CN111915788A - Anti-trailing method and system based on face recognition technology - Google Patents
Anti-trailing method and system based on face recognition technology Download PDFInfo
- Publication number
- CN111915788A CN111915788A CN202010730193.1A CN202010730193A CN111915788A CN 111915788 A CN111915788 A CN 111915788A CN 202010730193 A CN202010730193 A CN 202010730193A CN 111915788 A CN111915788 A CN 111915788A
- Authority
- CN
- China
- Prior art keywords
- owner
- person
- stranger
- library
- risk
- 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.)
- Pending
Links
Images
Classifications
-
- 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
-
- 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
- G07C9/38—Individual registration on entry or exit not involving the use of a pass with central registration
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method and a system for preventing following based on a face recognition technology, wherein first face data entering a gate of a community is acquired, non-owner personnel are recorded when entering the gate following an owner, and are added into a stranger base to be judged, and meanwhile, the ID of the owner entering the gate together with the first non-owner personnel within T1 time is associated; and then comparing the second non-owner person in the second face data with the to-be-judged stranger base, if the second non-owner person does not exist in the to-be-judged stranger base, taking out the owner ID passing through the first preset position within the time of T2, judging whether the owner ID exists in the owner ID associated with the second non-owner person to be judged currently, and when the time of the first high-risk person and/or the second high-risk person exceeds the time period of T4, sending the position information of the first high-risk person and/or the second high-risk person to a security system, so that the misjudgment rate is effectively improved, and a good prevention and control effect is achieved on strangers entering the residential area.
Description
Technical Field
The invention relates to the technical field of community security, in particular to a method and a system for preventing trailing based on a face recognition technology.
Background
In recent years, with the development of face recognition technology, access control systems based on face recognition technology have been gradually popularized. The functions realized by the face recognition access control systems are as follows: the human faces entering the recognition area are compared through the human face white list, when any one of the human face pictures in the recognition area is judged to be the human face according with the setting of the white list by the human face recognition system, the system can automatically open the entrance guard, and the trouble that a user manually swipes a card to open the door is avoided. But this also brings new problems and we have found a general problem that many times a person standing in the identification area waiting to be identified may not be on the white list, but he may also rely on following or "rubbing" the face of a person on the white list nearby to open a door or follow others into the community. If this occurs, even if a security guard is provided, it is not possible to directly recognize whether or not there is a rear entry.
For example, the invention patent with the patent application number of CN201710918054.X discloses an intelligent community security system and a detection method based on face recognition, and the intelligent community security system comprises a face acquisition module, a face recognition module, a control module, an alarm module, a property management module and a public security alarm module; the face acquisition module is used for acquiring face information of people entering and exiting the community and transmitting the face information to the face recognition module; the face acquisition module adopts a plurality of high-definition cameras; the high-definition cameras are respectively arranged at a community entrance, a building entrance, a resident door of each household and the periphery of the building; the face recognition module is used for comparing the collected face information with an information database and outputting a judgment result to the control module; the control module is respectively connected with the community monitoring management platform and the alarm module; alarm module with alarm information transmit respectively to property management module with police alarm module has safe and reliable, labour saving and time saving, detection efficiency height and the high advantage of intelligent degree. However, these solutions have some problems in practical implementation:
1. because the face input in the community is a slow process, the invention compares the collected face image with the established database, and the identity of a stranger entering the community cannot be judged when the stranger is not in the database, so the security effect is not ideal.
2. If only simply adopt the discovery that when the owner opens the door, also have unidentified people just reported to the police, not only can increase the security work load, also can cause very big puzzlement for owner's normal traffic to cause owner's complaint.
3. Sometimes, the owner brings relatives and friends together to enter a cell, and thus, a false alarm situation also occurs.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an anti-following method and system based on the face recognition technology aiming at the defects of the prior art, and the method and system have the advantages of intelligent anti-following, effective reduction of false alarm and guarantee of community safety.
