CN108446681A - Pedestrian's analysis method, device, terminal and storage medium - Google Patents
Pedestrian's analysis method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN108446681A CN108446681A CN201810443368.3A CN201810443368A CN108446681A CN 108446681 A CN108446681 A CN 108446681A CN 201810443368 A CN201810443368 A CN 201810443368A CN 108446681 A CN108446681 A CN 108446681A
- Authority
- CN
- China
- Prior art keywords
- facial image
- personnel
- default
- face database
- identifier
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- G06V40/172—Classification, e.g. identification
- G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
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)
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
Abstract
A kind of pedestrian's analysis method, including：Obtain the human face data preset in the first preset time period in face database；Identify whether the facial image in the default face database is the facial image for presetting the registered personnel in the first register base；If so, the facial image for being determined as the registered personnel in the default face database is stamped first identifier；If it is not, then identifying whether the facial image for not stamping the first identifier in the default face database is the facial image for presetting the unregistered personnel in the second register base；If so, the facial image for being determined as unregistered personnel in the default face database is stamped second identifier；Otherwise, it determines for the facial image of None- identified personnel, the facial image of the None- identified is stamped into third mark.The present invention also provides a kind of garden personnel analytical equipment, terminal and storage mediums.The present invention can quickly analyze the pedestrian in wisdom garden, and reduce data storage capacity.
Description
Technical field
The present invention relates to district management technical fields, and in particular to a kind of pedestrian's analysis method, device, terminal and storage are situated between
Matter.
Background technology
Existing pedestrian's analysis in a certain region is typically the face figure obtained every night in preset time period in the past
Piece filters out the face of registered personnel, is clustered to the face of remaining personnel, analyzes unregistered personnel.
If a certain community shares 22 cameras, 22 cameras can acquire 1,000,000 face picture number for every 30 days,
The new unregistered personnel occurred every month have 500, then are carried out to pedestrian according to existing pedestrian's analysis method in region
Analysis, there is following disadvantage：It needs to carry out clustering to 1,000,000 faces daily, while also needing to not step on 500 daily
Note personnel carry out colleague's analysis, and execution efficiency is very low, greatly limit community's number that single server can be supported；Often into
Intelligence community analysis of row needs to store millions of records, and the storage to database is also a greatly challenge；Per natural gift
The unregistered lists of persons being precipitated is all different, even same person, it is also possible to the head portrait analyzed is different, is unfavorable for intelligence
The administrative staff of intelligent garden manage.
Invention content
In view of the foregoing, it is necessary to propose a kind of pedestrian's analysis method, device, terminal and storage medium, it can be quickly
The pedestrian in wisdom garden is analyzed, and reduces data storage capacity.
First aspect present invention provides a kind of pedestrian's analysis method, is applied in terminal, the method includes：
Obtain the human face data preset in the first preset time period in face database；
Identify whether the facial image in the default face database is the people for presetting the registered personnel in the first register base
Face image；
When determining that the facial image in the default face database is the registered personnel in default first register base
When facial image, the facial image for being determined as the registered personnel in the default face database is stamped into first identifier；And
It is the registered personnel preset in the first register base when determining the facial image in the default face database not
Facial image when, identify whether the facial image that the first identifier is not stamped in the default face database is default second
The facial image of unregistered personnel in register base；
When determining that the facial image for not stamping the first identifier in the default face database is described default second to step on
When remembering the facial image of the unregistered personnel in library, the facial image for being determined as unregistered personnel in the default face database is beaten
Upper second identifier；Or
It is described default second when determining the facial image for not stamping the first identifier in the default face database not
When the facial image of the unregistered personnel in register base, determines and do not stamp the first identifier and institute in the default face database
The facial image for stating second identifier is the facial image of None- identified personnel, and the facial image of the None- identified is stamped third
Mark.
According to a preferred embodiment of the present invention, the face figure of the unregistered personnel of default second register base is obtained
As including：
The face images in the second preset time period in the default face database are obtained for the first time；
Identify the facial image of the registered personnel in the face images；
The facial image that the registered personnel are removed in the face images is determined as to the face of unregistered personnel
Image is simultaneously stored in default second register base.
According to a preferred embodiment of the present invention, the method further includes：
Facial image to stamping the third mark in the default face database carries out clustering；
The classification of the None- identified personnel is determined according to the cluster centre obtained after clustering.
According to a preferred embodiment of the present invention, the method further includes：
The quality of multiple facial images of same category of None- identified personnel is calculated according to preset model；
Using the highest facial image of quality as the facial image of the None- identified personnel of corresponding classification.
According to a preferred embodiment of the present invention, in can not know using the highest facial image of quality as corresponding classification
After the facial image of others' member, the method further includes：
The highest facial image of the quality is stored, the remaining facial image of corresponding classification is deleted.
According to a preferred embodiment of the present invention, the method further includes：
Obtain the acquisition time for the facial image that the second identifier is stamped in the default face database；
Obtain the facial image for stamping the first identifier in third preset time period before and after the acquisition time；
By the facial image of the corresponding second identifier of the acquisition time and the first identifier of stamping that obtains
Facial image is associated and stamps the mark of same administrative staff.
According to a preferred embodiment of the present invention, described obtain in the default face database stamps the second identifier
The acquisition time of facial image further includes：The mark of image capture device is obtained simultaneously；
The method further includes：It obtains before and after the acquisition time in third preset time period and the figure with like-identified
As stamping the facial image of the first identifier in facial image that collecting device acquires.
The second aspect of the present invention provides a kind of pedestrian's analytical equipment, runs in terminal, described device includes：
Acquisition module, for obtaining the human face data preset in the first preset time period in face database；
First identification module, whether the facial image in the default face database is in default first register base for identification
Registered personnel facial image；
First identifier module, for determining the facial image in the default face database for institute when first identification module
When stating the facial image of the registered personnel in default first register base, it will be determined as in the default face database described registered
The facial image of personnel stamps first identifier；
Second identification module, for determining that the facial image in the default face database is not when first identification module
When the facial image of the registered personnel in default first register base, identify described in not stamped in the default face database
Whether the facial image of first identifier is the facial image for presetting the unregistered personnel in the second register base；
Second identifier module determines for working as second identification module and does not stamp described in the default face database
When the facial image of one mark is the facial image of the unregistered personnel in default second register base, by the default face
The facial image for being determined as unregistered personnel in library stamps second identifier；
Third mark module determines for working as second identification module and does not stamp described in the default face database
When the facial image of one mark is not the facial image of the unregistered personnel in default second register base, determine described default
The facial image that the first identifier and the second identifier are not stamped in face database is the facial image of None- identified personnel,
The facial image of the None- identified is stamped into third mark.
