CN114973153A

CN114973153A - Smart campus security detection method, device, equipment and storage medium

Info

Publication number: CN114973153A
Application number: CN202210889601.7A
Authority: CN
Inventors: 徐丹
Original assignee: Guangzhou Hongtu Digital Technology Co ltd
Current assignee: Guangzhou Hongtu Digital Technology Co ltd
Priority date: 2022-07-27
Filing date: 2022-07-27
Publication date: 2022-08-30
Anticipated expiration: 2042-07-27
Also published as: CN114973153B

Abstract

The invention discloses a method, a device, equipment and a storage medium for detecting the safety of a smart campus, wherein the method comprises the following steps: setting a plurality of nodes on traffic for buildings in a campus; calling a camera to collect video data for each node; detecting a first user registered in a campus in video data; if the identity registered by the first user in the campus is a student or a teacher, determining that the first user is a second user; generating a passing network according to nodes passed by a second user and a first time length consumed by the nodes; detecting a third user which is not registered in the campus and does not meet a peer condition in the video data, wherein the peer condition is that the distance between the third user and any first user is less than a distance threshold value and the duration time exceeds a time threshold value; generating a passing link according to the nodes passed by the third user and the second time consumed by the nodes; matching the passing link with a passing network; and if the matching fails, executing an alarm operation on a third user. The safety of the campus is improved.

Description

Smart campus security detection method, device, equipment and storage medium

Technical Field

The invention relates to the technical field of education, in particular to a method, a device, equipment and a storage medium for intelligent campus security detection.

Background

A large number of teachers and students and other workers are arranged in the campus, the workers enter and exit frequently, and the safety risk is high.

At present, security in a campus mainly depends on patrol of security personnel, and continuous browsing of monitored video data and searching whether suspicious persons exist in the campus.

The security personnel manually carry out security protection mainly by means of subjective experience, so that the efficiency is low, people with risks are easy to miss, and security holes are generated.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for detecting the safety of a smart campus, aiming at improving the safety detection efficiency of the smart campus and further improving the safety.

According to an aspect of the present invention, there is provided a smart campus security detection method, including:

setting a plurality of nodes on traffic for buildings in a campus;

calling a camera to collect video data for each node;

detecting, in the video data, a first user that has been registered in the campus;

if the identity of the first user registered in the campus is a student or a teacher, determining that the first user is a second user;

generating a passing network according to the nodes passed by the second user and the first time length consumed by the second user;

detecting, in the video data, a third user that is not registered in the campus and does not satisfy a peer condition that a distance from any of the first users is less than a distance threshold and a duration exceeds a time threshold;

generating a passing link according to the node passed by the third user and a second time consumed by the third user passing through the node;

matching the traffic link with the traffic network;

and if the matching fails, executing an alarm operation on the third user.

Optionally, the generating a transit network according to the node passed by the second user and the first time length consumed by passing through the node includes:

if the second user appears from a first target point and a second target point continuously in time, determining that the second user moves from the first target point to the second target point, wherein the first target point and the second target point are both any nodes;

counting the first frequency and the first time length of all the second users moving from the first target point to the second target point;

identifying legitimacy of movement from the first target point to the second target point with reference to the first frequency;

and if the legality is legal, inserting the first target point and the second target point into a passing network, and establishing a first edge between the first target point and the second target point by referring to the first time length.

Optionally, the identifying the validity of the movement from the first target point to the second target point with reference to the first frequency includes:

counting second frequency of all the second users moving from the first target point to all the nodes;

calculating a ratio between the first frequency and the second frequency;

setting a legal threshold for moving from the first target point to the second target point;

if the ratio is greater than or equal to the legal threshold, determining that the legality of the target point moved from the first target point to the second target point is legal.

Optionally, the setting a legal threshold for the movement from the first target point to the second target point comprises:

counting the third frequency of all the second users moving from the first target point to any one node;

if the third frequency is smaller than or equal to a preset noise threshold value, filtering the node;

if filtering is completed, counting the number of the remaining nodes;

and setting a legal threshold value for the movement from the first target point to the second target point according to the quantity, wherein the legal threshold value is negatively related to the quantity.