The technical scheme for solving the technical problems is as follows: an anti-trailing method based on a face recognition technology comprises the following steps:
s1, acquiring first face data to enter a gate of a cell, performing face recognition, judging whether the first face data contains an owner, if so, executing S2, and if not, not opening the gate and executing S1;
s2, opening a gate, adding the first non-owner personnel in the first face data into a stranger base to be judged, associating the ID of an owner entering the first non-owner personnel together within the time T1, and executing S3;
s3, acquiring the face data obtained at the first preset position as second face data, comparing the second face data with a white list library storing the face data of an owner, if the face data exists in the white list library, judging as the owner, otherwise, judging as second non-owner and executing S4;
s4, comparing the second non-owner person with the to-be-determined stranger bottom library, if the second non-owner person exists in the to-be-determined stranger bottom library, executing S5, and if not, executing S6;
s5, taking out the owners I D passing the first preset position within the time of T2, judging whether the owners I D exist in the owners I D associated with the second non-owner to be judged currently, if so, judging that the low-risk personnel exist, adding the low-risk personnel into a low-risk personnel base, and if not, executing S6;
s6, comparing the second non-owner person with a high-risk stranger bottom library, if the second non-owner person exists in the high-risk stranger bottom library, judging the second non-owner person to be a first high-risk stranger and updating the position of the first high-risk stranger, if the second non-owner person does not exist in the high-risk stranger bottom library, adding the second non-owner person to the high-risk stranger bottom library, recording the position of the second high-risk stranger, and executing S7;
and S7, when the time of the first high-risk person and/or the second high-risk person is judged to exceed the T4 time period, the position information of the first high-risk person and/or the second high-risk person is sent to a security system.
The method has the advantages that the first face data entering the gate of the community is acquired, non-owner personnel enter the gate along with the owner and record the data, the data are added into a to-be-judged stranger base, and meanwhile I D of the owner entering the gate together with the first non-owner personnel within T1 time is correlated; then the second non-owner person in the second face data is compared with the stranger database to be judged, if the owner is not in the stranger base to be judged, the owner I D passing the first preset position within the time T2 is taken out, whether the owner I D exists in the owner I D related to the second non-owner person to be judged currently is judged, if the personnel with low risk exist, the personnel with low risk are judged and added into a low-risk personnel bottom library, if the personnel with high risk do not exist, the personnel with high risk are judged as the first personnel with high risk or the second personnel with high risk, when it is determined that the time of the first high risk person and/or the second high risk person exceeds the T4 time period, and the position information of the first high-risk personnel and/or the second high-risk personnel is sent to a security system, so that the misjudgment rate is effectively improved, and a good prevention and control effect is provided for strangers entering the cell at the tail.
Further, the first preset position is one or more of a main intersection, a building entrance, the periphery of a building and the like.
Further, also comprises
S8, acquiring third face data of a pre-entry unit door entrance, comparing the third face data with a white list library, judging as an owner if the third face data exists in the white list library, and executing S9 if the third face data does not exist in the white list library;
and S9, comparing a third non-owner person in the third face data with a resident person base library, judging as a resident person if the third non-owner person exists in the resident person base library, updating the time of the resident person entering the resident person base library, judging as a stranger if the third non-owner person does not exist in the resident person base library, adding the stranger base library, recording the time of the stranger entering the stranger base library, and judging the stranger as a resident person and deleting the stranger from the stranger base library when the time of the stranger entering the stranger exceeds a T3 time period.
The method has the advantages that the third face data which is pre-entered into the entrance of the cell gate is obtained, resident persons and the established resident person database are screened out through non-owner persons in the third face data and the time of entering the cell gate, the resident persons are screened out, and the misjudgment rate is reduced.
Further, the method also comprises the step of cleaning the stranger base database regularly at intervals of T5.
The beneficial effect of adopting the further scheme is that the problem that the resource waste is caused by overlarge data amount of the stranger database is avoided.
Further, the white list library is a database of an owner who completes face picture input, when the owner to be input records the face picture, the face picture is firstly compared with the resident personnel library, and when the owner to be input exists in the resident personnel library, the owner to be input is deleted from the resident personnel library.
The beneficial effect of adopting the further scheme is that the resident personnel who have carried out face information entry are deleted, so that the data of the resident personnel base is more accurate.