The third aspect of the present invention provides a kind of terminal, and the terminal includes processor, and the processor is deposited for executing
Pedestrian's analysis method is realized when the computer program stored in reservoir.
The third aspect of the present invention provides a kind of computer readable storage medium, is stored thereon with computer program, described
Pedestrian's analysis method is realized when computer program is executed by processor.
The present invention obtains the human face data preset in the first preset time period in face database；It identifies in the default face database
Facial image whether be registered personnel in default first register base facial image；If so, by the default face database
In be determined as the facial image of the registered personnel and stamp first identifier；Do not have in the default face database if it is not, then identifying
Have and stamps whether the facial image of the first identifier is the facial image for presetting the unregistered personnel in the second register base；If
It is that the facial image for being determined as unregistered personnel in the default face database is stamped into second identifier；Otherwise, it determines for that can not know
The facial image of the None- identified is stamped third mark by the facial image of others' member.Wherein, having stepped in the first register base
Unregistered personnel in note personnel and the second register base are obtained by obtaining the facial image in such as 30 days for the first time, subsequently
Being analyzed pedestrian all only needs to obtain the human face data in the default face database in the first preset time period in such as 24 hours.
It can effectively shorten and calculate the time, improve the calculated performance of computer, clustered repeatedly without the face to clustering, congruency
Under the conditions of energy, more gardens can be supported.
Secondly, the pedestrian in follow-up each pair of first preset time period analyzes, and actual amount of data has only added the
Such as 24 hours human face datas in one preset time period, may only will appear in first preset time period it is few it is new not
Registration of personnel data can greatly save memory space, reduce the difficulty of data base administration data.
In addition, analyze the human face data obtained in the first preset time period, the registered personnel that will identify that, not
Registration of personnel and new unregistered personnel use different marks, and over time, new unregistered personnel can be increasingly
Few, administrator need to only check that different marks can identify whether pedestrian belongs to new unregistered personnel, greatly reduce management
The difficulty of member's management.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the flow chart for pedestrian's analysis method that the embodiment of the present invention one provides.
Fig. 2 is the structure chart of pedestrian's analytical equipment provided by Embodiment 2 of the present invention.
Fig. 3 is the schematic diagram for the terminal that the embodiment of the present invention three provides.
Following specific implementation mode will be further illustrated the present invention in conjunction with above-mentioned attached drawing.
Specific implementation mode
To better understand the objects, features and advantages of the present invention, below in conjunction with the accompanying drawings and specific real
Applying example, the present invention will be described in detail.It should be noted that in the absence of conflict, the embodiment of the present invention and embodiment
In feature can be combined with each other.
Preferably, pedestrian's analysis method of the invention is applied in one or more terminal or server.The end
End be it is a kind of can be according to the instruction for being previously set or storing, the automatic equipment for carrying out numerical computations and/or information processing is hard
Part includes but not limited to microprocessor, application-specific integrated circuit, programmable gate array, embedded device etc..
The terminal can be the computing devices such as desktop PC, notebook, palm PC and cloud server.It is described
Terminal can carry out human-computer interaction with user by modes such as keyboard, mouse, remote controler, touch tablet or voice-operated devices.
Embodiment one
Fig. 1 is the flow chart for pedestrian's analysis method that the embodiment of the present invention one provides.Pedestrian's analysis method is applied to
Terminal.The execution sequence in flow chart shown in Fig. 1 can change according to different requirements, and certain steps can be omitted.
In the present embodiment, pedestrian's analysis method, which can be applied to have, takes pictures or the intelligent terminal of camera function
In, the terminal is not limited to PC, smart mobile phone, tablet computer, the desktop computer or all-in-one machine for being equipped with camera
Deng.
What the garden personnel analysis method can also be applied to be attached by terminal and by network and the terminal
In the hardware environment that server is constituted.Network includes but not limited to：Wide area network, Metropolitan Area Network (MAN) or LAN.The embodiment of the present invention
Pedestrian's analysis method can be executed by server, can also be executed by terminal, can also be and be total to by server and terminal
With execution.
For example, the terminal for needing progress pedestrian's analysis, the method that the present invention can be integrated directly in terminal are carried
Pedestrian's analytic function of confession, or installation is for realizing the client of the method for the present invention.For another example, method provided by the present invention
It can be operated in the equipment such as server in the form of Software Development Kit (Software Development Kit, SDK),
The interface of pedestrian's analytic function is provided in the form of SDK, terminal or other equipment can be realized by the interface of offer to wisdom
The pedestrian of garden analyzes.
As shown in Figure 1, pedestrian's analysis method specifically includes following steps：
Step 101：Obtain the human face data preset in the first preset time period in face database.
First preset time period is the pre-set period, can pre-set one section before current point in time
Period, for example, 24 hours before current point in time or one week etc. before current point in time.It can also pre-set
One time interval, for example, the 00 of the previous day:00 to 24:00.The present invention can be according to the purpose of actual analysis, to described
One preset time period be voluntarily arranged and change.
The default face database is pre-set database, is exclusively used in face number of the storage by the pedestrian of gate inhibition's banister
According to.The human face data may include, but be not limited to：Facial image.Facial image in the default face database is according to acquisition
Time sequencing stored.
In the present embodiment, can equipped with gate inhibition's banister inlet and exit be respectively mounted an image capture device,
Facial image of the acquisition by the pedestrian of the inlet of gate inhibition's banister and the exit by gate inhibition's banister respectively
The facial image of pedestrian.
