CN117421446B - Multi-crowd-oriented face quick retrieval analysis system and method - Google Patents
Multi-crowd-oriented face quick retrieval analysis system and method Download PDFInfo
- Publication number
- CN117421446B CN117421446B CN202311420281.1A CN202311420281A CN117421446B CN 117421446 B CN117421446 B CN 117421446B CN 202311420281 A CN202311420281 A CN 202311420281A CN 117421446 B CN117421446 B CN 117421446B
- Authority
- CN
- China
- Prior art keywords
- monitored
- visitor
- area
- garden
- personnel
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims description 35
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 238000010586 diagram Methods 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 230000001351 cycling effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims 2
- 230000007717 exclusion Effects 0.000 claims 1
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
- G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Library & Information Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of intelligent security, in particular to a face quick retrieval analysis system and a face quick retrieval analysis method for multiple people, wherein the system comprises an identity information identification module, a threat coefficient analysis module, an emergency measure implementation module and an emergency scheme calibration module, the threat coefficient analysis module is used for monitoring the state of an early warning device of an area to be monitored in real time, analyzing the advancing gesture of a visitor according to a monitoring result, predicting the follow-up route information of the visitor according to the analysis result, and calculating the threat coefficient of the visitor in a forbidden area of the area to be monitored.
Description
Technical Field
The invention relates to the technical field of intelligent security, in particular to a face rapid retrieval and analysis system and method for multiple people.
Background
With the development of intelligent technology, automatic character identification aiming at a video screen picture acquired by front-end monitoring equipment becomes an important development direction at present, wherein the automatic character identification is mainly realized based on face feature extraction and identification, and particularly in urban public spaces such as stations, squares, airports, commercial streets and the like, the identification can be rapidly locked by unfolding the identification aiming at the monitoring video picture with a large intersecting visual field range, so that the security and protection efficiency and pertinence are improved, and the public order and public safety are maintained.
The feature extraction and the identification of the face need stronger computing power, and particularly, a plurality of face areas exist in a monitoring video picture with a wide-angle visual field range, in the prior art, identity authentication can only be carried out through a face recognition device in a park, the advancing direction of a visitor in the monitoring area cannot be known, and when the visitor advances to a forbidden area, the visitor is likely to threaten a park security system, so that a face quick retrieval analysis system and a face quick retrieval analysis method for a plurality of people are needed.
Disclosure of Invention
The invention aims to provide a face quick retrieval analysis system and method for multiple crowds, which aims to solve the problems in the background technology, and the invention provides the following technical scheme:
a face quick retrieval analysis method for multiple people comprises the following steps:
s1, acquiring staff database data of an area to be monitored, checking identity information of personnel entering a garden according to staff warehousing information, monitoring a path of the personnel entering the garden, judging whether a attribution destination of the corresponding personnel entering the garden is abnormal according to a monitoring result, and generating an early warning signal according to a judging result;
s2, monitoring the state of an early warning device of the area to be monitored in real time, analyzing the advancing gesture of the visitor according to the monitoring result, predicting the follow-up route information of the visitor by combining the analysis result, and calculating the threat coefficient of the forbidden area of the area to be monitored;
S3, combining threat coefficients of a visitor in a forbidden zone of the area to be monitored to generate an emergency driving condition value, and combining information of personnel entering a garden in a staff table M1 in the area to be monitored to generate optimal emergency treatment personnel selection;
S4, comprehensively judging the rationality of the optimal emergency treatment personnel, calibrating the emergency treatment personnel by combining the judging result, and taking corresponding measures to drive away the visitor according to the calibrated emergency treatment personnel selection.
Further, the method in S1 includes the following steps:
Step 1001, obtaining employee database data in the area to be monitored, judging the information of the personnel entering the garden by combining the face recognition device, binding the judging result with the personnel entering the garden, marking as a set A,
A＝{[A1,P(A1)],[A2,P(A2)],[A3,P(A3)],...,[An,P(An)]},
Wherein A n represents the nth person entering the garden, P () represents a conditional judgment function, P (A n) represents the judgment result of the information of the nth person entering the garden, n represents the number of persons entering the garden,
If the face recognition device judges that the information of the person entering the garden is the data in the staff library, the judgment result of the corresponding information of the person entering the garden is output as 1,
If the face recognition device judges that the information of the person entering the garden is not the data in the staff library, outputting a judgment result of the information of the corresponding person entering the garden to be 0;
Step 1002, dividing the personnel entering the garden based on the determination result in step 1001, and recording the determination result in the personnel table M1 of the personnel entering the garden corresponding to the data in the staff library, wherein the determination result is not in the visitor table M2 of the personnel entering the garden corresponding to the data in the staff library;
step 1003, any one extracts the information of the personnel entering the garden in the staff table M1, and combines the staff database data matching result to obtain the corresponding personnel on duty purpose, monitors the corresponding personnel entering the garden on duty condition in real time, and sends the monitoring report to the cloud platform in real time;
step 1004, randomly extracting the information of the personnel entering the garden in the visitor table M2, identifying whether the personnel entering the garden enter a forbidden zone in real time through a security device in the area to be monitored,
If the security device equipped in the forbidden zone identifies the personnel entering the garden in the visitor table M2, an early warning signal is sent out, the personnel entering the garden corresponding to the triggering early warning signal is marked,
If the security device equipped in the forbidden zone does not identify the personnel entering the garden in the visitor table M2, no early warning signal is sent.