An anti-tailing system based on face recognition technology comprises: the system comprises a first face data acquisition module, a first execution module, a second face data acquisition module, a central calculation module and a security module;
the first face data acquisition module is used for acquiring first face data to enter a gate of a cell, performing face recognition, judging whether an owner exists in the first face data, controlling the first execution module to open the gate if the owner exists, sending first non-owner personnel data in the first face data to the central calculation module, controlling the first execution module not to open the gate if the owner does not exist, and continuously acquiring the first face data to enter the gate of the cell to judge whether the gate is opened;
the center module is used for adding the first non-owner personnel to a stranger base to be judged and associating I D of an owner entering the first non-owner personnel together within T1 time;
the second face data acquisition module is used for acquiring face data acquired at a first preset position as second face data, comparing the second face data with a white list library in which owner face data are stored, judging as an owner if the second face data exist in the white list library, and otherwise, judging as a second non-owner person and sending the second non-owner person data to the central computing module;
the central computing module is further used for comparing the second non-owner person with the stranger base library to be judged, if the second non-owner person exists in the stranger base library to be judged, executing S5, and if the second non-owner person does not exist in the stranger base library to be judged, executing S6;
s5, taking out the owner ID passing through the first preset position within the time of T2, judging whether the owner ID exists in the current owner ID associated with the second non-owner to be judged, if so, judging that the person with low risk exists and adding the person into a low risk person base, and if not, executing S6;
s6, comparing the second non-owner person with a high-risk stranger bottom library, if the second non-owner person exists in the high-risk stranger bottom library, judging the second non-owner person to be a first high-risk stranger and updating the position of the first high-risk stranger, if the second non-owner person does not exist in the high-risk stranger bottom library, adding the second non-owner person to the high-risk stranger bottom library, recording the position of the second high-risk stranger, and executing S7;
and S7, when the time of the first high-risk person and/or the second high-risk person is judged to exceed the T4 time period, the position information of the first high-risk person and/or the second high-risk person is sent to a security module.
The method has the advantages that the first face data entering the gate of the community is acquired, non-owner personnel enter the gate along with the owner and record the data, the data are added into a to-be-judged stranger base, and meanwhile I D of the owner entering the gate together with the first non-owner personnel within T1 time is correlated; then the second non-owner person in the second face data is compared with the stranger database to be judged, if the owner ID does not exist in the stranger database to be judged, the owner ID passing through the first preset position within the time of T2 is taken out, whether the owner ID exists in the owner ID related to the second non-owner person to be judged currently is judged, if the personnel with low risk exist, the personnel with low risk are judged and added into a low-risk personnel bottom library, if the personnel with high risk do not exist, the personnel with high risk are judged as the first personnel with high risk or the second personnel with high risk, when it is determined that the time of the first high risk person and/or the second high risk person exceeds the T4 time period, and the position information of the first high-risk personnel and/or the second high-risk personnel is sent to a security system, so that the misjudgment rate is effectively improved, and a good prevention and control effect is provided for strangers entering the cell at the tail.
Further, the first preset position is one or more of a main intersection, a building entrance, the periphery of a building and the like.
The system comprises a unit door data acquisition module, a central calculation module and a white list library, wherein the unit door data acquisition module is used for acquiring third face data which is pre-entered into a unit door entrance, comparing the third face data with the white list library, judging as an owner if the third face data exists in the white list library, and sending third non-owner personnel data in the third face data to the central calculation module if the third face data does not exist in the white list library;
the central computing module is further used for comparing third non-owner persons in the third face data with a resident person base library, judging as resident persons if the third non-owner persons exist in the resident person base library, updating the time of the resident persons entering the resident persons, judging as strangers if the third non-owner persons do not exist in the resident person base library, adding the strangers into a stranger base library, recording the time of the strangers entering the strangers, and judging the strangers as resident persons and deleting the strangers from the stranger base library when the time of the strangers entering the strangers exceeds T3 time period.
The method has the advantages that the third face data which is pre-entered into the entrance of the cell gate is obtained, resident persons and the established resident person database are screened out through non-owner persons in the third face data and the time of entering the cell gate, the resident persons are screened out, and the misjudgment rate is reduced.
Further, the system also comprises a timing cleaning module, wherein the timing cleaning module is used for cleaning the stranger database at regular intervals of T5 time periods.
The beneficial effect of adopting the further scheme is that the problem that the resource waste is caused by overlarge data amount of the stranger database is avoided.
Further, the white list library is a database of an owner who completes face picture input, when the owner to be input records the face picture, the face picture is firstly compared with the resident personnel library, and when the owner to be input exists in the resident personnel library, the owner to be input is deleted from the resident personnel library.
The beneficial effect of adopting the further scheme is that the resident personnel who have carried out face information entry are deleted, so that the data of the resident personnel base is more accurate.