The quantity of the default face database can be 1, or 2.It, will if pre-set a face database
The facial image of the image capture device acquisition of the inlet and exit of gate inhibition's banister is stored in a face database
In.If pre-set two face databases, the image capture device in the inlet of gate inhibition's banister and exit is acquired
Facial image be stored respectively in two face databases, that is, the facial image for acquiring the image capture device of the inlet
It is stored in default first face database, the facial image that the image capture device in the exit acquires is stored in default second
In face database.The human face data in default first face database can be obtained in first preset time period, can also be obtained
Human face data in default second face database.The people in default first face database and default second face database can also be obtained simultaneously
Face data.
Step 102：Identify whether the facial image in the default face database is registered in default first register base
The facial image of personnel.
Default first register base is pre-set register base, is exclusively used in recording registered personal information.It is described
Registration of personnel information includes, but are not limited to：The name of registered personnel, contact method (including phone number and mailbox etc.), family
The facial image of front yard address and registered personnel.
In the present embodiment, default first register base can be pre-stored in local data base.In other embodiment
In, to save the memory space of terminal, default first register base can be pre-stored in server, the server with
Connection is communicated by wired or wireless mode between the terminal.
In the present embodiment, whether the facial image in the identification default face database is in default first register base
The facial image of registered personnel specifically includes：
1) face area of the facial image in the default face database is detected using default Face datection algorithm.
In the present embodiment, the default face algorithm algorithm is pre-set face algorithm algorithm, the default face
Following at least one method can be used in algorithm algorithm：The method of feature based, the method based on cluster are based on artificial neural network
Method or method based on support vector machines.Pre-set face algorithm algorithm is calculated for existing face algorithm herein
Method, in this not go into detail.
2) face area in the default face database and first between the face area of the registered personnel are calculated
Similarity.
In the present embodiment, can be calculated by the method for template matches face area in the default face database with it is described
The first similarity between the face area of registered personnel.
3) judge whether first similarity is more than default first similarity threshold.
Default first similarity threshold is pre-set first similarity threshold, Ke Yishi, for example, 99%.
When first similarity is more than or equal to default first similarity threshold, the default face is determined
Facial image in library is the facial image of the registered personnel in default first register base；When first similarity is less than institute
When stating default first similarity threshold, it is to preset in the first register base to determine the facial image in the default face database not
The facial image of registration of personnel.
In the present embodiment, each facial image in the default face database need to be preset with described in the first register base
The facial image of each registered personnel matched one by one.If some facial image in the default face database with
First similarity of the facial image of any one registered personnel in default first register base is more than or equal to institute
When stating the first similarity threshold, then it is assumed that the facial image in the default face database is in default first register base
The facial image of registered personnel.If some facial image in the default face database is preset with described in the first register base
The first similarity of facial image of any one registered personnel when being respectively less than first similarity threshold, then it is assumed that institute
It is the facial image for presetting the registered personnel in the first register base to state the facial image in default face database not.
When determining that the facial image in the default face database is the registered personnel in default first register base
When facial image, step 103 is executed；Otherwise, it is described default first when determining the facial image in the default face database not
When the facial image of the registered personnel in register base, step 104 is executed.
Step 103：The facial image for being determined as the registered personnel in the default face database is stamped into first identifier.
The first identifier is used to identify the facial image of the registered personnel in the default face database, i.e., described in mark
Personnel in default face database are registered personnel.The first identifier can be the combination of one or more of：It is registered
The name of personnel；First pattern identification, for example, heart-shaped；First words identification, for example, " registered "；First colour code, example
Such as, green.
Step 104：Identify whether the facial image that the first identifier is not stamped in the default face database is default
The facial image of unregistered personnel in second register base.
Default second register base, for recording unregistered personal information.The unregistered personal information includes, but not
It is limited to：The facial image of unregistered personnel, the acquisition time of unregistered personnel acquire the image capture device letter of unregistered personnel
It ceases (for example, serial number).
In the present embodiment, the facial image of the unregistered personnel of default second register base is obtained by following step
's：
1) face images in the second preset time period in the default face database are obtained for the first time；Described second is default
Period can be 30 days.
2) facial image of the registered personnel in the face images is identified；
3) facial image that the registered personnel are removed in the face images is determined as to the people of unregistered personnel
Face image is simultaneously stored in default second register base.
It should be noted that the second preset time period is when obtaining one section that presets the facial image in face database for the first time
Between, after obtaining the facial image in default face database for the first time, facial image can be analyzed, by registered recognition of face
It is remaining to be denoted as unregistered personnel after out.Subsequently again to the default face in certain time (for example, first preset time period)
Facial image in library, which carries out analysis, to be judged according to the unregistered personnel determined for the first time.
In the present embodiment, do not stamped in the identification default face database first identifier facial image whether
Facial image for the unregistered personnel in default second register base specifically includes：
1) face that the first identifier is not stamped in the default face database is detected using default Face datection algorithm
The face area of image.
2) face area that the first identifier is not stamped in the default face database and the unregistered personnel are calculated
Face area between the second similarity.
In the present embodiment, it can be calculated in the default face database by the method for template matches and not stamp described first
The second similarity between the face area of mark and the face area of the unregistered personnel.
3) judge whether second similarity is more than default second similarity threshold.
Default second similarity threshold is pre-set second similarity threshold, Ke Yishi, for example, 98%.
When second similarity is more than or equal to default second similarity threshold, the default face is determined
The facial image that the first identifier is not stamped in library is the facial image of the unregistered personnel in default second register base；When
When second similarity is less than default second similarity threshold, determines and do not stamp described the in the default face database
The facial image of one mark is not the facial image of the unregistered personnel in default second register base.
It, need to will be each in the facial image for not stamping the first identifier in the default face database in the present embodiment
Facial image is opened to be matched one by one with the facial image of each unregistered personnel in default second register base.If institute
It states in the facial image and default second register base that some in default face database does not stamp the first identifier
When second similarity of the facial image of any one unregistered personnel is more than or equal to second similarity threshold, then recognize
It is not stepping in default second register base for the facial image for not stamping the first identifier in the default face database
The facial image of note personnel.If some in the default face database does not stamp facial image and the institute of the first identifier
The second similarity for stating any one of the default second register base facial image of unregistered personnel is respectively less than second phase
When like degree threshold value, then it is assumed that facial image that this in the default face database does not stamp the first identifier is not default the
The facial image of unregistered personnel in two register bases.
