CN110148234A - Campus brush face picks exchange method, storage medium and system - Google Patents
Campus brush face picks exchange method, storage medium and system Download PDFInfo
- Publication number
- CN110148234A CN110148234A CN201910334760.9A CN201910334760A CN110148234A CN 110148234 A CN110148234 A CN 110148234A CN 201910334760 A CN201910334760 A CN 201910334760A CN 110148234 A CN110148234 A CN 110148234A
- Authority
- CN
- China
- Prior art keywords
- information
- personnel
- picking
- preset
- incidence relation
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of campus brush faces to pick exchange method, storage medium and system；It solves and picks people by picking card to recognize, the problem of being easy by criminal using false claiming child, its key points of the technical solution are that according to motion analysis information is picked to analyze to picking action message, and judge whether to be mutually matched with default preset action message of picking；If currently picking action message and preset action message of picking being mutually matched success, the personnel's incidence relation picking personnel and being received between personnel is identified；Personnel's incidence relation and default preset personnel's incidence relation are mutually matched；If personnel's incidence relation matches unsuccessful with preset personnel's incidence relation, then feed back information warning, the present invention is directly by determining whether to the analysis for picking movement to pick child, if it is picking child, then the relationship of both sides is picked in judgement, it once picking child for dereferenced personnel, then will do it warning, improve the safety that child picks.
Description
Technical field
The present invention relates to intelligent and safe management method, in particular to campus brush face picks exchange method, storage medium and is
System.
Background technique
The task of kindergarten is to release the restriction of family suffered time, space, environment when cultivating children, allows child's body
Body, intelligence and mood are developed in a healthy way.It may be said that kindergarten is the happy world of child, child can be helped happy and healthy
Childhood day is spent on ground, is not only acquired, but also can be from small contact collective livelihood.Kindergarten education is as entire education body
It is the basis on basis, is that children are carried out with propaedeutic (good, the preliminary nature of personality complete health, behavioural habits and society
Common sense).Its educational class is not distinguished significantly, probably by five fields such as language, science, art, health and society and
Various activities are constituted.Every field mutually merges, and determines the content of courses.
The work rhythm of today's social life is getting faster, and many parents cannot physically go to kindergarten and pick the small of oneself
Child have to entrust relative good friend or nurse et al. to be responsible for picking, and this can come centainly to the work belt of picking of kindergarten child
Security risk.In the case where the personnel that pick are more, it will increase the difficulty that people is picked in staff's identification, child caused to be falsely taken
Consequence.It is not recorded reliably further, since picking information, the responsibility after generation problem between kindergarten and parents of infants is very
Difficulty defines.Currently, most of kindergartens, which are mainly recognized using card is picked, picks people, but pick that card is easily stolen to be taken and imitate
System also brings along security risk if losing, and criminal can falsely claim as one's own child using it, and then threaten the safety of child, so
The management of picking of kindergarten still has certain room for improvement at present.
Summary of the invention
The first object of the present invention is to provide a kind of campus brush face and picks exchange method, according to the analysis for picking movement and
The judgement of personnel is picked to improve the safety that child picks.
Above-mentioned technical purpose of the invention has the technical scheme that
A kind of campus brush face picks exchange method, comprising:
Obtain the current behavior information of current persons；
From the corresponding relationship between pre-set, behavioural information and command information, search and the current behavior information pair
The present instruction information answered；The behavioural information includes picking action message, and described instruction information includes and picks action message
It is mutual corresponding to pick motion analysis information；
According to picking motion analysis information to analyze to picking action message, and judge whether preset to pick with default
Action message is mutually matched；If currently picking action message and preset action message of picking being mutually matched success, identification is picked
Personnel and the personnel's incidence relation being received between personnel；
Personnel's incidence relation and default preset personnel's incidence relation are mutually matched；If personnel's incidence relation and preset personnel
Incidence relation matching is unsuccessful, then feeds back information warning.
Using the above scheme, personnel's movement before the kindergarten in crowd is obtained, i.e., analyzes to picking movement, is
It is no and it is default pick movement and be mutually matched, if can successful match, illustrate that just someone picks child now, is determining someone
Then further judge whether the people picked is correctly to pick personnel in the case where picking, i.e., by determining to pick personnel and connect
The relationship for the person of making a gift to someone illustrates that there are the risks that criminal falsely claims as one's own child if the two is not associate people；Therefore it is warned
Show feedback, Security Personnel is allowed to check, improves the safety during child picks, it is ensured that each child is to be associated
Personnel pick, and this kind of interrelational form can not be utilized by criminal.