Optionally, the establishing a first edge between the first target point and the second target point with reference to the duration includes:

counting an upper limit value and a lower limit value of the first duration;

searching a first branch point downwards from the upper limit value as a first endpoint value of a time range;

looking up a second partition point from the lower limit value as a second endpoint value of the time range;

a first edge is established pointing from the first object point to the second object point and the time range is set to the side length of the first edge.

Optionally, the generating a passing link according to the node passed by the third user and a second time duration consumed by passing the node includes:

if the third user appears from a first reference point and a second reference point continuously in time, determining that the third user moves from the first reference point to the second reference point, wherein the first reference point and the second reference point are both any nodes;

counting a second time length of the third user moving from the first reference point to the second reference point;

inserting the first reference point and the second reference point into a passing link, establishing a second edge pointing to the second reference point from the first reference point, and setting the side length of the second edge as the second time length.

Optionally, the matching the transit link with the transit network includes:

extracting a dependent node, a current node and a next node from the passing link, wherein the current node and the next node have a second edge, the dependent node is one or more other nodes sequenced before the current node, and the direction of the second edge is pointed to the next node from the current node;

searching the dependent node and the current node in the traffic network;

if the dependent node and the current node are searched, the current node is pointed to the next node from the current node under the condition that the dependent node appears in the traffic network;

if the next node is searched, inquiring a first edge between the current node and the next node in the passing network;

if the side length of the first edge is within the range of the side length of the second edge, determining that the passing link is successfully matched with the passing network;

if the side length of the first side is out of the range of the side length of the second side, determining that the matching between the passing link and the passing network fails;

and if the next node is not searched, determining that the matching of the passing link and the passing network fails.

According to another aspect of the present invention, there is provided a smart campus security detection apparatus, including:

the node setting module is used for setting a plurality of nodes on traffic for buildings in the campus;

the video data acquisition module is used for calling a camera to acquire video data for each node;

a registered user detection module for detecting a first user registered in the campus in the video data;

the user selection module is used for determining that the first user is a second user if the identity registered in the campus by the first user is a student or a teacher;

the passing network generation module is used for generating a passing network according to the nodes passed by the second user and the first time length consumed by the second user;

an unregistered user detection module, configured to detect, in the video data, a third user that is unregistered in the campus and does not satisfy a peer condition that a distance from any of the first users is less than a distance threshold and a duration of time exceeds a time threshold;

the passing link generation module is used for generating a passing link according to the node passed by the third user and a second time consumed by the third user passing through the node;

the passage matching module is used for matching the passage link with the passage network;

and the alarm operation execution module is used for executing alarm operation on the third user if the matching fails.

Optionally, the passing network generation module is further configured to:

calculating a ratio between the first frequency and the second frequency;

and if the ratio is larger than or equal to the legal threshold, determining that the legality of the target point moving from the first target point to the second target point is legal.

Optionally, the passing network generation module is further configured to:

if filtering is finished, counting the number of the remaining nodes;

Optionally, the passing network generation module is further configured to:

counting an upper limit value and a lower limit value of the first duration;

Optionally, the passing link generation module is further configured to:

Optionally, the traffic matching module is further configured to:

searching the dependent node and the current node in the traffic network;

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of smart campus security detection of any of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing a computer program for causing a processor to implement the method for smart campus security detection according to any one of the embodiments of the present invention when the computer program is executed.

