CN109492571A - Identify the method, apparatus and electronic equipment at human body age - Google Patents
Identify the method, apparatus and electronic equipment at human body age Download PDFInfo
- Publication number
- CN109492571A CN109492571A CN201811303378.3A CN201811303378A CN109492571A CN 109492571 A CN109492571 A CN 109492571A CN 201811303378 A CN201811303378 A CN 201811303378A CN 109492571 A CN109492571 A CN 109492571A
- Authority
- CN
- China
- Prior art keywords
- age
- human body
- frame image
- head
- current frame
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004590 computer program Methods 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 230000010355 oscillation Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
This application involves the method, apparatus and electronic equipment at identification human body age.According to an exemplary embodiment, a method of the identification human body age can include: the head of the human body in identification current frame image；Based on the preceding frame image of the preset quantity before the current frame image and the current frame image, the swing parameter on the head of the human body is determined；The first age of the human body is determined based on the swing parameter.
Description
Technical field
Present invention relates generally to field of image recognition, more particularly, to a kind of method, apparatus for identifying the human body age
And electronic equipment.
Background technique
In recent years, artificial intelligence is gradually put into business application in many aspects, to promote the further of business
Development.For example, monitor the volume of the flow of passengers, identification client characteristics in the environment of market and determine customer priorities etc..Age is client
One important feature, in many situations, it is desirable to be able to identify the age of client, so that it is determined that target customers, to carry out
Targeted business promotion etc..In general, can determine client age by recognition of face.However it specific is answered some
With under scene, such as in the environment of market, due to flow of the people is big, movement speed is fast and moving direction is random etc., camera shooting
Head is often difficult to be accurately captured the entire facial information of each object, therefore cannot accurately differentiate the age of each object.
A kind of existing technical solution is to collect the video for largely covering various scenes, then by manually come to disengaging pair
The age of elephant is judged.Later, the data result that can be provided with face recognition algorithms compares, to find algorithm
Defect improves recognition success rate and accuracy to improve algorithm.However, this prior art relies basically on IPC (net
Network camera) algorithm promotion, be limited by the development of face recognition technology, rely solely on face recognition algorithms in a short time still
It is difficult to fundamentally improve age recognition accuracy.
Summary of the invention
In view of above-mentioned prior art situation, the application proposes a kind of method, apparatus and electronic equipment for identifying the human body age,
It can identify the age of object by many algorithms, improve recognition success rate.
According to an exemplary embodiment, a kind of method for identifying the human body age is provided, can include: identification current frame image
In human body head；Previous frame figure based on the preset quantity before the current frame image and the current frame image
Picture determines the swing parameter on the head of the human body；The first age of the human body is determined based on the swing parameter.
According to another exemplary embodiment, a kind of device identifying the human body age is provided, can include: human body head identification
Unit is configured to the head of the human body in identification current frame image；Parameter determination unit is swung, the present frame is configured to
The preceding frame image of preset quantity before image and the current frame image determines the swing ginseng on the head of the human body
Number；And the first age recognition unit, it is configured to the first age that the swing parameter determines the human body.
According to another exemplary embodiment, a kind of electronic equipment is provided, can include: camera, for obtaining human body
Image；And processor, the computer program instructions in run memory are configured to execute the above method.
According to another exemplary embodiment, a kind of computer readable storage medium is provided, computer journey can be stored with thereon
Sequence instruction, the computer program instructions make the processor execute the above method when being run by processor.
The above and other feature and advantage of the application will become aobvious and easy from the following description to exemplary embodiment
See.
Detailed description of the invention
The exemplary embodiment of the application is described in more detail in conjunction with the accompanying drawings, the application above-mentioned and its
His purpose, feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present application, and structure
At part of specification, it is used to explain the application together with the embodiment of the present application, does not constitute the limitation to the application.Attached
In figure, identical reference label typically represents same parts or step.
Fig. 1 illustrates the flow charts according to the age recognition methods of one exemplary embodiment of the application.
Fig. 2 illustrates the schematic diagram of the determination head oscillation parametric procedure according to one exemplary embodiment of the application.
Fig. 3 illustrates the flow chart of the age recognition methods according to one exemplary embodiment of the application.
Fig. 4 illustrate according to one exemplary embodiment of the application really dating identification stability method flow chart.
Fig. 5 illustrates the functional block diagram of the age identification device according to one exemplary embodiment of the application.
Fig. 6 illustrates the structural block diagram of the electronic equipment according to one exemplary embodiment of the application.
Specific embodiment
In the following, the exemplary embodiment that the application will be described in detail by referring to the drawings.Obviously, described embodiment is only
It is a part of the embodiment of the application, rather than the whole embodiments of the application, it should be appreciated that the application is not shown by described herein
The limitation of example embodiment.