When determining that the facial image for not stamping the first identifier in the default face database is described default second to step on
When remembering the facial image of the unregistered personnel in library, step 105 is executed；Otherwise, when determining in the default face database not beating
When the facial image of the upper first identifier is not the facial image of the unregistered personnel in default second register base, execute
Step 106.
Step 105：The facial image for being determined as unregistered personnel in the default face database is stamped into second identifier.
The second identifier is used to identify the facial image of the unregistered personnel in default second face database, that is, identifies
Personnel in the default face database are unregistered personnel.The second identifier can be the combination of one or more of：The
Two pattern identifications, for example, round；Second words identification, for example, " unregistered "；Second colour code, for example, red.
106：Determine the facial image that the first identifier and the second identifier are not stamped in the default face database
For the facial image of None- identified personnel, the facial image of the None- identified is stamped into third mark.
The third identifies the facial image for identifying the None- identified personnel in the default face database, that is, identifies institute
The personnel stated in default face database are None- identified personnel, and None- identified personnel can be understood as new unregistered personnel.It is described
Third mark can be the combination of one or more of：Third pattern identification, for example, question mark；Third words identification, for example,
" None- identified "；Third colour code, for example, grey.
The corresponding personnel of facial image that the third mark is stamped in the default face database are referred to as None- identified
Personnel.
Further to analyze and counting in first preset time period through the None- identified of gate inhibition's banister
The quantity of personnel, the method can also include：To stamped in the default face database facial image of third mark into
Row clustering；The classification of the None- identified personnel is determined according to the cluster centre obtained after clustering.
In the present embodiment, cluster centre is obtained after clustering, the quantity of the cluster centre can not be known to be described
The classification of others' member.According to the classification of the None- identified personnel, you can learn in first preset time period by described
The quantity of the None- identified personnel of gate inhibition's banister.
For ease of being subsequently tracked management to None- identified personnel, the method can also include：According to preset model
Calculate the quality of multiple facial images of same category of None- identified personnel；Using the highest facial image of quality as corresponding class
The facial image of other None- identified personnel.
As pre-set model, the quality for calculating facial image, the preset model can wrap the model that sets
It includes, but is not limited to：Mean square error (mean squared error, MSE) and Y-PSNR ((peak signal to
Noise rate, PSNR).Mean square error remembers that Y-PSNR is the prior art, is no longer described in detail herein.
In the present embodiment, using the highest facial image of quality as the facial image of the None- identified personnel of corresponding classification,
It can be convenient for subsequently when needing to analyse whether to occur new None- identified personnel, it is only necessary to be carried out with the highest facial image of quality
Comparison, and the highest facial image of quality is the most clear, thus recognition effect is more.
Further, be the memory space for saving the default face database, using the highest facial image of quality as
After the facial image of the None- identified personnel of corresponding classification, the method can also include：Store the highest people of the quality
Face image deletes the remaining facial image of corresponding classification.
Further, the method can also include：It obtains in the default face database and stamps the second identifier
The acquisition time of facial image；Obtain the people for stamping the first identifier in third preset time period before and after the acquisition time
Face image；By the people for stamping the first identifier of the facial image of the corresponding second identifier of the acquisition time and acquisition
Face image is associated and stamps the mark of same administrative staff.
For example, the acquisition time T for the facial image A that the second identifier is stamped in the default face database is obtained,
All facial image list B (B1, B2, B3 ..., Bn) for stamping the first identifier before and after acquisition time T in 30 seconds, by institute
List B (B1, B2, B3 ..., Bn) composition set C are stated, facial image is finally stamped to the mark of set C.
In the present embodiment, the facial image of the unregistered personnel of some time point acquisition is obtained and one before and after the time point
The facial image of all registered personnel acquired in the section time, then it is assumed that the unregistered personnel are with the registered personnel
Same administrative staff, to which unregistered personnel and registered personnel are associated storage.
Further, if the gate inhibition's banister quantity being arranged in wisdom garden is more and/or described image acquisition is set
Standby quantity is more, and the method can also include：Obtain the face figure that the second identifier is stamped in the default face database
The acquisition time of picture and the mark of image capture device；It obtains before and after the acquisition time in third preset time period and there is phase
The facial image of the first identifier is stamped in facial image with the image capture device acquisition of mark.
In the present embodiment, while the mark of image capture device is obtained, the image capture device with same mark is adopted
It is more realistic that the facial image of collection carries out colleague's analysis.It so can guarantee that two or more table images acquisition apart from each other is set
The facial image of standby acquisition, even if before and after the acquisition time in third preset time period, according to the mark of image capture device
Whether it is colleague's that knowledge can be distinguished.
Further, in order to be more accurate the registered personnel in the determination default face database, reduction will not step on
Note personnel or None- identified personnel are mistakenly identified as security risk caused by registered personnel, improve the safety of wisdom garden,
Pre-set first similarity threshold is more than pre-set second similarity threshold.
In conclusion the present invention obtains the human face data preset in the first preset time period in face database；It identifies described pre-
If whether the facial image in face database is the facial image for presetting the registered personnel in the first register base；If so, will be described
The facial image for being determined as the registered personnel in default face database stamps first identifier；If it is not, then identifying described default
Whether the facial image that the first identifier is not stamped in face database is the people for presetting the unregistered personnel in the second register base
Face image；If so, the facial image for being determined as unregistered personnel in the default face database is stamped second identifier；Otherwise, really
It is set to the facial image of None- identified personnel, the facial image of the None- identified is stamped into third mark.Wherein, the first registration
The unregistered personnel in registered personnel and the second register base in library are by obtaining the facial image in such as 30 days for the first time
It obtains, subsequently being analyzed pedestrian all only needs to obtain in the default face database in the first preset time period in such as 24 hours
Human face data.It can effectively shorten and calculate the time, improve the calculated performance of computer, repeatedly without the face to clustering
It clusters, under the conditions of equal performance, can support more gardens.
Secondly, the pedestrian in follow-up each pair of first preset time period analyzes, and actual amount of data has only added the
Such as 24 hours human face datas in one preset time period, may only will appear in first preset time period it is few it is new not
Memory space is greatly saved in registration of personnel data, reduces the difficulty of data base administration data.