Drawings
FIG. 1 is a flow chart of an anti-following method based on face recognition technology;
FIG. 2 is a block diagram of one embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
Example 1
Referring to fig. 1, a method for preventing trailing based on a face recognition technology includes the following steps:
s1, acquiring first face data to enter a gate of a cell, performing face recognition, judging whether the first face data contains an owner, if so, executing S2, and if not, not opening the gate and executing S1;
s2, opening a gate, adding the first non-owner personnel in the first face data into a stranger base to be judged, associating the ID of an owner entering the first non-owner personnel together within the time T1, and executing S3;
s3, acquiring the face data obtained at the first preset position as second face data, comparing the second face data with a white list library storing the face data of an owner, if the face data exists in the white list library, judging as the owner, otherwise, judging as second non-owner and executing S4;
s4, comparing the second non-owner person with the to-be-determined stranger bottom library, if the second non-owner person exists in the to-be-determined stranger bottom library, executing S5, and if not, executing S6;
s5, taking out the owner ID passing through the first preset position within the time of T2, judging whether the owner ID exists in the current owner ID associated with the second non-owner to be judged, if so, judging that the person with low risk exists and adding the person into a low risk person base, and if not, executing S6;
s6, comparing the second non-owner person with a high-risk stranger bottom library, if the second non-owner person exists in the high-risk stranger bottom library, judging the second non-owner person to be a first high-risk stranger and updating the position of the first high-risk stranger, if the second non-owner person does not exist in the high-risk stranger bottom library, adding the second non-owner person to the high-risk stranger bottom library, recording the position of the second high-risk stranger, and executing S7;
and S7, when the time of the first high-risk person and/or the second high-risk person is judged to exceed the T4 time period, the position information of the first high-risk person and/or the second high-risk person is sent to a security system.
Acquiring first face data entering a gate of a community, recording when non-owner personnel enter the gate along with an owner, adding the data into a to-be-judged stranger base, and associating ID of the owner entering the gate together with the first non-owner personnel within T1 time; then the second non-owner person in the second face data is compared with the stranger database to be judged, if the owner ID does not exist in the stranger database to be judged, the owner I D passing the first preset position within the time of T2 is taken out, whether the owner ID exists in the IDs of the owners related to the second non-owner person to be judged currently is judged, if the personnel with low risk exist, the personnel with low risk are judged and added into a low-risk personnel bottom library, if the personnel with high risk do not exist, the personnel with high risk are judged as the first personnel with high risk or the second personnel with high risk, when it is determined that the time of the first high risk person and/or the second high risk person exceeds the T4 time period, and the position information of the first high-risk personnel and/or the second high-risk personnel is sent to a security system, so that the misjudgment rate is effectively improved, and a good prevention and control effect is provided for strangers entering the cell at the tail.
In this embodiment, the owner is a user who has performed face information entry, that is, a user in the white list library, and a high-risk stranger is a stranger who acts alone, and the stranger-to-be-determined base library is used for storing non-owner persons in the first face data, and may be understood as a stranger who has just entered the cell. T1 is 5 seconds, and may be adjusted to 3 seconds, 4 seconds, 6 seconds, 7 seconds, 8 seconds, or the like, as the case may be. T2 is 5 seconds, and may be adjusted to 3 seconds, 4 seconds, 6 seconds, 7 seconds, 8 seconds, or the like, as the case may be. T4 is 5 seconds, and may be adjusted to 3 seconds, 4 seconds, 6 seconds, 7 seconds, 8 seconds, or the like, as the case may be.
The first preset position is one or more of a main intersection, a building entrance, the periphery of a building and the like.
S8, acquiring third face data of a pre-entry unit door entrance, comparing the third face data with a white list library, judging as an owner if the third face data exists in the white list library, and executing S9 if the third face data does not exist in the white list library;
and S9, comparing a third non-owner person in the third face data with a resident person base library, judging as a resident person if the third non-owner person exists in the resident person base library, updating the time of the resident person entering the resident person base library, judging as a stranger if the third non-owner person does not exist in the resident person base library, adding the stranger base library, recording the time of the stranger entering the stranger base library, and judging the stranger as a resident person and deleting the stranger from the stranger base library when the time of the stranger entering the stranger exceeds a T3 time period.
And acquiring third face data of a pre-entry unit door entrance, screening out resident persons and an established resident person database by combining non-owner persons in the third face data and the time of entering the unit door, screening out the resident persons, and reducing the misjudgment rate.
In this embodiment, the resident is a user who stays in the cell but does not enter face data, T3 is 12 hours, and may be adjusted to 11 hours, 10 hours, 9 hours, 8 hours, and the like as needed
And cleaning the stranger bottom database regularly at intervals of T5 time. The data volume of the stranger database is prevented from being too large, so that resource waste is avoided, in the embodiment, T5 is 24 hours, and can be adjusted to 36 hours, 48 hours and the like according to actual conditions.