As described above, there are the following problems for existing age identifying schemes:
1. place one's entire reliance upon face recognition technology, and is difficult to collect complete facial image number in many application scenarios
According to；
2. face recognition algorithms are difficult to significantly improve the accuracy rate of age identification in a short time；
3. collecting the video for largely covering various scenes, is judged with the age manually to disengaging object, automate journey
Spend low, person works' amount is big, can not get rid of the associated disadvantage of artificial treatment.
In view of the above-mentioned drawbacks in the prior art, the basic conception of the application is to realize the age using more novel algorithm
Intelligent recognition.For example, the motion feature of human body, such as human body head can be passed through when face recognition algorithms cannot be used
Swing parameter, to identify the human body age.The mobile behavior of the human body of all ages and classes has its characteristic feature, and head is energy
Enough human body parts for most conveniently capturing human motion feature.In addition, also utilizing some auxiliary in some embodiments of the present invention
Means realize that the age identifies, such as human motion speed, crowd's information etc., to improve the success rate of age identification.One
In a little embodiments, additionally uses recognition result judgement of stability, improves the age based on means such as the weighted averages of application scenarios
The accuracy of identification.By using the solution of the present invention, with traditional single age recognition mode phase dependent on recognition of face
Than the success rate and accuracy of age identification is greatly improved.
It should be noted that the above-mentioned basic conception of the application can be applied not only to the business ring such as market, shopping center
In border, it can also be applied in other scenes, such as stream of people's age of the scenes such as community, park, crossing identifies etc..
After describing the basic principle of the application, carry out the various non-limits for specifically introducing the application below with reference to the accompanying drawings
Property embodiment processed.
Fig. 1 illustrates the flow charts according to the age recognition methods of one exemplary embodiment of the application.As shown in Figure 1, year
Age recognition methods 100 may begin at step S110, identify the head of the human body in current frame image.Current frame image can be for example
By any frame image in stream of people's video of IP Camera (IPC) capture, it can use various existing or following open
The algorithm of hair identifies the human body head in current frame image, image recognition algorithm such as, but not limited to neural network based
Deng.In step s 110, the head of each human body in image, such as positive head, lateral head and back side head can be identified,
And it is not limited to whether it has complete face.That is, in the method 100, can only lead to independent of recognition of face
Human body head is crossed to carry out age identification, described in face specific as follows.
With continued reference to Fig. 1, in step S112, based on the predetermined quantity between current frame image and the current frame image
Preceding frame image determines the swing parameter of human body head.Here, swinging parameter may include in such as amplitude of fluctuation and hunting frequency
At least one, for example, swing parameter may include amplitude of fluctuation, can also only include hunting frequency, can also include simultaneously
Amplitude of fluctuation and hunting frequency, wherein swinging parameter based on multiple image and can track the movement on head and realize.Fig. 2
Show the schematic diagram for determining the process for swinging parameter.As shown in Fig. 2, several before current frame image and current frame image
In preceding frame image (being referred to as image 10), human body head is had identified, as shown in block 11, and can determine human body head
The center position 12 in portion.By tracking the movement on human body head, the movement of the central point 12 on human body head can be determined
Track is the amplitude of fluctuation and hunting frequency that can determine human body head based on the motion track.
Referring back to Fig. 1, in step S114, the human body age can be determined based on parameter is swung.For convenience,
The human body age determined based on swing parameter was known as the first age below.By having counted great amount of samples discovery, human body is being moved
Swing parameter when dynamic, typically the swing parameter of human body head, there are correlations with the human body age.In general, human body
Age is bigger, and head oscillation frequency is lower；The human body age is smaller, and head oscillation frequency is higher.On the other hand, a middle-aged person moves
Figure is more steady when dynamic, and head oscillation amplitude is lower, and the age is higher and lower, and head oscillation amplitude can all increase.Based on this
A little features can be used and swing parameter such as one or more of amplitude of fluctuation and hunting frequency to determine the human body age.
Step S114 can be realized in several ways.Such as in one example, empirical data can be had previously been based on to build
Vertical one will swing parameter look-up table associated with the human body age, by directly determining the human body age with reference to the look-up table.This
Kind implementation is relatively simple, it is easy to accomplish, and related calculation amount is small, is conducive to save hardware resource.Show another
It can be directly input with human body head motion track with one neural network model of precondition, the neural network model in example,
It is output with the age.It is thus possible to track 13 shown in Fig. 2 is directly input to the neural network model, to determine human body year
Age.Here, head oscillation parameter is embodied in track 13, therefore the neural network model is substantially also based on swing parameter and comes
Determine the human body age.Although the operand that this implementation needs is larger, age prediction can be further increased
Accuracy.