In addition, analyze the human face data obtained in the first preset time period, the registered personnel that will identify that, not
Registration of personnel and new unregistered personnel use different marks, and over time, new unregistered personnel only can be more next
Fewer, administrator need to only check that different marks can identify whether pedestrian belongs to new unregistered personnel, greatly reduce pipe
The difficulty of reason person's management.
Above-mentioned Fig. 1 describes pedestrian's analysis method of the present invention in detail, with reference to the 2nd~3 figure, respectively to described in realization
The function module of the software systems of pedestrian's analysis method and the hardware system structure of realization pedestrian's analysis method are situated between
It continues.
It should be appreciated that the embodiment is only purposes of discussion, do not limited by this structure in patent claim.
Embodiment two
Fig. 2 is the functional block diagram of pedestrian's analytical equipment provided by Embodiment 2 of the present invention.
Pedestrian's analytical equipment 20 is run in terminal.Pedestrian's analytical equipment 20 may include multiple by program code segments
The function module formed.The program code of each program segment in pedestrian's analytical equipment 20 can be stored in the terminal
Memory in, and performed by least one processor by the terminal, to execute the analysis to the pedestrian of wisdom garden.
In the present embodiment, function of the pedestrian's analytical equipment 20 performed by it can be divided into multiple functions
Module.The function module may include：Acquisition module 201, the first identification module 202, first identifier module 203, second are known
Other module 204, second identifier module 205, third mark module 206, cluster module 207, computing module 208 and the 4th identify mould
Block 209.It is communicated by least one communication bus between above-mentioned modules.It refers to that one kind can be located to invent so-called module
Reason device is performed and can complete the series of computation machine program segment of fixed function, and storage is in memory.In this implementation
In example, the function about each module will be described in detail in subsequent embodiment.
Acquisition module 201, for obtaining the human face data preset in the first preset time period in face database.
First identification module 202, whether the facial image in the default face database is default first registration for identification
The facial image of registered personnel in library.
First identifier module 203, for determining the face figure in the default face database when first identification module 202
When as being the facial image for presetting the registered personnel in the first register base, it will be determined as in the default face database described
The facial image of registered personnel stamps first identifier.
Second identification module 204, for determining the face figure in the default face database when first identification module 202
When as not being the facial image for presetting the registered personnel in the first register base, identify in the default face database without beating
Whether the facial image of the upper first identifier is the facial image for presetting the unregistered personnel in the second register base.
Second identifier module 205 is determined in the default face database for working as second identification module 204 and is not stamped
It, will be described pre- when the facial image of the first identifier is the facial image of the unregistered personnel in default second register base
If the facial image for being determined as unregistered personnel in face database stamps second identifier.
Third mark module 206 is determined in the default face database for working as second identification module 204 and is not stamped
When the facial image of the first identifier is not the facial image of the unregistered personnel in default second register base, institute is determined
State the people that the facial image of the first identifier and the second identifier is not stamped in default face database as None- identified personnel
The facial image of the None- identified is stamped third mark by face image.
Further to analyze and counting in first preset time period through the None- identified of gate inhibition's banister
The quantity of personnel, pedestrian's analytical equipment 20 can also include：Cluster module 207, for being beaten in the default face database
The facial image of the upper third mark carries out clustering；The cluster module 207 is additionally operable to obtain according to after clustering
Cluster centre determine the classification of the None- identified personnel.
For ease of being subsequently tracked management to None- identified personnel, pedestrian's analytical equipment 20 can also include：Meter
Calculate module 208, the quality of multiple facial images for calculating same category of None- identified personnel according to preset model；It is described
Computing module 208 is additionally operable to using the highest facial image of quality as the facial image of the None- identified personnel of corresponding classification.
Further, be the memory space for saving the default face database, using the highest facial image of quality as
After the facial image of the None- identified personnel of corresponding classification, pedestrian's analytical equipment 20 can also include：Store the matter
Highest facial image is measured, the remaining facial image of corresponding classification is deleted.
Further, the acquisition module 201 is additionally operable to obtain in the default face database and stamps the second identifier
Facial image acquisition time；Acquisition module 201 is additionally operable to obtain before and after the acquisition time in third preset time period
Stamp the facial image of the first identifier；Pedestrian's analytical equipment 20 can also include：4th mark module 209, is used for
By the facial image for stamping the first identifier of the facial image of the corresponding second identifier of the acquisition time and acquisition
It is associated and stamps the mark of same administrative staff.
Further, if the gate inhibition's banister quantity being arranged in wisdom garden is more and/or described image acquisition is set
Standby quantity is more, acquisition module 201, is additionally operable to obtain the facial image for stamping the second identifier in the default face database
Acquisition time and image capture device mark；It is default to be additionally operable to third before and after obtaining the acquisition time for acquisition module 201
The face figure of the first identifier is stamped in period and in the facial image of the acquisition of the image capture device with like-identified
Picture.
Further, in order to be more accurate the registered personnel in the determination default face database, reduction will not step on
Note personnel or None- identified personnel are mistakenly identified as security risk caused by registered personnel, improve the safety of wisdom garden,
Pre-set first similarity threshold is more than pre-set second similarity threshold.
In conclusion the present invention obtains the human face data preset in the first preset time period in face database；It identifies described pre-
If whether the facial image in face database is the facial image for presetting the registered personnel in the first register base；If so, will be described
The facial image for being determined as the registered personnel in default face database stamps first identifier；If it is not, then identifying described default
Whether the facial image that the first identifier is not stamped in face database is the people for presetting the unregistered personnel in the second register base
Face image；If so, the facial image for being determined as unregistered personnel in the default face database is stamped second identifier；Otherwise, really
It is set to the facial image of None- identified personnel, the facial image of the None- identified is stamped into third mark.Wherein, the first registration
The unregistered personnel in registered personnel and the second register base in library are by obtaining the facial image in such as 30 days for the first time
It obtains, subsequently being analyzed pedestrian all only needs to obtain in the default face database in the first preset time period in such as 24 hours
Human face data.It can effectively shorten and calculate the time, improve the calculated performance of computer, repeatedly without the face to clustering
It clusters, under the conditions of equal performance, can support more gardens.
