CN110148234B - Campus face brushing receiving and sending interaction method, storage medium and system - Google Patents
Campus face brushing receiving and sending interaction method, storage medium and system Download PDFInfo
- Publication number
- CN110148234B CN110148234B CN201910334760.9A CN201910334760A CN110148234B CN 110148234 B CN110148234 B CN 110148234B CN 201910334760 A CN201910334760 A CN 201910334760A CN 110148234 B CN110148234 B CN 110148234B
- Authority
- CN
- China
- Prior art keywords
- information
- receiving
- preset
- person
- school
- 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.)
- Active
Links
Images
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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Alarm Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a campus face brushing receiving and sending interaction method, a storage medium and a system; the technical scheme is that the method comprises the steps of analyzing the receiving and sending action information according to the receiving and sending action analysis information, and judging whether the receiving and sending action information is matched with preset receiving and sending action information or not; if the current receiving and sending action information is successfully matched with the preset receiving and sending action information, identifying the personnel association relationship between the receiving and sending personnel and the received personnel; matching the personnel association relation with a preset personnel association relation; if the person association relationship is unsuccessfully matched with the preset person association relationship, warning information is fed back, the infant picking and delivering method and the infant picking and delivering system directly determine whether the infant picking and delivering system is used for picking and delivering the infant or not through analysis of the picking and delivering action, if the infant picking and delivering system is used for picking and delivering the infant, the relationship between the picking and delivering parties is judged, and once the infant picking and delivering is performed by non-associated persons, warning is given, and safety of picking and delivering the infant.
Description
Technical Field
The invention relates to an intelligent security management method, in particular to a campus face brushing receiving and sending interaction method, a storage medium and a system.
Background
The kindergarten aims to relieve the restriction of time, space and environment on family culture of children and lead the body, intelligence and mood of the children to be healthily developed. The kindergarten can be said to be the happy place of child, can help child's healthy happy place to spend childhood time, not only learns knowledge, but also can contact the collective life from childhood. Kindergarten education is the foundation of the whole education system, and is prepared education (complete and healthy in character, good in behavior habit, and preliminary natural and social common knowledge) for children. The education course is not obviously distinguished and is probably composed of five fields of language, science, art, health, society and the like and various activities. The fields are fused with each other to determine teaching contents.
The working rhythm of the current social life is faster and faster, many parents cannot go to the kindergarten to pick up and deliver their children, and only the relatives, friends, nurses and other people need to be entrusted to take charge of picking up and delivering, and certain potential safety hazards can be brought to the picking up and delivering work of the kindergarten children. Under the condition that the number of the receiving and sending persons is large, the difficulty of identifying the receiving and sending persons by the staff is increased, and the result that the infants are falsely claimed is caused. Furthermore, because the pick-up information is not reliably recorded, the responsibility between the kindergarten and the parents of the baby is difficult to define after a problem occurs. At present, most kindergartens mainly adopt the pick-up and delivery card to identify the pick-up and delivery person, but the pick-up and delivery card is easy to be stolen and copied, if the pick-up and delivery card is lost, the safety hazard can be brought, lawless persons can use the pick-up and delivery card to impersonate the baby, and then the safety of the baby is threatened, so that the pick-up and delivery management of the kindergartens still has certain improvement space at present.
Disclosure of Invention
The first purpose of the invention is to provide a campus face brushing receiving and sending interaction method, which improves the safety of infant receiving and sending according to the analysis of receiving and sending actions and the judgment of receiving and sending personnel.
The technical purpose of the invention is realized by the following technical scheme:
a campus face brushing receiving and sending interaction method comprises the following steps:
acquiring current behavior information of current personnel;
searching current instruction information corresponding to the current behavior information from a preset corresponding relation between the behavior information and the instruction information; the behavior information comprises receiving and sending action information, and the instruction information comprises receiving and sending action analysis information corresponding to the receiving and sending action information;
analyzing the receiving and sending action information according to the receiving and sending action analysis information, and judging whether the receiving and sending action information is matched with preset receiving and sending action information or not; if the current receiving and sending action information is successfully matched with the preset receiving and sending action information, identifying the personnel association relationship between the receiving and sending personnel and the received personnel;
matching the personnel association relation with a preset personnel association relation; and if the person association relation is unsuccessfully matched with the preset person association relation, feeding back warning information.