In above-mentioned steps, swing parameter such as amplitude of fluctuation and/or hunting frequency based on human body head have determined people
First age of body.Compared with such as human body face, human body head is the characteristics of human body captured more easily by camera, especially
It is when for example flow of the people is larger, human body face is likely to be blocked by other people, or cannot be by due to the direction of travel for people
Camera captures, and human body head feature is then easy to accurately be captured, such as by the way that camera is mounted on high bit
Set place, can capture the head feature of most of human bodies in intensive people flow, so can the movement based on head feature and extract
Head oscillation parameter, such as amplitude of fluctuation and/or hunting frequency.As previously mentioned, amplitude of fluctuation and hunting frequency are and human body year
Two parameters that age is closely related are embodied in human body head because human body has different motion features at the different ages
Swing parameter such as amplitude and frequency on.Therefore, by determining human body First Year based on amplitude of fluctuation and/or hunting frequency
The success rate of age identification can be improved in age.
As previously mentioned, face can be used for the identification of human body age in the case where that can capture full facial, and
Accuracy with higher.Therefore, in some embodiments, it can also identify the face in current frame image, and be based on institute
The face of identification determines the human body age.For ease of description, the human body age determined based on recognition of face is known as the below
Two ages.It is appreciated that the age identification process based on face can before the step S110-S114 of Fig. 1, later or with
It is carried out at least partly overlappingly, and what the present invention was not limited to them executes sequence.Equally, permitted for what is be discussed in detail below
Other more steps, the present invention do not limit its yet and execute sequence, these steps can successively be carried out by different order, or can be simultaneously
Row executes, unless it based on context can be determined with respect to execution sequence.
In some embodiments of the invention, the human body age can also be identified by a variety of householder methods, it below will ginseng
It is described in detail according to Fig. 3.As shown in figure 3, can determine the number in current frame image in step S116, this can be such as
Using the human body head recognition result of step S110, the quantity on the head identified is counted to realize.Next in step
In rapid S118, judge whether number is more than first threshold.If being no more than first threshold, illustrates that flow of the people is smaller, at this time may be used
To execute the identification of auxiliary age using velocity information for example described below and group information；On the other hand, if it exceeds
One threshold value then illustrates that flow of the people is larger, and larger limitation of everyone movement at this time by surrounding population is then difficult to according to individual
Movement speed or community information carry out the identification of auxiliary age, and need to consider other age means of identification.By being based on
Flow of the people takes different age identifying schemes for different flows of the people to be finely divided to scene, can further mention
The accuracy of high age identification, and improve the universality that the solution of the present invention is directed to different scenes.
With continued reference to Fig. 3, in the step s 120, it is less than or equal to first threshold in response to number, present frame can be based on
Image and several preceding frame images determine the movement speed of human body, and then in step S122, the movement speed based on human body
To determine the human body age.For convenience, the human body age determined based on human motion speed is hereinafter known as third year
Age.In general, the age is bigger, movement speed is slower；Age is smaller, and movement speed is faster.It is also possible to which statistics is a large amount of in advance
Sample establishes being associated between movement speed and age, can also consider other factors such as density of stream of people etc. simultaneously.In this way,
It can be based on human motion speed in step S122, or can be combined with other auxiliary informations such as density of stream of people, come true
Determine the human body age.It in some embodiments, can be with when determining the human body age based on human motion speed in step S122
Consider relative velocity.For example, the movement speed of current human can be compared with the movement speed of surrounding body, its speed is determined
Difference is spent, the movement speed of human body and the speed difference relative to surrounding body can be taken into consideration, then to determine human body year
Age.In general, the human body age is smaller, relative velocity is faster.Velocity and acceleration is all the important characterization ginseng of human motion
Number, it is closely related with the human body age.By determining the human body age based on speed and/or acceleration, can be further improved
The success rate and accuracy of age identification.
In some embodiments, determine that number is less than or equal to first threshold in response to step S118, it optionally, can be with
The group where human body is determined based on present frame and previous frame in step S124.Multiple human body categories can be determined there are many mode
In the group that one is gone together.It is closer and human body that motion track (direction) is roughly the same is a group for example, can identify,
It can identify the several artificial groups, etc. talked.After identifying group, in step S126, it can be based on
Intragroup information about firms determines the human body age.For convenience, hereinafter by based on Group Membership Information and determination
The human body age was known as the 4th age.For example, can determine the year of current human if intragroup multiple member ages are close
Age is also close with other members.For another example can determine current human if there are two a middle-aged person and a children in group
For the elderly, they belong to the same family.It is different that age identification is carried out from the information above based on human body itself, group's letter
Breath is to carry out the identification of human body age using the information of other members in group, therefore can provide human body itself to provide
Additional information further increases the accuracy of age identification.
