CN116095269B - Intelligent video security system and method thereof - Google Patents
Intelligent video security system and method thereof Download PDFInfo
- Publication number
- CN116095269B CN116095269B CN202211370450.0A CN202211370450A CN116095269B CN 116095269 B CN116095269 B CN 116095269B CN 202211370450 A CN202211370450 A CN 202211370450A CN 116095269 B CN116095269 B CN 116095269B
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- mysql
- correlation
- pedestrians
- pending
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 33
- 238000004891 communication Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims 4
- 230000000875 corresponding effect Effects 0.000 description 14
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
-
- 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
-
- 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
- G07C9/10—Movable barriers with registering means
- G07C9/15—Movable barriers with registering means with arrangements to prevent the passage of more than one individual at a time
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses an intelligent video security system and a method thereof, relating to the technical field of security systems, wherein a first MySQL is configured and used for backing up personal states of pedestrians who get access to a monitoring place authority and also for backing up matching states among all pedestrians; when the pedestrian entering and exiting the monitoring place is not in the first MySQL, configuring the pedestrian as a pending pedestrian, and configuring the person of the last entering and exiting monitoring place of the pending pedestrian as a follower; and the steps are actively implemented; if the preset number critical value B is smaller than Ren Yidai in the preset time period to determine the number of the corresponding followers of the pedestrian, calculating the total correlation value A among all the followers by using a preset scoring mechanism, and configuring the total correlation value A into the security alarm index of the pedestrian to be determined; the invention has the functions of actively identifying the person who does not swipe the card and enters and exits the gate machine together with the rest of the pedestrians who swipe the card, configuring the pedestrians as undetermined pedestrians and carrying out identification and inference on the pedestrians.
Description
Technical Field
The invention relates to the technical field of security systems, in particular to an intelligent video security system and a method thereof.
Background
With the improvement of people's safety protection consciousness, when various security protection systems are applied in our lives, pedestrians in communities or markets and the like generally need to swipe cards through gate machines of the security protection systems, and the security protection systems can be started only under the authorized condition, so that people can get in or out of specific places.
The existing security system aims at the situation that the walking speeds of pedestrians are different, a special module is generally arranged for increasing the opening time of the gate machine, however, the situation that other pedestrians can go in and out together without swiping cards is caused, and the place has certain danger, so that security is arranged at the gate machine to be attended by a plurality of places under the situation that the security system is arranged, and further the manpower cost is wasted.
Disclosure of Invention
In order to solve the technical problems, the invention provides an intelligent video security method, which comprises the following steps of
S1, configuring a first MySQL, wherein the first MySQL is used for backing up personal states of pedestrians who get access to a monitoring place authority, and is also used for backing up matching states among all pedestrians, and the personal states comprise face states and communication modes of the pedestrians;
s2, when the pedestrian entering and exiting the monitoring place is not in the first MySQL, configuring the pedestrian as a pending pedestrian, and configuring the person of the last entering and exiting monitoring place of the pending pedestrian as a follower; and the steps are actively implemented;
s3, the face states of the persons to be determined and the persons to be followed are in one-to-one correspondence and transmitted to a second MySQL, if in the preset time period, the preset number critical value B in the second MySQL is smaller than the number of the persons to be followed corresponding to the Ren Yidai determined pedestrians, the preset scoring mechanism is utilized to calculate the total correlation value A among all the persons to be followed, and the total correlation value A is configured to be the security alarm index of the person to be determined;
the method for calculating the total correlation value A among all the followers by using a preset scoring mechanism comprises the following steps:
grouping follower pairs, wherein each group is different to form (n-1) n/2 sets;
if 2 followers in any set are relevant, the set is configured as set one, otherwise configured as set two;
the number of the integrated units is summarized and configured as a correlation total value A.
The technical scheme of the invention is as follows:
further, also comprises
When the preset score critical value I is smaller than Ren Yidai to determine the security alarm index of the pedestrian, the correlation indexes Ax, x=1 and 2 … n between the corresponding each followed person and the rest of the followed persons are sequentially calculated;
transmitting an approval command to the terminal of the follower with the maximum relevance index, wherein the approval command comprises the face state of the pending pedestrian.