Preferably, the method for personnel's incidence relation that identification is picked personnel and is received between personnel is as follows:
It obtains the first face identification information for the personnel that pick and obtains the second recognition of face information for the personnel that are received；
The corresponding preset authorization for picking personnel is searched from pre-set database according to the second recognition of face information
First face identification information and preset authorization face identification information are mutually matched by recognition of face information；
If the first face identification information and preset authorization face identification information successful match, feeds back personnel's incidence relation and institute is pre-
If preset personnel's incidence relation be mutually matched success；
If the first face identification information matches unsuccessful with preset authorization face identification information, personnel's incidence relation and institute are fed back
Preset preset personnel's incidence relation is mutually matched unsuccessful.
Using the above scheme, the preset authorization face identification information of corresponding guardian, the monitoring have been preset in the database
The quantity of people can be set, i.e., often pick the personnel of child, by the first face identification information that real-time detection arrives with
And the second recognition of face information, it is corresponding to it the preset authorization recognition of face for the personnel that pick by the second recognition of face information searching
Information is matched, if can successful match, explanation is the personnel of being mutually related, if matching is unsuccessful, illustrates it is not mutual
Associated personnel.
Preferably, the information warning includes sound information warning and/or light warning information and/or short message warning
Information and/or vibration warning information.
Using the above scheme, the setting of multiple warning mode, can be suitable for various types of environment, it is ensured that security people
Member and related personnel recognize situation, while above warning way can use one such or several combination, mention
The effect of height warning.
Preferably, personnel go to school, the method for situation and classes are over situation statistics is as follows:
Obtain current time information；
State is picked according to current time information with determine to be presently in；If current time information is default upper class hour
Between, then being presently in state is to serve state；If current time information is default classes are over time, it is presently in state
For the state that connects that classes are over；
Obtain the facial recognition information of current persons；
The corresponding preset face for being picked personnel is searched from pre-set database according to facial recognition information to know
Other information；
If facial recognition information and preset facial recognition information are mutually matched success, state is picked to deposit according to what is be presently in
Storage is into corresponding database and forms corresponding statistical information for transferring.
Using the above scheme, determine that child goes to school or classes are over according to time state, respectively to child go to school with
And classes are over is recorded, record determines it is which student by face identification functions, and this information that will acquire into
Row record, is transferred with facilitating.
Preferably, statistics whether all students that go to school leave school situation method it is as follows:
It is to go to school on the statistical information stored in database and database of going to school is that database corresponding to state is served in definition
Learn statistical information；Database corresponding to state that definition connects that classes are over is that classes are over database and the statistics letter stored in classes are over database
Breath is classes are over statistical information；
Classes are in database of transferring that classes are over, and statistical information is mutually compared with the statistical information of going to school in database of going to school, will
In the presence of statistics record being marked and being stored for by the personnel of picking without classes are over statistics record of going to school
It transfers.
Using the above scheme, from the statistical information of going to school of statistics with analyzed in classes are over statistical information, the two carries out
It compares, statistical information of going to school if it exists and there is no classes are over statistical informations, then explanation is still in school and does not leave school, needs
Related personnel is wanted to pay attention to.
Preferably, as follows by the method that personnel's physical condition detects is picked:
Obtain the facial recognition information of current persons；
The corresponding preset face for being picked personnel is searched from pre-set database according to facial recognition information to know
Other information；
If facial recognition information and preset facial recognition information are mutually matched success, the physical condition information of current persons is obtained
And it is stored.
Using the above scheme, recognition of face is carried out to current persons, which student determination be, and to obtaining the student
Physical condition information is stored, and supervision of the kindergarten to child body state is improved.
Preferably, the physical condition information includes body temperature information；It is preset if current body temperature information is greater than or is lower than
Benchmark body temperature information, then the body temperature information for the personnel that picked is fed back to this and is picked and pick personnel corresponding to personnel.
Using the above scheme, if exception occurs in the body temperature of child, abnormal body temperature situation is fed back into prison in time
People, i.e. reception staff are protected, allows guardian that can recognize the physical condition of child in time, is seen a doctor in time.
The second object of the present invention is to provide a kind of storage medium, can store corresponding instruction set, acts according to picking
Analysis and pick personnel judgement to improve the safety that child picks.
Above-mentioned technical purpose of the invention has the technical scheme that
A kind of storage medium, is stored with instruction set, and described instruction collection is suitable for a processor and loads and execute following processing, wraps
It includes:
Obtain the current behavior information of current persons；
From the corresponding relationship between pre-set, behavioural information and command information, search and the current behavior information pair
The present instruction information answered；The behavioural information includes picking action message, and described instruction information includes and picks action message
It is mutual corresponding to pick motion analysis information；
According to picking motion analysis information to analyze to picking action message, and judge whether preset to pick with default
Action message is mutually matched；If currently picking action message and preset action message of picking being mutually matched success, identification is picked
Personnel and the personnel's incidence relation being received between personnel；
Personnel's incidence relation and default preset personnel's incidence relation are mutually matched；If personnel's incidence relation and preset personnel
Incidence relation matching is unsuccessful, then feeds back information warning.