Described above is the human body age is identified by multiple means, first, second, third and fourth has been determined respectively
Age.It is understood that by video image realize the above-mentioned age identification when, due to human motion and ambient lighting etc. because
The influence of element, recognition result are likely to occur fluctuation.For example, can use aforementioned for the video image including multiple image
Method determined first, second, third or the 4th the age multiple age values, and these age values are different each other.At this point,
The stability of recognition result becomes judgement and identifies whether accurately to consider.Fig. 4, which is shown based on stability, judges recognition result
The method flow diagram of accuracy.As shown in figure 4, for multiple image, can use in aforementioned identification algorithm in step S142
Any one, determine corresponding first, second, third or the 4th multiple age values at age can then in step S144
Whether reach second threshold with the stability of the multiple age value of determination, i.e., whether identified age value is stable.For example, can be with
Determine ratio shared by the age value of most frequent appearance in these age values.For example, if its ratio reaches second threshold, such as
66.7%, 70%, 75%, 80% etc., then it can confirm in step S146 and identify successfully, and using the stationary value as being known
Other human body age.On the other hand, if recognition result stability is not up to the preset threshold, such as identified multiple ages
Value is evenly distributed in a larger range, then can confirm recognition failures in step S148.In this way, it is lower to remove accuracy
Recognition result, and only include the higher recognition result of accuracy, so that it is guaranteed that the reliability of recognition result.
Referring back to Fig. 3, after step S126, or when determining that number is more than first threshold in step S118,
Step S128 can be then proceeded to, determines that the age identifies whether success.When proceeding to S128 from step S118, it is only necessary to which determination is
It is no successfully to identify the first age and the second age；When proceeding to S128 from step S126, then need to determine whether successfully to identify
First, second, third and fourth age.The standard that success identifies is as having identified stable knot referring to as Fig. 4 description
Fruit.If recognition result is unstable, or do not identify at all it is any as a result, if all think age recognition failures.
In step S128, at least one of first to fourth age is successfully identified as long as determining, then it is assumed that success
The human body age is identified, step S130 can be continued to progress, according to application scenarios, the age that success is identified is weighted and averaged,
To determine the final age of human body.By the age weighted average identified that will succeed, various factors can be comprehensively considered to the age
The contribution of recognition result improves the whole accuracy rate of identification model to reduce the error of age identification.In adding for step S130
When weight average, one or more of first to fourth age of successfully identification is not only considered, it is also contemplated that be based on applied field
The basal year level that scape determines.For example, client is mostly student group, then basal year level is smaller, for example, if it is accessory shop
12-16 years old；If it is market, customer group is mostly young man, such as basal year level can be 22-30 years old.The final age can root
It is determined according to following formula:
Final age=+ w5* the 4th year+w2*+w4* third age at the second age the first age+w3* of w1* basal year level
Age.
Wherein, w1 to w5 is the weight parameter at corresponding age.When fail identify some age when, can correspondingly adjust
Parameter w1 to w5 is saved, to avoid influence of the age to the final age for the identification that fails.It is then possible to proceed to step
S140 terminates the processing to present frame, continues with next frame.
If confirming any one in first to fourth age of identification that fails in step S128, then it is assumed that this
The age recognition failures of individual.In some embodiments, as shown in step S132, which can be included into recognition failures people
Group, and count the number of recognition failures crowd.In step S134, it can be determined that whether the number of recognition failures crowd reaches
Third threshold value.If third threshold value has not yet been reached, to step S140, if having reached third threshold value, that is, one is had accumulated
When quantitative recognition failures human body, then it can be determined using predetermined age distribution in recognition failures crowd in step S136
The age of each human body.For example, predetermined age distribution can be the reference age distribution for carrying out the scene of age identification, such as quotient
The age distribution of registered members, under the age distribution of community resident or similar scene before age distribution for identifying etc..
After the age of human body has been determined by predetermined age distribution, step S140 can be proceeded to, continues the processing of next frame.
Fig. 5 illustrates the functional block diagram of the device 200 at the identification human body age according to one exemplary embodiment of the application.Such as
Shown in Fig. 5, age identification device 200 may include human body head recognition unit 202, swing parameter determination unit 204 and First Year
Age recognition unit 206.Human body head recognition unit 202 can be used to identify the head of the human body in current frame image, swing parameter
Determination unit 204 can be used for the preceding frame image based on the preset quantity before current frame image and current frame image, determine
The swing parameter of the human body head identified, such as amplitude of fluctuation and hunting frequency etc..First age recognition unit 206 then can be used
In the first age for identifying human body based on identified swing parameter.
In some instances, optionally, identify that the device 200 at human body age may also include in current frame image for identification
Human body face face identification unit 208 and the second year at the second age for determining human body based on the face identified
Age recognition unit 210.
In some instances, optionally, it identifies that the device 200 at human body age may also include counting unit 212, is used for really
Number in settled prior image frame；Speed determining unit 214 is used to be less than or equal to first threshold in response to number, from working as
Prior image frame and preceding frame image determine the movement speed of human body；And third age recognition unit 216, it is used for based on human body
Movement speed determine third age of human body.In some embodiments, third age recognition unit 216 is also based on people
The movement speed of body and the third age that human body is determined relative to the relative moving speed of surrounding body.In some instances,
Optionally, it identifies that the device 200 at human body age may also include group identification unit 218, is used to be less than in response to number or wait
In first threshold, the group that human body belongs to is determined based on current frame image and preceding frame image；And the 4th age recognition unit
220, it is used to determine the 4th age of human body based on the information about firms in group.