By adopting the scheme, the personnel actions in the crowd in front of the kindergarten are obtained, namely the pickup actions are analyzed, whether the personnel actions are matched with the preset pickup actions or not is judged, if the matching is successful, the current person is picking up the baby, and whether the person is the correct person is further judged under the condition that the person is picked up or not is determined, namely the relationship between the person to be picked up and the person to be picked up is judged, and if the person to be picked up and the person to be picked up are not related, the risk that a lawless person falsely picks up the baby is judged; therefore, the alarm feedback is carried out, security personnel can check the alarm feedback, the safety in the infant receiving and delivering process is improved, each infant is ensured to be received and delivered by the personnel associated with the infant, and the association mode cannot be utilized by lawbreakers.
Preferably, the method of identifying the person relationship between the receiving person and the receiving person is as follows:
acquiring first face identification information of a receiving person and second face identification information of a received person;
searching preset authorized face identification information of the corresponding receiving and sending personnel from a preset database according to the second face identification information, and matching the first face identification information with the preset authorized face identification information;
if the first face identification information is successfully matched with the preset authorized face identification information, the feedback person incidence relation is successfully matched with the preset person incidence relation;
and if the first face identification information is unsuccessfully matched with the preset authorized face identification information, the feedback person incidence relation is unsuccessfully matched with the preset person incidence relation.
By adopting the scheme, the preset authorized face identification information corresponding to the guardian is preset in the database, the number of the guardians can be set, namely, the personnel of the infant are frequently delivered, the preset authorized face identification information corresponding to the delivery personnel is searched for through the second face identification information for matching through the first face identification information and the second face identification information detected in real time, if the matching is successful, the personnel are related to each other, and if the matching is unsuccessful, the personnel are not related to each other.
Preferably, the warning information includes sound warning information and/or light warning information and/or short message warning information and/or vibration warning information.
By adopting the scheme, the arrangement of various warning modes can be suitable for various types of environments, security personnel and related personnel can be ensured to know the conditions, and the warning modes can adopt one or combination of more of the warning modes, so that the warning effect is improved.
Preferably, the statistical method for the school and school situation of the staff is as follows:
acquiring current time information;
judging the current receiving and sending state according to the current time information; if the current time information is the preset learning time, the current state is the learning sending state; if the current time information is the preset school playing time, the current state is the school receiving and playing state;
acquiring face identification information of a current person;
searching preset facial recognition information of the corresponding person to be picked up from a preset database according to the facial recognition information;
if the face identification information is successfully matched with the preset face identification information, storing the face identification information into a corresponding database according to the current receiving and sending state and forming corresponding statistical information for calling.
By adopting the scheme, whether the child is to school or to put school is judged according to the time state, the school and the put school of the child are recorded respectively, which student is determined by the face recognition function, and the acquired information is recorded so as to be convenient to call.
Preferably, the method for counting the leaving condition of all students is as follows:
defining a database corresponding to the state of the school entry as a school entry database and defining statistical information stored in the school entry database as school entry statistical information; defining a database corresponding to the school receiving and releasing state as a school releasing database and defining statistical information stored in the school releasing database as school releasing statistical information;
and calling the playing statistical information in the playing database and the upper school statistical information in the upper school database to be compared with each other, marking the picked-up personnel with the upper school statistical information record but without the playing statistical information record, and storing the marked picked-up personnel for calling.
By adopting the scheme, the statistical information of the school and the statistical information of the school are analyzed and compared, if the statistical information of the school exists and the statistical information of the school does not exist, the fact that the school is still in the school but not out of the school is shown, and the attention of related personnel is needed.
Preferably, the method for detecting the physical condition of the person to be sent is as follows:
acquiring face identification information of a current person;
searching preset facial recognition information of the corresponding person to be picked up from a preset database according to the facial recognition information;
and if the facial recognition information is successfully matched with the preset facial recognition information, acquiring and storing the body state information of the current personnel.
By adopting the scheme, the face recognition is carried out on the current personnel, which student is determined, the body state information of the obtained student is stored, and the supervision of the kindergarten on the body state of the child is improved.
Preferably, the physical state information includes body temperature information; and if the current body temperature information is greater than or lower than the preset reference body temperature information, feeding back the body temperature information of the picked-up person to the picked-up person corresponding to the picked-up person.
By adopting the scheme, if the body temperature of the child is abnormal, the abnormal body temperature condition is timely fed back to the guardian, namely, the guardian can timely know the body condition of the child and timely seek medical advice.