Using the above scheme, personnel's movement before the kindergarten in crowd is obtained, i.e., analyzes to picking movement, is
It is no and it is default pick movement and be mutually matched, if can successful match, illustrate that just someone picks child now, is determining someone
Then further judge whether the people picked is correctly to pick personnel in the case where picking, i.e., by determining to pick personnel and connect
The relationship for the person of making a gift to someone illustrates that there are the risks that criminal falsely claims as one's own child if the two is not associate people；Therefore it is warned
Show feedback, Security Personnel is allowed to check, improves the safety during child picks, it is ensured that each child is to be associated
Personnel pick, and this kind of interrelational form can not be utilized by criminal.
The third object of the present invention is to provide a kind of intelligent and safe management system based on kindergarten, according to picking movement
The judgement of personnel is analyzed and picked to improve the safety that child picks.
Above-mentioned technical purpose of the invention has the technical scheme that
A kind of intelligent and safe management system based on kindergarten, comprising:
Processor, for loading and executing instruction collection；And
Above-mentioned storage medium.
Using the above scheme, personnel's movement before the kindergarten in crowd is obtained, i.e., analyzes to picking movement, is
It is no and it is default pick movement and be mutually matched, if can successful match, illustrate that just someone picks child now, is determining someone
Then further judge whether the people picked is correctly to pick personnel in the case where picking, i.e., by determining to pick personnel and connect
The relationship for the person of making a gift to someone illustrates that there are the risks that criminal falsely claims as one's own child if the two is not associate people；Therefore it is warned
Show feedback, Security Personnel is allowed to check, improves the safety during child picks, it is ensured that each child is to be associated
Personnel pick, and this kind of interrelational form can not be utilized by criminal.
In conclusion the invention has the following advantages: directly by determining whether to the analysis for picking movement to connect
Child is sent, if it is child is picked, then determines that the relationship for picking both sides then will do it once picking child for dereferenced personnel
Warning improves the safety that child picks.
Detailed description of the invention
Fig. 1 is the flow diagram for picking monitoring and managing method；
Fig. 2 is the flow diagram of the method for personnel's incidence relation that identification is picked personnel and is received between personnel；
Fig. 3 be personnel go to school situation and classes are over situation statistics method flow diagram；
Fig. 4 be statistics whether all students that go to school leave school situation method flow diagram；
Fig. 5 is the flow diagram for being picked the method that personnel's physical condition detects.
Specific embodiment
Below in conjunction with attached drawing, invention is further described in detail.
This specific embodiment is only explanation of the invention, is not limitation of the present invention, those skilled in the art
Member can according to need the modification that not creative contribution is made to the present embodiment after reading this specification, but as long as at this
All by the protection of Patent Law in the scope of the claims of invention.
The embodiment of the present invention provides a kind of campus brush face and picks exchange method, comprising: obtains the current behavior of current persons
Information；From the corresponding relationship between pre-set, behavioural information and command information, search corresponding with current behavior information
Present instruction information；Behavioural information includes picking action message, and command information includes and picks that action message is mutual corresponding to be connect
Send motion analysis information；According to picking motion analysis information to analyze to picking action message, and judge whether pre- with institute
If preset action message of picking be mutually matched；If currently picking action message and preset action message of picking being mutually matched into
Function then identifies the personnel's incidence relation picking personnel and being received between personnel；By personnel's incidence relation with it is default pre-
The personnel incidence relation of setting is mutually matched；If personnel's incidence relation matches unsuccessful with preset personnel's incidence relation, warning is fed back
Information.
In the embodiment of the present invention, personnel's movement before the kindergarten in crowd is obtained, i.e., is analyzed to picking movement,
Whether pick movement with default and be mutually matched, if can successful match, illustrate that positive someone picks child now, has determining
People then further judges whether the people picked is correctly to pick personnel in the case where picking, i.e., by determine pick personnel and by
The relationship of personnel is picked, if the two is not associate people, illustrates that there are the risks that criminal falsely claims as one's own child；Therefore it carries out
Warning feedback, allows Security Personnel to check, improves the safety during child picks, it is ensured that each child is to close therewith
The personnel of connection pick, and this kind of interrelational form can not be utilized by criminal.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In addition, the terms "and/or", only a kind of incidence relation for describing affiliated partner, indicates may exist
Three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A and B, these three situations of individualism B.Separately
Outside, character "/" herein typicallys represent the relationship that forward-backward correlation object is a kind of "or" unless otherwise specified.