According to the invention, employee database data in the area to be monitored is obtained, the information of the personnel entering the garden is judged by combining the face recognition device, and the mechanical energy of the personnel entering the garden is divided according to the judgment result, so that data reference is provided for the follow-up judgment of whether the personnel entering the garden threatens the security of the garden.
Further, the method in S2 includes the following steps:
step 2001, based on the analysis result of step 1004, arbitrarily extracting one of the marked garden entering personnel, and marking as visitor B;
2002, constructing a longitude and latitude coordinate system by taking a garden entrance of a region to be monitored as an origin, and marking coordinate points formed by all security devices in the region to be monitored in the longitude and latitude coordinate system;
step 2003, acquiring a route diagram of an area to be monitored, and mapping a travel route in the area to be monitored into a longitude and latitude coordinate system by combining the route diagram;
Step 2004, combining the analysis results of steps 2002 and 2003, sequentially combining security devices in the area to be monitored in pairs, and marking as a set C,
C＝[(C1,C2),(C2,C3),(C3,C4),...,(Cm-1,Cm)],
Wherein (C m-1,Cm) represents the combination of the (m-1) th security device and the (m) th security device in the area to be monitored, and m represents the number of the security devices in the area to be monitored;
Step 2005, based on the analysis result of step 2004, extracting any element in the set C to analyze the comprehensive travel speed value of the visitor B, and recording the analysis result of the combination (C m-1,Cm) as
Wherein the method comprises the steps ofIndicating the time when the mth security device in the area to be monitored recognizes visitor B,Indicating the time when the m-1 th security device in the area to be monitored recognizes the visitor B,Representing the distance value from the mth security device to the (m-1) th security device of the visitor B in the area to be monitored;
Step 2006, a circulation step 2005 obtains comprehensive travelling speed values of the visitors B under each combination in the set C, records the obtained data into a table M3, analyzes the subsequent route information of the visitors in combination with the data in the table M3, calculates threat coefficients of the visitors B to the forbidden zone of the area to be monitored according to the analysis result,
In the longitude and latitude coordinate system, a coordinate point formed by an mth security device is used as a circle center, the product result of the minimum value data and unit time in the table M3 is used as an inner circle radius, the product result of the maximum value data and unit time in the table M3 is used as an outer circle radius, a circular ring is constructed and recorded as a circular ring G, wherein the unit time is preset customization,
Analyzing threat coefficients of different time nodes in forbidden areas of the area to be monitored of the visitor B, and recording the corresponding threat coefficients of the a-th time node of the forbidden areas of the area to be monitored of the visitor B asWherein each time node is separated by e steps, e is a database preset value,
Wherein alpha represents a proportionality coefficient, the proportionality coefficient is a database preset value, min () represents a minimum function, max () represents a maximum function, H () represents a condition judgment function,Representing the shortest distance value from the position of the visitor B after the mth security device travels a time nodes to the forbidden zone, S G represents the area of the circular ring, S Forbidden zone represents the area of the forbidden zone in the area to be monitored,Representing the intersection area of the circular ring and the area of the forbidden zone in the area to be monitored,
If it isThen
If it isThen
A point o1 is taken as an origin, a time node is taken as an x1 axis, a threat coefficient is taken as a y axis, a first plane rectangular coordinate system is constructed, in the first plane rectangular coordinate system, coordinate points of threat coefficients formed by different time nodes of a forbidden zone of a region to be monitored of a visitor B are marked, two adjacent coordinate points are sequentially connected, a fitting fold line N1 (x 1) is generated, transfer fold points of the fitting fold line N1 (x 1) are marked, threat coefficients of the forbidden zone of the region to be monitored of the visitor B are calculated, and the threat coefficients are marked as Safe B,
Wherein beta represents a proportionality coefficient, the proportionality coefficient is a database preset value, and q represents the number of the traveling time nodes of the visitor B.
According to the method, the comprehensive travelling speed value of the visitor in the area to be monitored is analyzed, the follow-up travelling route of the visitor is predicted by combining the analysis result, the threat coefficient of the visitor in the forbidden zone of the area to be monitored is calculated according to the prediction result, and data reference is provided for the follow-up screening of the optimal emergency driving personnel.
Further, the method in S3 includes the following steps:
Step 3001, generating an emergency driving-off condition value by combining the analysis result of step 2006, if Safe B is not in a preset interval, sending a driving-off signal to the cloud platform, and if Safe B is in the preset interval, not sending the driving-off signal to the cloud platform;
Step 3002, monitoring the state of the driving-off signal lamp in the cloud platform in real time, acquiring the position information of the staff in the area to be monitored through the cloud platform in real time, marking in a longitude and latitude coordinate system, extracting the staff with the position information in the ring G, marking the emergency treatment personnel selection fit of the s-th staff as Fitness s,
Fitnesss＝γ·G(s)·ds→B，
Wherein gamma represents a proportionality coefficient, the proportionality coefficient is a database preset value, G(s) represents the number of staff at the duty destination of the s-th staff, and d s→B represents the distance between the s-th staff and the visitor B;
Step 3003, cycling step 3002 to obtain the emergency treatment personnel selection compliance degree of the corresponding personnel in the ring G, generating an emergency treatment personnel priority sequence according to the order from large to small, marking the emergency treatment personnel priority sequence as a sequence R, and taking the first element in the sequence R as the current optimal emergency treatment personnel selection.