A second object of the present invention is to provide a storage medium capable of storing a corresponding instruction set and improving the safety of infant delivery by analyzing the delivery operation and judging the delivery person.
The technical purpose of the invention is realized by the following technical scheme:
a storage medium storing a set of instructions adapted to be loaded by a processor and to perform a process comprising:
acquiring current behavior information of current personnel;
searching current instruction information corresponding to the current behavior information from a preset corresponding relation between the behavior information and the instruction information; the behavior information comprises receiving and sending action information, and the instruction information comprises receiving and sending action analysis information corresponding to the receiving and sending action information;
analyzing the receiving and sending action information according to the receiving and sending action analysis information, and judging whether the receiving and sending action information is matched with preset receiving and sending action information or not; if the current receiving and sending action information is successfully matched with the preset receiving and sending action information, identifying the personnel association relationship between the receiving and sending personnel and the received personnel;
matching the personnel association relation with a preset personnel association relation; and if the person association relation is unsuccessfully matched with the preset person association relation, feeding back warning information.
By adopting the scheme, the personnel actions in the crowd in front of the kindergarten are obtained, namely the pickup actions are analyzed, whether the personnel actions are matched with the preset pickup actions or not is judged, if the matching is successful, the current person is picking up the baby, and whether the person is the correct person is further judged under the condition that the person is picked up or not is determined, namely the relationship between the person to be picked up and the person to be picked up is judged, and if the person to be picked up and the person to be picked up are not related, the risk that a lawless person falsely picks up the baby is judged; therefore, the alarm feedback is carried out, security personnel can check the alarm feedback, the safety in the infant receiving and delivering process is improved, each infant is ensured to be received and delivered by the personnel associated with the infant, and the association mode cannot be utilized by lawbreakers.
A third object of the present invention is to provide a kindergarten-based intelligent security management system that improves the security of baby delivery based on analysis of delivery operations and judgment of delivery personnel.
The technical purpose of the invention is realized by the following technical scheme:
a kindergarten-based intelligent security management system, comprising:
a processor for loading and executing a set of instructions; and
the storage medium described above.
By adopting the scheme, the personnel actions in the crowd in front of the kindergarten are obtained, namely the pickup actions are analyzed, whether the personnel actions are matched with the preset pickup actions or not is judged, if the matching is successful, the current person is picking up the baby, and whether the person is the correct person is further judged under the condition that the person is picked up or not is determined, namely the relationship between the person to be picked up and the person to be picked up is judged, and if the person to be picked up and the person to be picked up are not related, the risk that a lawless person falsely picks up the baby is judged; therefore, the alarm feedback is carried out, security personnel can check the alarm feedback, the safety in the infant receiving and delivering process is improved, each infant is ensured to be received and delivered by the personnel associated with the infant, and the association mode cannot be utilized by lawbreakers.
In conclusion, the invention has the following beneficial effects: whether the infant is delivered or not is directly determined through analysis of the delivering action, if the infant is delivered, the relationship between the infant and the delivering party is judged, and once the infant is delivered by a non-related person, warning is given, so that the safety of delivering the infant is improved.
Drawings
FIG. 1 is a block flow diagram of a delivery supervision method;
FIG. 2 is a block flow diagram of a method of identifying a person-to-person relationship between a sending person and a received person;
FIG. 3 is a block flow diagram of a method for statistics of school and school attendance of a person;
FIG. 4 is a block flow diagram of a method of counting the departure of all students;
fig. 5 is a block flow diagram of a method of physical condition detection of a person being picked up.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present invention.
The embodiment of the invention provides a campus face brushing receiving and sending interaction method, which comprises the following steps: acquiring current behavior information of current personnel; searching current instruction information corresponding to the current behavior information from a preset corresponding relation between the behavior information and the instruction information; the behavior information comprises receiving and sending action information, and the instruction information comprises receiving and sending action analysis information corresponding to the receiving and sending action information; analyzing the receiving and sending action information according to the receiving and sending action analysis information, and judging whether the receiving and sending action information is matched with preset receiving and sending action information or not; if the current receiving and sending action information is successfully matched with the preset receiving and sending action information, identifying the personnel association relationship between the receiving and sending personnel and the received personnel; matching the personnel association relation with a preset personnel association relation; and if the person association relation is unsuccessfully matched with the preset person association relation, feeding back warning information.