The embodiment of the present invention is described in further detail with reference to the accompanying drawings of the specification.
Referring to Figure 1, the embodiment of the present invention provides a kind of campus brush face and picks exchange method, wherein about picking supervision
The main flow of method is described as follows.
As shown in Figure 1:
Step 1100: obtaining the current behavior information of current persons.
Wherein, the current behavior information of current persons is obtained by camera, behavioural information includes very more movement letter
Breath, for example, movement of walking about, movement of running, mentioning thing and acting etc., and behavioural information further includes picking action message, that is, is picked
The conventional action of child；Picking action message includes having the movement of child, the movement for leading child etc. in arms.
Step 1200: from the corresponding relationship between pre-set, behavioural information and command information, lookup and current line
For the corresponding present instruction information of information；Command information include with pick action message it is mutual corresponding pick motion analysis letter
Breath.
Wherein, action messages much more very is obtained from camera, then carries out which is analyzed by command information dynamic
Work, which belongs to, picks action message, to screen required information.
Step 1300: according to picking motion analysis information to analyze to picking action message, and judging whether and institute
Preset preset action message of picking is mutually matched；If currently picking action message and preset action message of picking being mutually matched into
Function then identifies the personnel's incidence relation picking personnel and being received between personnel.
Wherein, need to initially set up in analytic process it is preset pick action message, that is, be basic Matching Model, the foundation
In the process, it needs to carry out model training, the method being somebody's turn to do is as follows:
The acquisition of training information saves acquisition according to the storage format of setting using multiple depth information frames and bone information frame
The original activities information that device transmits, the sample data as original activities；Regularization is carried out to sample data, i.e., first
By discretization skeleton point coordinate then the discrete sample three-dimensional vector collection for turning to movement of sample data is mentioned by feature again
Algorithm is taken to obtain characteristic 3 D vector set；To form corresponding basic Matching Model.
The method packet of " by discretization skeleton point coordinate, by the discrete sample three-dimensional vector collection for turning to movement of sample data "
Include following processing step:
A. unified coordinate system is coordinately transformed the depth information data of every frame and bone information data, they are unified
Into same world coordinate system；
B. discretization skeleton point coordinate carries out sliding-model control to bone information data point coordinate each in present frame, discrete
The step of change are as follows:
I) according to the same skeleton point coordinate in the adjacent each frame in front and back, the motion vector of the skeleton point is calculated；
Ii) the unit cube in the corresponding target discrete coordinate system of the skeleton point is searched；
Iii) the motion vector of the skeleton point is synthesized in the current motion vector of unit cube；
C. discretization depth information data coordinates, will if the skeleton point is hand point that is, in discretization skeleton point coordinate
Depth data point near the skeleton point also carries out discretization, the unit cube corresponding to depth information data after discretization
Possess motion vector identical with the skeleton point；
D. above-mentioned a, b, step c are repeated to each frame, a corresponding sample three-dimensional vector is generated to each movement to be identified
Collection.
" feature extraction algorithm " specifically:
A. it calculates each three-dimensional coordinate point and concentrates the number occurred in whole three-dimensional vectors；
B. its characteristic coefficient is calculated according to its frequency of occurrence, that is, the characteristic coefficient=three-dimensional coordinate point frequency of occurrence/movement is three-dimensional
The number of vector set；
C. if characteristic coefficient is greater than 50%, then it is assumed that the three-dimensional vector collection of the point belongs to characteristic 3 D vector set.
To picking in action message progress analytic process, fuzzy diagnosis, contracting are carried out by characteristic 3 D vector set first
It behind small search range, is further carried out and accurately identifies, to assert that movement to be identified is that current candidate acts.The setting
Storage format includes following field: movement ID, denomination of dive, the logarithm of action message frame, depth information frame and bone information frame.
Each element in depth information frame is the depth information in its respective coordinates；Bone information frame has human body skeleton point number of coordinates
According to composition；The logarithm of action message frame refers to how many is to depth information frame and bone information frame in a movement.Collector packet
Include depth finding camera and third party SDK.
" fuzzy diagnosis " specifically: calculate characteristic 3 D vector all in the three-dimensional vector collection and current system away from
From if the distance is less than threshold values corresponding to this feature three-dimensional vector, by the corresponding movement work of this characteristic 3 D vector
For a candidate actions." accurately identifying " specifically: to all candidate actions, be ranked up according to apart from ascending, then
Successively to the sample three-dimensional vector collection in each candidate actions, it is calculated at a distance from the three-dimensional vector collection of movement to be identified, such as
Wherein minimum range is less than preset threshold values to fruit, then automatic assert that picking action message picks action message mutual with preset
With success, i.e. completion identification process.