According to the method, threat coefficient values of the areas to be monitored are combined by visitors, emergency driving-off conditions are generated, workers which accord with the execution of emergency driving-off personnel are analyzed according to the emergency driving-off conditions, the emergency treatment personnel selection fitting degree of the corresponding workers is calculated, a priority sequence is generated, and data reference is provided for the follow-up judgment of the rationality of the optimal emergency treatment personnel selection.
Further, the method in S4 includes the following steps:
Step 4001, calibrating a sequence R by combining importance degrees of positions of workers in the ring G, calibrating elements in the sequence R from small to large according to the importance degrees of the positions of the corresponding workers in the ring G, generating a new emergency treatment personnel priority sequence, and recording the new emergency treatment personnel priority sequence as a sequence R *, wherein the importance degrees are queried through a database preset form, and importance degree conditions corresponding to different positions are recorded in the database preset form;
Step 4002, extracting the first element in the sequence R *, judging the similarity degree of the first element in the sequence R * and the first element in the sequence R, combining the judging result to generate an emergency treatment scheme,
If the similarity degree of the first element in the sequence R * and the first element in the sequence R is equal to 1, the judgment result of the corresponding staff as the optimal emergency treatment staff is reasonable, the cloud platform is used for informing the corresponding staff to go to the visitor B to take the driving measures,
If the similarity degree of the first element in the sequence R * and the first element in the sequence R is equal to 0, the first element in the sequence R * is used as the optimal emergency treatment personnel, and the cloud platform is used for informing the corresponding personnel to go to the visitor B to take the driving measures.
A multi-crowd-oriented face quick retrieval analysis system, the system comprising the following modules:
Identity information recognition module: the identity information recognition module is used for acquiring staff database data of an area to be monitored, checking the identity information of the personnel entering the garden according to the staff warehousing information, monitoring the path of the personnel entering the garden, judging whether the attribution destination of the corresponding personnel entering the garden is abnormal according to the monitoring result, and generating an early warning signal according to the judging result;
Threat coefficient analysis module: the threat coefficient analysis module is used for monitoring the state of the early warning device of the area to be monitored in real time, analyzing the advancing gesture of the visitor according to the monitoring result, predicting the follow-up route information of the visitor by combining the analysis result, and calculating the threat coefficient of the forbidden zone of the area to be monitored;
The emergency measure implementation module is as follows: the emergency measure implementation module is used for generating an emergency driving condition value by combining threat coefficients of a visitor in a forbidden zone of a region to be monitored and generating optimal emergency treatment personnel options by combining personnel information of a garden entering person in a staff table M1 in the region to be monitored;
An emergency scheme calibration module: the emergency scheme calibration module is used for comprehensively judging the rationality of the optimal emergency treatment personnel, calibrating the emergency treatment personnel according to the judging result, and taking corresponding measures to drive away the visitor according to the calibrated emergency treatment personnel.
Further, the identity information recognition module comprises a face recognition unit, a data comparison unit and a data division unit:
the face recognition unit is used for acquiring employee database data in the area to be monitored and judging information of personnel entering a garden by combining a face recognition device;
The data comparison unit is used for comparing the analysis result of the face recognition unit with the data in the staff database;
The data dividing unit is used for acquiring the analysis result of the data comparing unit and classifying the personnel entering the garden according to the analysis result.
Further, the threat coefficient analysis module includes a data acquisition unit, a visitor data analysis unit, and a threat coefficient analysis unit:
the data acquisition unit is used for mapping the route in the area to be monitored and the position information of the security device into a longitude and latitude coordinate system and acquiring the visitor route in real time in the longitude and latitude coordinate system;
the visitor data analysis unit is used for comprehensively analyzing the advancing speed of the corresponding visitor by combining the analysis result of the data acquisition unit;
the threat coefficient analysis unit is used for combining the analysis result of the visitor data analysis unit to judge the threat coefficient value of the forbidden zone of the area to be monitored of the visitor.
Further, the emergency measure implementation module comprises an emergency driving condition generation unit, a priority sequence generation unit and an optimal emergency treatment personnel confirmation unit:
The emergency driving-off condition generating unit is used for generating an emergency driving-off condition value based on the analysis result of the threat coefficient analysis module, judging whether the threat coefficient of the corresponding visitor is in a preset interval in real time, and sending the judgment result to the cloud platform;
The priority sequence generation unit is used for monitoring the state of the driving-off signal lamp in the cloud platform in real time, calculating the competence fit value of the staff in the emergency driving-off range, and generating a priority sequence by combining the calculation result;
The optimal emergency treatment personnel confirming unit is used for acquiring the analysis result of the priority sequence production unit and taking the first element in the sequence as the optimal emergency treatment personnel.
Further, the emergency solution calibration module includes an emergency solution calibration unit and a driving-away measure execution unit:
The emergency scheme calibration unit is used for judging whether the analysis result of the optimal emergency treatment personnel confirmation unit is reasonable or not, and calibrating the optimal emergency treatment personnel in real time by combining the judgment result;
the driving-away measure executing unit is used for notifying corresponding staff to execute the visitor driving-away task through the cloud platform.
According to the method and the device for monitoring the visitor trajectory, the follow-up travelling route of the visitor is predicted, the threat coefficient formed by the forbidden zone of the area to be monitored of the corresponding visitor is calculated according to the prediction result, and the calculated result is pushed to related staff to execute the driving task, so that the security of the area to be monitored is improved, and meanwhile, the scheduling of the staff in the area to be monitored is more reasonably realized.