The white list library is a database of an owner who finishes inputting the face picture, when the owner to be input records the face picture, the database is firstly compared with the resident personnel library, and when the owner to be input exists in the resident personnel library, the owner to be input is deleted from the resident personnel library. And the resident personnel who have been subjected to the face information input are deleted, so that the data of the resident personnel base library is more accurate.
Example 2
Referring to fig. 2, on the basis of embodiment 1, an anti-following system based on a face recognition technology includes: the system comprises a first face data acquisition module, a first execution module, a second face data acquisition module, a central calculation module and a security module;
the first face data acquisition module is used for acquiring first face data to enter a gate of a cell, performing face recognition, judging whether an owner exists in the first face data, controlling the first execution module to open the gate if the owner exists, sending first non-owner personnel data in the first face data to the central calculation module, controlling the first execution module not to open the gate if the owner does not exist, and continuously acquiring the first face data to enter the gate of the cell to judge whether the gate is opened;
the center module is used for adding the first non-owner personnel to a stranger base to be judged and associating I D of an owner entering the first non-owner personnel together within T1 time;
the second face data acquisition module is used for acquiring face data acquired at a first preset position as second face data, comparing the second face data with a white list library in which owner face data are stored, judging as an owner if the second face data exist in the white list library, and otherwise, judging as a second non-owner person and sending the second non-owner person data to the central computing module;
the central computing module is further used for comparing the second non-owner person with the stranger base library to be judged, if the second non-owner person exists in the stranger base library to be judged, executing S5, and if the second non-owner person does not exist in the stranger base library to be judged, executing S6;
s5, taking out the owner ID passing through the first preset position within the time of T2, judging whether the owner ID exists in the current owner ID associated with the second non-owner to be judged, if so, judging that the person with low risk exists and adding the person into a low risk person base, and if not, executing S6;
s6, comparing the second non-owner person with a high-risk stranger bottom library, if the second non-owner person exists in the high-risk stranger bottom library, judging the second non-owner person to be a first high-risk stranger and updating the position of the first high-risk stranger, if the second non-owner person does not exist in the high-risk stranger bottom library, adding the second non-owner person to the high-risk stranger bottom library, recording the position of the second high-risk stranger, and executing S7;
and S7, when the time of the first high-risk person and/or the second high-risk person is judged to exceed the T4 time period, the position information of the first high-risk person and/or the second high-risk person is sent to a security module.
Acquiring first face data entering a gate of a community, recording when non-owner personnel enter the gate along with an owner, adding the data into a to-be-judged stranger base, and associating ID of the owner entering the gate together with the first non-owner personnel within T1 time; then the second non-owner person in the second face data is compared with the stranger database to be judged, if the owner ID does not exist in the stranger database to be judged, the owner I D passing the first preset position within the time of T2 is taken out, whether the owner ID exists in the IDs of the owners related to the second non-owner person to be judged currently is judged, if the personnel with low risk exist, the personnel with low risk are judged and added into a low-risk personnel bottom library, if the personnel with high risk do not exist, the personnel with high risk are judged as the first personnel with high risk or the second personnel with high risk, when it is determined that the time of the first high risk person and/or the second high risk person exceeds the T4 time period, and the position information of the first high-risk personnel and/or the second high-risk personnel is sent to a security system, so that the misjudgment rate is effectively improved, and a good prevention and control effect is provided for strangers entering the cell at the tail.
In this embodiment, the first face data module may be a face capture machine, a face recognition camera having a face recognition function, and the like, and may be installed at a gate according to the number of gates, the central module may use a computer, the first execution module may use an electromagnetic lock, and when the first face recognition module detects that an owner exists, the first execution module is controlled to open the gate. The second face data acquisition module can use a face snapshot machine and a camera with a face recognition function, a plurality of face snapshot machines can be arranged in the cell, and the security module is a security system.
The first preset position is one or more of a main intersection, a building entrance, the periphery of a building and the like.