Above-mentioned carries out drop precision sliding-model control to initial data, can not only reduce the noise of initial data also in this way
Operand can be reduced；Meanwhile multi-level features matching algorithm is used, further speed up action training recognition speed.
Step 1400: personnel's incidence relation and default preset personnel's incidence relation are mutually matched；If personnel are associated with
Relationship matches unsuccessful with preset personnel's incidence relation, then feeds back information warning.
Wherein, information warning include sound information warning and/or light warning information and/or short message information warning and/
Or vibration warning information；Sound information warning, which passes through the equipment such as loudspeaker, to be reminded, and light warning information passes through setting and exists
The indoor warning lamp of security is warned, and short message information warning is on the reminding short message or intelligent terminal sent by mobile phone
The pop window information etc. that APP software is sent, vibration warning information are to pass through mobile phone or the equipment transmission with vibrating sensor
Vibration action is reminded；The mode warned above can also use several combinations, the present embodiment using one of which
In, it is preferred to use the mode that sound information warning and light warning information be combined with each other.
Wherein, as shown in Fig. 2, identification pick personnel and the method for personnel's incidence relation that is received between personnel such as
Under:
Step 1410: obtaining the first face identification information for the personnel that pick and obtain the second recognition of face letter for the personnel that are received
Breath；
Step 1420: being searched from pre-set database according to the second recognition of face information and corresponding pick personnel's
First face identification information and preset authorization face identification information are mutually matched by preset authorization face identification information；
Step 1430: if the first face identification information and preset authorization face identification information successful match, feeding back personnel's association
Relationship and default preset personnel's incidence relation are mutually matched success；
Step 1440: if the first face identification information matched with preset authorization face identification information it is unsuccessful, feed back personnel pass
Connection relationship is mutually matched unsuccessful with default preset personnel's incidence relation.
The preset authorization face identification information of corresponding guardian is preset in the database, the quantity of the guardian can be into
Row setting, i.e., often pick the personnel of child, the first face identification information and the second recognition of face arrived by real-time detection
Information is matched by the be corresponding to it preset authorization face identification information of the personnel that pick of the second recognition of face information searching,
If can successful match, explanation is the personnel of being mutually related, if matching is unsuccessful, illustrates not to be the personnel of being mutually related.
In the management of kindergarten, going to school that classes are over situation is counted to child is needed, avoids child from occurring unnecessary
It is dangerous.Wherein, as shown in figure 3, personnel go to school, the method for situation and classes are over situation statistics is as follows:
Step 2100: obtaining current time information.
Wherein, the acquisition of temporal information obtains the local corresponding time by modes such as internets.
Step 2200: state is picked with determine to be presently according to current time information.
Wherein, if current time information is default time for school, the state that is presently in is to serve state；If working as
Preceding temporal information is default classes are over time, then being presently in state is the state that connects that classes are over；In the present embodiment, it is default on
It is 6 points to 10 points between class hour, default classes are over time is 15 points to 18 points.
Step 2300: obtaining the facial recognition information of current persons.
Wherein, the facial recognition information of related personnel is identified by default photographic device.Identification process is generally divided
Three steps: (1) the image surface archives of face are initially set up,.With the image surface file of the face of video camera acquisition units personnel or take him
Photo formed image surface file, and by these image surface file generated face lines (Faceprint) coding be stored up.(2), it obtains
Current human body image surface.I.e. with the image surface of the current discrepancy personnel of cameras capture, or photo is taken to input, and by current image surface
File generated face line coding.(3), with the comparison of current face line coding and archives inventory.The face line of image surface that will be current is compiled
Code carries out retrieval with the face line coding in archives inventory and compares.Above-mentioned " face line coding " mode is the essence according to face face
Feature and beginning carry out work.This face line coding can resist light, skin color, facial hair, hair style, glasses, expression
With the variation of posture, there is powerful reliability, so that it be allow accurately to recognize someone from million people.Face
Identification process can be completed automatic, continuous, in real time using common image processing equipment.
Step 2400: being searched from pre-set database according to facial recognition information and corresponding picked personnel
Preset facial recognition information.
Wherein, it is to carry out identity validation to the looks picture that is detected or carry out target in image surface library searching that looks, which compare,
Rope.This is actually to say, the image surface sampled is successively compared with the image surface of inventory, and finds out optimal matching pair
As.So the description of image surface determines the specific method and performance of face recognizing.Mainly using feature vector and face line template two
Kind description method:
1, levy vector method: this method is size, position, the distance etc. of the first image surfaces such as determining eye iris, the wing of nose, corners of the mouth face profile
Then attribute calculates their geometric feature again, and these characteristic quantities form a feature vector for describing the image surface.
2, face line template: this method is to store several standard image surface templates or image surface organ template in library, is being carried out
When comparison, all pixels of image surface will be sampled and matched with templates all in library using normalization correlative measurement.In addition, also
The method combined using the auto-correlation network or feature of pattern-recognition with template.