In this embodiment, a plurality of nodes on traffic are set for buildings in a campus; calling a camera to collect video data for each node; detecting a first user registered in a campus in video data; if the identity registered by the first user in the campus is a student or a teacher, determining that the first user is a second user; generating a passing network according to nodes passed by a second user and a first time length consumed by the nodes; detecting a third user which is not registered in the campus and does not meet a peer condition in the video data, wherein the peer condition is that the distance between the third user and any first user is less than a distance threshold value and the duration time exceeds a time threshold value; generating a passing link according to the nodes passed by the third user and the second time consumed by the nodes; matching the passing link with a passing network; and if the matching fails, executing an alarm operation on a third user. The walking path detection precision of each personage is high, and the walking path through teachers and students is as the reference, compares with the walking path of other personages, can accurately find the personage that has the risk, reduces the security leak, has improved safety inspection's in the campus efficiency, improves the security in campus.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart illustrating a method for detecting security of a smart campus according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a smart campus security detection apparatus according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device implementing the method for detecting the security of the smart campus according to the embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, 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, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of a method for smart campus security detection according to an embodiment of the present invention, where the method may be performed by a smart campus security detection device, the smart campus security detection device may be implemented in a form of hardware and/or software, and the smart campus security detection device may be configured in an electronic device. As shown in fig. 1, the method includes:

step 101, a plurality of nodes on traffic are set for buildings in a campus.

Generally, a campus is built with a variety of buildings, such as libraries, dining halls, teaching buildings, administrative buildings, basketball courts, football stadiums, and so on, which mainly serve teachers and students, and in daily teaching, teachers and students often walk between the buildings.

In this embodiment, an electronic map may be constructed in advance for the campus, and a plurality of nodes on the traffic may be set in the electronic map according to the distribution of the buildings, that is, the nodes may accommodate normal passage of pedestrians.

In a specific implementation, the nodes are mostly main traffic roads and are main focuses of safety monitoring, for example, a stair opening, a road bifurcation, and the like, so as to monitor a normal walking path of a user as much as possible.

In addition, the nodes also include positions on a general road, for example, 2 to 3 nodes are arranged in the middle of a long corridor, and the like, so as to cover the normal walking path of the user as comprehensively and accurately as possible, which is not limited in this embodiment.

And 102, calling a camera to collect video data for each node.

One or more cameras can be deployed in each node, and during monitoring, one or more cameras can be called to face each node to acquire video data from the node at different angles, wherein the facing to the node can mean that the camera range of the camera covers the area of the node actually represented in the campus.

Step 103, detecting a first user registered in the campus in the video data.

In this embodiment, a user who learns and works in a campus may register user information in advance, and the user is denoted as a first user for convenience of distinction. The user information of the first user may include a name, an identity (e.g., teacher, student, cleaner, chef, administrative staff, etc.), a class, face data, and the like.

The method comprises the steps of providing multi-frame image data in video data, carrying out face recognition in the image data, detecting the similarity between the face data in the image data and the face data of a first user, and determining that the first user is detected in the frame of image data if the similarity exceeds a preset threshold value.

And step 104, if the identity registered in the campus by the first user is a student or a teacher, determining that the first user is a second user.

Students and teachers have high walking frequency among the buildings, cleaners, chefs, administrative staff and the like have relatively fixed workplaces and rarely walk among the buildings, so that the walking paths of the students and the teachers have higher reference value for analyzing normal walking paths.

After detecting the first user, the identity of the first user can be inquired in user information registered in the campus, if the identity of the first user is a student or a teacher, the first user is selected to analyze the walking path of the first user, and the selected first user is marked as a second user for distinguishing.

And 105, generating a passing network according to the nodes passed by the second user and the first time length consumed by the passed nodes.

In a specific implementation, the walking path of the second user is divided into node representations, so that main elements of the walking path can be simplified into the sequence of the nodes and the first time consumed between the nodes, and the two nodes are generated into a directed graph which is recorded as a passing network.

In one embodiment of the present invention, step 105 may include the steps of:

step 1051, determining that the second user moves from the first target point to the second target point if the second user appears from the first target point and the second target point continuously in time.

In this embodiment, the nodes may be sorted according to the time when the second user appears at each node, and two adjacent nodes are selected as the first target point and the second target point according to the sorting, that is, the first target point and the second target point are both any node, and the time when the second user appears at the first target point is earlier than the time when the second user appears at the second target point.