In the embodiment of the invention, the personnel actions in the crowd in front of the kindergarten are acquired, namely the pickup actions are analyzed, whether the personnel actions are matched with the preset pickup actions or not is judged, if the matching is successful, the current person is picking up the baby, and whether the person is the correct person is further judged under the condition that the person is picked up or not is determined, namely the relationship between the person to be picked up and the person to be picked up is judged, and if the person to be picked up and the person to be picked up are not related, the risk that a lawless person falsely picks up the baby is judged; therefore, the alarm feedback is carried out, security personnel can check the alarm feedback, the safety in the infant receiving and delivering process is improved, each infant is ensured to be received and delivered by the personnel associated with the infant, and the association mode cannot be utilized by lawbreakers.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship, unless otherwise specified.
The embodiments of the present invention will be described in further detail with reference to the drawings attached hereto.
Referring to fig. 1, an embodiment of the present invention provides a campus face brushing delivery interaction method, wherein a main flow of a delivery supervision method is described as follows.
As shown in fig. 1:
step 1100: and acquiring the current behavior information of the current personnel.
The method comprises the steps that current behavior information of current personnel is obtained through a camera, the behavior information comprises a great amount of action information, such as walking action, running action, object lifting action and the like, and the behavior information further comprises receiving and sending action information, namely conventional actions of receiving and sending children; the pick-up action information includes actions of holding a child, pulling a child, and the like.
Step 1200: searching current instruction information corresponding to the current behavior information from a preset corresponding relation between the behavior information and the instruction information; the instruction information includes transfer operation analysis information corresponding to the transfer operation information.
When a large amount of action information is acquired from the camera, the action information is analyzed through the instruction information to screen the required information.
Step 1300: analyzing the receiving and sending action information according to the receiving and sending action analysis information, and judging whether the receiving and sending action information is matched with preset receiving and sending action information or not; and if the current receiving and sending action information is successfully matched with the preset receiving and sending action information, identifying the personnel association relationship between the receiving and sending personnel and the received personnel.
The method comprises the following steps that in the analysis process, preset receiving and sending action information needs to be established firstly, namely a basic matching model is established, in the establishing process, model training needs to be carried out, and the method comprises the following steps:
the method comprises the steps that a plurality of depth information frames and skeleton information frames are used for collecting training information, original action information transmitted by a collector is stored according to a set storage format and serves as sample data of original actions; carrying out regularization processing on sample data, namely discretizing the sample data into a sample three-dimensional vector set of actions through discretizing the coordinates of the skeleton points, and then obtaining a characteristic three-dimensional vector set through a characteristic extraction algorithm; thereby forming a corresponding base matching model.
The method for discretizing the sample data into the sample three-dimensional vector set of the motion by discretizing the coordinates of the bone points comprises the following processing steps of:
a. a unified coordinate system, namely, the depth information data and the skeleton information data of each frame are subjected to coordinate transformation and unified into the same world coordinate system;
b. discretizing the skeleton point coordinates, namely discretizing each skeleton information data point coordinate in the current frame, wherein the discretizing step comprises the following steps:
i) calculating the motion vector of the skeleton point according to the same skeleton point coordinate in each frame adjacent to the front frame and the rear frame;
ii) finding a unit cube in a target discrete coordinate system corresponding to the skeleton point;
iii) synthesizing the motion vector of the bone point into the current motion vector of the unit cube;
c. discretizing the depth information data coordinates, namely discretizing the depth data points near the skeleton point if the skeleton point is a hand point during discretizing the skeleton point coordinates, wherein the discretized unit cube corresponding to the depth information data has the same motion vector as the skeleton point;
d. and repeating the steps a, b and c for each frame, and generating a corresponding sample three-dimensional vector set for each action to be recognized.
The feature extraction algorithm is specifically as follows:
a. calculating the occurrence frequency of each three-dimensional coordinate point in all three-dimensional vector sets;
b. calculating a characteristic coefficient according to the occurrence frequency, namely, the characteristic coefficient = the occurrence frequency of the three-dimensional coordinate point/the number of the action three-dimensional vector set;
c. and if the characteristic coefficient is more than 50%, the three-dimensional vector set of the point is considered to belong to the characteristic three-dimensional vector set.
In the process of analyzing the sent action information, firstly, fuzzy recognition is carried out through a characteristic three-dimensional vector set, after the search range is narrowed, accurate recognition is further carried out, and therefore the action to be recognized is determined to be a current candidate action. The set storage format includes the following fields: action ID, action name, logarithm of action information frame, depth information frame, and skeleton information frame. Each element in the depth information frame is depth information on its corresponding coordinate; the skeleton information frame is composed of human skeleton point coordinate data; the logarithm of action information frames refers to how many pairs of depth information frames and skeleton information frames are in an action. The collector comprises a depth detection camera and a third-party SDK.