The practical core of face recognition technology is " partial body's signature analysis " and " figure/nerve recognizer." this
Algorithm is the method using each organ of human body face and characteristic portion.Geometrical relationship majority is such as corresponded to according to formation identification parameter and number
It is compared, judges and confirmation according to initial parameter all in library.It is general to require to judge the time lower than 1 second.
Step 2500: if facial recognition information and preset facial recognition information are mutually matched success, basis is presently in
Pick state and transferred with storing into corresponding database and being formed corresponding statistical information.
Wherein, if face recognition success, illustrate that the corresponding student crosses and come to school or classes are over, then it will be corresponding
Data are counted.
By aggregated statistical information, as shown in figure 4, whether can leave school to the student to go to school point
Analysis, the specific method is as follows:
Step 3100: it is the statistics stored in database and database of going to school of going to school that database corresponding to state is served in definition
Information is statistical information of going to school；It database corresponding to state that definition connects that classes are over is that classes are over database and is stored in classes are over database
Statistical information be classes are over statistical information.
Step 3200: statistical information that classes are in database of transferring that classes are over in database of going to school go to school statistical information into
Row mutually compares.
Step 3300: statistics record of going to school will be present and carried out without the personnel that picked of classes are over statistics record
It marks and is stored for transferring.
From in the statistical information of going to school of statistics with analyzed in classes are over statistical information, the two is compared, if it exists on
It learns statistical information and there is no classes are over statistical information, then explanation is still in school and does not leave school, and related personnel is needed to infuse
Meaning.
It in the management of kindergarten, needs to be monitored the physical condition of child, as shown in figure 5, therefore being picked personnel's body
The method of body situation detection is as follows:
Step 4100: obtaining the facial recognition information of current persons.
Step 4200: being searched from pre-set database according to facial recognition information and corresponding picked personnel
Preset facial recognition information.
Step 4300: if facial recognition information and preset facial recognition information are mutually matched success, obtaining current persons
Physical condition information and stored.
Wherein, physical condition information includes body temperature information, heart rate information etc.；The acquisition of the information can use Worn type
Smart machine is obtained, i.e. the equipment such as Intelligent bracelet.
Step 4400: if current body temperature information is greater than or lower than default benchmark body temperature information, will be picked personnel
Body temperature information feed back to this and picked and pick personnel corresponding to personnel.
If exception occurs in the body temperature of child, abnormal body temperature situation is fed back into guardian, i.e. recipient in time
Member, allows guardian that can recognize the physical condition of child in time, sees a doctor in time.
The embodiment of the present invention provides a kind of storage medium, and storage medium is stored with instruction set, which is suitable for a processing
Device is loaded and is executed including Fig. 1-Fig. 5.Each step in process.
Computer storage medium for example, USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM),
Random access memory (Random Access Memory, RAM), magnetic or disk etc. be various to can store program code
Medium.
Based on the same inventive concept, the embodiment of the present invention provides a kind of intelligent and safe management system based on kindergarten, packet
It includes: processor, for loading and executing instruction collection；And above-mentioned storage medium.
It is apparent to those skilled in the art that for convenience and simplicity of description, only with above-mentioned each function
The division progress of module can according to need and for example, in practical application by above-mentioned function distribution by different function moulds
Block is completed, i.e., the internal structure of device is divided into different functional modules, to complete all or part of function described above
Energy.The specific work process of the system, apparatus, and unit of foregoing description, can be with reference to corresponding in preceding method embodiment
Journey, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, module or unit
Division, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or group
Part can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown
Or the mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer readable storage medium.Based on this understanding, the technical solution of the application substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) or processor (processor) execute each implementation of the application
The all or part of the steps of example method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory, arbitrary access
The various media that can store program code such as memory, magnetic or disk.
More than, above embodiments are only described in detail to the technical solution to the application, but above embodiments
Illustrate to be merely used to help understand method and its core concept of the invention, should not be construed as limiting the invention.This technology
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by the technical staff in field, should all cover in this hair
Within bright protection scope.
Claims (9)
1. a kind of campus brush face picks exchange method, characterized in that include:
Obtain the current behavior information of current persons；
From the corresponding relationship between pre-set, behavioural information and command information, search and the current behavior information pair
The present instruction information answered；The behavioural information includes picking action message, and described instruction information includes and picks action message
It is mutual corresponding to pick motion analysis information；
According to picking motion analysis information to analyze to picking action message, and judge whether preset to pick with default
Action message is mutually matched；If currently picking action message and preset action message of picking being mutually matched success, identification is picked
Personnel and the personnel's incidence relation being received between personnel；
Personnel's incidence relation and default preset personnel's incidence relation are mutually matched；If personnel's incidence relation and preset personnel
Incidence relation matching is unsuccessful, then feeds back information warning.