In the case where the second user appears from the first target point and the second target point continuously in time, it can be considered that the second user moves from the first target point to the second target point.

Step 1052, counting a first frequency and a first duration of all the second users moving from the first target point to the second target point.

And screening the same walking path aiming at all the second users, wherein the walking path refers to moving from the first target point to the second target point, and therefore the same walking path refers to moving from the same first target point to the same second target point.

And for the same more walking paths, counting a first frequency and a first time length of the same walking paths in a latest period of time, wherein the first time length is time consumed for moving from a first target point to a second target point.

Step 1053, identify the validity of the movement from the first target point to the second target point with reference to the first frequency.

Under the condition that the geographic positions of all buildings are determined, walking paths formed by the second users when the buildings are used have certain similarity, and therefore, the legality of the buildings can be reflected to a certain degree by analyzing the first frequency of moving from one node (a first target point) to another node (a second target point).

In a specific implementation, the second frequency of all the second users moving from the current first target point to all other nodes (including the current second target point) is counted, and the second frequency is the total frequency.

Calculating the ratio between the first frequency and the second frequency can obtain the probability of moving from the first target point to the second target point.

A legal threshold is set for moving from the first target point to the second target point and the ratio is compared to the legal threshold.

If the ratio is greater than or equal to the legal threshold, determining that the legality of the target point moving from the first target point to the second target point is legal.

If the ratio is less than the legal threshold, determining that the legality of the target point moving from the first target point to the second target point is illegal.

Further, the legal threshold may be a default empirical value, or may be dynamically adjusted, so as to improve the accuracy of the validity detection as much as possible while ensuring the accuracy.

Considering that the walking path of the second user is constrained to a certain extent by roads, for example, the main road in the campus may be a building such as a teaching building, an administrative building, a library, etc., the walking path is more, the ratio is lower, while some corridors in the campus may only pass buildings such as dormitories, dining rooms, etc., the administrative path is more single, the ratio is higher, etc.

Then, a third frequency of all second users moving from the current first target point to any single node may be counted.

If the third frequency is less than or equal to the preset noise threshold, which indicates that the third frequency is low, the node may be filtered if the third frequency is possibly a walking path generated by the second user crossing a non-road such as a railing, a green lawn and the like, and the third frequency is not a normal walking path.

And if the filtering is finished, counting the number of the residual nodes.

And setting a legal threshold value for moving from the first target point to the second target point according to the number, wherein the legal threshold value is negatively related to the number, namely, the larger the number of the remaining nodes is, the larger the number of nodes which can be run by the first target point is, the lower the legal threshold value is, and conversely, the smaller the number of the remaining nodes is, the smaller the number of nodes which can be run by the first target point is, the higher the legal threshold value is.

Step 1054, if the validity is legal, inserting a first destination point and a second destination point in the transit network, and establishing a first edge between the first destination point and the second destination point with reference to the first time length.

If it is legal to move from the first target point to the second target point, two nodes can be inserted into the transit network, respectively representing the first target point and the second target point, and a first edge is established between the first target point and the second target point with reference to the first time length.

In a specific implementation, the upper limit value and the lower limit value of the first duration may be counted.

The first partition point is searched downward from the upper limit value as the first endpoint value of the time range, so as to filter out the first time length which is close to the upper limit value and is higher than the first endpoint value, for example, the first time length with the highest 10% is filtered out.

The second cut-off point is searched upward from the lower limit value as the second endpoint value of the time range, so as to filter out the first time length which is close to the lower limit value and is lower than the second endpoint value, such as filtering out the lowest 10% of the first time length.

Within the time range (i.e., between the first endpoint value and the second endpoint value), the time spent by most of the second users walking from the first path to the second path may be excluded from the first time period generated by occasional behaviors such as meeting friends on the road, running busy in an emergency, etc.

And 106, detecting a third user which is not registered in the campus and does not meet the same-row condition in the video data.