In the foregoing intelligent video security method, the correlation total value a among all the followers is calculated by using a preset scoring mechanism and is configured as follows:
if the pedestrian x and the pedestrian y are related, configuring a related index Cx and y according to the degree of closeness of the correlation of the pedestrian x and the pedestrian y;
grouping the follower pairs, wherein each group is different, and forming (n-1) n/2 sets, and obtaining correlation indexes Cx, y (k), k=1, 2 … of the two follower pairs in each set, (n-1) n/2;
the correlation total value A between the followers corresponding to the pending pedestrian is calculated by using the following formula,
in the foregoing intelligent video security method, the gate machine is equipped with a face recognition component for collecting the face status of pedestrians entering and exiting the monitoring location via the gate machine, and comparing the face status with the first MySQL implementation.
In the foregoing intelligent video security method, the gate machine is further provided with a distance monitor electrically connected to the face recognition component, and when a person comes in and goes out of the collecting distance of the face recognition component, the face recognition component is activated by the distance monitor, so as to collect the face state of the person.
The intelligent video security method further comprises the steps of
A third MySQL is preset and used for backing up the face states of all people without access to the monitoring place authority;
if the preset fraction critical value II is larger than the security alarm index of the undetermined pedestrian, backing up the face state of the undetermined pedestrian into a third MySQL.
The intelligent video security method further comprises the steps of
If the recognized face state of the pending pedestrian is in the third MySQL, an early warning message is generated and transmitted to the corresponding terminal.
The invention provides an intelligent video security system which is used in a place provided with a gate machine and is characterized in that: comprises
The PC comprises a backup module, wherein the backup module is used for backing up a first MySQL and a second MySQL respectively, the first MySQL is used for backing up the personal state of pedestrians who get access to the monitoring place permission, and is also used for backing up the matching state among all pedestrians, and the personal state comprises the face state and the communication mode of the pedestrians;
the face recognition component is arranged at the gate machine position of the monitoring place and is electrically connected to the PC, when a pedestrian entering and exiting the monitoring place is not in the first MySQL, the face recognition component configures the pedestrian as a pending pedestrian, configures the person of the pending pedestrian, which enters and exits the monitoring place, as a followed person, and simultaneously corresponds the face states of the pending pedestrian and the followed person one by one and transmits the face states to the second MySQL;
the PC is configured to dynamically operate the content in the second MySQL, if the preset number critical value B in the second MySQL is smaller than Ren Yidai corresponding follower number of the determined pedestrian in the preset time period, the correlation total value A among all the follower is calculated by utilizing a preset scoring mechanism, and the correlation total value A is configured to be the security alarm index of the determined pedestrian;
the method for calculating the total correlation value A among all the followers by using a preset scoring mechanism comprises the following steps:
grouping follower pairs, wherein each group is different to form (n-1) n/2 sets;
if 2 followers in any set are relevant, the set is configured as set one, otherwise configured as set two;
the number of the integrated units is summarized and configured as a correlation total value A.
The beneficial effects of the invention are as follows:
the invention has the functions of actively identifying the person who does not swipe the card and enters and exits the gate machine together with the rest of the pedestrians who swipe the card, configuring the pedestrians as undetermined pedestrians and carrying out identification and inference on the pedestrians.
Drawings
FIG. 1 is a flow chart of the method steps of the present invention.
Detailed Description
Example 1: the intelligent video security system provided by the embodiment is used in a place provided with a gate machine and comprises a PC and a face recognition component.
The PC comprises a backup module, wherein the backup module is respectively backed up with a first MySQL and a second MySQL, the first MySQL is used for backing up the personal state of pedestrians who get access to the monitoring place permission, and is also used for backing up the matching state among all pedestrians, and the personal state comprises the face state and the communication mode of the pedestrians.
The face recognition component is arranged at the gate machine position of the monitoring place and is electrically connected to the PC, when the pedestrian entering and exiting the monitoring place is not in the first MySQL, the face recognition component configures the pedestrian as a pending pedestrian, configures the person entering and exiting the monitoring place last to the pending pedestrian as a followed person, and simultaneously corresponds the face states of the pending pedestrian and the followed person one by one and transmits the face states to the second MySQL.
And (3) configuring the PC to perform dynamic operation on the content in the second MySQL, if the preset number critical value B in the second MySQL is smaller than the number of the followers corresponding to the Ren Yidai determined pedestrian in the preset time period, calculating the correlation total value A among all the followers by utilizing a preset scoring mechanism, and configuring the correlation total value A into the security alarm index of the determined pedestrian.
The invention thus has the function of actively recognizing the person who is not swiping the card but who is going to get in and out of the gate machine with the rest of the swiping the card, configuring the person to be the pending person and carrying out recognition inference on who he is.