2. brush face in campus according to claim 1 picks exchange method, characterized in that identification is picked personnel and is received
The method of personnel's incidence relation between personnel is as follows:
It obtains the first face identification information for the personnel that pick and obtains the second recognition of face information for the personnel that are received；
The corresponding preset authorization for picking personnel is searched from pre-set database according to the second recognition of face information
First face identification information and preset authorization face identification information are mutually matched by recognition of face information；
If the first face identification information and preset authorization face identification information successful match, feeds back personnel's incidence relation and institute is pre-
If preset personnel's incidence relation be mutually matched success；
If the first face identification information matches unsuccessful with preset authorization face identification information, personnel's incidence relation and institute are fed back
Preset preset personnel's incidence relation is mutually matched unsuccessful.
3. brush face in campus according to claim 1 picks exchange method, it is characterized in that: the information warning includes that sound is alert
Show information and/or light warning information and/or short message information warning and/or vibration warning information.
4. brush face in campus according to claim 1 picks exchange method, characterized in that personnel go to school situation and classes are over feelings
The method of condition statistics is as follows:
Obtain current time information；
State is picked according to current time information with determine to be presently in；If current time information is default upper class hour
Between, then being presently in state is to serve state；If current time information is default classes are over time, it is presently in state
For the state that connects that classes are over；
Obtain the facial recognition information of current persons；
The corresponding preset face for being picked personnel is searched from pre-set database according to facial recognition information to know
Other information；
If facial recognition information and preset facial recognition information are mutually matched success, state is picked to deposit according to what is be presently in
Storage is into corresponding database and forms corresponding statistical information for transferring.
5. brush face in campus according to claim 4 picks exchange method, characterized in that statistics whether it is all go to school student from
The method of school situation is as follows:
It is to go to school on the statistical information stored in database and database of going to school is that database corresponding to state is served in definition
Learn statistical information；Database corresponding to state that definition connects that classes are over is that classes are over database and the statistics letter stored in classes are over database
Breath is classes are over statistical information；
Classes are in database of transferring that classes are over, and statistical information is mutually compared with the statistical information of going to school in database of going to school, will
In the presence of statistics record being marked and being stored for by the personnel of picking without classes are over statistics record of going to school
It transfers.
6. brush face in campus according to claim 1 picks exchange method, characterized in that picked the detection of personnel's physical condition
Method it is as follows:
Obtain the facial recognition information of current persons；
The corresponding preset face for being picked personnel is searched from pre-set database according to facial recognition information to know
Other information；
If facial recognition information and preset facial recognition information are mutually matched success, the physical condition information of current persons is obtained
And it is stored.
7. brush face in campus according to claim 6 picks exchange method, it is characterized in that: the physical condition information includes body
Warm information；If current body temperature information is greater than or lower than default benchmark body temperature information, by the body temperature information for the personnel that picked
It feeds back to this and is picked and pick personnel corresponding to personnel.
8. a kind of storage medium, characterized in that it is stored with instruction set, and described instruction collection is suitable for a processor and loads and execute such as
Lower processing, comprising:
Obtain the current behavior information of current persons；
From the corresponding relationship between pre-set, behavioural information and command information, search and the current behavior information pair
The present instruction information answered；The behavioural information includes picking action message, and described instruction information includes and picks action message
It is mutual corresponding to pick motion analysis information；
According to picking motion analysis information to analyze to picking action message, and judge whether preset to pick with default
Action message is mutually matched；If currently picking action message and preset action message of picking being mutually matched success, identification is picked
Personnel and the personnel's incidence relation being received between personnel；
Personnel's incidence relation and default preset personnel's incidence relation are mutually matched；If personnel's incidence relation and preset personnel
Incidence relation matching is unsuccessful, then feeds back information warning.