Secondly, the pedestrian in follow-up each pair of first preset time period analyzes, and actual amount of data has only added the
Such as 24 hours human face datas in one preset time period, may only will appear in first preset time period it is few it is new not
Memory space is greatly saved in registration of personnel data, reduces the difficulty of data base administration data.
In addition, analyze the human face data obtained in the first preset time period, the registered personnel that will identify that, not
Registration of personnel and new unregistered personnel use different marks, and over time, new unregistered personnel only can be more next
Fewer, administrator need to only check that different marks can identify whether pedestrian belongs to new unregistered personnel, greatly reduce pipe
The difficulty of reason person's management.
Embodiment three
Fig. 3 is the schematic diagram for the terminal 1 that the embodiment of the present invention three provides.The terminal 1 includes memory 20, processor
30, computer program 40, the image capture device 50 that can be run in the memory 20 and on the processor 30 are stored in
And at least one communication bus 60.The processor 30 realizes above-mentioned pedestrian's analysis method when executing the computer program 40,
Such as step 101~106 shown in FIG. 1.Alternatively, the processor 30 realizes above-mentioned apparatus when executing the computer program 40
The function of each module/unit in embodiment, such as the module 201~209 in Fig. 2.
Illustratively, the computer program 40 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 20, and are executed by the processor 30, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 40 in the terminal 1 is described.For example, the computer program 40 can be divided into
Acquisition module 201, the first identification module 202, first identifier module 203, the second identification module 204, second identifier mould in Fig. 2
Block 205, third mark module 206, cluster module 207, computing module 208 and the 4th mark module 209, each unit concrete function
Referring to embodiment two and its corresponding description.
The terminal 1 can be the computing devices such as desktop PC, notebook, palm PC and cloud server.This
Field technology personnel are appreciated that the schematic diagram 3 is only the example of terminal 1, and the not restriction of structure paired terminal 1 can be with
Including components more more or fewer than diagram, certain components or different components are either combined, such as the terminal 1 may be used also
To include input-output equipment, network access equipment, bus etc..
Alleged processor 30 can be central processing unit, can also be other general processors, digital signal processor,
Application-specific integrated circuit, ready-made programmable gate array either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor 30 can also be any conventional processor
Deng the processor 30 is the control centre of the terminal 1, utilizes each portion of various interfaces and the entire terminal of connection 1
Point.
The memory 20 can be used for storing the computer program 40 and/or module/unit, and the processor 30 passes through
Operation executes the computer program and/or module/unit being stored in the memory 20, and calls and be stored in memory
Data in 20 realize the various functions of the terminal 1.The memory 20 can include mainly storing program area and storage data
Area, wherein storing program area can storage program area, needed at least one function application program (such as sound-playing function,
Image player function etc.) etc.；Storage data field can be stored uses created data (such as audio data, electricity according to terminal 1
Script for story-telling etc.) etc..In addition, memory 20 may include high-speed random access memory, can also include nonvolatile memory, example
Such as hard disk, memory, plug-in type hard disk, intelligent memory card, safe digital card, flash card, at least one disk memory, flash memory
Device or other volatile solid-state parts.
If the integrated module/unit of the terminal 1 is realized in the form of SFU software functional unit and as independent product
Sale in use, can be stored in a computer read/write memory medium.Based on this understanding, in present invention realization
All or part of flow in embodiment method is stated, relevant hardware can also be instructed to complete by computer program, institute
The computer program stated can be stored in a computer readable storage medium, which, can when being executed by processor
The step of realizing above-mentioned each embodiment of the method.Wherein, the computer program includes computer program code, the computer
Program code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer can
Reading medium may include：Any entity or device, recording medium, USB flash disk, mobile hard of the computer program code can be carried
Disk, magnetic disc, CD, computer storage, read-only memory, random access memory, electric carrier signal, telecommunication signal and soft
Part distribution medium etc..It should be noted that the content that the computer-readable medium includes can be stood according in jurisdiction
The requirement of method and patent practice carries out increase and decrease appropriate, such as is calculated according to legislation and patent practice in certain jurisdictions
Machine readable medium does not include electric carrier signal and telecommunication signal.
In several embodiments provided by the present invention, it should be understood that disclosed terminal and method can pass through it
Its mode is realized.For example, terminal embodiment described above is only schematical, for example, the division of the unit, only
Only a kind of division of logic function, formula that in actual implementation, there may be another division manner.
In addition, each functional unit in each embodiment of the present invention can be integrated in same treatment unit, it can also
That each unit physically exists alone, can also two or more units be integrated in same unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of hardware adds software function module.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, it will be understood by those of ordinary skill in the art that, it can be to the present invention's
Technical solution is modified or equivalent replacement, without departing from the spirit of the technical scheme of the invention and range.
Claims (10)
1. a kind of pedestrian's analysis method is applied in terminal, which is characterized in that the method includes：
Obtain the human face data preset in the first preset time period in face database；
Identify whether the facial image in the default face database is the face figure for presetting the registered personnel in the first register base
Picture；
When determining that the facial image in the default face database is the face of the registered personnel in default first register base
When image, the facial image for being determined as the registered personnel in the default face database is stamped into first identifier；And
It is the people for presetting the registered personnel in the first register base when determining the facial image in the default face database not
When face image, identify whether the facial image that the first identifier is not stamped in the default face database is default second registration
The facial image of unregistered personnel in library；
When determining that the facial image for not stamping the first identifier in the default face database is default second register base
In unregistered personnel facial image when, the facial image for being determined as unregistered personnel in the default face database is stamped
Two marks；Or
It is default second registration when determining the facial image for not stamping the first identifier in the default face database not
When the facial image of the unregistered personnel in library, determines and do not stamp the first identifier and described in the default face database
The facial image of two marks is the facial image of None- identified personnel, and the facial image of the None- identified is stamped third mark
Know.
2. the method as described in claim 1, which is characterized in that the face figure of the unregistered personnel of default second register base
The acquisition of picture includes：
The face images in the second preset time period in the default face database are obtained for the first time；
Identify the facial image of the registered personnel in the face images；
The facial image that the registered personnel are removed in the face images is determined as to the facial image of unregistered personnel
And it is stored in default second register base.
3. method as claimed in claim 2, which is characterized in that the method further includes：
Facial image to stamping the third mark in the default face database carries out clustering；
The classification of the None- identified personnel is determined according to the cluster centre obtained after clustering.
