looked into according to the movement in two dimensional image
Find the standard three-dimensional manikin of respective action.Wherein, standard three-dimensional manikin can different sexes according to user, difference
Height is set.
S1203, two dimensional image and standard three-dimensional manikin input deep neural network are trained, are obtained corresponding
Three-dimensional prediction model.
Wherein, the working principle of deep neural network is to imitate human brain form of thinking, so that speech recognition speed is more
Fastly, recognition accuracy is also higher.In embodiment, by the standard three of the two dimensional image comprising standard operation and corresponding standard operation
Dimension manikin is inputted as training sample respectively in the model of deep neural network, and passes through the model pair of deep neural network
It is trained, and corresponding three-dimensional prediction model can be obtained.Wherein, three-dimensional prediction model is used for be detected according to getting
Image prediction obtains the practical three-dimensional (3 D) manikin that active user corresponds to figure, lacks asking for depth information to solve two dimensional image
Topic.
In embodiment, after getting image to be detected, image to be detected can be directly inputted to the three of training in advance
Prediction model is tieed up, the practical three-dimensional (3 D) manikin comprising corresponding figure can be obtained by image to be detected.Fig. 3 is of the invention real
A kind of image to be detected for applying example offer is converted to the display schematic diagram of practical three-dimensional (3 D) manikin.With reference to shown in the left figure of Fig. 3,
Fig. 3 left figure is image to be detected that a frame keeps standing activities, by image to be detected input three-dimensional prediction mould trained in advance
After type, corresponding practical three-dimensional (3 D) manikin can be obtained according to three-dimensional prediction model prediction, i.e., it is practical as shown in Fig. 3 right figure
Three-dimensional (3 D) manikin.
S130, according to the parameter of key point each in practical three-dimensional (3 D) manikin, determine the actual body parameter of user.
Wherein, the parameter of each key point can be understood as the three-dimensional coordinate of each artis of user body parts.In reality
It applies in example, it, can be according to the fixation position of artis from each practical 3 D human body mould after obtaining practical three-dimensional (3 D) manikin
The three-dimensional coordinate of each artis is got in type, and the actual body parameter of user is determined according to the parameter of each key point.Its
In, body parameter includes at least one of following: the relative angle of relative position and each key point between each key point.Accordingly
, actual body parameter includes at least one of following: practical relative position and practical relative angle between each key point.Herein
It should be noted that this programme is illustratively by taking the practical relative position between each key point is with practical relative angle as an example
Actual body parameter is illustrated.In the actual mechanical process for determining user's sign, each key point can also be passed through
Practical three-dimensional coordinate determines other body parameters of user, to determine user's sign according to body parameter.
In embodiment, actual body parameter can be understood as practical relative position and each key point between each key point
Practical relative angle.Wherein, the practical relative position of each key point can be understood as the reality between each artis of user
The relative difference of border position;The practical relative angle variation of each key point can be understood as the reality between each artis of user
The relative difference of border angle.
It should be noted that the actual body parameter of user need to each artis in same frame image to be detected it
Between relative position and relative angle analyzed, can just determine to obtain.It is to be understood that in the actual body for determining user
In the actual mechanical process of parameter, in obtaining practical three-dimensional (3 D) manikin after the parameter of each key point, need to each key
Relative position and relative angle between point are calculated.
Fig. 4 is a kind of display schematic diagram of key point provided in an embodiment of the present invention.As shown in the left figure in Fig. 4, user
Standing activities are being kept, the corresponding image to be detected of the movement is input to three-dimensional prediction model, corresponding reality can be obtained
Border three-dimensional (3 D) manikin, and the three-dimensional coordinate for extracting each key point can be identified from practical three-dimensional (3 D) manikin, such as Fig. 4 right figure
Shown in show each key point.For example, showing 15 key points in figure as shown in right in Figure 4, respectively close
Key point 1, key point 2, key point 3 ... key point 15.Wherein, each key point, that is, different artis, for example, key point 1 is
Head, key point 2 are neck, and key point 3 is left shoulder, and key point 4 is left elbow, and key point 5 is left wrist, and key point 6 is right shoulder, are closed
Key point 7 is right elbow, and key point 8 is right wrist, and key point 9 is abdomen, and key point 10 is left buttocks, and key point 11 is left knee, is closed
Key point 12 is left foot point, and key point 13 is right hips, and key point 14 is right knee, and key point 15 is right crus of diaphragm point.Certainly, in determination
It, can be according to user's sign to be determined, to obtain the ginseng of corresponding each key point in the actual mechanical process of user's sign
Number, obtains without all key points to user to be detected.For example, determining whether in user to be detected for high-low shoulder
When, the parameter of key point 1, key point 2, key point 3, key point 6 can be directly acquired, i.e. acquisition head, neck, left shoulder and right shoulder
Parameter, to judge whether the relative position of left shoulder and right shoulder is symmetrical, without obtaining other key points parameter, with
And calculate the relative position between other key points and relative angle.