Considering the factors of conveying garbage, transporting food materials, visiting students, parents and the like, other users except for the employees and the teachers of the campus can frequently enter the campus, temporary passing permission can be issued by the employees and the teachers of the campus in advance for the users, temporary basic information such as names, face data, visiting time, visiting things and the like is registered for the users, wherein if face recognition is carried out in the video data, the face data is detected to indicate that the identity of the users is temporary visitors, and the users can legally enter and exit the campus.

In some special cases, some users cannot reserve in advance, and arrive at the campus without reservation, at the moment, the first user accessible by the first user is in the same line, so that the first user can legally enter and exit the campus.

Under the condition that the users do not reserve in advance and the first user does not have the same line, the users enter the campus and need to be monitored intensively.

In this embodiment, a peer condition may be preset, where the peer condition indicates that the first user is in peer, specifically, a distance between the first user and any one of the first users is less than a distance threshold, and a duration exceeds a time threshold.

In a specific implementation, if a user not registered in the campus is detected in the video data, skeletal key points may be further detected for the user not registered in the campus and a first user in the vicinity thereof, and a spatial distance between the skeletal key points may be calculated as a distance between the user not registered in the campus and the first user in the vicinity thereof.

The distance is compared to a distance threshold, and if the distance is less than the distance threshold, a timing operation may be performed, counting the time duration, and comparing the time duration to a time threshold.

And if the duration time exceeds a time threshold, determining that the same-row condition is met, and confirming that the user which is not registered in the campus is a third user.

And step 107, generating a passing link according to the nodes passed by the third user and the second time consumed by the nodes passed by the third user.

In a specific implementation, a walking path of a third user is divided into node representations, so that main elements of the walking path can be simplified into the sequence of the nodes and the second time consumed between the nodes, and the two nodes are generated into a directed graph which is recorded as a passing link.

In one embodiment of the present invention, step 107 may comprise the steps of:

step 1071, if the third user appears from the first reference point, the second reference point continuously in time, determining that the third user moves from the first reference point to the second reference point.

In this embodiment, the nodes may be sorted according to the time when the third user appears at each node, and two adjacent nodes are selected according to the sorting as the first reference point and the second reference point, that is, the first reference point and the second reference point are both any node, and the time when the third user appears at the first reference point is earlier than the time when the third user appears at the second reference point.

For the case where the third user appears from the first reference point and the second reference point continuously in time, the third user may be considered to move from the first reference point to the second reference point.

And step 1072, counting a second time length of the third user moving from the first reference point to the second reference point.

For the third user, a second time length of the third user moving from the first reference point to the second reference point in the current time can be counted, wherein the second time length refers to the time consumed by the third user moving from the first reference point to the second reference point.

Step 1073, inserting the first reference point and the second reference point in the traffic link, establishing a second edge pointing from the first reference point to the second reference point, and setting the side length of the second edge as a second duration.

And creating a temporary passing link for a third user, inserting two nodes into the passing link, respectively representing a first reference point and a second reference point, creating a second edge with a direction from the first reference point to the second reference point at the first reference point and the second reference point, and setting the side length of the second edge as a second duration.

And step 108, matching the passing link with the passing network.

And matching the passing network representing the walking path of the teacher and the teacher (second user) with the passing link of the walking path of the key monitoring user (third user), and detecting whether the passing link of the walking path of the key monitoring user (third user) is normal or not.

In one embodiment of the present invention, step 108 may include the steps of:

and 1081, extracting the dependent node, the current node and the next node from the passing link.

In this embodiment, the pass links are sequentially traversed according to the order of the second edge, and when each match occurs, the dependent node, the current node, and the next node are respectively extracted from the pass links.

The second edge represents the ordering among the nodes, and then the dependent node is one or more other nodes ordered before the current node, the next node is a node ordered after the current node, the current node and the next node have a second edge, and the direction of the second edge is from the current node to the next node.