Drawings
FIG. 1 is a flow diagram of a face quick search analysis method for multiple people in the invention;
fig. 2 is a schematic block diagram of a face quick search analysis system for multiple people according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: referring to fig. 1, in this embodiment:
a face quick retrieval analysis method for multiple people comprises the following steps:
s1, acquiring staff database data of an area to be monitored, checking identity information of personnel entering a garden according to staff warehousing information, monitoring a path of the personnel entering the garden, judging whether a attribution destination of the corresponding personnel entering the garden is abnormal according to a monitoring result, and generating an early warning signal according to a judging result;
the method in S1 comprises the following steps:
Step 1001, obtaining employee database data in the area to be monitored, judging the information of the personnel entering the garden by combining the face recognition device, binding the judging result with the personnel entering the garden, marking as a set A,
A＝{[A1,P(A1)],[A2,P(A2)],[A3,P(A3)],...,[An,P(An)]},
Wherein A n represents the nth person entering the garden, P () represents a conditional judgment function, P (A n) represents the judgment result of the information of the nth person entering the garden, n represents the number of persons entering the garden,
If the face recognition device judges that the information of the person entering the garden is the data in the staff library, the judgment result of the corresponding information of the person entering the garden is output as 1,
If the face recognition device judges that the information of the person entering the garden is not the data in the staff library, outputting a judgment result of the information of the corresponding person entering the garden to be 0;
Step 1002, dividing the personnel entering the garden based on the determination result in step 1001, and recording the determination result in the personnel table M1 of the personnel entering the garden corresponding to the data in the staff library, wherein the determination result is not in the visitor table M2 of the personnel entering the garden corresponding to the data in the staff library;
step 1003, any one extracts the information of the personnel entering the garden in the staff table M1, and combines the staff database data matching result to obtain the corresponding personnel on duty purpose, monitors the corresponding personnel entering the garden on duty condition in real time, and sends the monitoring report to the cloud platform in real time;
step 1004, randomly extracting the information of the personnel entering the garden in the visitor table M2, identifying whether the personnel entering the garden enter a forbidden zone in real time through a security device in the area to be monitored,
If the security device equipped in the forbidden zone identifies the person entering the garden in the visitor table M2, an early warning signal is sent out, and the person entering the garden corresponding to the triggering early warning signal is marked;
If the security device equipped in the forbidden zone does not identify the personnel entering the garden in the visitor table M2, no early warning signal is sent.
S2, monitoring the state of an early warning device of the area to be monitored in real time, analyzing the advancing gesture of the visitor according to the monitoring result, predicting the follow-up route information of the visitor by combining the analysis result, and calculating the threat coefficient of the forbidden area of the area to be monitored;
the method in S2 comprises the steps of:
step 2001, based on the analysis result of step 1004, arbitrarily extracting one of the marked garden entering personnel, and marking as visitor B;
2002, constructing a longitude and latitude coordinate system by taking a garden entrance of a region to be monitored as an origin, and marking coordinate points formed by all security devices in the region to be monitored in the longitude and latitude coordinate system;
step 2003, acquiring a route diagram of an area to be monitored, and mapping a travel route in the area to be monitored into a longitude and latitude coordinate system by combining the route diagram;
Step 2004, combining the analysis results of steps 2002 and 2003, sequentially combining security devices in the area to be monitored in pairs, and marking as a set C,
C＝[(C1,C2),(C2,C3),(C3,C4),...,(Cm-1,Cm)],
Wherein (C m-1,Cm) represents the combination of the (m-1) th security device and the (m) th security device in the area to be monitored, and m represents the number of the security devices in the area to be monitored;
Step 2005, based on the analysis result of step 2004, extracting any element in the set C to analyze the comprehensive travel speed value of the visitor B, and recording the analysis result of the combination (C m-1,Cm) as
Wherein the method comprises the steps ofIndicating the time when the mth security device in the area to be monitored recognizes visitor B,Indicating the time when the m-1 th security device in the area to be monitored recognizes the visitor B,Representing the distance value from the mth security device to the (m-1) th security device of the visitor B in the area to be monitored;
Step 2006, a circulation step 2005 obtains comprehensive travelling speed values of the visitor B under each combination in the set C, records the obtained data into a table M3, analyzes the follow-up route information of the visitor in combination with the data in the table M3, calculates threat coefficients of the visitor B to a forbidden zone of the area to be monitored according to the analysis result, wherein the unit time is a preset value,
In the longitude and latitude coordinate system, a coordinate point formed by an mth security device is taken as a circle center, the product result of the minimum value data and the unit time in the table M3 is taken as an inner circle radius, the product result of the maximum value data and the unit time in the table M3 is taken as an outer circle radius, a circular ring is constructed and recorded as a circular ring G,
Analyzing threat coefficients of different time nodes in forbidden areas of the area to be monitored of the visitor B, and recording the corresponding threat coefficients of the a-th time node of the forbidden areas of the area to be monitored of the visitor B asWherein each time node is separated by e steps, e is a database preset value,
Wherein alpha represents a proportionality coefficient, the proportionality coefficient is a database preset value, min () represents a minimum function, max () represents a maximum function, H () represents a condition judgment function,Representing the shortest distance value from the position of the visitor B after the mth security device travels a time nodes to the forbidden zone, S G represents the area of the circular ring, S Forbidden zone represents the area of the forbidden zone in the area to be monitored,Representing the intersection area of the circular ring and the area of the forbidden zone in the area to be monitored,
If it isThen
If it isThen
A point o1 is taken as an origin, a time node is taken as an x1 axis, a threat coefficient is taken as a y axis, a first plane rectangular coordinate system is constructed, in the first plane rectangular coordinate system, coordinate points of threat coefficients formed by different time nodes of a forbidden zone of a region to be monitored of a visitor B are marked, two adjacent coordinate points are sequentially connected, a fitting fold line N1 (x 1) is generated, transfer fold points of the fitting fold line N1 (x 1) are marked, threat coefficients of the forbidden zone of the region to be monitored of the visitor B are calculated, and the threat coefficients are marked as Safe B,
Wherein beta represents a proportionality coefficient, the proportionality coefficient is a database preset value, and q represents the number of the traveling time nodes of the visitor B.