Certainly, this 15 key points illustratively only are shown in the right figure in Fig. 4 in the present embodiment, not only limited
This 15 key points.When determining user's posture, the parameter of other key points can also be obtained, for example, to be checked determining
When surveying user and whether there is X-type leg or O-shaped leg, it need to determine three-dimensional coordinate on the inside of the left leg of user to be detected (in Fig. 4 not
Display) and right leg on the inside of three-dimensional coordinate (in Fig. 4 not show), and according to the three-dimensional coordinate of medial leg and knee
The relative position of three-dimensional coordinate and relative angle can just accurately determine user to be detected lacking with the presence or absence of X-type leg or O-shaped leg
It falls into.
S140, user's sign is determined according to actual body parameter and standard physical parameter.
Wherein, standard physical parameter can be understood as body parameter corresponding to user's specification body.In embodiment, exist
After obtaining the actual body parameter of user, directly by the actual body parameter of user standard body corresponding with the movement and figure
Body parameter is compared, if the difference between actual body parameter and standard physical parameter within the scope of preset difference value,
Show that the standard degree of user's body reaches standard degree threshold value, i.e., the user's body is standard;Conversely, if actual body parameter and
Difference between standard physical parameter then shows that the standard degree of user's body is not up to standard degree threshold not within the scope of preset difference value
Value, i.e., the user's body is non-type, is existing defects.For example, as shown in right in Figure 4, if user to be detected
The relative position of left shoulder and right shoulder is simultaneously asymmetrical, and degree of being above standard threshold value, then shows that there are high-low shoulders by user to be detected
Defect.
After determining user's posture, determine that the actual body of user is enclosed in combination with the height information and weight information of user
The body fat information for spending information and user, specifically sees below the description of embodiment, details are not described herein.
The technical solution of the present embodiment, by obtaining image to be detected;By image to be detected input three-dimensional trained in advance
Prediction model obtains corresponding practical three-dimensional (3 D) manikin, and three-dimensional prediction model is will be right in two dimensional image and two dimensional image
It answers figure and the standard three-dimensional manikin of movement to input deep neural network training to obtain;According in practical three-dimensional (3 D) manikin
The parameter of each key point determines the actual body parameter of user;User is determined according to actual body parameter and standard physical parameter
Sign realizes without repeatedly shooting multiple human body images with different view, can conveniently and efficiently determine user's sign.
On the basis of the above embodiments, in step S130 according to the parameter of key point each in practical three-dimensional (3 D) manikin,
The actual body parameter for determining user, specifically includes step S1301-S1302:
S1301, the practical three-dimensional coordinate for extracting each key point in practical three-dimensional (3 D) manikin.
Wherein, the practical three-dimensional coordinate of each key point refers to practical three of each artis on each position of user's body
Tie up coordinate.In embodiment, by three-dimensional prediction model prediction obtain the corresponding practical three-dimensional (3 D) manikin of image to be detected it
It afterwards, can be according to the practical three-dimensional coordinate of each artis of fixation position acquisition of artis, for example, coordinate corresponding to x, y and z
Value.Certainly, the corresponding unique practical three-dimensional (3 D) manikin of every frame image to be detected, i.e. any two image to be detected are corresponding
Practical three-dimensional (3 D) manikin is different, between each artis extracted in the practical three-dimensional (3 D) manikin of any two
Practical three-dimensional coordinate is also different.
S1302, the actual body parameter that user is determined according to the practical three-dimensional coordinate of each key point.
Wherein, actual body parameter includes at least one of following: practical relative position and practical phase between each key point
To angle.
In embodiment, after obtaining practical three-dimensional coordinate, each pass can be determined according to the occurrence of practical three-dimensional coordinate
Relative position and relative angle between key point determine the actual body parameter of user.For example, can be according to user's to be detected
Three-dimensional coordinate on the inside of left leg and the relative position between the three-dimensional coordinate of left knee and the three-dimensional coordinate on the inside of right leg
Relative position between the three-dimensional coordinate of right knee, it may be determined that defect of the user to be detected with the presence or absence of X-type leg or O-shaped leg.
It is to be understood that in embodiment, user's sign can be determined according to one of parameter in actual body parameter, it can also basis
Two of them parameter in actual body parameter determines user's sign, herein without limiting, can carry out according to the actual situation really
Determine the number of actual body parameter.
Certainly, in the actual body parameter for determining user, only according to the specific of the practical three-dimensional coordinate of a key point
Value, can not determine the actual body parameter of user, it can be understood as, need to each key point corresponding to the image to be detected it
Between practical three-dimensional coordinate be compared, to determine the actual body parameter of user.
Fig. 5 is the flow chart of the determination method of another user's sign provided in an embodiment of the present invention.The present embodiment be
On the basis of above-described embodiment, further embody is made to the determination method of user's sign.The present embodiment is applied to true
Under the scene for determining user's actual body degree of enclosing information and body fat information, referring to Fig. 5, the determination method of user's sign is specifically included
Following steps:
S210, image to be detected is obtained.
S220, the three-dimensional prediction model for training image to be detected input in advance, obtain corresponding practical 3 D human body mould
Type.
Wherein, three-dimensional prediction model is that the standard three-dimensional people of figure and movement will be corresponded in two dimensional image and two dimensional image
Body Model input deep neural network training obtains.