The "fuzzy recognition" is specifically: and calculating the distances between the three-dimensional vector set and all the characteristic three-dimensional vectors in the current system, and if the distances are smaller than the threshold value corresponding to the characteristic three-dimensional vectors, taking the action corresponding to the characteristic three-dimensional vectors as a candidate action. The "precise identification" is specifically: and sorting all the candidate actions according to the distance from small to large, then sequentially calculating the distance between the sample three-dimensional vector set in each candidate action and the three-dimensional vector set of the action to be identified, and if the minimum distance is smaller than a preset threshold value, automatically determining that the receiving and sending action information is successfully matched with the preset receiving and sending action information, namely finishing the identification process.
The precision-reducing discretization processing is carried out on the original data, so that the noise of the original data can be reduced, and the operation amount can be reduced; meanwhile, a multi-level feature matching algorithm is adopted, and the action training and recognition speed is further increased.
Step 1400: matching the personnel association relation with a preset personnel association relation; and if the person association relation is unsuccessfully matched with the preset person association relation, feeding back warning information.
The warning information comprises sound warning information and/or lamplight warning information and/or short message warning information and/or vibration warning information; the voice warning information is reminded through equipment such as a loudspeaker, the light warning information is warned through a warning lamp arranged in a security room, the short message warning information is reminded through a mobile phone or pop-up window information sent by APP software on an intelligent terminal, and the like, and the vibration warning information is reminded through vibration actions sent by the mobile phone or equipment with a vibration sensor; the above warning mode can adopt one of them, also can adopt the combination of several kinds, in this embodiment, preferably adopts the mode that sound warning information and light warning information combine each other.
As shown in fig. 2, the method for identifying the person association relationship between the receiving person and the receiving person is as follows:
step 1410: acquiring first face identification information of a receiving person and second face identification information of a received person;
step 1420: searching preset authorized face identification information of the corresponding receiving and sending personnel from a preset database according to the second face identification information, and matching the first face identification information with the preset authorized face identification information;
step 1430: if the first face identification information is successfully matched with the preset authorized face identification information, the feedback person incidence relation is successfully matched with the preset person incidence relation;
step 1440: and if the first face identification information is unsuccessfully matched with the preset authorized face identification information, the feedback person incidence relation is unsuccessfully matched with the preset person incidence relation.
Preset authorized face identification information corresponding to guardians is preset in a database, the number of the guardians can be set, namely, the guardians frequently receive and send infants, the preset authorized face identification information corresponding to the guardians is searched for and matched with the second face identification information through the first face identification information and the second face identification information detected in real time, if the matching is successful, the matched persons are related persons, and if the matching is unsuccessful, the matched persons are not related persons.
In the management of a kindergarten, the learning and leaving conditions of the infants need to be counted, and unnecessary dangers of the infants are avoided. As shown in fig. 3, the statistical method for the school situation and the school situation of the staff is as follows:
step 2100: and acquiring current time information.
The time information can be obtained through the internet and other modes, and the corresponding local time can be obtained.
Step 2200: and judging the current receiving and sending state according to the current time information.
If the current time information is the preset time for getting to school, the current state is the state for getting to school; if the current time information is the preset school playing time, the current state is the school receiving and playing state; in this embodiment, the preset school time is from 6 to 10, and the preset school time is from 15 to 18.
Step 2300: face identification information of the current person is acquired.
Wherein, the face identification information of the related person is identified by the preset camera device. The identification process generally comprises three steps: (1) firstly, establishing a face image file of the face. That is, a camera is used for collecting face image files of faces of unit personnel or taking pictures of the face image files to form face image files, and the face image files are generated into face print (Faceprint) codes and stored. (2) And acquiring the current human body face image. That is, the face image of the person who is coming in and going out is captured by the camera or the photo is taken for input, and the face print code is generated by the current face image file. (3) And comparing the current face print code with the file stock. The face print code of the current face image is searched and compared with the face print code in the file stock. The above-described "face-print coding" approach works based on the essential features and beginning of the face of a human face. The facial print code is resistant to changes in light, skin tone, facial hair, hairstyle, glasses, expression and posture, and has strong reliability, so that it can accurately recognize a person from millions of people. The human face recognition process can be automatically, continuously and in real time completed by using common image processing equipment.