S3, combining threat coefficients of the visitor to the forbidden zone of the area to be monitored to generate an emergency driving condition value, and combining the information of the personnel entering the garden in the staff form in the area to be monitored to generate optimal emergency treatment personnel selection;
The method in S3 comprises the following steps:
Step 3001, generating an emergency driving-off condition value by combining the analysis result of step 2006, if Safe B is not in a preset interval, sending a driving-off signal to the cloud platform, and if Safe B is in the preset interval, not sending the driving-off signal to the cloud platform;
Step 3002, monitoring the state of the driving-off signal lamp in the cloud platform in real time, acquiring the position information of the staff in the area to be monitored through the cloud platform in real time, marking in a longitude and latitude coordinate system, extracting the staff with the position information in the ring G, marking the emergency treatment personnel selection fit of the s-th staff as Fitness s,
Fitnesss＝γ·G(s)·ds→B，
Wherein gamma represents a proportionality coefficient, the proportionality coefficient is a database preset value, G(s) represents the number of staff at the duty destination of the s-th staff, and d s→B represents the distance between the s-th staff and the visitor B;
Step 3003, cycling step 3002 to obtain the emergency treatment personnel selection compliance degree of the corresponding personnel in the ring G, generating an emergency treatment personnel priority sequence according to the order from large to small, marking the emergency treatment personnel priority sequence as a sequence R, and taking the first element in the sequence R as the current optimal emergency treatment personnel selection.
S4, comprehensively judging the rationality of the optimal emergency treatment personnel, calibrating the emergency treatment personnel by combining the judging result, and taking corresponding measures to drive away the visitor according to the calibrated emergency treatment personnel selection.
The method in S4 includes the steps of:
Step 4001, calibrating a sequence R by combining importance degrees of positions of workers in the ring G, calibrating elements in the sequence R from small to large according to the importance degrees of the positions of the corresponding workers in the ring G, generating a new emergency treatment personnel priority sequence, and recording the new emergency treatment personnel priority sequence as a sequence R *, wherein the importance degrees are queried through a database preset form, and importance degree conditions corresponding to different positions are recorded in the database preset form;
Step 4002, extracting the first element in the sequence R *, judging the similarity degree of the first element in the sequence R * and the first element in the sequence R, combining the judging result to generate an emergency treatment scheme,
If the similarity degree of the first element in the sequence R * and the first element in the sequence R is equal to 1, the judgment result of the corresponding staff as the optimal emergency treatment staff is reasonable, the cloud platform is used for informing the corresponding staff to go to the visitor B to take the driving measures,
If the similarity degree of the first element in the sequence R * and the first element in the sequence R is equal to 0, the first element in the sequence R * is used as the optimal emergency treatment personnel, and the cloud platform is used for informing the corresponding personnel to go to the visitor B to take the driving measures.
In this embodiment: a face quick search analysis system (shown in figure 2) for multiple people is disclosed, which is used for realizing the specific scheme content of the method.
Example 2: setting a person B entering a garden as a visitor, setting 10 security devices in the area to be monitored,
Constructing a longitude and latitude coordinate system by taking a garden entrance of the area to be monitored as an origin, marking coordinate points formed by each security device in the area to be monitored in the longitude and latitude coordinate system, mapping a travel route in a route schematic diagram of the area to be monitored into the longitude and latitude coordinate system,
Setting the position of the visitor B at the moment at the 6 th security device, wherein a forbidden zone exists at the 7 th security device, wherein 3 routes are shared from the 6 th security device to the 7 th security device, and the travel route of the visitor B is combined through the formulaThe comprehensive travelling speed value of the visitor B among the security devices is calculated and recorded as V (1,2)、V(2,3)、V(3,4)、V(4,5)、V(5,6), wherein the V (2,3) value is the largest, the V (4,5) value is the smallest,
In a longitude and latitude coordinate system, a coordinate point formed by a 6 th security device is taken as a circle center, a value of a product result of V (4,5) and unit time is taken as an inner circle radius, a product result of V (2,3) and unit time is taken as an outer circle radius, a circular ring is constructed and recorded as a circular ring G,
Analyzing threat coefficients of different time nodes in a forbidden zone of a zone to be monitored of the visitor B by monitoring intersection relation between the annular ring B and the zone to be monitored in real time in the advancing process of the visitor B, wherein the corresponding threat coefficients of an a-th time node of the forbidden zone of the zone to be monitored of the visitor B are recorded as follows
If it isThen
If it isThen
A point o1 is taken as an origin, a time node is taken as an x1 axis, a threat coefficient is taken as a y axis, a first plane rectangular coordinate system is constructed, in the first plane rectangular coordinate system, coordinate points of threat coefficients formed by different time nodes of a forbidden zone of a region to be monitored of a visitor B are marked, two adjacent coordinate points are sequentially connected, a fitting fold line N1 (x 1) is generated, transfer fold points of the fitting fold line N1 (x 1) are marked, threat coefficients of the forbidden zone of the region to be monitored of the visitor B are calculated, and the threat coefficients are marked as Safe B,
If Safe B is not in the preset interval, a driving-off signal is sent to the cloud platform, and if Safe B is in the preset interval, a driving-off signal is not sent to the cloud platform.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A face quick retrieval and analysis method for multiple people is characterized by comprising the following steps:
s1, acquiring staff database data of an area to be monitored, checking identity information of personnel entering a garden according to staff warehousing information, monitoring a path of the personnel entering the garden, judging whether a attribution destination of the corresponding personnel entering the garden is abnormal according to a monitoring result, and generating an early warning signal according to a judging result;
the method in S1 comprises the following steps:
Step 1001, obtaining employee database data in the area to be monitored, judging the information of the personnel entering the garden by combining the face recognition device, binding the judging result with the personnel entering the garden, marking as a set A,
，