S230, the height ratio simulated between height in the practical height obtained in advance and practical three-dimensional (3 D) manikin is determined
Example.
Wherein, the practical height obtained in advance, can directly be obtained by tape measure, and user's body can also be stored in advance in
It levies in the local data base of locking equipment really, and is loaded directly into acquisition from local data base.
Wherein, simulation height can be understood as the height information obtained in the practical three-dimensional (3 D) manikin.In embodiment,
Practical three-dimensional (3 D) manikin is that height restores the figure of user to be detected, i.e., by practical three-dimensional (3 D) manikin can be calculated to
The numerical value and relative scale at each position of user are detected, but is calculated from practical three-dimensional (3 D) manikin only each
The numerical value at position, there is no units.
In actual operation, when the height of a people being described, by by centimetre or meter as unit of, to the user's
Height information is embodied.For example, the height that the height of user A is 1 meter 76 or user A is 176 centimetres.In embodiment,
When obtaining practical three-dimensional (3 D) manikin, the corresponding simulation body of user to be detected can only be obtained by practical three-dimensional (3 D) manikin
It is high.Such as, it is assumed that it is 1.79 that simulation height is obtained from the practical three-dimensional (3 D) manikin of user B to be detected, but concrete unit is
How much, it is unclear.It therefore, can be 1 meter 79 by the practical height of the user B to be detected measured in step S230,
Then the height ratio of the simulation height He practical height of user B to be detected is 1:100.
S240, according to simulated body degree of the enclosing information in height ratio, practical height and practical three-dimensional (3 D) manikin, determine
Actual body degree of the enclosing information of user.
Wherein, body aesthetics information includes: enclosing for the corporal parts such as bust, waistline, hip circumference, upper-arm circumference, thigh circumference
Spend information.In embodiment, after the height ratio being calculated between simulation height and practical height, from practical three-dimensional people
Simulation degree of the enclosing information of other body parts obtained in body Model, then the other positions in corresponding portion are calculated by the height ratio
Actually degree of enclosing information.It is to be understood that the ratio between simulation degree of the enclosing information at other positions and corresponding actually degree of enclosing information
Example, is 1:1 with height ratio.For example, the height ratio between simulation height and practical height is 1:100, then user its
Ratio between simulation degree of the enclosing information at its position and corresponding actually degree of enclosing information is also 1:100.
It is to be appreciated that after obtaining simulated body degree of enclosing information in practical three-dimensional (3 D) manikin, according to height ratio
Example can extrapolate actual body degree of the enclosing information of user.Certainly, actual body degree of the enclosing information Yu gender and height of user
It is related.In embodiment, by taking body aesthetics information is bust, waist and hip circumference as an example, to the actual body degree of enclosing for determining user
Information is illustrated.For example, the standard measurements of the chest, waist and hips (bust, waist and hip circumference) for the women that height is 160 centimetres are respectively 86.01 lis
Rice, 60.71 centimetres and 87.27 centimetres;And the standard measurements of the chest, waist and hips (bust, waist and hip circumference) for the male that height is 175 centimetres are respectively
It is 106.7 centimetres, 73.5 centimetres and 112 centimetres.Assuming that obtaining the simulation three of user B to be detected from practical three-dimensional (3 D) manikin
Enclosing information (bust, waist and hip circumference) is respectively 0.84,0.56 and 0.82, according to height ratio be 1:100, can be calculated to
The practical measurements of the chest, waist and hips information (bust, waist and hip circumference) for detecting user B is respectively 84 centimetres, 56 centimetres and 82 centimetres.Certainly, pass through
The method of collected image to be detected also can measure actual body degree of the enclosing information at other positions of user to be detected.
The technical solution of the present embodiment, on the basis of above scheme, by obtain user to be detected practical height and
Actual weight;Determine the height ratio simulated between height in practical height and practical three-dimensional (3 D) manikin;According to height ratio,
Simulated body degree of enclosing information in practical height and practical three-dimensional (3 D) manikin, determines actual body degree of the enclosing information of user, real
Show actual body degree of the enclosing information that user to be detected can be directly estimated by image to be detected that shooting obtains, without
It is measured one by one by scale.
On the basis of the above embodiments, in order to determine that the body fat information of user further includes step after step S240
S250:
S250, the body fat information that user is determined according to the actual weight and actual body degree of enclosing information that obtain in advance.
Wherein, the practical height obtained in advance can be obtained directly by scale measurement, can also be stored in advance in user
Sign is loaded directly into acquisition really in the local data base of locking equipment from local data base.