Example 2: the intelligent video security method provided by the embodiment is used in a place provided with a gate machine and is used for taking care of pedestrians who often do not swipe cards and come in and go out of the gate machine together with other swipe cards, and because security levels of all places have differences, the critical value can be adjusted and the index can be collected according to the security levels.
The intelligent video security method provided by the embodiment, as shown in fig. 1, comprises the following steps
S1, configuring a first MySQL, wherein the first MySQL is used for backing up personal states of pedestrians who get access to the monitoring place permission, and is also used for backing up matching states among all pedestrians, and the personal states comprise face states and communication modes of the pedestrians.
The first MySQL includes monitoring personal status of resident and visitors allowed to access, and selects resident sites as examples, and the first MySQL includes personal status of resident and visitors allowed according to usual conditions, including cell police, cell server, visitors authorized by resident, and other similar visitors.
The security-managing server performs overall configuration on the matching states of all pedestrians, and selects living places to be used as examples, and selects all people in one family to be configured as corresponding, and people belonging to relatives or friends to be configured as corresponding.
In the remaining examples, the following configuration can also be selected: if there is a correlation between the pedestrian x and the pedestrian y, the correlation indices Cx, y are configured according to the degree of closeness of the correlation therebetween, and the correlation indices Cx, y are configured as odd numbers or even numbers, the degree of closeness of the correlation between the pedestrian x and the pedestrian y being indicated by the quantification.
For example, the correlation index selection configuration between people in a family is larger, and the correlation index selection configuration between people belonging to relatives or friends is smaller, so that the effect of distinguishing the two is achieved.
S2, when the pedestrian entering and exiting the monitoring place is not in the first MySQL, configuring the pedestrian as a pending pedestrian, and configuring the person of the last entering and exiting monitoring place of the pending pedestrian as a follower; and this step is actively implemented.
A face recognition component is provided at the gateway for gathering the face status of pedestrians entering and exiting the monitoring location via the gateway and comparing the face status to the first MySQL implementation.
From the standpoint of energy conservation, the gate machine is also provided with a distance monitor electrically connected with the face recognition component, and when a person comes in and goes out of the collecting distance of the face recognition component, the face recognition component is activated by the distance monitor, so that the face state of the person is collected.
The face recognition component further comprises an internet of things camera, when a person enters and exits the gathering distance of the face recognition component, the internet of things camera gathers images of a specific place, and the gathered images cannot be immediately transmitted to the security command place; firstly, selecting a face photo from collected images, then identifying the face photo, then deducing whether the pedestrian is in the first MySQL, defining the pedestrian as a pending pedestrian only when the pedestrian is not in the first MySQL, configuring the person of the last access monitoring place of the pending pedestrian as a follower, otherwise, closing an Internet of things camera, interrupting the collection of images, and temporarily registering collected contents in a backup module of a face identification component.
S3, the face states of the person to be determined and the person to be followed are in one-to-one correspondence, and the face states are transmitted to the second MySQL to continue operation.
If the preset number threshold value B is smaller than Ren Yidai in the second MySQL in the preset time period to determine the number of the corresponding followers of the pedestrian, calculating the total correlation value A among all the followers by using a preset scoring mechanism, and configuring the total correlation value A into the security alarm index of the undetermined pedestrian, wherein the larger the number of the total correlation value A is, the larger the number of the security alarm index is.
Selecting a residential site for example, assuming that a pending pedestrian is always following an occupant in the same home, or the same occupant is coming in and going out of the gate machine, the person representing the pending pedestrian may be the occupant, or a parent or friend of the following pedestrian, namely:
and when the preset score critical value I is smaller than Ren Yidai to determine the security alarm index of the pedestrian, sequentially calculating the corresponding correlation indexes Ax, x=1 and 2 … n between each followed person and the rest followed persons.
Transmitting an approval command to the terminal of the follower with the maximum relevance index, wherein the approval command comprises the face state of the pending pedestrian.
The function of the steps is to pick out the follower with the highest probability of being the parent or friend of the pending pedestrian and identify the pending pedestrian via the follower:
if the person to be followed identifies that the person to be determined is a person or friend of the person to be determined, the person to be determined is selected to move from the second MySQL to the first MySQL, so that the person to be determined has the authority of entering and exiting the gate machine, and repeated operation is avoided;
if the person to be followed identifies that the person to be determined is not a person or friend of the person to be determined, the person to be determined is represented to have a certain danger, and the security and protection server tells the person to be followed about the situation on the one hand and continuously tracks the person to be determined on the other hand;
if there is less correlation between pedestrians that a certain pending pedestrian gets in and out of the gate machine together, it is more likely that pending pedestrian is not a person or friend of a person in the surveillance venue, such as a promoter, etc.