Step 2400: and searching preset facial recognition information of the corresponding person to be picked up from a preset database according to the facial recognition information.
Wherein, the face comparison is to confirm the identity of the detected face image or to search the target in the face image library. This means that the sampled face images are compared with the face images in the stock in sequence, and the best matching object is found. Therefore, the description of the face image determines the specific method and performance of face image recognition. Two description methods of a characteristic vector and a surface pattern template are mainly adopted:
1. the vectored representation: the method is that the size, position, distance and other attributes of facial image five sense organ contour such as iris, nose wing, mouth angle and the like are firstly determined, then the geometrical characteristic quantities of the facial image five sense organ contour are calculated, and the characteristic quantities form a characteristic vector for describing the facial image.
2. Surface pattern template method: the method is to store several standard face image templates or face image organ templates in the library, and to match all the pixels of the sampled face image with all the templates in the library by using normalized correlation measurement during the comparison. In addition, there are methods that use pattern-recognized autocorrelation networks or features in conjunction with templates.
The core of the face recognition technology is actually 'local human body feature analysis' and 'graph/nerve recognition algorithm'. "this algorithm is a method using the organs and features of the human face. If the corresponding geometric relationship is multiple data, the identification parameters are compared with all the original parameters in the database, judged and confirmed. Generally requiring a judgment time of less than 1 second.
Step 2500: if the face identification information is successfully matched with the preset face identification information, storing the face identification information into a corresponding database according to the current receiving and sending state and forming corresponding statistical information for calling.
If the face recognition is successful, the corresponding student learns or has already put the student, and then corresponding data are counted.
Through the summarized statistical information, as shown in fig. 4, it can be analyzed whether the students in the school have departed from the school, and the specific method is as follows:
step 3100: defining a database corresponding to the state of the school entry as a school entry database and defining statistical information stored in the school entry database as school entry statistical information; and defining the database corresponding to the accepting and releasing state as a releasing database and the statistical information stored in the releasing database as releasing statistical information.
Step 3200: and calling the put statistics information in the put-school database and comparing the put-school statistics information with the upper-school statistics information in the upper-school database.
Step 3300: the picked-up person who has the upper school statistics record but does not have the lower school statistics record is marked and stored for retrieval.
And analyzing the statistical information from the school statistics information and the school statistics information, comparing the statistical information with the school statistics information, and if the school statistics information exists and the school statistics information does not exist, indicating that the school is still in the school and is not out of the school, so that the attention of related personnel is required.
In the management of a kindergarten, since it is necessary to monitor the physical condition of a child, as shown in fig. 5, a method of detecting the physical condition of a person to be delivered is as follows:
step 4100: face identification information of the current person is acquired.
Step 4200: and searching preset facial recognition information of the corresponding person to be picked up from a preset database according to the facial recognition information.
Step 4300: and if the facial recognition information is successfully matched with the preset facial recognition information, acquiring and storing the body state information of the current personnel.
Wherein, the body state information comprises body temperature information, heart rate information and the like; this information's acquirement can adopt wearable smart machine to acquire, equipment such as intelligent bracelet promptly.
Step 4400: and if the current body temperature information is greater than or lower than the preset reference body temperature information, feeding back the body temperature information of the picked-up person to the picked-up person corresponding to the picked-up person.
If the body temperature of the child is abnormal, the abnormal body temperature condition is timely fed back to the guardian, namely, the guardian can timely know the body condition of the child and timely seek medical advice.
Embodiments of the present invention provide a storage medium storing a set of instructions adapted to be loaded and executed by a processor, including fig. 1-5. Each step in the flow.
Computer storage media include, for example: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Based on the same invention concept, the embodiment of the invention provides an intelligent safety management system based on a kindergarten, which comprises: a processor for loading and executing a set of instructions; and the storage medium described above.
It will be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.
The above embodiments are only used to describe the technical solutions of the present application in detail, but the above embodiments are only used to help understanding the method and the core idea of the present invention, and should not be construed as limiting the present invention. Those skilled in the art should also appreciate that they can easily conceive of various changes and substitutions within the technical scope of the present disclosure.