In embodiment, body fat information can be calculated by default calculation formula, but due to the body of male and female
The parameter and women at each position have certain difference, and when calculating body fat information, the corresponding body fat of male and female calculates public
Formula is also distinguishing.For example, the calculation formula of male's body fat: BF1=(495/BD) -450;Wherein, BD1 is median, BF1
What is indicated is male's body fat, meanwhile, BD1=(1.21142+ (0.0085* weight (Kg))-(0.0050* bust (cm))-
(0.0061* hip circumference (cm))-(0.0138* waistline (cm))).The calculation formula of women body fat: BF2=(495/BD) -450;Its
In, BD2 is median, and what BF2 was indicated is women body fat, meanwhile, BD2=(1.168297- (0.02824* waistline (cm))+
(0.000122098* waistline (cm) * waistline (cm))-(0.00733128* hip circumference (cm))+(0.00510477* height (cm))-
(the 0.00216161* age (year)).Wherein, the body fat calculation formula of above-mentioned sex is the rule found by big data
The formula restrained and extrapolated.It should be noted that measurements of the chest, waist and hips information of the body fat calculation formula with user in the present embodiment
(bust, hip circumference, waistline) and weight/height are related.When the body fat information to user calculates, user can be only determined
Measurements of the chest, waist and hips information, without determine user other positions body aesthetics information.Certainly, if the body at other positions can be used
Degree of enclosing information determines the body fat information of user, also belongs to technical solution of the present invention.
The technical solution of the present embodiment, on the basis of above scheme, according to actual weight and actual body degree of enclosing information
The body fat information for determining user realizes the body that user to be detected can be directly estimated by image to be detected that shooting obtains
Rouge information, it is more simple and fast than using traditional resistance measurement body fat.
On the basis of the above embodiments, in order to determine user's body health degree, step S240 or step S250 it
Afterwards, further include step S260:
S260, standard sign of being sought peace according to user's body determine user's body health degree.
In embodiment, user's body health degree can pass through actual body degree of the enclosing information of user and the body fat of user
Information is assessed to obtain.Specifically, before being measured to user's sign, the standard physical degree of enclosing of user is believed in advance
A value range is arranged in breath and standard body fat information, can be denoted as preset standard body aesthetics range and preset standard body fat model
It encloses, when actual body degree of the enclosing information of user to be detected is within the scope of preset standard body aesthetics, it is believed that user to be detected
Body aesthetics be standard, i.e., also show that user's body to be detected is healthy indirectly;Certainly, when the reality of user to be detected
Border body fat information is within the scope of preset standard body fat, it is believed that the body fat of user to be detected is standard, i.e. also indirect earth's surface
Bright user's body to be detected is healthy.
It should be noted that in order to more accurately determine user's body health degree, it can be simultaneously to user to be detected
Body aesthetics and body fat information be determined, and treated according to actual body degree of the enclosing information and body fat information of user to be detected
The health degree of detection user is assessed.Certainly, in the actual operation process, the wheat of user's sign locking equipment really can be passed through
Gram wind plays back the result information of user's sign, while showing in user's sign really display screen of locking equipment.
For example, the practical body fat information of user to be detected not within the scope of preset standard body fat, is then played and is shown similar to " body fat is inclined
The evaluating result of height ".Certainly, only evaluating result can also be played out by microphone, or only by display screen to assessment
As a result it is shown.
Fig. 6 is the flow chart of the determination method of another user's sign provided in an embodiment of the present invention.The present embodiment is tangible
On the basis of above-described embodiment, as a preferred embodiment, the determination method of user's sign is specifically described.It, should with reference to Fig. 6
The determination method of user's sign specifically comprises the following steps:
S310, user's frontal upright image is obtained.
In embodiment, in order to improve the determination accuracy rate of user's sign, the front for directly acquiring user to be detected is stood
Two-dimension human body image, as image to be detected.
S320, frontal upright image is input to three-dimensional prediction model, obtains corresponding practical three-dimensional (3 D) manikin.
S330, the practical height and actual weight for obtaining user.
S340, the height ratio simulated between height in practical height and practical three-dimensional (3 D) manikin is determined.
S350, according to simulated body degree of the enclosing information in height ratio, practical height and practical three-dimensional (3 D) manikin, determine
Actual body degree of the enclosing information of user.
S360, the body fat information that user is determined according to actual weight and actual body degree of enclosing information.
S370, according to the parameter of key point each in practical three-dimensional (3 D) manikin, determine the actual body parameter of user;
S380, user's sign is determined according to actual body parameter and standard physical parameter.
It should be noted that step S370-S380 only need to just can be performed in step S320, be not required to again step S360 it
After execute.It is to be understood that after obtaining practical three-dimensional (3 D) manikin in step s 320, so that it may be performed simultaneously step
S370-S380 and step S330-S360, i.e. the two steps can be synchronous execution.Certainly, step S370-S380, and
What step S330-S360 was also possible to independently execute, it even need to only determine user's posture, then follow the steps S310, S320, S370
With S380;If need to only determine actual body degree of the enclosing information of user, S310-S350 is thened follow the steps;If needing to determine
The body fat information of user need to execute step S360 on the basis of determining actual body degree of the enclosing information of user.
Fig. 7 is a kind of structural block diagram of the determination device of user's sign provided in an embodiment of the present invention.The use of the present embodiment
The determining device of family sign is configured in PC machine, and with reference to Fig. 7, the determination device of user's sign includes: the first acquisition module
410, the first determining module 420, the second determining module 430 and third determining module 440.