4. method as claimed in claim 3, which is characterized in that the method further includes：
The quality of multiple facial images of same category of None- identified personnel is calculated according to preset model；
Using the highest facial image of quality as the facial image of the None- identified personnel of corresponding classification.
5. method as claimed in claim 4, which is characterized in that using the highest facial image of quality as the nothing of corresponding classification
After method identifies the facial image of personnel, the method further includes：
The highest facial image of the quality is stored, the remaining facial image of corresponding classification is deleted.
6. the method as described in any one of claim 1 to 5, which is characterized in that the method further includes：
Obtain the acquisition time for the facial image that the second identifier is stamped in the default face database；
Obtain the facial image for stamping the first identifier in third preset time period before and after the acquisition time；
By the face for stamping the first identifier of the facial image of the corresponding second identifier of the acquisition time and acquisition
Image is associated and stamps the mark of same administrative staff.
7. method as claimed in claim 6, which is characterized in that described obtain stamps second mark in the default face database
The acquisition time of the facial image of knowledge further includes：
The mark of image capture device is obtained simultaneously；
Obtain before and after the acquisition time people that in third preset time period and the image capture device with like-identified acquires
The facial image of the first identifier is stamped in face image.
8. a kind of pedestrian's analytical equipment, runs in terminal, which is characterized in that described device includes：
Acquisition module, for obtaining the human face data preset in the first preset time period in face database；
First identification module, whether the facial image in the default face database is to preset in the first register base for identification
The facial image of registration of personnel；
First identifier module, for determining that the facial image in the default face database is described pre- when first identification module
If when the facial image of the registered personnel in the first register base, the registered personnel will be determined as in the default face database
Facial image stamp first identifier；
Second identification module, the facial image for being determined when first identification module in the default face database is not described
When the facial image of the registered personnel in default first register base, identifies in the default face database and do not stamp described first
Whether the facial image of mark is the facial image for presetting the unregistered personnel in the second register base；
Second identifier module determines that described first is not stamped in the default face database marks for working as second identification module
It, will be in the default face database when facial image of knowledge is the facial image of the unregistered personnel in default second register base
The facial image for being determined as unregistered personnel stamps second identifier；
Third mark module determines that described first is not stamped in the default face database marks for working as second identification module
When the facial image of knowledge is not the facial image of the unregistered personnel in default second register base, the default face is determined
The facial image that the first identifier and the second identifier are not stamped in library is the facial image of None- identified personnel, by institute
The facial image for stating None- identified stamps third mark.
9. a kind of terminal, it is characterised in that：The terminal includes processor, and the processor is used to execute to store in memory
Pedestrian's analysis method as described in any one of claim 1 to 7 is realized when computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that：The computer program
Pedestrian's analysis method as described in any one of claim 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810443368.3A CN108446681B (en) | 2018-05-10 | 2018-05-10 | Pedestrian analysis method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810443368.3A CN108446681B (en) | 2018-05-10 | 2018-05-10 | Pedestrian analysis method, device, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108446681A true CN108446681A (en) | 2018-08-24 |
| CN108446681B CN108446681B (en) | 2020-12-15 |
Family
ID=63203378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810443368.3A Active CN108446681B (en) | 2018-05-10 | 2018-05-10 | Pedestrian analysis method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108446681B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658572A (en) * | 2018-12-21 | 2019-04-19 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109816582A (en) * | 2019-01-28 | 2019-05-28 | 重庆中科云从科技有限公司 | Control safety protection method and device in area |
| CN110298254A (en) * | 2019-05-30 | 2019-10-01 | 罗普特科技集团股份有限公司 | A kind of analysis method and system for personnel's abnormal behaviour |
| CN110837821A (en) * | 2019-12-05 | 2020-02-25 | 深圳市亚略特生物识别科技有限公司 | Identity recognition method, equipment and electronic system based on biological characteristics |
| CN111079469A (en) * | 2018-10-18 | 2020-04-28 | 深圳云天励飞技术有限公司 | Method, device and equipment for processing face image and readable storage medium |
| CN111126119A (en) * | 2018-11-01 | 2020-05-08 | 百度在线网络技术（北京）有限公司 | Method and device for counting user behaviors arriving at store based on face recognition |
| CN111626079A (en) * | 2019-02-27 | 2020-09-04 | 杭州海康威视数字技术股份有限公司 | Personnel counting method and device and electronic equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646197A (en) * | 2012-02-20 | 2012-08-22 | 华焦宝 | Pre-warning information issuing method and system |
| US20130216107A1 (en) * | 2012-02-20 | 2013-08-22 | Chih-Hsung Huang | Method of surveillance by face recognition |
| CN103399896A (en) * | 2013-07-19 | 2013-11-20 | 广州华多网络科技有限公司 | Method and system for recognizing association relationships among users |
| CN103514694A (en) * | 2013-09-09 | 2014-01-15 | 重庆邮电大学 | Intrusion detection monitoring system |
| CN105208528A (en) * | 2015-09-24 | 2015-12-30 | 山东合天智汇信息技术有限公司 | Peer recognition system and method |
| CN105488478A (en) * | 2015-12-02 | 2016-04-13 | 深圳市商汤科技有限公司 | Face recognition system and method |
| CN106408832A (en) * | 2016-08-29 | 2017-02-15 | 重庆交通大学 | Interference-free visitor monitoring method and interference-free visitor monitoring system |