Claims (7)
1. A campus face brushing receiving and sending interaction method is characterized by comprising the following steps:
acquiring current behavior information of current personnel;
searching current instruction information corresponding to the current behavior information from a preset corresponding relation between the behavior information and the instruction information; the behavior information comprises receiving and sending action information, and the instruction information comprises receiving and sending action analysis information corresponding to the receiving and sending action information;
analyzing the receiving and sending action information according to the receiving and sending action analysis information, and judging whether the receiving and sending action information is matched with preset receiving and sending action information or not;
the method comprises the following steps that firstly, preset receiving and sending action information needs to be established in the analysis process, model training needs to be carried out in the establishing process, and the method comprises the following steps: the method comprises the steps that a plurality of depth information frames and skeleton information frames are used for collecting training information, original action information transmitted by a collector is stored according to a set storage format and serves as sample data of original actions; carrying out regularization processing on sample data, firstly discretizing the sample data into a sample three-dimensional vector set of actions through discretizing the coordinates of the skeleton points, and then obtaining a characteristic three-dimensional vector set through a characteristic extraction algorithm; thereby forming a corresponding base matching model;
if the current receiving and sending action information is successfully matched with the preset receiving and sending action information, identifying the personnel association relationship between the receiving and sending personnel and the received personnel;
matching the personnel association relation with a preset personnel association relation; if the person association relation is unsuccessfully matched with the preset person association relation, warning information is fed back;
the statistical method of the school and school situation of the person is as follows:
acquiring current time information;
judging the current receiving and sending state according to the current time information; if the current time information is the preset learning time, the current state is the learning sending state; if the current time information is the preset school playing time, the current state is the school receiving and playing state;
acquiring face identification information of a current person;
searching preset facial recognition information of the corresponding person to be picked up from a preset database according to the facial recognition information;
if the face identification information is successfully matched with the preset face identification information, storing the face identification information into a corresponding database according to the current receiving and sending state and forming corresponding statistical information for calling;
the method for counting the leaving condition of all students is as follows:
defining a database corresponding to the state of the school entry as a school entry database and defining statistical information stored in the school entry database as school entry statistical information; defining a database corresponding to the school receiving and releasing state as a school releasing database and defining statistical information stored in the school releasing database as school releasing statistical information;
and calling the playing statistical information in the playing database and the upper school statistical information in the upper school database to be compared with each other, marking the picked-up personnel with the upper school statistical information record but without the playing statistical information record, and storing the marked picked-up personnel for calling.
2. The campus face brushing pick-up interaction method as claimed in claim 1, wherein the method for identifying the person association relationship between the pick-up person and the received person is as follows:
acquiring first face identification information of a receiving person and second face identification information of a received person;
searching preset authorized face identification information of the corresponding receiving and sending personnel from a preset database according to the second face identification information, and matching the first face identification information with the preset authorized face identification information;
if the first face identification information is successfully matched with the preset authorized face identification information, the feedback person incidence relation is successfully matched with the preset person incidence relation;
and if the first face identification information is unsuccessfully matched with the preset authorized face identification information, the feedback person incidence relation is unsuccessfully matched with the preset person incidence relation.
3. The campus brushing and sending interaction method according to claim 1, wherein the campus brushing and sending interaction method comprises the following steps: the warning information comprises sound warning information and/or lamplight warning information and/or short message warning information and/or vibration warning information.
4. The campus brushing face pick-up interaction method as claimed in claim 1, wherein the method for detecting the physical condition of the picked-up person is as follows:
acquiring face identification information of a current person;
searching preset facial recognition information of the corresponding person to be picked up from a preset database according to the facial recognition information;
and if the facial recognition information is successfully matched with the preset facial recognition information, acquiring and storing the body state information of the current personnel.
5. The campus brushing and sending interaction method according to claim 4, wherein the campus brushing and sending interaction method comprises the following steps: the body state information comprises body temperature information; and if the current body temperature information is greater than or lower than the preset reference body temperature information, feeding back the body temperature information of the picked-up person to the picked-up person corresponding to the picked-up person.