Further, if the preset score threshold value II is larger than the security alarm index of the undetermined pedestrian, backing up the face state of the undetermined pedestrian into a third MySQL; the third MySQL is used for backing up the face status of all people who do not have access to the monitoring location authority, and when the pending pedestrian is recognized again and is also in the third MySQL, the early warning message is transmitted to the corresponding terminal, such as the mobile phone or other similar devices of the security server, so that the security server can more quickly take relevant operations.
The invention provides two methods for calculating a correlation total value A between all followers.
The first method is as follows: the pedestrians are only configured to be relevant or irrelevant, but the exact relevance index is not configured, the follower pairs are formed into groups, and each group is different, so that (n-1) n/2 sets are formed.
If 2 followers in any set are relevant, the set is configured as set one, or set two.
The number of the integrated units is summarized and configured as a correlation total value A.
If a certain pending pedestrian follows ten persons in a preset time period, the first pedestrian is related to the second pedestrian, the third pedestrian is related to the fourth pedestrian, the fifth pedestrian is related to the sixth pedestrian, and the rest pedestrians are not related, so that the total correlation value between the followers corresponding to the pending pedestrian is 3.
If a pending pedestrian is associated with a second, third, fourth, and fifth pedestrian, respectively, of ten persons visiting for a predetermined period of time, the association index of the pending pedestrian is 4.
The second method is as follows: the follower x and the follower y are related, and the related indexes Cx and y are configured for the connection of the two followers according to the degree of closeness of the follower x and the follower y, and under the configuration, the operation method of the total correlation value is as follows:
grouping the follower pairs, wherein each group is different, and forming (n-1) n/2 sets, and obtaining correlation indexes Cx, y (k), k=1, 2 … of the two follower pairs in each set, (n-1) n/2;
the correlation total value A between the followers corresponding to the pending pedestrian is calculated by using the following formula,
if a certain pending pedestrian follows ten persons in a preset time period, among the following persons, the correlation index of the first pedestrian and the second pedestrian is 2, the correlation index of the third pedestrian and the fourth pedestrian is 1, the correlation index of the fifth pedestrian and the sixth pedestrian is 1, and the rest pedestrians are not correlated, so that the correlation index corresponding to the pending pedestrian is a=2+1+1=4.
If the first pedestrian is related to the second, third, fourth and fifth pedestrians in the ten persons visited in the preset time period, and the correlation indexes are 1, 0.5, 2 and 1, respectively, the correlation index of the first pedestrian is a=1+0.5+2+1=4.5.
In addition to the embodiments described above, other embodiments of the invention are possible. All technical schemes formed by equivalent substitution or equivalent transformation fall within the protection scope of the invention.
Claims (6)
1. An intelligent video security method is characterized in that: comprises the following steps
S1, configuring a first MySQL, wherein the first MySQL is used for backing up personal states of pedestrians who get access to a monitoring place authority, and is also used for backing up matching states among all pedestrians, and the personal states comprise face states and communication modes of the pedestrians;
s2, when the pedestrian entering and exiting the monitoring place is not in the first MySQL, configuring the pedestrian as a pending pedestrian, and configuring the person of the last entering and exiting monitoring place of the pending pedestrian as a follower; and the steps are actively implemented;
s3, the face states of the persons to be determined and the persons to be followed are in one-to-one correspondence and transmitted to a second MySQL, if in the preset time period, the preset number critical value B in the second MySQL is smaller than the number of the persons to be followed corresponding to the Ren Yidai determined pedestrians, the preset scoring mechanism is utilized to calculate the total correlation value A among all the persons to be followed, and the total correlation value A is configured to be the security alarm index of the person to be determined;
the method for calculating the total correlation value A among all the followers by using a preset scoring mechanism comprises the following steps:
grouping follower pairs, wherein each group is different to form (n-1) n/2 sets;
if 2 followers in any set are relevant, the set is configured as set one, otherwise configured as set two;
the number of the integration is integrated, and the integration is configured as a correlation total value A;
also comprises
When the preset score critical value I is smaller than Ren Yidai to determine the security alarm index of the pedestrian, the correlation indexes Ax, x=1 and 2 … n between the corresponding each followed person and the rest of the followed persons are sequentially calculated;
transmitting an approval instruction to the terminal of the follower with the maximum correlation index, wherein the approval instruction comprises the face state of the pending pedestrian;
the correlation total value A among all the followers is calculated by using a preset scoring mechanism and is configured as follows:
if the pedestrian x and the pedestrian y are related, configuring a related index Cx and y according to the degree of closeness of the correlation of the pedestrian x and the pedestrian y;
grouping the follower pairs, wherein each group is different, and forming (n-1) n/2 sets, and obtaining correlation indexes Cx, y (k), k=1, 2 … of the two follower pairs in each set, (n-1) n/2;
the following formula is used to calculate the total correlation value A between the followers corresponding to the pending pedestrian,
。
2. the intelligent video security method of claim 1, wherein: the monitoring site is equipped with a face recognition component for gathering the face status of pedestrians entering and exiting the monitoring site via the gate machine and comparing the face status to the first MySQL implementation.