| CN106446816A (en) * | 2016-09-14 | 2017-02-22 | 北京旷视科技有限公司 | Face recognition method and device |
| CN106548148A (en) * | 2016-10-26 | 2017-03-29 | 北京意泰物联软件科技有限公司 | Method and system for identifying unknown face in video |
| CN107316011A (en) * | 2017-05-24 | 2017-11-03 | 杭州励飞软件技术有限公司 | Data processing method, device and storage medium |
| CN107480246A (en) * | 2017-08-10 | 2017-12-15 | 北京中航安通科技有限公司 | A kind of recognition methods of associate people and device |
| CN107808149A (en) * | 2017-11-17 | 2018-03-16 | 腾讯数码（天津）有限公司 | A kind of face information mask method, device and storage medium |
-
2018
- 2018-05-10 CN CN201810443368.3A patent/CN108446681B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646197A (en) * | 2012-02-20 | 2012-08-22 | 华焦宝 | Pre-warning information issuing method and system |
| US20130216107A1 (en) * | 2012-02-20 | 2013-08-22 | Chih-Hsung Huang | Method of surveillance by face recognition |
| CN103399896A (en) * | 2013-07-19 | 2013-11-20 | 广州华多网络科技有限公司 | Method and system for recognizing association relationships among users |
| CN103514694A (en) * | 2013-09-09 | 2014-01-15 | 重庆邮电大学 | Intrusion detection monitoring system |
| CN105208528A (en) * | 2015-09-24 | 2015-12-30 | 山东合天智汇信息技术有限公司 | Peer recognition system and method |
| CN105488478A (en) * | 2015-12-02 | 2016-04-13 | 深圳市商汤科技有限公司 | Face recognition system and method |
| CN106408832A (en) * | 2016-08-29 | 2017-02-15 | 重庆交通大学 | Interference-free visitor monitoring method and interference-free visitor monitoring system |
| CN106446816A (en) * | 2016-09-14 | 2017-02-22 | 北京旷视科技有限公司 | Face recognition method and device |
| CN106548148A (en) * | 2016-10-26 | 2017-03-29 | 北京意泰物联软件科技有限公司 | Method and system for identifying unknown face in video |
| CN107316011A (en) * | 2017-05-24 | 2017-11-03 | 杭州励飞软件技术有限公司 | Data processing method, device and storage medium |
| CN107480246A (en) * | 2017-08-10 | 2017-12-15 | 北京中航安通科技有限公司 | A kind of recognition methods of associate people and device |
| CN107808149A (en) * | 2017-11-17 | 2018-03-16 | 腾讯数码（天津）有限公司 | A kind of face information mask method, device and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| JUN LI ET AL: "Face recognition algorithms for embedded entrance guard system", 《COMPUTER MODELLING & NEW TECHNOLOGIES》 * |
| SONIYA V ET AL: "ATTENDANCE AUTOMATION USING FACE RECOGNITION BIOMETRIC AUTHENTICATION", 《 2017 INTERNATIONAL CONFERENCE ON POWER AND EMBEDDED DRIVE CONTROL (ICPEDC)》 * |
| 吴美香等: "基于人脸识别的移动课堂考勤***的设计与实现", 《软件》 * |
| 徐茜亮等: "人脸识别技术在矿井人员管理***中的应用", 《工矿自动化》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111079469A (en) * | 2018-10-18 | 2020-04-28 | 深圳云天励飞技术有限公司 | Method, device and equipment for processing face image and readable storage medium |
| CN111079469B (en) * | 2018-10-18 | 2023-11-17 | 深圳云天励飞技术有限公司 | Face image processing method, device, equipment and readable storage medium |
| CN111126119A (en) * | 2018-11-01 | 2020-05-08 | 百度在线网络技术（北京）有限公司 | Method and device for counting user behaviors arriving at store based on face recognition |
| CN109658572A (en) * | 2018-12-21 | 2019-04-19 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109658572B (en) * | 2018-12-21 | 2020-09-15 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| US11410001B2 (en) | 2018-12-21 | 2022-08-09 | Shanghai Sensetime Intelligent Technology Co., Ltd | Method and apparatus for object authentication using images, electronic device, and storage medium |
| CN109816582A (en) * | 2019-01-28 | 2019-05-28 | 重庆中科云从科技有限公司 | Control safety protection method and device in area |
| CN111626079A (en) * | 2019-02-27 | 2020-09-04 | 杭州海康威视数字技术股份有限公司 | Personnel counting method and device and electronic equipment |
| CN110298254A (en) * | 2019-05-30 | 2019-10-01 | 罗普特科技集团股份有限公司 | A kind of analysis method and system for personnel's abnormal behaviour |
| CN110837821A (en) * | 2019-12-05 | 2020-02-25 | 深圳市亚略特生物识别科技有限公司 | Identity recognition method, equipment and electronic system based on biological characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108446681B (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446681A (en) | Pedestrian's analysis method, device, terminal and storage medium | |
| CN109359538A (en) | Training method, gesture identification method, device and the equipment of convolutional neural networks | |
| CN107480624B (en) | Permanent resident population's acquisition methods, apparatus and system, computer installation and storage medium | |
| CN108347490A (en) | A kind of campus application apparatus and system based on biological identification technology | |
| CN202815946U (en) | Intelligent network face recognition attendance system | |
| WO2021031600A1 (en) | Data collection method and apparatus, computer device, and storage medium | |
| CN105007395A (en) | Privacy processing method for continuously recording video | |
| CN113052079B (en) | Regional passenger flow statistical method, system, equipment and medium based on face clustering | |
| CN106296017A (en) | Management method that a kind of guest room is moved in and device | |
| CN106469181A (en) | A kind of user behavior pattern analysis method and device | |
| CN109446932A (en) | A kind of dressing inspection method, device, terminal device and computer storage medium | |
| CN114066534A (en) | Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence | |
| CN113903068A (en) | Stranger monitoring method, device and equipment based on human face features and storage medium | |
| CN108520579A (en) | With administrative staff's correlating method, device, terminal and storage medium | |
| CN110580942A (en) | novel physical examination report generation method, device, medium and terminal equipment | |
| CN109885597A (en) | Tenant group processing method, device and electric terminal based on machine learning | |
| CN105868693A (en) | Identity authentication method and system | |
| CN109740417A (en) | Invoice type recognition methods, device, storage medium and computer equipment | |
| CN109903411A (en) | A kind of meeting signature device and application method based on recognition of face | |
| CN115422452A (en) | Smart home control method, device, equipment and storage medium based on big data | |
| CN110310164A (en) | Image processing system, method, platform, machine readable media and equipment | |
| CN113705469A (en) | Face recognition method and device, electronic equipment and computer readable storage medium | |
| CN109801394B (en) | Staff attendance checking method and device, electronic equipment and readable storage medium | |
| CN103336800A (en) | Fingerprint storage and comparison method based on behavior analysis | |
| CN112329635A (en) | Method and device for counting store passenger flow |
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 |