It should be understood that such as -4 descriptions referring to Fig.1 of front, first to fourth age recognition unit, 206,210,216 and
220 can also determine the stability of its recognition result, determine whether to realize and successfully identify.
With continued reference to Fig. 5, in some instances, optionally, the device 200 at identification human body age may also include weighted average
Unit 222, the first age, the second age, third age and the 4th age that success can be identified are weighted and averaged, to obtain
The final age of human body.In weighted average, it is also contemplated that the human body basal year level determined by application scenarios, i.e. average year
Age.
In some instances, optionally, identify that the device 200 at human body age may also include recognition failures statistic unit 224,
It, which can count to fail, identifies the recognition failures crowd at its age；And pre- dating allocation unit 226, it is used to respond
Reach a threshold value in the quantity of recognition failures crowd, determines the 5th of the human body in recognition failures crowd the using predetermined age distribution
Age.
The concrete function of each unit and module in above-mentioned age identification device 200 and operation have been described above with reference to figure
It is discussed in detail in the age recognition methods of 1 to Fig. 4 description, therefore is only briefly explained here, and it is detailed that its repetition is omitted
Thin description.It may be implemented in image processing electronics according to the age identification device 200 of the embodiment of the present application, such as can be with
It is integrated into image processing electronics as a software module and/or hardware module.
Described above is according to some embodiments of the application identification human body age method and apparatus, it should be appreciated that it is right
It, can there are many variations in form and details in embodiment described above.For example, in above method and device, really
The fixed age can be accurate age value, be also possible to the age bracket or the probability distribution at age of estimation.In addition,
In above method and device, it can be combined with other auxiliary informations to carry out age identification, such as height, gender etc., all
It is that those skilled in the art are readily apparent that and implement under teachings of the present application, therefore should be regarded as falling in appended claims limit
In fixed the scope of the present invention.
Fig. 6 shows the structural block diagram of the example electronic device 300 of achievable age identification device 200.As shown in figure 5,
Electronic equipment 300 may include processor 310, camera 320 and memory 330, they are connected to each other by bus 360.
Processor 310 can be central processing unit (CPU) or have data-handling capacity and/or instruction execution capability
Other forms processing unit, and can control the other assemblies in electronic equipment to execute desired function.
The image of the available identification scene of camera 320 comprising one or more human bodies to be identified.
Memory 330 may include various forms of computer readable storage mediums, such as volatile memory and/or non-
Volatile memory.Volatile memory for example may include random access memory (RAM) and/or cache memory
(cache) etc..Nonvolatile memory for example may include read-only memory (ROM), hard disk, flash memory etc..It can in memory 330
To be stored with computer program instructions, processor 310 can run these computer program instructions, to realize the application above
Each embodiment age recognition methods and/or other desired functions.
In some instances, electronic equipment 300 may also include input unit 340 and output unit 350.Input unit 340
With output unit 350 can be performed it is various output and input function, such as input unit 340 is subjected to the registered members of business place
The result identified before under data, community resident data or similar scene waits until that output unit 350 can export the age
Recognition result etc..Processor 310 is connect by bus 360 with modules or unit, to control their operation.
Other than the above method and equipment, embodiments herein can also be computer program product comprising meter
Calculation machine program instruction, it is above-described according to this that the computer program instructions execute processor
Apply for the step in the age recognition methods of embodiment.
The computer program product can be write with any combination of one or more programming languages for holding
The program code of row the embodiment of the present application operation, programming language includes object oriented program language, such as Java,
C++ etc. further includes conventional procedural programming language, such as " C " language or similar programming language.Program code
It can fully execute on the user computing device, partly execute, held as an independent software package on a user device
Part executes on a remote computing or completely in remote computing device or service on the user computing device for row, part
It is executed on device.
In addition, embodiments herein can also be computer readable storage medium, it is stored thereon with computer program and refers to
It enables, it is above-described according to the embodiment of the present application that the computer program instructions execute processor
Age recognition methods in step.
The computer readable storage medium can be using any combination of one or more readable mediums.Readable medium can
To be readable signal medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can include but is not limited to electricity, magnetic, light, electricity
Magnetic, the system of infrared ray or semiconductor, device or device, or any above combination.Readable storage medium storing program for executing it is more specific
Example (non exhaustive list) includes: the electrical connection with one or more conducting wires, portable disc, hard disk, random access memory
Device (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc
Read-only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The basic principle of the application is described in conjunction with specific embodiments above, however, it is desirable to, it is noted that in this application
The advantages of referring to, advantage, effect etc. are only exemplary rather than limitation, must not believe that these advantages, advantage, effect etc. are the application
Each embodiment is prerequisite.In addition, detail disclosed above is merely to exemplary effect and the work being easy to understand
With, rather than limit, it is that must be realized using above-mentioned concrete details that above-mentioned details, which is not intended to limit the application,.