3. The intelligent video security method according to claim 2, wherein: the gate machine is also provided with a distance monitor electrically connected with the face recognition component, and when a person comes in and goes out of the collecting distance of the face recognition component, the face recognition component is activated by the distance monitor so as to collect the face state of the person.
4. An intelligent video security method according to any one of claims 1-3, wherein: also comprises
A third MySQL is preset and used for backing up the face states of all people without access to the monitoring place authority;
if the preset fraction critical value II is larger than the security alarm index of the undetermined pedestrian, backing up the face state of the undetermined pedestrian into a third MySQL.
5. The intelligent video security method according to claim 4, wherein: also comprises
If the recognized face state of the pending pedestrian is in the third MySQL, an early warning message is generated and transmitted to the corresponding terminal.
6. An intelligent video security system for use in a venue equipped with a gate machine, characterized by: comprises
The PC comprises a backup module, wherein the backup module is used for backing up a first MySQL and a second MySQL respectively, the first MySQL is used for backing up the personal state of pedestrians who get access to the monitoring place permission, and is also used for backing up the matching state among all pedestrians, and the personal state comprises the face state and the communication mode of the pedestrians;
the face recognition component is arranged at the gate machine position of the monitoring place and is electrically connected to the PC, when a pedestrian entering and exiting the monitoring place is not in the first MySQL, the face recognition component configures the pedestrian as a pending pedestrian, configures the person of the pending pedestrian, which enters and exits the monitoring place, as a followed person, and simultaneously corresponds the face states of the pending pedestrian and the followed person one by one and transmits the face states to the second MySQL;
the PC is configured to dynamically operate the content in the second MySQL, if the preset number critical value B in the second MySQL is smaller than Ren Yidai corresponding follower number of the determined pedestrian in the preset time period, the correlation total value A among all the follower is calculated by utilizing a preset scoring mechanism, and the correlation total value A is configured to be the security alarm index of the determined pedestrian;
when the preset score critical value I is smaller than Ren Yidai to determine the security alarm index of the pedestrian, the correlation indexes Ax, x=1 and 2 … n between the corresponding each followed person and the rest of the followed persons are sequentially calculated;
transmitting an approval instruction to the terminal of the follower with the maximum correlation index, wherein the approval instruction comprises the face state of the pending pedestrian;
the method for calculating the total correlation value A among all the followers by using a preset scoring mechanism comprises the following steps:
grouping follower pairs, wherein each group is different to form (n-1) n/2 sets;
if 2 followers in any set are relevant, the set is configured as set one, otherwise configured as set two;
the number of the integration is integrated, and the integration is configured as a correlation total value A;
the correlation total value A among all the followers is calculated by using a preset scoring mechanism and is configured as follows:
if the pedestrian x and the pedestrian y are related, configuring a related index Cx and y according to the degree of closeness of the correlation of the pedestrian x and the pedestrian y;
grouping the follower pairs, wherein each group is different, and forming (n-1) n/2 sets, and obtaining correlation indexes Cx, y (k), k=1, 2 … of the two follower pairs in each set, (n-1) n/2;
the following formula is used to calculate the total correlation value A between the followers corresponding to the pending pedestrian,
。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211370450.0A CN116095269B (en) | 2022-11-03 | 2022-11-03 | Intelligent video security system and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211370450.0A CN116095269B (en) | 2022-11-03 | 2022-11-03 | Intelligent video security system and method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116095269A CN116095269A (en) | 2023-05-09 |