Wherein, first module 410 is obtained, for obtaining image to be detected;
First determining module 420 obtains corresponding for the three-dimensional prediction model that image to be detected input is trained in advance
Practical three-dimensional (3 D) manikin, the three-dimensional prediction model are that the standard of figure and movement will be corresponded in two dimensional image and two dimensional image
Three-dimensional (3 D) manikin input deep neural network training obtains;
Second determining module 430 determines the reality of user for the parameter according to key point each in practical three-dimensional (3 D) manikin
Border body parameter;
Third determining module 440, for determining user's sign according to actual body parameter and standard physical parameter.
Technical solution provided in this embodiment, by obtaining image to be detected;By image to be detected input training in advance
Three-dimensional prediction model, obtains corresponding practical three-dimensional (3 D) manikin, and three-dimensional prediction model is by two dimensional image and two dimensional image
Middle corresponding figure and the input deep neural network training of the standard three-dimensional manikin of movement obtain;According to practical 3 D human body mould
The parameter of each key point in type determines the actual body parameter of user;It is determined according to actual body parameter and standard physical parameter
User's sign realizes without repeatedly shooting multiple human body images with different view, can conveniently and efficiently determine user's sign.
On the basis of the above embodiments, user's sign includes at least one of following: user's posture, the reality of user
Body aesthetics information, the body fat information of user.
On the basis of the above embodiments, the three-dimensional prediction model is by corresponding body in two dimensional image and two dimensional image
Type and the input deep neural network training of the standard three-dimensional manikin of movement obtain, and are specifically used for:
User is acquired in the two dimensional image at same visual angle;
According in two dimensional image figure and movement find corresponding standard three-dimensional manikin;
Two dimensional image and standard three-dimensional manikin input deep neural network are trained, obtained corresponding three-dimensional pre-
Survey model.
On the basis of the above embodiments, the second determining module, comprising:
Extraction unit, for extracting the practical three-dimensional coordinate of each key point in practical three-dimensional (3 D) manikin;
Determination unit determines the actual body parameter of user for the practical three-dimensional coordinate according to each key point;The reality
Body parameter includes at least one of following: practical relative position and practical relative angle between each key point.
On the basis of the above embodiments, described device, further includes:
4th determining module, for obtaining corresponding in the three-dimensional prediction model that image to be detected input is trained in advance
After practical three-dimensional (3 D) manikin, the height ratio simulated between height in practical height and practical three-dimensional (3 D) manikin is determined;
5th determining module, for according to the simulated body in height ratio, practical height and practical three-dimensional (3 D) manikin
Degree of enclosing information determines actual body degree of the enclosing information of user.
On the basis of the above embodiments, described device, further includes:
6th determining module, for determining the body fat information of user according to actual weight and actual body degree of enclosing information.
On the basis of the above embodiments, described device, further includes:
7th determining module, for determining user's body health degree according to user's body standard sign of seeking peace.
On the basis of the above embodiments, the actual body parameter includes at least one of following: between each key point
Practical relative position and practical relative angle.
The determination side of user's sign provided by any embodiment of the invention can be performed in the determination device of above-mentioned user's sign
Method has the corresponding functional module of execution method and beneficial effect.
Fig. 8 is a kind of structural schematic diagram of user's sign provided in an embodiment of the present invention locking equipment really.It, should with reference to Fig. 8
Really locking equipment includes: processor 510, memory 520, input unit 530 and output device 540 to user's sign.The user
Really the quantity of processor 510 can be one or more to sign in locking equipment, in Fig. 8 by taking a processor 510 as an example.It should
Really the quantity of memory 520 can be one or more to user's sign in locking equipment, be with a memory 520 in Fig. 8
Example.Really the processor 510 of locking equipment, memory 520, input unit 530 and output device 540 can lead to user's sign
It crosses bus or other modes connects, in Fig. 8 for being connected by bus.In embodiment, user's sign locking equipment really
It can be PC machine.
Memory 520 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, user's sign as described in any embodiment of that present invention corresponding program instruction of locking equipment/module (example really
Such as, first in the determination device of user's sign obtains module 410, the first determining module 420, the second determining module 430 and the
Three determining modules 440).Memory 520 can mainly include storing program area and storage data area, wherein storing program area can deposit
Application program needed for storing up operating system, at least one function;Storage data area can be stored to be created according to using for equipment
Data etc..In addition, memory 520 may include high-speed random access memory, it can also include nonvolatile memory, such as
At least one disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory
520 can further comprise the memory remotely located relative to processor 510, these remote memories can pass through network connection
To equipment.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 530 can be used for receiving the number or character information of input, and generate the user setting with equipment
And the related key signals input of function control, it can also be the camera for obtaining image and obtain picking up for audio data
Sound equipment.Output device 540 may include the audio frequency apparatuses such as loudspeaker.It should be noted that input unit 530 and output device
540 concrete composition may be set according to actual conditions.
Software program, instruction and the module that processor 510 is stored in memory 520 by operation, thereby executing setting
Standby various function application and data processing realizes the determination method of above-mentioned user's sign.
Really locking equipment can be used for executing user's sign that above-mentioned any embodiment provides to user's sign of above-mentioned offer
It determines method, has corresponding function and beneficial effect.