Wherein the method comprises the steps ofRepresenting the nth person entering the garden, P () represents a conditional judgment function,Represents the judgment result of the nth person entering the garden, n represents the number of persons entering the garden,
If the face recognition device judges that the information of the person entering the garden is the data in the staff library, the judgment result of the corresponding information of the person entering the garden is output as 1,
If the face recognition device judges that the information of the person entering the garden is not the data in the staff library, outputting a judgment result of the information of the corresponding person entering the garden to be 0;
Step 1002, dividing the personnel entering the garden based on the determination result in step 1001, and recording the determination result in the personnel table M1 of the personnel entering the garden corresponding to the data in the staff library, wherein the determination result is not in the visitor table M2 of the personnel entering the garden corresponding to the data in the staff library;
step 1003, any one extracts the information of the personnel entering the garden in the staff table M1, and combines the staff database data matching result to obtain the corresponding personnel on duty purpose, monitors the corresponding personnel entering the garden on duty condition in real time, and sends the monitoring report to the cloud platform in real time;
step 1004, randomly extracting the information of the personnel entering the garden in the visitor table M2, identifying whether the personnel entering the garden enter a forbidden zone in real time through a security device in the area to be monitored,
If the security device equipped in the forbidden zone identifies the personnel entering the garden in the visitor table M2, an early warning signal is sent out, the personnel entering the garden corresponding to the triggering early warning signal is marked,
If the security device equipped in the forbidden zone does not identify the personnel entering the garden in the visitor table M2, an early warning signal is not sent;
s2, monitoring the state of an early warning device of the area to be monitored in real time, analyzing the advancing gesture of the visitor according to the monitoring result, predicting the follow-up route information of the visitor by combining the analysis result, and calculating the threat coefficient of the forbidden area of the area to be monitored;
the method in S2 comprises the following steps:
step 2001, based on the analysis result of step 1004, arbitrarily extracting one of the marked garden entering personnel, and marking as visitor B;
2002, constructing a longitude and latitude coordinate system by taking a garden entrance of a region to be monitored as an origin, and marking coordinate points formed by all security devices in the region to be monitored in the longitude and latitude coordinate system;
step 2003, acquiring a route diagram of an area to be monitored, and mapping a travel route in the area to be monitored into a longitude and latitude coordinate system by combining the route diagram;
Step 2004, combining the analysis results of steps 2002 and 2003, sequentially combining security devices in the area to be monitored in pairs, and marking as a set C,
，
Wherein the method comprises the steps ofRepresenting the combination of the m-1 th security device and the m-th security device in the area to be monitored, wherein m represents the number of the security devices in the area to be monitored;
Step 2005, based on the analysis result of step 2004, extracting any element in the set C to analyze the comprehensive travelling speed value of the visitor B, and combining The analysis result of (2) is recorded as，
，
Wherein the method comprises the steps ofIndicating the time when the mth security device in the area to be monitored recognizes visitor B,Indicating the time when the m-1 th security device in the area to be monitored recognizes the visitor B,Representing the distance value from the mth security device to the (m-1) th security device of the visitor B in the area to be monitored;
Step 2006, a circulation step 2005 obtains comprehensive travelling speed values of the visitors B under each combination in the set C, records the obtained data into a table M3, analyzes the subsequent route information of the visitors in combination with the data in the table M3, calculates threat coefficients of the visitors B to the forbidden zone of the area to be monitored according to the analysis result,
In the longitude and latitude coordinate system, a coordinate point formed by an mth security device is used as a circle center, the product result of the minimum value data and unit time in the table M3 is used as an inner circle radius, the product result of the maximum value data and unit time in the table M3 is used as an outer circle radius, a circular ring is constructed and recorded as a circular ring G, wherein the unit time is preset customization,
Analyzing threat coefficients of different time nodes in forbidden areas of the area to be monitored of the visitor B, and recording the corresponding threat coefficients of the a-th time node of the forbidden areas of the area to be monitored of the visitor B asWherein each time node is separated by e steps, e is a database preset value,
，
Wherein the method comprises the steps ofRepresents a proportionality coefficient, wherein the proportionality coefficient is a database preset value, min () represents a minimum function, max () represents a maximum function, H () represents a condition judgment function,Representing the shortest distance value from the position of the visitor B after the mth security device travels a time nodes to the forbidden zone,The area of the circular ring is indicated,Indicating the area of the exclusion zone in the area to be monitored,Representing the intersection area of the circular ring and the area of the forbidden zone in the area to be monitored,
If it isThen，
If it isThen，
Constructing a first plane rectangular coordinate system by taking a point o1 as an origin, taking a time node as an x1 axis and a threat coefficient as a y axis, marking coordinate points of threat coefficients formed by different time nodes of a forbidden zone of a visitor B to-be-monitored area in the first plane rectangular coordinate system, sequentially connecting two adjacent coordinate points, and generating a fitting broken lineAnd fit the broken lineMarking transfer folding points, calculating threat coefficients of a zone to be monitored in a visitor B, and marking the threat coefficients as，
，
Wherein the method comprises the steps ofRepresenting a proportionality coefficient, wherein the proportionality coefficient is a database preset value,Representing the number of guest B travel time nodes;
S3, combining threat coefficients of a visitor in a forbidden zone of the area to be monitored to generate an emergency driving condition value, and combining information of personnel entering a garden in a staff table M1 in the area to be monitored to generate optimal emergency treatment personnel selection;
S4, comprehensively judging the rationality of the optimal emergency treatment personnel, calibrating the emergency treatment personnel by combining the judging result, and taking corresponding measures to drive away the visitor according to the calibrated emergency treatment personnel selection.