Device involved in the application, device, equipment, system block diagram only as illustrative example and be not intended to
It is required that or hint must be attached in such a way that box illustrates, arrange, configure.As those skilled in the art will appreciate that
, it can be connected by any way, arrange, configure these devices, device, equipment, system.Such as "include", "comprise", " tool
" etc. word be open vocabulary, refer to " including but not limited to ", and can be used interchangeably with it.Vocabulary used herein above
"or" and "and" refer to vocabulary "and/or", and can be used interchangeably with it, unless it is not such that context, which is explicitly indicated,.Here made
Vocabulary " such as " refers to phrase " such as, but not limited to ", and can be used interchangeably with it.
It may also be noted that each component or each step are can to decompose in the device of the application, device and method
And/or reconfigure.These decompose and/or reconfigure the equivalent scheme that should be regarded as the application.
The above description of disclosed aspect is provided so that any person skilled in the art can make or use this
Application.Various modifications in terms of these are readily apparent to those skilled in the art, and are defined herein
General Principle can be applied to other aspect without departing from scope of the present application.Therefore, the application is not intended to be limited to
Aspect shown in this, but according to principle disclosed herein and the consistent widest range of novel feature.
In order to which purpose of illustration and description has been presented for above description.In addition, this description is not intended to the reality of the application
It applies example and is restricted to form disclosed herein.Although already discussed above multiple exemplary aspects and embodiment, this field skill
Its certain modifications, modification, change, addition and sub-portfolio will be recognized in art personnel.
Claims (14)
1. a kind of method for identifying the human body age, comprising:
Identify the head of the human body in current frame image；
Based on the preceding frame image of the preset quantity before the current frame image and the current frame image, the people is determined
The swing parameter on the head of body；
The first age of the human body is determined based on the swing parameter.
2. the method for claim 1, wherein the parameter that swings includes at least one in amplitude of fluctuation and hunting frequency
It is a.
3. the method for claim 1, wherein determining that the swing parameter on the head of the human body includes:
Determine the center on the head of the human body；
The position at the center on head described in the preceding frame image based on the current frame image and the preset quantity determines institute
State the motion track on head；And
The swing parameter on the head is determined based on the motion track.
4. the first age for the method for claim 1, wherein determining the human body based on the swing parameter includes:
With reference to the age-related look-up table of the swing parameter by human body head, to determine the first age of the human body.
5. the method as described in claim 1, further includes:
Identify the face of the human body in the current frame image；And
The second age of the human body is determined based on the face identified.
6. method as claimed in claim 5, further includes:
Determine the number in the current frame image；
It is less than or equal to first threshold in response to the number, described in the current frame image and preceding frame image determination
The movement speed of human body；And
The third age of the human body is determined based on the movement speed.
7. method as claimed in claim 6, wherein the third age for determining the human body based on the movement speed includes:
The movement speed of the human body is compared with the movement speed of surrounding body, to determine speed difference；And
The third age of the human body is determined based on the movement speed and the speed difference.
8. method as claimed in claim 6, further includes:
It is less than or equal to first threshold in response to the number, institute is determined based on the current frame image and the preceding frame image
State the group that human body belongs to；And
The 4th age of the human body is determined based on the information about firms in the group.
9. method according to claim 8, wherein determine first age, second age, the third age and
The step of at least one in 4th age includes:
It is determined in first age, second age, the third age and the 4th age based on multiple image
At least one multiple age values；
When the stability of the multiple age value reaches second threshold, determine that the age identifies successfully, and by the multiple year
Age of the stationary value as the human body in age value, otherwise, it determines age recognition failures.
10. method according to claim 8, further includes:
The age that success identifies in first age, second age, the third age and the 4th age is added
Weight average, to obtain the final age of the human body.
11. method according to claim 8, further includes:
When the first age, the second age, third age and four ages of the determining human body that fails, by the human body
It is added to recognition failures crowd；
Reach third threshold value in response to the quantity of the recognition failures crowd, determines the recognition failures using predetermined age distribution
5th age of the human body in crowd.
12. a kind of device for identifying the human body age, comprising:
Human body head recognition unit is configured to the head of the human body in identification current frame image；
Swing parameter determination unit, the preset quantity being configured to before the current frame image and the current frame image
Preceding frame image, determine the swing parameter on the head of the human body；And
First age recognition unit is configured to the first age that the swing parameter determines the human body.
13. a kind of electronic equipment, comprising:
Camera, for obtaining the image of human body；And
Processor is configured to the computer program instructions in run memory and is required described in any one of 1-11 with perform claim
Method.