The unit door data acquisition module is used for acquiring third face data which is pre-entered into a unit door entrance, comparing the third face data with a white list library, judging as an owner if the third face data exists in the white list library, and sending third non-owner personnel data in the third face data to the central calculation module if the third face data does not exist in the white list library;
the central computing module is further used for comparing third non-owner persons in the third face data with a resident person base library, judging as resident persons if the third non-owner persons exist in the resident person base library, updating the time of the resident persons entering the resident persons, judging as strangers if the third non-owner persons do not exist in the resident person base library, adding the strangers into a stranger base library, recording the time of the strangers entering the strangers, and judging the strangers as resident persons and deleting the strangers from the stranger base library when the time of the strangers entering the strangers exceeds T3 time period.
And acquiring third face data of a pre-entry unit door entrance, screening out resident persons and an established resident person database by combining non-owner persons in the third face data and the time of entering the unit door, screening out the resident persons, and reducing the misjudgment rate.
The system further comprises a timing cleaning module, and the timing cleaning module is used for cleaning the stranger database regularly every T4 time period.
The problem that resources are wasted due to the fact that the data size of the stranger base is too large is solved. The white list library is a database of an owner who finishes inputting the face picture, when the owner to be input records the face picture, the database is firstly compared with the resident personnel library, and when the owner to be input exists in the resident personnel library, the owner to be input is deleted from the resident personnel library. And the resident personnel who have been subjected to the face information input are deleted, so that the data of the resident personnel base library is more accurate.
The technical solutions provided by the embodiments of the present invention are described in detail above, and the principles and embodiments of the present invention are explained herein by using specific examples, and the descriptions of the embodiments are only used to help understanding the principles of the embodiments of the present invention; also, while the present invention has been described with respect to particular embodiments and with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that the foregoing descriptions of the present invention are provided for illustration and not for the purpose of limiting the invention as defined by the appended claims.
Claims (10)
1. An anti-trailing method based on a face recognition technology is characterized by comprising the following steps:
s1, acquiring first face data to enter a gate of a cell, performing face recognition, judging whether the first face data contains an owner, if so, executing S2, and if not, not opening the gate and executing S1;
s2, opening a gate, adding the first non-owner personnel in the first face data into a stranger base to be judged, associating the ID of an owner entering the first non-owner personnel together within the time T1, and executing S3;
s3, acquiring the face data obtained at the first preset position as second face data, comparing the second face data with a white list library storing the face data of an owner, if the face data exists in the white list library, judging as the owner, otherwise, judging as second non-owner and executing S4;
s4, comparing the second non-owner person with the to-be-determined stranger bottom library, if the second non-owner person exists in the to-be-determined stranger bottom library, executing S5, and if not, executing S6;
s5, taking out the owner ID passing through the first preset position within the time of T2, judging whether the owner ID exists in the current owner ID associated with the second non-owner to be judged, if so, judging that the person with low risk exists and adding the person into a low risk person base, and if not, executing S6;
s6, comparing the second non-owner person with a high-risk stranger bottom library, if the second non-owner person exists in the high-risk stranger bottom library, judging the second non-owner person to be a first high-risk stranger and updating the position of the first high-risk stranger, if the second non-owner person does not exist in the high-risk stranger bottom library, adding the second non-owner person to the high-risk stranger bottom library, recording the position of the second high-risk stranger, and executing S7;
and S7, when the time of the first high-risk person and/or the second high-risk person is judged to exceed the T4 time period, the position information of the first high-risk person and/or the second high-risk person is sent to a security system.
2. The method of claim 1, wherein the first predetermined location is one or more of a major intersection, a building entrance, a building perimeter, and the like.
3. The method of claim 1, further comprising
S8, acquiring third face data of a pre-entry unit door entrance, comparing the third face data with a white list library, judging as an owner if the third face data exists in the white list library, and executing S9 if the third face data does not exist in the white list library;
and S9, comparing a third non-owner person in the third face data with a resident person base library, judging as a resident person if the third non-owner person exists in the resident person base library, updating the time of the resident person entering the resident person base library, judging as a stranger if the third non-owner person does not exist in the resident person base library, adding the stranger base library, recording the time of the stranger entering the stranger base library, and judging the stranger as a resident person and deleting the stranger from the stranger base library when the time of the stranger entering the stranger exceeds a T3 time period.
4. The method of claim 3, further comprising cleaning the stranger bank periodically every T5 time period.
5. The method according to any one of claims 1 to 4, wherein the white list library is a database of an owner who has completed the face picture entry, and when the owner to be entered enters the face picture, the white list library is compared with the resident personnel library first, and when the owner to be entered exists in the resident personnel library, the owner to be entered is deleted from the resident personnel library.