2. The method for rapid face search analysis for multiple people according to claim 1, wherein the method in S3 comprises the following steps:
Step 3001, combining the analysis results of step 2006, generating an emergency driving condition value, if If the driving signal is not in the preset interval, a driving signal is sent to the cloud platform, ifIn a preset interval, a driving-off signal is not sent to the cloud platform;
Step 3002, monitoring the state of a driving signal lamp in the cloud platform in real time, acquiring the position information of the staff in the area to be monitored through the cloud platform in real time, marking in a longitude and latitude coordinate system, extracting the staff with the position information in the ring G, and marking the emergency treatment personnel selection fit degree of the s-th staff as ，
，
Wherein the method comprises the steps ofRepresenting a proportionality coefficient, wherein the proportionality coefficient is a database preset value,Indicating the number of staff members at the s-th staff member on-duty destination,Representing the distance between the s-th staff member and visitor B;
Step 3003, cycling step 3002 to obtain the emergency treatment personnel selection compliance degree of the corresponding personnel in the ring G, generating an emergency treatment personnel priority sequence according to the order from large to small, marking the emergency treatment personnel priority sequence as a sequence R, and taking the first element in the sequence R as the current optimal emergency treatment personnel selection.
3. The method for rapid face search analysis for multiple people according to claim 2, wherein the method in S4 comprises the following steps:
Step 4001, calibrating the sequence R by combining the importance degree of the positions of the workers in the ring G, calibrating the importance degree of the elements in the sequence R according to the positions of the corresponding workers in the ring G from small to large, generating a new emergency treatment personnel priority sequence, and recording the new emergency treatment personnel priority sequence as a sequence The importance degree is queried through a database preset form, wherein the importance degree conditions corresponding to different positions are recorded in the database preset form;
step 4002, extract sequence First element of (3) judgment sequenceThe first element of the sequence R is similar to the first element of the sequence R, an emergency treatment scheme is generated by combining the judging result,
If the sequence isThe similarity degree of the first element in the sequence R and the first element in the sequence R is equal to 1, the judgment result of the corresponding staff as the optimal emergency processing staff is reasonable, the cloud platform is used for informing the corresponding staff to go to the visitor B for taking the driving measures,
If the sequence isThe first element of the sequence is similar to the first element of the sequence R to a degree equal to 0, the sequence is thenThe first element in the system is used as an optimal emergency processing person, and the cloud platform informs corresponding staff to go to the visitor B to take a driving-away measure.
4. A face rapid search analysis system applied to the multi-crowd-oriented face rapid search analysis method of any one of claims 1 to 3, characterized in that the system comprises the following modules:
Identity information recognition module: the identity information recognition module is used for acquiring staff database data of an area to be monitored, checking the identity information of the personnel entering the garden according to the staff warehousing information, monitoring the path of the personnel entering the garden, judging whether the attribution destination of the corresponding personnel entering the garden is abnormal according to the monitoring result, and generating an early warning signal according to the judging result;
Threat coefficient analysis module: the threat coefficient analysis module is used for monitoring the state of the early warning device of the area to be monitored in real time, analyzing the advancing gesture of the visitor according to the monitoring result, predicting the follow-up route information of the visitor by combining the analysis result, and calculating the threat coefficient of the forbidden zone of the area to be monitored;
The emergency measure implementation module is as follows: the emergency measure implementation module is used for generating an emergency driving condition value by combining threat coefficients of a visitor in a forbidden zone of a region to be monitored and generating optimal emergency treatment personnel options by combining personnel information of a garden entering person in a staff table M1 in the region to be monitored;
An emergency scheme calibration module: the emergency scheme calibration module is used for comprehensively judging the rationality of the optimal emergency treatment personnel, calibrating the emergency treatment personnel according to the judging result, and taking corresponding measures to drive away the visitor according to the calibrated emergency treatment personnel.
5. The face quick search analysis system according to claim 4, wherein the identity information recognition module comprises a face recognition unit, a data comparison unit and a data division unit:
the face recognition unit is used for acquiring employee database data in the area to be monitored and judging information of personnel entering a garden by combining a face recognition device;
The data comparison unit is used for comparing the analysis result of the face recognition unit with the data in the staff database;
The data dividing unit is used for acquiring the analysis result of the data comparing unit and classifying the personnel entering the garden according to the analysis result.