For example, in a certain transit link, a part of the nodes and their second edges (represented by arrows) are as follows: node a → node B → node C → node D → node E → node F, if traverse to node D and set the number of dependent nodes to two, then the dependent nodes are node B, node C and the next node is node F.

In the initial stage of the communication link, the dependent nodes can be empty, the number of the dependent nodes is equal to or less than the set number.

Step 1082, searching for dependent nodes and current nodes in the transit network.

The dependent node, the current node and the next node form a section of walking path, and the probability of the section of walking path can be converted into the probability of the next node after the dependent node and the current node.

Considering that the building distribution in the campus is interconnected, but the walking path is clear, accordingly, the traffic network is mostly a directed cyclic graph, but the sequence of each ring is clear, and if matching is performed only by the current node and the next node, the limitation of the ring is easily broken, so that matching is performed by adding a dependent node.

In this embodiment, if the dependent node and the current node are extracted from the transit link, the same dependent node and current node can be searched for in the transit network, and the order between the nodes (i.e., the direction represented by the second edge) is kept consistent except that the nodes are the same.

And 1083, if the dependent node and the current node are searched, directing the current node to the next node from the current node under the condition that the dependent node appears in the traffic network.

If the dependent node and the current node are searched in the passing network, the part of the walking path which belongs to the second user from the current node to the next node, namely the dependent node, the current node and the next node, can be further searched in the passing network under the condition that the dependent node appears.

Step 1084, if the next node is found, the first edge between the current node and the next node is queried in the transit network.

If the next node is searched in the transit network, the first edge between the current node and the next node can be queried in the transit network, and then the direction of the first edge between the current node and the next node in the transit network is the same as the direction of the first edge between the current node and the next node in the transit link.

At this time, the side length of the first edge between the current node and the next node in the transit network may be compared with the side length of the first edge between the current node and the next node in the transit link.

And 1085, if the side length of the first side is within the range of the side length of the second side, determining that the passing link is successfully matched with the passing network.

If the side length of the first side is within the range of the side length of the second side, the successful matching of the passing link and the passing network can be confirmed, and the walking path of the third user belongs to the normal category.

And step 1086, determining that the matching between the passing link and the passing network fails if the side length of the first side is out of the range of the side length of the second side.

If the side length of the first side is out of the range of the side length of the second side, it can be confirmed that the matching between the passing link and the passing network fails, and the walking path of the third user belongs to the abnormal category.

And 1087, if the next node is not searched, determining that the matching between the traffic link and the traffic network fails.

If the next node is not searched in the passing network, the passing link and the passing network are confirmed to be matched unsuccessfully, and the fact that the walking path of the third user belongs to the abnormal category is indicated.

And step 109, if the matching fails, executing an alarm operation on a third user.

If the matching of the passing link and the passing network fails, the risk coefficient of the third user is higher, at the moment, an alarm operation can be executed on the third user, security personnel is prompted to monitor the third user, and operations such as interception, inquiry and the like are executed in due time.

In this embodiment, a plurality of nodes on traffic are set for buildings in a campus; calling a camera to collect video data for each node; detecting a first user registered in a campus in video data; if the identity registered by the first user in the campus is a student or a teacher, determining that the first user is a second user; generating a passing network according to nodes passed by a second user and a first time length consumed by the nodes; detecting a third user which is not registered in the campus and does not meet a peer condition in the video data, wherein the peer condition is that the distance between the third user and any first user is less than a distance threshold value and the duration time exceeds a time threshold value; generating a passing link according to the nodes passed by the third user and the second time consumed by the nodes; matching the passing link with a passing network; and if the matching fails, performing alarm operation on a third user. The walking path detection precision of each personage is high, and the walking path through teachers and students is as the reference, compares with the walking path of other personages, can accurately find the personage that has the risk, reduces the security leak, has improved safety inspection's in the campus efficiency, improves the security in campus.