9. a kind of campus brush face picks interactive system, characterized in that include:
Processor, for loading and executing instruction collection；And
Storage medium as claimed in claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910334760.9A CN110148234B (en) | 2019-04-24 | 2019-04-24 | Campus face brushing receiving and sending interaction method, storage medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910334760.9A CN110148234B (en) | 2019-04-24 | 2019-04-24 | Campus face brushing receiving and sending interaction method, storage medium and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110148234A true CN110148234A (en) | 2019-08-20 |
| CN110148234B CN110148234B (en) | 2021-06-18 |
Family
ID=67594409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910334760.9A Active CN110148234B (en) | 2019-04-24 | 2019-04-24 | Campus face brushing receiving and sending interaction method, storage medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110148234B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689653A (en) * | 2019-08-30 | 2020-01-14 | 江苏齐龙电子科技有限公司 | Intelligent security access control system |
| CN114023052A (en) * | 2021-11-04 | 2022-02-08 | 浙江大华技术股份有限公司 | Alarm method, alarm device, storage medium and electronic device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5955952A (en) * | 1997-10-24 | 1999-09-21 | Sunset Advertising Enterprises, Inc. | Method and system for locating a lost person or lost personal property |
| CN104200558A (en) * | 2014-08-29 | 2014-12-10 | 中国电子科技集团公司第二十九研究所 | Security sending and pickup control system based on biometric feature recognition and security sending and pickup control method based on biometric feature recognition |
| CN104517081A (en) * | 2014-12-12 | 2015-04-15 | 成都心泽科技有限公司 | Morning check device |
| CN104835230A (en) * | 2015-05-25 | 2015-08-12 | 郭萌 | Method for controlling locks through human face |
| CN108230517A (en) * | 2018-01-30 | 2018-06-29 | 上海思愚智能科技有限公司 | Gate inhibition's release method, device and electronic equipment |
| CN208188888U (en) * | 2017-11-06 | 2018-12-04 | 北京上古视觉科技有限公司 | System that device is registered in a kind of children education and children education is registered |
-
2019
- 2019-04-24 CN CN201910334760.9A patent/CN110148234B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5955952A (en) * | 1997-10-24 | 1999-09-21 | Sunset Advertising Enterprises, Inc. | Method and system for locating a lost person or lost personal property |
| CN104200558A (en) * | 2014-08-29 | 2014-12-10 | 中国电子科技集团公司第二十九研究所 | Security sending and pickup control system based on biometric feature recognition and security sending and pickup control method based on biometric feature recognition |
| CN104517081A (en) * | 2014-12-12 | 2015-04-15 | 成都心泽科技有限公司 | Morning check device |
| CN104835230A (en) * | 2015-05-25 | 2015-08-12 | 郭萌 | Method for controlling locks through human face |
| CN208188888U (en) * | 2017-11-06 | 2018-12-04 | 北京上古视觉科技有限公司 | System that device is registered in a kind of children education and children education is registered |
| CN108230517A (en) * | 2018-01-30 | 2018-06-29 | 上海思愚智能科技有限公司 | Gate inhibition's release method, device and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689653A (en) * | 2019-08-30 | 2020-01-14 | 江苏齐龙电子科技有限公司 | Intelligent security access control system |
| CN114023052A (en) * | 2021-11-04 | 2022-02-08 | 浙江大华技术股份有限公司 | Alarm method, alarm device, storage medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110148234B (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11978256B2 (en) | Face concealment detection | |
| Soukupova et al. | Eye blink detection using facial landmarks | |
| Cardinaux et al. | Video based technology for ambient assisted living: A review of the literature | |
| US11908245B2 (en) | Monitoring and analyzing body language with machine learning, using artificial intelligence systems for improving interaction between humans, and humans and robots | |
| Yu et al. | An online one class support vector machine-based person-specific fall detection system for monitoring an elderly individual in a room environment | |
| Wang et al. | Fall detection based on dual-channel feature integration | |
| CN106295568B (en) | The mankind's nature emotion identification method combined based on expression and behavior bimodal | |
| CN109614882A (en) | A kind of act of violence detection system and method based on human body attitude estimation | |
| Brdiczka et al. | Learning situation models in a smart home | |
| Zhou et al. | Activity analysis, summarization, and visualization for indoor human activity monitoring | |
| CN110291489A (en) | The efficient mankind identify intelligent assistant's computer in calculating | |
| US7319780B2 (en) | Imaging method and system for health monitoring and personal security | |
| CN110110710A (en) | A kind of scene abnormality recognition methods, system and intelligent terminal | |
| CN110287825B (en) | Tumble action detection method based on key skeleton point trajectory analysis | |
| CN109377616A (en) | A kind of access control system based on two-dimension human face identification | |
| CN106384237A (en) | Member authentication-management method, device and system based on face identification | |
| CN105913528A (en) | Method and device for processing access control data, method and device for access control | |
| CN104933827A (en) | Rotary camera-based alarm method and terminal | |
| CN106897659A (en) | The recognition methods of blink motion and device | |
| US10769909B1 (en) | Using sensor data to detect events | |
| CN103123690B (en) | Information acquisition device, information acquisition method, identification system and identification method | |
| CN111163650A (en) | Reminding method and reminding system based on intelligent terminal | |
| WO2020195376A1 (en) | Monitoring device, suspicious object detecting method, and recording medium | |
| US10943442B1 (en) | Customized notifications based on device characteristics | |
| CN110276320A (en) | Guard method, device, equipment and storage medium based on recognition of face |
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 |