14. a kind of computer readable storage medium is stored thereon with computer program instructions, the computer program instructions are in quilt
Processor makes the processor execute such as method of any of claims 1-11 when running.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811303378.3A CN109492571B (en) | 2018-11-02 | 2018-11-02 | Method and device for identifying human age and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811303378.3A CN109492571B (en) | 2018-11-02 | 2018-11-02 | Method and device for identifying human age and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109492571A true CN109492571A (en) | 2019-03-19 |
| CN109492571B CN109492571B (en) | 2020-10-09 |
Family
ID=65693763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811303378.3A Active CN109492571B (en) | 2018-11-02 | 2018-11-02 | Method and device for identifying human age and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109492571B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993150A (en) * | 2019-04-15 | 2019-07-09 | 北京字节跳动网络技术有限公司 | The method and apparatus at age for identification |
| CN110852814A (en) * | 2020-01-14 | 2020-02-28 | 深圳惠通天下信息技术有限公司 | Advertisement delivery self-service system and method |
| CN112906525A (en) * | 2021-02-05 | 2021-06-04 | 广州市百果园信息技术有限公司 | Age identification method and device and electronic equipment |
| WO2022048572A1 (en) * | 2020-09-02 | 2022-03-10 | 杭州海康威视数字技术股份有限公司 | Target identification method and apparatus, and electronic device |
| WO2024008009A1 (en) * | 2022-07-05 | 2024-01-11 | 华为技术有限公司 | Age identification method and apparatus, electronic device, and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101206538A (en) * | 2006-12-18 | 2008-06-25 | 郑小军 | Hand-drawing pen mouse with flat end, movable head and movable double-lever part |
| CN101388080A (en) * | 2008-10-23 | 2009-03-18 | 北京航空航天大学 | Passerby gender classification method based on multi-angle information fusion |
| WO2016090522A1 (en) * | 2014-12-12 | 2016-06-16 | Xiaoou Tang | Method and apparatus for predicting face attributes |
| CN105787440A (en) * | 2015-11-10 | 2016-07-20 | 深圳市商汤科技有限公司 | Security protection management method and system based on face features and gait features |
| CN105893966A (en) * | 2016-04-04 | 2016-08-24 | 上海大学 | Human body gait information collection and gait form classification and identification system and method |
| WO2016183380A1 (en) * | 2015-05-12 | 2016-11-17 | Mine One Gmbh | Facial signature methods, systems and software |
| CN106682637A (en) * | 2016-12-30 | 2017-05-17 | 深圳先进技术研究院 | Display item attraction degree analysis and system |
| CN106951871A (en) * | 2017-03-24 | 2017-07-14 | 北京地平线机器人技术研发有限公司 | Movement locus recognition methods, device and the electronic equipment of operating body |
| CN107909026A (en) * | 2016-11-30 | 2018-04-13 | 深圳奥瞳科技有限责任公司 | Age and gender assessment based on the small-scale convolutional neural networks of embedded system |
| US20180181196A1 (en) * | 2016-12-22 | 2018-06-28 | Samsung Electronics Co., Ltd. | Method for displaying image, storage medium, and electronic device |
-
2018
- 2018-11-02 CN CN201811303378.3A patent/CN109492571B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101206538A (en) * | 2006-12-18 | 2008-06-25 | 郑小军 | Hand-drawing pen mouse with flat end, movable head and movable double-lever part |
| CN101388080A (en) * | 2008-10-23 | 2009-03-18 | 北京航空航天大学 | Passerby gender classification method based on multi-angle information fusion |
| WO2016090522A1 (en) * | 2014-12-12 | 2016-06-16 | Xiaoou Tang | Method and apparatus for predicting face attributes |
| WO2016183380A1 (en) * | 2015-05-12 | 2016-11-17 | Mine One Gmbh | Facial signature methods, systems and software |
| CN105787440A (en) * | 2015-11-10 | 2016-07-20 | 深圳市商汤科技有限公司 | Security protection management method and system based on face features and gait features |
| CN105893966A (en) * | 2016-04-04 | 2016-08-24 | 上海大学 | Human body gait information collection and gait form classification and identification system and method |
| CN107909026A (en) * | 2016-11-30 | 2018-04-13 | 深圳奥瞳科技有限责任公司 | Age and gender assessment based on the small-scale convolutional neural networks of embedded system |
| US20180181196A1 (en) * | 2016-12-22 | 2018-06-28 | Samsung Electronics Co., Ltd. | Method for displaying image, storage medium, and electronic device |
| CN106682637A (en) * | 2016-12-30 | 2017-05-17 | 深圳先进技术研究院 | Display item attraction degree analysis and system |
| CN106951871A (en) * | 2017-03-24 | 2017-07-14 | 北京地平线机器人技术研发有限公司 | Movement locus recognition methods, device and the electronic equipment of operating body |
Non-Patent Citations (11)
| Title |
|---|
| CHUEN, BENZ KEK YEO, ET AL.: "A preliminary study of gait-based age estimation techniques", 《ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA)》 * |