6. An anti-tailing system based on face recognition technology is characterized by comprising: the system comprises a first face data acquisition module, a first execution module, a second face data acquisition module, a central calculation module and a security module;
the first face data acquisition module is used for acquiring first face data to enter a gate of a cell, performing face recognition, judging whether an owner exists in the first face data, controlling the first execution module to open the gate if the owner exists, sending first non-owner personnel data in the first face data to the central calculation module, controlling the first execution module not to open the gate if the owner does not exist, continuously acquiring the first face data to enter the gate of the cell, and judging whether the gate is opened or not;
the center module is used for adding the first non-owner personnel into a stranger base to be judged and associating the ID of an owner entering the first non-owner personnel together within T1 time;
the second face data acquisition module is used for acquiring face data acquired at a first preset position as second face data, comparing the second face data with a white list library in which owner face data are stored, judging as an owner if the second face data exist in the white list library, and otherwise, judging as a second non-owner person and sending the second non-owner person data to the central computing module;
the central computing module is further used for comparing the second non-owner person with the stranger base library to be judged, if the second non-owner person exists in the stranger base library to be judged, executing S5, and if the second non-owner person does not exist in the stranger base library to be judged, executing S6;
s5, taking out the owner ID passing through the first preset position within the time of T2, judging whether the owner ID exists in the current owner ID associated with the second non-owner to be judged, if so, judging that the person with low risk exists and adding the person into a low risk person base, and if not, executing S6;
s6, comparing the second non-owner person with a high-risk stranger bottom library, if the second non-owner person exists in the high-risk stranger bottom library, judging the second non-owner person to be a first high-risk stranger and updating the position of the first high-risk stranger, if the second non-owner person does not exist in the high-risk stranger bottom library, adding the second non-owner person to the high-risk stranger bottom library, recording the position of the second high-risk stranger, and executing S7;
and S7, when the time of the first high-risk person and/or the second high-risk person is judged to exceed the T4 time period, the position information of the first high-risk person and/or the second high-risk person is sent to a security module.
7. The system of claim 6, wherein the first predetermined location is one or more of a major intersection, a building entrance, a building perimeter, and the like.
8. The system according to claim 6, further comprising a unit door data acquisition module, wherein the unit door data acquisition module is configured to acquire third face data that is to enter a unit door entrance, compare the third face data with a white list library, determine that the third face data is an owner if the third face data exists in the white list library, and send third non-owner personnel data in the third face data to the central computing module if the third face data does not exist in the white list library;
the central computing module is further used for comparing third non-owner persons in the third face data with a resident person base library, judging as resident persons if the third non-owner persons exist in the resident person base library, updating the time of the resident persons entering the resident persons, judging as strangers if the third non-owner persons do not exist in the resident person base library, adding the strangers into a stranger base library, recording the time of the strangers entering the strangers, and judging the strangers as resident persons and deleting the strangers from the stranger base library when the time of the strangers entering the strangers exceeds T3 time period.
9. The system of claim 8, further comprising a timed cleaning module for periodically cleaning the stranger ground library every T5 time periods.
10. The system according to any one of claims 6 to 9, wherein the white list library is a database of an owner who has completed the face picture entry, and when the owner to be entered enters the face picture, the database is compared with the resident staff library first, and when the owner to be entered exists in the resident staff library, the database is deleted from the resident staff library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010730193.1A CN111915788A (en) | 2020-07-27 | 2020-07-27 | Anti-trailing method and system based on face recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010730193.1A CN111915788A (en) | 2020-07-27 | 2020-07-27 | Anti-trailing method and system based on face recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111915788A true CN111915788A (en) | 2020-11-10 |
Family