Example two

Fig. 2 is a schematic structural diagram of a smart campus security detection apparatus according to a second embodiment of the present invention. As shown in fig. 2, the apparatus includes:

a node setting module 201, configured to set a plurality of nodes on traffic for a building in a campus;

the video data acquisition module 202 is used for calling a camera to acquire video data for each node;

a registered user detection module 203, configured to detect, in the video data, a first user that is registered in the campus;

a user selection module 204, configured to determine that the first user is a second user if the identity of the first user registered in the campus is a student or a teacher;

a transit network generation module 205, configured to generate a transit network according to the node passed by the second user and a first time duration consumed by passing through the node;

an unregistered user detection module 206, configured to detect, in the video data, a third user that is unregistered in the campus and does not satisfy a peer condition that a distance from any of the first users is less than a distance threshold and a duration of time exceeds a time threshold;

a passing link generation module 207, configured to generate a passing link according to the node that the third user passes through and a second duration consumed by passing through the node;

a traffic matching module 208 for matching the traffic link with the traffic network;

and an alarm operation executing module 209, configured to execute an alarm operation on the third user if the matching fails.

In an embodiment of the present invention, the passing network generation module 205 is further configured to:

calculating a ratio between the first frequency and the second frequency;

if filtering is finished, counting the number of the remaining nodes;

counting an upper limit value and a lower limit value of the first duration;

searching a second branch point upwards from the lower limit value as a second endpoint value of the time range;

In an embodiment of the present invention, the transit link generation module 207 is further configured to:

inserting the first reference point and the second reference point in a transit link, establishing a second edge pointing from the first reference point to the second reference point, and setting the side length of the second edge as the second duration.

In an embodiment of the present invention, the traffic matching module 208 is further configured to:

searching the dependent node and the current node in the traffic network;

if the next node is searched, inquiring a first edge between the current node and the next node in the traffic network;

The intelligent campus security detection device provided by the embodiment of the invention can execute the intelligent campus security detection method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the intelligent campus security detection method.

EXAMPLE III

FIG. 3 illustrates a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. Processor 11 performs the various methods and processes described above, such as the smart campus security detection method.

In some embodiments, the smart campus security detection method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When loaded into RAM 13 and executed by processor 11, the computer program may perform one or more of the steps of the smart campus security detection method described above. Alternatively, in other embodiments, processor 11 may be configured to perform the wisdom campus security detection method by any other suitable means (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of transit networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a transit network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A smart campus security detection method is characterized by comprising the following steps:

setting a plurality of nodes on traffic for buildings in a campus;

calling a camera to collect video data for each node;

matching the traffic link with the traffic network;

and if the matching fails, executing an alarm operation on the third user.

2. The method of claim 1, wherein generating a transit network based on the nodes traversed by the second user and a first time period consumed traversing the nodes comprises:

3. The method of claim 2, wherein said identifying the validity of the movement from the first target point to the second target point with reference to the first frequency comprises:

calculating a ratio between the first frequency and the second frequency;

4. The method of claim 3, wherein setting a legal threshold for moving from the first target point to the second target point comprises:

counting third frequency of all the second users moving from the first target point to any node;

if filtering is completed, counting the number of the remaining nodes;

5. The method of claim 2, wherein said establishing a first edge between said first target point and said second target point with reference to said duration comprises:

counting an upper limit value and a lower limit value of the first duration;

6. The method of any of claims 1-5, wherein generating a transit link based on the node traversed by the third user and the second length of time spent traversing the node comprises:

7. The method of any of claims 1-5, wherein the matching the transit link with the transit network comprises:

searching the dependent node and the current node in the traffic network;

8. The utility model provides a wisdom campus safety inspection device which characterized in that includes:

the passing network generation module is used for generating a passing network according to the nodes passed by the second user and the first time span consumed by the second user passing through the nodes;

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the smart campus security detection method of any one of claims 1-7.

10. A computer-readable storage medium, wherein a computer program is stored, which when executed, causes a processor to implement the smart campus security detection method of any one of claims 1 to 7.