6. The face quick search analysis system of claim 5, wherein the threat coefficient analysis module comprises a data acquisition unit, a guest data analysis unit, and a threat coefficient analysis unit:
the data acquisition unit is used for mapping the route in the area to be monitored and the position information of the security device into a longitude and latitude coordinate system and acquiring the visitor route in real time in the longitude and latitude coordinate system;
the visitor data analysis unit is used for comprehensively analyzing the advancing speed of the corresponding visitor by combining the analysis result of the data acquisition unit;
the threat coefficient analysis unit is used for combining the analysis result of the visitor data analysis unit to judge the threat coefficient value of the forbidden zone of the area to be monitored of the visitor.
7. The face quick search analysis system of claim 6, wherein the emergency measure implementation module comprises an emergency driving condition generation unit, a priority sequence generation unit, and an optimal emergency treatment personnel confirmation unit:
The emergency driving-off condition generating unit is used for generating an emergency driving-off condition value based on the analysis result of the threat coefficient analysis module, judging whether the threat coefficient of the corresponding visitor is in a preset interval in real time, and sending the judgment result to the cloud platform;
The priority sequence generation unit is used for monitoring the state of the driving-off signal lamp in the cloud platform in real time, calculating the competence fit value of the staff in the emergency driving-off range, and generating a priority sequence by combining the calculation result;
The optimal emergency treatment personnel confirming unit is used for acquiring the analysis result of the priority sequence production unit and taking the first element in the sequence as the optimal emergency treatment personnel.
8. The face quick search analysis system of claim 7, wherein the emergency plan calibration module comprises an emergency plan calibration unit and a drive-away measure execution unit:
The emergency scheme calibration unit is used for judging whether the analysis result of the optimal emergency treatment personnel confirmation unit is reasonable or not, and calibrating the optimal emergency treatment personnel in real time by combining the judgment result;
the driving-away measure executing unit is used for notifying corresponding staff to execute the visitor driving-away task through the cloud platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311420281.1A CN117421446B (en) | 2023-10-30 | 2023-10-30 | Multi-crowd-oriented face quick retrieval analysis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311420281.1A CN117421446B (en) | 2023-10-30 | 2023-10-30 | Multi-crowd-oriented face quick retrieval analysis system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117421446A CN117421446A (en) | 2024-01-19 |
| CN117421446B true CN117421446B (en) | 2024-08-13 |
Family
ID=89532210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311420281.1A Active CN117421446B (en) | 2023-10-30 | 2023-10-30 | Multi-crowd-oriented face quick retrieval analysis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117421446B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109447048A (en) * | 2018-12-25 | 2019-03-08 | 苏州闪驰数控系统集成有限公司 | A kind of artificial intelligence early warning system |
| CN115909617A (en) * | 2023-01-06 | 2023-04-04 | 之江实验室 | Visitor early warning method, system and device based on multi-source heterogeneous data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9711036B2 (en) * | 2012-09-21 | 2017-07-18 | Google Inc. | Leveraging neighborhood to handle potential visitor at a smart-home |
-
2023
- 2023-10-30 CN CN202311420281.1A patent/CN117421446B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109447048A (en) * | 2018-12-25 | 2019-03-08 | 苏州闪驰数控系统集成有限公司 | A kind of artificial intelligence early warning system |
| CN115909617A (en) * | 2023-01-06 | 2023-04-04 | 之江实验室 | Visitor early warning method, system and device based on multi-source heterogeneous data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117421446A (en) | 2024-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598885B (en) | Monitoring system and alarm method thereof | |
| US10812761B2 (en) | Complex hardware-based system for video surveillance tracking | |
| EP2219379B1 (en) | Social network construction based on data association | |
| CN105323550B (en) | Method and apparatus for video search and playback | |
| WO2019153193A1 (en) | Taxi operation monitoring method, device, storage medium, and system | |
| CN109461106A (en) | A kind of multidimensional information perception processing method | |
| CN106023253A (en) | Urban target trajectory tracking method | |
| AU2017436901A1 (en) | Methods and apparatus for automated surveillance systems | |
| US20100007738A1 (en) | Method of advanced person or object recognition and detection | |
| CN108898520B (en) | Student safety monitoring method and system based on trajectory data | |
| CN111325954B (en) | Personnel loss early warning method, device, system and server | |
| CN101751553A (en) | Method for analyzing and predicting large-scale crowd density | |
| CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
| Shen et al. | Outlier detection from vehicle trajectories to discover roaming events | |
| CN115101216A (en) | New infectious disease monitoring and coping system based on big data | |
| EP3910539A1 (en) | Systems and methods of identifying persons-of-interest | |
| CN115294519A (en) | Abnormal event detection and early warning method based on lightweight network | |
| KR102573708B1 (en) | Apparatus and method for controlling situation board of transport information center | |
| Telaumbanua et al. | Vehicle detection and identification using computer vision technology with the utilization of the yolov8 deep learning method | |
| CN117421446B (en) | Multi-crowd-oriented face quick retrieval analysis system and method | |
| CN114706988A (en) | Monitoring and early warning method and device based on knowledge graph | |
| CN112330742A (en) | Method and device for recording activity routes of key personnel in public area | |
| Ho et al. | Public space behavior modeling with video and sensor analytics | |
| KR101516672B1 (en) | Method for detecting video that utilize smarter video control center using the same system | |
| Anithadevi et al. | An Improved SSD Object Detection Algorithm For Safe Social Distancing and Face Mask Detection In Public Areas Through Intelligent Video Analytics |
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 |