| HSUNG, TAI-CHIU， ET.AL: "Recording of Natural Head Position Using Stereophotogrammetry: A New Technique and Reliability Study", 《JOURNAL OF ORAL AND MAXILLOFACIAL SURGERY》 * |
| LEE, HENG-JU,ET.AL: "Detection of gait instability using the center of mass and center of pressure inclination angles", 《ARCHIVES OF PHYSICAL MEDICINE AND REHABILITATION》 * |
| NABILA, M., ET.AL: "Gait-based human age classification using a silhouette model", 《IET BIOMETRICS》 * |
| PUNYANI, P.,ET.AL: "A Comparison Study of Face, Gait and Speech Features for Age Estimation", 《ADVANCES IN ELECTRONICS, COMMUNICATION AND COMPUTING》 * |
| XIANG LI，ET.AL,: "Gait-based human age estimation using age group-dependent manifold learning and regression", 《MULTIMED TOOLS APPLLICATION》 * |
| 李立: "蛇形机器人水下运动仿真及控制的研究", 《中国优秀硕士论文全文数据库》 * |
| 李翔: "基于人体关节点的步态识别算法研究", 《优秀硕士论文全文数据库 信息科技辑》 * |
| 杨畅: "基于步态监测的年龄识别问题研究与实现", 《优秀硕士论文全文数据库 信息科技辑》 * |
| 谢春华: "基于人脸图像的年龄估计方法研究", 《优秀硕士论文全文数据库 信息科技辑》 * |
| 黄秋红: "三维姿势与步态分析在不同年龄健康人群平衡评估中的应用", 《临床研究》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993150A (en) * | 2019-04-15 | 2019-07-09 | 北京字节跳动网络技术有限公司 | The method and apparatus at age for identification |
| CN110852814A (en) * | 2020-01-14 | 2020-02-28 | 深圳惠通天下信息技术有限公司 | Advertisement delivery self-service system and method |
| WO2022048572A1 (en) * | 2020-09-02 | 2022-03-10 | 杭州海康威视数字技术股份有限公司 | Target identification method and apparatus, and electronic device |
| CN112906525A (en) * | 2021-02-05 | 2021-06-04 | 广州市百果园信息技术有限公司 | Age identification method and device and electronic equipment |
| CN112906525B (en) * | 2021-02-05 | 2024-10-18 | 广州市百果园信息技术有限公司 | Age identification method and device and electronic equipment |
| WO2024008009A1 (en) * | 2022-07-05 | 2024-01-11 | 华为技术有限公司 | Age identification method and apparatus, electronic device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109492571B (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492571A (en) | Identify the method, apparatus and electronic equipment at human body age | |
| CN108090458B (en) | Human body falling detection method and device | |
| CN106295567B (en) | A kind of localization method and terminal of key point | |
| Hoang Ngan Le et al. | Robust hand detection and classification in vehicles and in the wild | |
| Gall et al. | Hough forests for object detection, tracking, and action recognition | |
| US20170193286A1 (en) | Method and device for face recognition in video | |
| CN108351967A (en) | A kind of plurality of human faces detection method, device, server, system and storage medium | |
| CN109447156B (en) | Method and apparatus for generating a model | |
| CN110222686B (en) | Object detection method, object detection device, computer equipment and storage medium | |
| CN108224691A (en) | A kind of air conditioner system control method and device | |
| US20140348391A1 (en) | Snow classifier context window reduction using class t-scores and mean differences | |
| Neumann et al. | Future event prediction: If and when | |
| CN111353451A (en) | Battery car detection method and device, computer equipment and storage medium | |
| WO2013119420A1 (en) | Method and apparatus for unattended image capture | |
| CN110751675B (en) | Urban pet activity track monitoring method based on image recognition and related equipment | |
| CN106663196A (en) | Computerized prominent person recognition in videos | |
| KR102550964B1 (en) | Apparatus and Method for Measuring Concentrativeness using Personalization Model | |
| WO2022062968A1 (en) | Self-training method, system, apparatus, electronic device, and storage medium | |
| US20080175447A1 (en) | Face view determining apparatus and method, and face detection apparatus and method employing the same | |
| CN109977735A (en) | Move the extracting method and device of wonderful | |
| CN108319916A (en) | Face identification method, device, robot and storage medium | |
| CN110414544B (en) | Target state classification method, device and system | |
| Hammam et al. | Real-time multiple spatiotemporal action localization and prediction approach using deep learning | |
| Salma et al. | Smart parking guidance system using 360o camera and haar-cascade classifier on iot system | |
| CN109063790A (en) | Object identifying model optimization method, apparatus and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240905 Address after: 207S, Building 5, Northwest Shenjiu Science and Technology Entrepreneurship Park, Intersection of Taohua Road and Binglang Road, Fubao Community, Fubao Street, Futian District, Shenzhen City, Guangdong Province 518000 Patentee after: Shenzhen Sweet Potato Robot Co.,Ltd. Country or region after: China Address before: 100080 No. 1, No. 3, Zhongguancun Street, Haidian District, Beijing 318 Patentee before: BEIJING HORIZON ROBOTICS TECHNOLOGY RESEARCH AND DEVELOPMENT Co.,Ltd. Country or region before: China |