6. A storage medium having stored thereon a set of instructions adapted to be loaded by a processor and to perform a process comprising:
acquiring current behavior information of current personnel;
searching current instruction information corresponding to the current behavior information from a preset corresponding relation between the behavior information and the instruction information; the behavior information comprises receiving and sending action information, and the instruction information comprises receiving and sending action analysis information corresponding to the receiving and sending action information;
analyzing the receiving and sending action information according to the receiving and sending action analysis information, and judging whether the receiving and sending action information is matched with preset receiving and sending action information or not;
the method comprises the following steps that firstly, preset receiving and sending action information needs to be established in the analysis process, model training needs to be carried out in the establishing process, and the method comprises the following steps: the method comprises the steps that a plurality of depth information frames and skeleton information frames are used for collecting training information, original action information transmitted by a collector is stored according to a set storage format and serves as sample data of original actions; carrying out regularization processing on sample data, firstly discretizing the sample data into a sample three-dimensional vector set of actions through discretizing the coordinates of the skeleton points, and then obtaining a characteristic three-dimensional vector set through a characteristic extraction algorithm; thereby forming a corresponding base matching model;
if the current receiving and sending action information is successfully matched with the preset receiving and sending action information, identifying the personnel association relationship between the receiving and sending personnel and the received personnel;
matching the personnel association relation with a preset personnel association relation; if the person association relation is unsuccessfully matched with the preset person association relation, warning information is fed back;
the statistical method of the school and school situation of the person is as follows:
acquiring current time information;
judging the current receiving and sending state according to the current time information; if the current time information is the preset learning time, the current state is the learning sending state; if the current time information is the preset school playing time, the current state is the school receiving and playing state;
acquiring face identification information of a current person;
searching preset facial recognition information of the corresponding person to be picked up from a preset database according to the facial recognition information;
if the face identification information is successfully matched with the preset face identification information, storing the face identification information into a corresponding database according to the current receiving and sending state and forming corresponding statistical information for calling;
the method for counting the leaving condition of all students is as follows:
defining a database corresponding to the state of the school entry as a school entry database and defining statistical information stored in the school entry database as school entry statistical information; defining a database corresponding to the school receiving and releasing state as a school releasing database and defining statistical information stored in the school releasing database as school releasing statistical information;
and calling the playing statistical information in the playing database and the upper school statistical information in the upper school database to be compared with each other, marking the picked-up personnel with the upper school statistical information record but without the playing statistical information record, and storing the marked picked-up personnel for calling.
7. The utility model provides a campus brush face meets and send off interactive system, characterized by includes:
a processor for loading and executing a set of instructions; and
the storage medium of claim 6.
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 CN110148234A (en) | 2019-08-20 |
| CN110148234B true 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) |
Families Citing this family (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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110148234A (en) | 2019-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009521B (en) | Face image matching method, device, terminal and storage medium | |
| Vishnu et al. | Human fall detection in surveillance videos using fall motion vector modeling | |
| CN106897658B (en) | Method and device for identifying human face living body | |
| US20210248356A1 (en) | Method and apparatus for face recognition | |
| CN100361131C (en) | Information processing apparatus, information processing method, and computer program | |
| CN109522815A (en) | A kind of focus appraisal procedure, device and electronic equipment | |
| CN105590097B (en) | Dual camera collaboration real-time face identification security system and method under the conditions of noctovision | |
| CN112328999A (en) | Double-recording quality inspection method and device, server and storage medium | |
| Indi et al. | Detection of malpractice in e-exams by head pose and gaze estimation | |
| CN109886080A (en) | Human face in-vivo detection method, device, electronic equipment and readable storage medium storing program for executing | |
| JP2005202653A (en) | Behavior recognition device and method, animal object recognition device and method, equipment control device and method, and program | |
| CN108229375B (en) | Method and device for detecting face image | |
| KR102593624B1 (en) | Online Test System using face contour recognition AI to prevent the cheating behaviour and method thereof | |
| CN110148234B (en) | Campus face brushing receiving and sending interaction method, storage medium and system | |
| KR102581415B1 (en) | UBT system using face contour recognition AI to prevent the cheating behaviour and method thereof | |
| CN114495241A (en) | Image identification method and device, electronic equipment and storage medium | |
| CN109190528A (en) | Biopsy method and device | |
| CN111931628A (en) | Training method and device of face recognition model and related equipment | |
| Chua et al. | Vision-based hand grasping posture recognition in drinking activity | |
| KR20230007250A (en) | UBT system using face contour recognition AI and method thereof | |
| KR20230110681A (en) | Online Test System using face contour recognition AI to prevent the cheating behaviour by using a front camera of examinee terminal and an auxiliary camera and method thereof | |
| Saraswat et al. | Anti-spoofing-enabled contactless attendance monitoring system in the COVID-19 pandemic | |
| CN111738199A (en) | Image information verification method, image information verification device, image information verification computing device and medium | |
| CN107363862B (en) | Social intercourse system based on robot | |
| CN110443122A (en) | Information processing method and Related product |
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 |