CN116095269B true CN116095269B (en) | 2023-10-20 |
Family
ID=86210954
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211370450.0A Active CN116095269B (en) | 2022-11-03 | 2022-11-03 | Intelligent video security system and method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116095269B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106454282A (en) * | 2016-12-09 | 2017-02-22 | 南京创维信息技术研究院有限公司 | Security and protection monitoring method, apparatus and system |
CN109636397A (en) * | 2018-11-13 | 2019-04-16 | 平安科技(深圳)有限公司 | Transit trip control method, device, computer equipment and storage medium |
CN111784900A (en) * | 2020-06-20 | 2020-10-16 | 深圳南亿科技股份有限公司 | Intelligent management system for intelligent community |
CN112818854A (en) * | 2021-02-01 | 2021-05-18 | 南通大学 | All-weather video person searching method applied to campus security |
WO2022126669A1 (en) * | 2020-12-16 | 2022-06-23 | 中电海康集团有限公司 | Subway pedestrian flow network fusion method based on video pedestrian recognition, and pedestrian flow prediction method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070071404A1 (en) * | 2005-09-29 | 2007-03-29 | Honeywell International Inc. | Controlled video event presentation |
-
2022
- 2022-11-03 CN CN202211370450.0A patent/CN116095269B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106454282A (en) * | 2016-12-09 | 2017-02-22 | 南京创维信息技术研究院有限公司 | Security and protection monitoring method, apparatus and system |
CN109636397A (en) * | 2018-11-13 | 2019-04-16 | 平安科技(深圳)有限公司 | Transit trip control method, device, computer equipment and storage medium |
CN111784900A (en) * | 2020-06-20 | 2020-10-16 | 深圳南亿科技股份有限公司 | Intelligent management system for intelligent community |
WO2022126669A1 (en) * | 2020-12-16 | 2022-06-23 | 中电海康集团有限公司 | Subway pedestrian flow network fusion method based on video pedestrian recognition, and pedestrian flow prediction method |
CN112818854A (en) * | 2021-02-01 | 2021-05-18 | 南通大学 | All-weather video person searching method applied to campus security |
Non-Patent Citations (2)
Title |
---|
人工智能与传统产业融合创新机制研究——基于对中国智能安防产业创新网络的分析;张昕蔚 等;科学学研究;第40卷(第6期);1105-1116 * |
安防系统视频监控及周界报警系统的构建;罗惠敏;;无锡职业技术学院学报(03);57-59 * |
Also Published As
Publication number | Publication date |
---|---|
CN116095269A (en) | 2023-05-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6905850B2 (en) | Image processing system, imaging device, learning model creation method, information processing device | |
JP6885682B2 (en) | Monitoring system, management device, and monitoring method | |
CN202257856U (en) | Driver fatigue-driving monitoring device | |
CN202130312U (en) | Driver fatigue driving monitoring device | |
CN108469806A (en) | Alternative expression is man-machine to drive middle driving power transfer method altogether | |
CN103839346A (en) | Intelligent door and window anti-intrusion device and system and intelligent door control system | |
CN113763620B (en) | Combined access control, method and device for controlling combined access control and storage medium | |
RU2714389C1 (en) | Rescue system and rescue method, and server used for rescue system and rescue method | |
CN102354409A (en) | Access control system based on face recognition | |
CN101739742A (en) | Networking type multi-channel access control and attendance system | |
CN106454282A (en) | Security and protection monitoring method, apparatus and system | |
US11539922B2 (en) | Point-to-point visual communications in a security monitoring system | |
CN114140275A (en) | Smart community cloud platform system with health care function | |
CN101720024A (en) | Intelligent recognition monitoring system and monitoring method thereof | |
Praveen et al. | Face recognition: challenges and issues in smart city/environments | |
CN114612813A (en) | Identity recognition method, model training method, device, equipment and storage medium | |
CN113256859A (en) | Epidemic prevention channel system | |
CN115171260A (en) | Intelligent access control system based on face recognition | |
CN116095269B (en) | Intelligent video security system and method thereof | |
CN108537920B (en) | Visitor monitoring method and system based on face recognition | |
CN112085878B (en) | House supervisory systems based on waste classification | |
CN114005235A (en) | Security monitoring method, system, medium and electronic terminal | |
CN109993869A (en) | A kind of remote door access system based on Identification of Images | |
CN111960200B (en) | Resident building elevator control system based on voice recognition and face recognition | |
CN203025900U (en) | Face recognition alarm apparatus |
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 |