The embodiment of the present invention also provides a kind of storage medium comprising computer executable instructions, and the computer is executable
Instruction by computer processor when being executed for executing a kind of determination method of user's sign, comprising:
Obtain image to be detected;
By image to be detected input three-dimensional prediction model trained in advance, corresponding practical three-dimensional (3 D) manikin is obtained, it should
Three-dimensional prediction model is to input the standard three-dimensional manikin that figure and movement are corresponded in two dimensional image and two dimensional image deeply
Degree neural metwork training obtains;
According to the parameter of key point each in practical three-dimensional (3 D) manikin, the actual body parameter of user is determined;
User's sign is determined according to actual body parameter and standard physical parameter.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The determination method for user's sign that executable instruction is not limited to the described above operates, and any embodiment of that present invention institute can also be performed
Relevant operation in the determination method of user's sign of offer, and have corresponding function and beneficial effect.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be robot, personal computer, server or the network equipment etc.) executes use described in any embodiment of that present invention
The determination method of family sign.
It is worth noting that, in the determination device of above-mentioned user's sign, included each unit and module only according to
What function logic was divided, but be not limited to the above division, as long as corresponding functions can be realized;In addition, each
The specific name of functional unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (11)
1. a kind of determination method of user's sign characterized by comprising
Obtain image to be detected;
By described image to be detected input three-dimensional prediction model trained in advance, corresponding practical three-dimensional (3 D) manikin, institute are obtained
Stating three-dimensional prediction model is to input the standard three-dimensional manikin that figure and movement are corresponded in two dimensional image and two dimensional image
Deep neural network training obtains;
According to the parameter of each key point in the practical three-dimensional (3 D) manikin, the actual body parameter of user is determined;
User's sign is determined according to the actual body parameter and standard physical parameter.
2. the determination method of user's sign according to claim 1, which is characterized in that user's sign include it is following extremely
One item missing: user's posture, actual body degree of the enclosing information of user, the body fat information of user.
3. the determination method of user's sign according to claim 1, which is characterized in that the three-dimensional prediction model is by two
The standard three-dimensional manikin input deep neural network training that figure and movement are corresponded in dimension image and two dimensional image obtains,
Include:
User is acquired in the two dimensional image at same visual angle;
According in the two dimensional image figure and movement find corresponding standard three-dimensional manikin;
The two dimensional image and standard three-dimensional manikin input deep neural network are trained, obtain corresponding three
Tie up prediction model.
4. the determination method of user's sign according to claim 1, which is characterized in that described according to the practical three-dimensional people
The parameter of each key point in body Model determines the actual body parameter of user, comprising:
Extract the practical three-dimensional coordinate of each key point in the practical three-dimensional (3 D) manikin;
The actual body parameter of user is determined according to the practical three-dimensional coordinate of each key point.
5. the determination method of user's sign according to claim 1, which is characterized in that inputted by described image to be detected
Three-dimensional prediction model trained in advance, after obtaining corresponding practical three-dimensional (3 D) manikin, further includes:
Determine the height ratio simulated between height in the practical height obtained in advance and the practical three-dimensional (3 D) manikin;
According to simulated body degree of the enclosing information in the height ratio, the practical height and the practical three-dimensional (3 D) manikin,
Determine actual body degree of the enclosing information of user.
6. the determination method of user's sign according to claim 5, which is characterized in that further include:
The body fat information of user is determined according to the actual weight and actual body degree of the enclosing information that obtain in advance.
7. the determination method of user's sign according to claim 5 or 6, which is characterized in that further include:
User's body health degree is determined according to user's body standard sign of seeking peace.
8. the determination method of user's sign according to claim 1, which is characterized in that under the actual body parameter includes
State at least one: practical relative position and practical relative angle between each key point.
9. a kind of determination device of user's sign characterized by comprising
First obtains module, for obtaining image to be detected;
First determining module obtains corresponding reality for the three-dimensional prediction model that the input of described image to be detected is trained in advance
Border three-dimensional (3 D) manikin, the three-dimensional prediction model are that the standard of figure and movement will be corresponded in two dimensional image and two dimensional image
Three-dimensional (3 D) manikin input deep neural network training obtains;
Second determining module determines the reality of user for the parameter according to each key point in the practical three-dimensional (3 D) manikin
Body parameter;
Third determining module, for determining user's sign according to the actual body parameter and standard physical parameter.
10. a kind of user's sign locking equipment really characterized by comprising memory and one or more processors;
The memory, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as the determination method of user's sign described in any one of claims 1-8.