ID=73281774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010730193.1A Pending CN111915788A (en) | 2020-07-27 | 2020-07-27 | Anti-trailing method and system based on face recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111915788A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113838230A (en) * | 2021-09-02 | 2021-12-24 | 珠海格力电器股份有限公司 | Door lock control method and device, door lock and storage medium |
| CN114973486A (en) * | 2022-04-20 | 2022-08-30 | 上海奂燎智能科技有限公司 | Intelligent alarm method and device for machine room and electronic equipment |
| CN117830960A (en) * | 2024-03-05 | 2024-04-05 | 毕昇云(武汉)信息技术有限公司 | Smart community-based risk identification method, device, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520579A (en) * | 2018-03-14 | 2018-09-11 | 深圳励飞科技有限公司 | With administrative staff's correlating method, device, terminal and storage medium |
| CN109657608A (en) * | 2018-12-17 | 2019-04-19 | 中通服公众信息产业股份有限公司 | Trailing analysis method based on face recognition technology |
| CN110446015A (en) * | 2019-08-30 | 2019-11-12 | 北京青岳科技有限公司 | A kind of abnormal behaviour monitoring method based on computer vision and system |
| CN110874878A (en) * | 2018-08-09 | 2020-03-10 | 深圳云天励飞技术有限公司 | Pedestrian analysis method, device, terminal and storage medium |
| CN111028118A (en) * | 2019-11-29 | 2020-04-17 | 武汉虹信技术服务有限责任公司 | System and method for rapidly positioning newly-added floating population in community management field |
-
2020
- 2020-07-27 CN CN202010730193.1A patent/CN111915788A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520579A (en) * | 2018-03-14 | 2018-09-11 | 深圳励飞科技有限公司 | With administrative staff's correlating method, device, terminal and storage medium |
| CN110874878A (en) * | 2018-08-09 | 2020-03-10 | 深圳云天励飞技术有限公司 | Pedestrian analysis method, device, terminal and storage medium |
| CN109657608A (en) * | 2018-12-17 | 2019-04-19 | 中通服公众信息产业股份有限公司 | Trailing analysis method based on face recognition technology |
| CN110446015A (en) * | 2019-08-30 | 2019-11-12 | 北京青岳科技有限公司 | A kind of abnormal behaviour monitoring method based on computer vision and system |
| CN111028118A (en) * | 2019-11-29 | 2020-04-17 | 武汉虹信技术服务有限责任公司 | System and method for rapidly positioning newly-added floating population in community management field |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113838230A (en) * | 2021-09-02 | 2021-12-24 | 珠海格力电器股份有限公司 | Door lock control method and device, door lock and storage medium |
| CN114973486A (en) * | 2022-04-20 | 2022-08-30 | 上海奂燎智能科技有限公司 | Intelligent alarm method and device for machine room and electronic equipment |
| CN117830960A (en) * | 2024-03-05 | 2024-04-05 | 毕昇云(武汉)信息技术有限公司 | Smart community-based risk identification method, device, equipment and medium |
| CN117830960B (en) * | 2024-03-05 | 2024-05-14 | 毕昇云(武汉)信息技术有限公司 | Smart community-based risk identification method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111915788A (en) | Anti-trailing method and system based on face recognition technology | |
| CN109658554B (en) | Intelligent residential district security protection system based on big data | |
| CN105632001A (en) | Security and protection monitoring method and system based on face recognition | |
| CN204087316U (en) | A kind of Yunmen access control system of sending framework based on raspberry | |
| CN108009728B (en) | Regional security management method and system in park | |
| CN109598661A (en) | Intelligence community security system and detection method based on recognition of face | |
| CN109784231B (en) | Security information management method, device and storage medium | |
| CN110222640A (en) | Monitor recognition methods, device, method and the storage medium of suspect in place | |
| CN109657608B (en) | Trailing analysis method based on face recognition technology | |
| CN110246074A (en) | A kind of community security protection management system and method based on multidimensional acquisition | |
| CN105426869A (en) | Face recognition system and recognition method based on railway security check | |
| CN108399671A (en) | A kind of Internet of Things vena metacarpea video gate inhibition integrated system | |
| CN110942580A (en) | Intelligent building visitor management method and system and storage medium | |
| CN110619699A (en) | Case office building access control system and control method | |
| CN201465201U (en) | Community visitor self-help management system | |
| CN113611032A (en) | Access control management method and system based on face recognition | |
| CN112785765A (en) | Intelligent home remote control user authorization method based on big data analysis and intelligent home cloud control platform | |
| CN105574498A (en) | Face recognition system and recognition method based on customs security check | |
| CN118298537A (en) | Intelligent access control passing method and device | |
| CN113114969B (en) | Intelligent video intercom monitoring system and intercom monitoring method for intelligent building based on big data | |
| CN116342076B (en) | Engineering information management system and management method | |
| CN206672171U (en) | Floating population management system with early warning function | |
| KR20220132854A (en) | A system and method for managing a gate | |
| CN204537273U (en) | A kind of photographing device of swiping the card for gate control system | |
| CN204303055U (en) | Embedded intelligence door-lock controller |
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 | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20221230 |
|
| AD01 | Patent right deemed abandoned |