11. a kind of storage medium comprising computer executable instructions, which is characterized in that the computer executable instructions by
For executing the determination method such as user's sign described in any one of claims 1-8 when computer processor executes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811638496.XA CN109409348A (en) | 2018-12-29 | 2018-12-29 | A kind of determination method, apparatus, equipment and the storage medium of user's sign |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811638496.XA CN109409348A (en) | 2018-12-29 | 2018-12-29 | A kind of determination method, apparatus, equipment and the storage medium of user's sign |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109409348A true CN109409348A (en) | 2019-03-01 |
Family
ID=65462749
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811638496.XA Pending CN109409348A (en) | 2018-12-29 | 2018-12-29 | A kind of determination method, apparatus, equipment and the storage medium of user's sign |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109409348A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110123331A (en) * | 2019-04-17 | 2019-08-16 | 平安科技(深圳)有限公司 | Human body body and constitution collecting method, device and storage medium |
CN110705421A (en) * | 2019-09-25 | 2020-01-17 | 浙江鸿泉电子科技有限公司 | Body type data processing method and device |
CN111105347A (en) * | 2019-11-19 | 2020-05-05 | 贝壳技术有限公司 | Method, device and storage medium for generating panoramic image with depth information |
CN112287869A (en) * | 2020-11-10 | 2021-01-29 | 上海依图网络科技有限公司 | Image data detection method and device |
CN112401369A (en) * | 2020-11-23 | 2021-02-26 | 叠境数字科技(上海)有限公司 | Body parameter measuring method, system, equipment, chip and medium based on human body reconstruction |
CN112419479A (en) * | 2020-11-10 | 2021-02-26 | 广州二元科技有限公司 | Body type data calculation method based on weight, height and body image |
CN112861598A (en) * | 2019-11-27 | 2021-05-28 | 上海联影智能医疗科技有限公司 | System and method for manikin estimation |
CN113012281A (en) * | 2021-03-25 | 2021-06-22 | 北京百度网讯科技有限公司 | Human body model determining method and device, electronic equipment and storage medium |
US11055835B2 (en) | 2019-11-19 | 2021-07-06 | Ke.com (Beijing) Technology, Co., Ltd. | Method and device for generating virtual reality data |
WO2021175208A1 (en) * | 2020-03-02 | 2021-09-10 | 京东方科技集团股份有限公司 | Human body model modeling method and apparatus, electronic device and storage medium |
CN113467259A (en) * | 2020-06-29 | 2021-10-01 | 青岛海信电子产业控股股份有限公司 | Intelligent equipment and body management method |
CN114514562A (en) * | 2019-09-26 | 2022-05-17 | 亚马逊技术有限公司 | Predictive personalized three-dimensional body model |
CN114842147A (en) * | 2022-05-16 | 2022-08-02 | 聚好看科技股份有限公司 | Method for measuring human body parameters and electronic equipment |
CN114964451A (en) * | 2022-04-19 | 2022-08-30 | 深圳创维-Rgb电子有限公司 | Weight management method, system, weight scale and computer readable storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150206341A1 (en) * | 2014-01-23 | 2015-07-23 | Max-Planck-Gesellschaft Zur Foerderung Der Wissenschaften E.V. | Method for providing a three dimensional body model |
CN104813340A (en) * | 2012-09-05 | 2015-07-29 | 体通有限公司 | System and method for deriving accurate body size measures from a sequence of 2d images |
CN106551698A (en) * | 2015-09-30 | 2017-04-05 | 捷荣科技集团有限公司 | A kind of auxiliary body shaping method and system based on anthropometric dummy |
CN107170039A (en) * | 2017-05-12 | 2017-09-15 | 西安蒜泥电子科技有限责任公司 | The generation method of human body three-dimensional data model libraries |
CN107194987A (en) * | 2017-05-12 | 2017-09-22 | 西安蒜泥电子科技有限责任公司 | The method being predicted to anthropometric data |
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 |
CN108805977A (en) * | 2018-06-06 | 2018-11-13 | 浙江大学 | A kind of face three-dimensional rebuilding method based on end-to-end convolutional neural networks |
-
2018
- 2018-12-29 CN CN201811638496.XA patent/CN109409348A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104813340A (en) * | 2012-09-05 | 2015-07-29 | 体通有限公司 | System and method for deriving accurate body size measures from a sequence of 2d images |
US20150206341A1 (en) * | 2014-01-23 | 2015-07-23 | Max-Planck-Gesellschaft Zur Foerderung Der Wissenschaften E.V. | Method for providing a three dimensional body model |
CN106551698A (en) * | 2015-09-30 | 2017-04-05 | 捷荣科技集团有限公司 | A kind of auxiliary body shaping method and system based on anthropometric dummy |
CN107170039A (en) * | 2017-05-12 | 2017-09-15 | 西安蒜泥电子科技有限责任公司 | The generation method of human body three-dimensional data model libraries |
CN107194987A (en) * | 2017-05-12 | 2017-09-22 | 西安蒜泥电子科技有限责任公司 | The method being predicted to anthropometric data |
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 |
CN108805977A (en) * | 2018-06-06 | 2018-11-13 | 浙江大学 | A kind of face three-dimensional rebuilding method based on end-to-end convolutional neural networks |
Non-Patent Citations (3)
Title |
---|
IGNASI RIUS ET AL.: "3D Action Modeling and Reconstruction for 2D Human Body Tracking", 《PATTERN RECOGNITION AND IMAGE ANALYSIS. ICAPR 2005》 * |
吴立娟: "《休闲体育与全民健身》", 30 June 2016 * |
邓卫燕: "基于用户照片和神经网络的三维个性化人体建模方法研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020211255A1 (en) * | 2019-04-17 | 2020-10-22 | 平安科技(深圳)有限公司 | Human body shape and physique data acquisition method, device and storage medium |
CN110123331A (en) * | 2019-04-17 | 2019-08-16 | 平安科技(深圳)有限公司 | Human body body and constitution collecting method, device and storage medium |
CN110705421A (en) * | 2019-09-25 | 2020-01-17 | 浙江鸿泉电子科技有限公司 | Body type data processing method and device |
US11836853B2 (en) | 2019-09-26 | 2023-12-05 | Amazon Technologies, Inc. | Generation and presentation of predicted personalized three-dimensional body models |
CN114514562A (en) * | 2019-09-26 | 2022-05-17 | 亚马逊技术有限公司 | Predictive personalized three-dimensional body model |
CN114514562B (en) * | 2019-09-26 | 2023-06-13 | 亚马逊技术有限公司 | Predictive personalized three-dimensional body model |
CN111105347B (en) * | 2019-11-19 | 2020-11-13 | 贝壳找房(北京)科技有限公司 | Method, device and storage medium for generating panoramic image with depth information |
CN111105347A (en) * | 2019-11-19 | 2020-05-05 | 贝壳技术有限公司 | Method, device and storage medium for generating panoramic image with depth information |
US11721006B2 (en) | 2019-11-19 | 2023-08-08 | Realsee (Beijing) Technology Co., Ltd. | Method and device for generating virtual reality data |
US11055835B2 (en) | 2019-11-19 | 2021-07-06 | Ke.com (Beijing) Technology, Co., Ltd. | Method and device for generating virtual reality data |
CN112861598A (en) * | 2019-11-27 | 2021-05-28 | 上海联影智能医疗科技有限公司 | System and method for manikin estimation |
WO2021175208A1 (en) * | 2020-03-02 | 2021-09-10 | 京东方科技集团股份有限公司 | Human body model modeling method and apparatus, electronic device and storage medium |
CN113467259A (en) * | 2020-06-29 | 2021-10-01 | 青岛海信电子产业控股股份有限公司 | Intelligent equipment and body management method |
CN112287869A (en) * | 2020-11-10 | 2021-01-29 | 上海依图网络科技有限公司 | Image data detection method and device |
CN112419479A (en) * | 2020-11-10 | 2021-02-26 | 广州二元科技有限公司 | Body type data calculation method based on weight, height and body image |
CN112401369A (en) * | 2020-11-23 | 2021-02-26 | 叠境数字科技(上海)有限公司 | Body parameter measuring method, system, equipment, chip and medium based on human body reconstruction |
CN113012281A (en) * | 2021-03-25 | 2021-06-22 | 北京百度网讯科技有限公司 | Human body model determining method and device, electronic equipment and storage medium |
CN113012281B (en) * | 2021-03-25 | 2024-02-13 | 北京百度网讯科技有限公司 | Determination method and device for human body model, electronic equipment and storage medium |
CN114964451A (en) * | 2022-04-19 | 2022-08-30 | 深圳创维-Rgb电子有限公司 | Weight management method, system, weight scale and computer readable storage medium |
CN114842147A (en) * | 2022-05-16 | 2022-08-02 | 聚好看科技股份有限公司 | Method for measuring human body parameters and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109409348A (en) | A kind of determination method, apparatus, equipment and the storage medium of user's sign | |
CN111881705B (en) | Data processing, training and identifying method, device and storage medium | |
CN111460872B (en) | Image processing method and device, image equipment and storage medium | |
CN109621332A (en) | A kind of attribute determining method, device, equipment and the storage medium of body-building movement | |
CN109191588A (en) | Move teaching method, device, storage medium and electronic equipment | |
CN109684920A (en) | Localization method, image processing method, device and the storage medium of object key point | |
US20100312143A1 (en) | Human body measurement system and information provision method using the same | |
CN105094335B (en) | Situation extracting method, object positioning method and its system | |
CN105740780A (en) | Method and device for human face in-vivo detection | |
CN106952335B (en) | Method and system for establishing human body model library | |
CN107930048B (en) | Space somatosensory recognition motion analysis system and motion analysis method | |
CN110532874B (en) | Object attribute recognition model generation method, storage medium and electronic device | |
CN103100193A (en) | Image processing device, image processing method, and program | |
CN105243375B (en) | A kind of motion characteristic extracting method and device | |
CN110210284A (en) | A kind of human body attitude behavior intelligent Evaluation method | |
US10648883B2 (en) | Virtual testing model for use in simulated aerodynamic testing | |
KR20220028654A (en) | Apparatus and method for providing taekwondo movement coaching service using mirror dispaly | |
CN110717391A (en) | Height measuring method, system, device and medium based on video image | |
WO2020147796A1 (en) | Image processing method and apparatus, image device, and storage medium | |
CN110246209A (en) | Image processing method and device | |
CN108346156A (en) | User's stature parameter acquiring method and device | |
CN109409199A (en) | Micro- expression training method, device, storage medium and electronic equipment | |
CN109407826A (en) | Ball game analogy method, device, storage medium and electronic equipment | |
Kirmizibayrak et al. | Digital analysis and visualization of swimming motion | |
CN115568823A (en) | Method, system and device for evaluating human body balance ability |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |