A roof safety guarantee system based on edge computing

Abstract

The embodiment of the application discloses an edge computing-based roof safety guarantee system, and relates to the technical field of image recognition.The system comprises a camera, which is installed on a target roof and is used for collecting target roof image information in real time; an edge computing module, which is connected with the camera and is used for identifying whether personnel exist in the target roof image information and whether the identified target personnel enter a pre-set dangerous area; and an alarm module, which is connected with the edge computing module and is used for alarming when the edge computing module identifies that the identified target personnel in the target roof image information enter the dangerous area.The application can effectively reduce the occurrence of jumping-off events and guarantee the safety of personnel.

Description

Technical Field

[0001] This invention belongs to the field of image recognition technology, and in particular relates to a rooftop security system based on edge computing. Background Technology

[0002] With the increasingly fast pace of life, young people are facing greater and greater pressure. Many young people, even students, have poor coping skills when faced with setbacks and are not mentally sound. They may be unable to cope with even the slightest setbacks, leading them to contemplate suicide by jumping off buildings.

[0003] To effectively reduce and prevent suicide attempts, existing safety measures primarily involve installing security access control systems at the rooftop stairwells, preventing unauthorized personnel from entering. However, these systems are easily compromised by individuals contemplating suicide, rendering them ineffective. Another safety measure involves installing surveillance cameras on the roof, allowing security personnel to remotely monitor for potential suicide attempts and implement timely emergency measures to prevent them from jumping. However, relying on surveillance cameras is highly dependent on manual intervention and may not promptly detect anomalies, resulting in poor monitoring effectiveness and low safety standards on the rooftop. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a rooftop safety assurance system based on edge computing to address the problems of existing safety assurance solutions being highly dependent on manual intervention, unable to promptly detect potential jump / accidental fall events, and thus having low rooftop safety assurance. The present invention can intelligently, automatically, and comprehensively monitor potential jump / accidental fall events on rooftops and issue timely alarms, effectively reducing the occurrence of safety accidents and greatly enhancing safety assurance.

[0005] This invention provides a rooftop security system based on edge computing, comprising:

[0006] The camera is installed on the roof of the target building to collect real-time images of the roof.

[0007] An edge computing module, connected to the camera, is used to identify whether there are people in the target rooftop image information and whether the identified target people have entered a pre-set danger zone.

[0008] The alarm module, connected to the edge computing module, is used to issue an alarm when a target person identified in the target rooftop image information by the edge computing module enters a dangerous area.

[0009] In an optional embodiment, the edge computing module is further configured to determine whether the target person is moving toward a preset danger edge side on the target rooftop;

[0010] The system also includes:

[0011] A controllable baffle control module, connected to the edge computing module, is used to control the controllable baffle on the dangerous edge side to rise when the edge computing module determines that the target person is moving towards the dangerous edge side of the roof plane of the target building, so as to prevent the target person from falling from the dangerous edge side.

[0012] In one alternative embodiment, the roof plane has a safe edge side for personnel access; the dangerous edge side is another side of the roof plane that is not a safe edge side.

[0013] In an optional embodiment, the edge computing module includes:

[0014] The personnel identification unit is used to identify whether there are personnel in the target rooftop image information;

[0015] A personnel positioning unit is used to locate the position information of the target personnel identified by the personnel identification unit within the rooftop plane.

[0016] The intrusion danger zone determination unit is used to determine whether the target person is in a pre-set danger zone based on the target person's location information on the roof plane;

[0017] The movement determination unit is used to determine the movement direction of the target person based on the position information of the target person located in the roof plane at each consecutive moment within a certain period of time by the personnel positioning unit, and to determine whether the target person is moving towards the danger edge.

[0018] In one alternative embodiment, the camera is specifically positioned on the safety edge side of the target rooftop and the camera direction is directed towards the entire rooftop, including the non-safety edge side.

[0019] In one optional embodiment, the position information of the target person on the roof plane is the coordinates of the target person in a preset two-dimensional rectangular coordinate system on the roof plane; wherein, the preset two-dimensional rectangular coordinate system takes the safe edge side of the roof plane as the bottom end, the left edge point of the bottom end as the origin of the coordinate system, the rightward direction from the bottom end as the X-axis, and the direction perpendicular to the X-axis from the origin as the Y-axis;

[0020] The intrusion danger zone determination unit includes:

[0021] The judgment value calculation subunit is used to calculate the judgment value of whether the target personnel have entered the danger zone according to the first formula;

[0022] The first judgment subunit is used to determine whether the judgment value of whether the target person has entered the danger zone is equal to 1. If yes, it is determined that the person has entered the danger zone; otherwise, it is determined that the person has not entered the danger zone.

[0023] The first formula is:

[0024]

[0025] In the first formula, W(t) represents the judgment value of whether the target personnel have entered the danger zone at the current moment; [x(t), y(t)] represents the coordinates of the target personnel in the preset two-dimensional rectangular coordinate system at the current moment; X0 represents the length value of the safe edge side; Y0 represents the length value of the danger edge side perpendicular to the safe edge side; L represents the maximum vertical distance between the nearest edges in the danger zone; V[,,] represents the existence of a function, and the overall function is valid if one or more of the formulas in the parentheses are true; ∧[] represents all functions, and the overall function is valid when all the formulas in the parentheses are true, otherwise the overall function is not true.

[0026] In an optional embodiment, the movement determining unit includes:

[0027] The movement direction vector calculation subunit is used to calculate the movement direction vector of the target person on the target rooftop according to the second formula;

[0028] The control value calculation subunit is used to calculate the control value of the controllable baffle on the danger edge side according to the third formula;

[0029] The second judgment subunit is used to determine whether the control value of the controllable baffle on the dangerous edge side is equal to 1. If it is, it determines that the target person is moving towards the dangerous edge side.

[0030] The second formula is:

[0031]

[0032] In the second formula, [X(t), Y(t)] represents the movement direction vector of the target personnel on the rooftop of the target building over a period of time; 'a' represents an integer variable, taking values ​​of... [x(ta×T), y(ta×T)] represents the coordinates of the target person in the preset two-dimensional rectangular coordinate system at time ta×T; {x[t-(a-1)×T], y[t-(a-1)×T]} represents the coordinates of the target person in the preset two-dimensional rectangular coordinate system at time t-(a-1)×T; t0 represents the initial time when the target person is identified as appearing on the rooftop; T represents the calculation and detection period of the edge computing module; S(a) represents the distance the target person moves in the rooftop image information from time t-(a-1)×T to time ta×T; Indicates rounding down;

[0033] The third formula is:

[0034]

[0035] In the third formula, E(t) represents the controllable baffle value on the danger edge side at the current moment; else represents the value of the controllable baffle value other than the controllable baffle value at the current moment. and All other cases.

[0036] In one optional embodiment, the rooftop security system based on edge computing further includes: a mobile terminal carried by the management personnel;

[0037] The alarm module is specifically used to send alarm information to the mobile terminal when the edge computing module identifies a target person entering a dangerous area from the target rooftop image information; the alarm information includes at least: target rooftop identification information and target rooftop image information;

[0038] The mobile terminal is used to display the received alarm information.

[0039] This invention provides a rooftop safety system based on edge computing. First, a camera collects real-time images of the rooftop. Then, an edge computing module identifies whether anyone has entered a pre-defined danger zone within the rooftop images; if so, an alarm is automatically triggered. This invention can intelligently, automatically, and comprehensively monitor events where people approach the dangerous edge of the rooftop and issue timely alarms, effectively reducing the occurrence of jumps / accidental falls and greatly improving rooftop safety. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of a rooftop safety protection system based on edge computing, provided as an embodiment of the present invention. Detailed Implementation

[0042] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0043] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0044] Figure 1 This is a schematic diagram of a rooftop safety system based on edge computing, provided as an embodiment of the present invention. See also... Figure 1 The system includes:

[0045] Camera 1 is installed on the roof of the target building to collect real-time image information of the target roof.

[0046] Edge computing module 2, connected to camera 1, is used to identify whether there are people in the target rooftop image information and whether the identified target people have entered the pre-set danger zone;

[0047] Alarm module 3, connected to edge computing module 2, is used to issue an alarm when the edge computing module 2 identifies a target person entering a dangerous area from the target rooftop image information.

[0048] The beneficial effects of the above technical solution are as follows: The rooftop safety protection system based on edge computing provided by this embodiment of the invention first collects rooftop image information in real time through camera 1, and then identifies whether anyone has entered a pre-set danger zone in the rooftop image information through edge computing module 2. If so, an alarm is automatically triggered. This invention can intelligently, automatically, and comprehensively monitor events of people approaching the dangerous edge of the rooftop and issue timely alarms, effectively reducing the occurrence of jumping / accidental falls and greatly improving the safety of rooftops.

[0049] As an optional embodiment, the edge computing module 2 is also used to determine whether the target person is moving toward the preset danger edge side of the target rooftop;

[0050] The rooftop plane has a safe edge side for personnel to enter (i.e., the side leading to the rooftop staircase); the dangerous edge side is any other side of the rooftop plane that is not a safe edge side.

[0051] The edge computing-based rooftop security system also includes:

[0052] A controllable baffle control module, connected to the edge computing module 2, is used to control the controllable baffle on the dangerous edge side to rise when the edge computing module 2 determines that the target person is moving towards the dangerous edge side of the roof plane of the target building, so as to prevent the target person from falling from the dangerous edge side. The controllable baffle can be a vertical baffle set around the dangerous edge, and the vertical raising and lowering of the controllable baffle can be controlled.

[0053] The beneficial effects of the above technical solution are as follows: when a target person is identified as being in a dangerous area on the roof, the path of the target person is further used to determine whether the person is approaching the dangerous edge. If so, it is determined that the target person has a safety hazard of jumping / accidental fall, and the controllable baffle on the dangerous edge side is raised to effectively prevent the target person from falling from the dangerous edge side.

[0054] As an optional embodiment, the edge computing module 2 includes:

[0055] The personnel identification unit is used to identify whether there are personnel in the target rooftop image information;

[0056] A personnel positioning unit is used to locate the position information of the target personnel identified by the personnel identification unit within the rooftop plane.

[0057] The intrusion danger zone determination unit is used to determine whether the target person is in a pre-set danger zone based on the target person's location information on the roof plane;

[0058] The movement determination unit is used to determine the movement direction of the target person based on the position information of the target person located in the roof plane at each consecutive moment within a certain period of time by the personnel positioning unit, and to determine whether the target person is moving towards the danger edge.

[0059] The beneficial effects of the above technical solution are as follows: First, it identifies whether there are people on the rooftop. If so, it determines the location information of the people. Then, based on this location information, it determines whether the people are in the danger zone. Furthermore, if the people are in the danger zone, it determines whether they are moving towards the edge of the danger zone. If so, it determines that there is a safety hazard of jumping / accidental fall. The whole process has the advantage of accurate judgment. In addition, the whole process is progressive. If the result of one step is negative, it can be determined that there is no safety hazard of jumping / accidental fall, and subsequent steps do not need to be executed, thereby improving the execution efficiency of the system.

[0060] As an optional embodiment, the camera is specifically located on the safety edge side of the target rooftop and the camera direction is towards the entire rooftop, including the non-safety edge side.

[0061] The beneficial effects of the above technical solution are as follows: by setting the camera on the safe edge side of the roof, it is possible to collect image information from the non-safe edge side and the roof from all directions, which makes it easier to identify whether there is a safety hazard of jumping / accidental fall based on this image information.

[0062] As an optional embodiment, the location information of the target person on the roof plane is the coordinates of the target person in a preset two-dimensional rectangular coordinate system on the roof plane; wherein, the preset two-dimensional rectangular coordinate system takes the safe edge side of the roof plane as the bottom end, the left edge point of the bottom end as the origin of the coordinate system, the rightward direction from the bottom end as the X-axis, and the direction perpendicular to the X-axis from the origin as the Y-axis;

[0063] The intrusion danger zone determination unit includes:

[0064] The judgment value calculation subunit is used to calculate the judgment value of whether the target personnel have entered the danger zone according to the first formula;

[0065] The first judgment subunit is used to determine whether the judgment value of whether the target person has entered the danger zone is equal to 1. If yes, it is determined that the person has entered the danger zone; otherwise, it is determined that the person has not entered the danger zone.

[0066] The first formula is:

[0067]

[0068] In the first formula, W(t) represents the judgment value of whether the target personnel have entered the danger zone at the current moment. If W(t) = 1, it means that the target personnel have entered the danger zone on the edge side at the current moment; if W(t) = 0, it means that the target personnel have not entered the danger zone on the edge side at the current moment; [x(t), y(t)] represents the coordinates of the target personnel in the preset two-dimensional rectangular coordinate system at the current moment; X0 represents the length value of the safety edge side; Y0 represents the length value of the danger edge side perpendicular to the safety edge side; L represents the maximum vertical distance between the nearest edges in the danger zone; V[,,] represents the existence function. If one or more of the formulas in the parentheses are true, the overall function is true; ∧[] represents the entire function. The overall function is true when all the formulas in the parentheses are true, otherwise the overall function is not true.

[0069] The beneficial effects of the above technical solution are as follows: the location information of personnel is represented by two-dimensional coordinate values, which facilitates calculation and effectively improves the system execution efficiency. Using the first formula (1), the system determines whether the personnel have entered the danger zone on the edge of the danger zone based on the current coordinate position of the target personnel, thereby promptly knowing whether personnel have entered the danger zone, facilitating automatic monitoring in an unsupervised state, and better controlling and preventing the occurrence of danger.

[0070] As an optional embodiment, the movement determination unit includes:

[0071] The movement direction vector calculation subunit is used to calculate the movement direction vector of the target person on the target rooftop according to the second formula;

[0072] The control value calculation subunit is used to calculate the control value of the controllable baffle on the danger edge side according to the third formula;

[0073] The second judgment subunit is used to determine whether the control value of the controllable baffle on the dangerous edge side is equal to 1. If it is, it determines that the target person is moving towards the dangerous edge side.

[0074] The second formula is:

[0075]

[0076] In the second formula, [X(t), Y(t)] represents the movement direction vector of the target personnel on the rooftop of the target building over a period of time; 'a' represents an integer variable, taking values ​​of... [x(ta×T), y(ta×T)] represents the coordinates of the target person in the preset two-dimensional rectangular coordinate system at time ta×T; {x[t-(a-1)×T], y[t-(a-1)×T]} represents the coordinates of the target person in the preset two-dimensional rectangular coordinate system at time t-(a-1)×T; t0 represents the initial time when the target person is identified as appearing on the rooftop; T represents the calculation and detection period of the edge computing module; S(a) represents the distance the target person moves in the rooftop image information from time t-(a-1)×T to time ta×T; Indicates rounding down;

[0077] The third formula is:

[0078]

[0079] In the third formula, E(t) represents the control value of the controllable baffle on the danger edge side at the current moment; else represents the value of the controllable baffle except for the controllable baffle on the danger edge side. Know In all other cases, if E(t) = 1, indicating that the target person is currently moving towards the danger edge, an alarm is triggered, and the controllable baffles on each danger edge are opened and remain open until the staff closes them; if E(t) = 0, indicating that the target person is not currently moving towards the danger edge, no alarm is triggered, and no control is applied to the controllable baffles on each danger edge.

[0080] The beneficial effects of the above technical solution are as follows: by using the second formula (2) to detect the movement coordinates of the target personnel through the edge computing module, the comprehensive movement direction of the target personnel on the roof can be known, so that only personnel moving towards the dangerous edge will be subject to subsequent alarm and control measures, so as to avoid unnecessary control and save resources; then, by using the third formula (3) to determine whether the personnel are moving towards the dangerous edge side based on the comprehensive movement direction of the personnel on the roof, and to control the controllable baffles on each dangerous edge side, thereby using the baffles to assist in protection, providing rescue personnel and staff with some rescue time.

[0081] As an optional embodiment, the rooftop security system based on edge computing also includes: a mobile terminal carried by the management personnel;

[0082] The alarm module is specifically used to send alarm information to the mobile terminal when the edge computing module identifies a target person entering a dangerous area from the target rooftop image information; the alarm information includes at least: target rooftop identification information and target rooftop image information;

[0083] The mobile terminal is used to display the received alarm information.

[0084] The beneficial effects of the above technical solution are as follows: when it is discovered that people on the roof have entered the dangerous area, an alarm message can be sent to the mobile terminal carried by the management personnel, so that the management personnel can quickly understand the situation on the roof and take timely measures to prevent the occurrence of jumping incidents.

[0085] As can be seen from the above embodiments, adding an edge computing module to a camera can detect human movement, and an alarm will be triggered when someone approaches the edge of the roof. Furthermore, in the aforementioned rooftop plane, only the side leading to the rooftop staircase is considered a safe edge, while the other three sides are considered dangerous edges. A coordinate system is established for the rooftop plane, with the safe edge side as the bottom, the left edge of the bottom as the origin, the X-axis pointing right from the bottom, and the Y-axis pointing upwards from the origin on the left dangerous edge side. When a person is detected, their coordinates can be located. Based on the person's current coordinates, it can be determined whether the person has entered the dangerous area of ​​the dangerous edge side. If they have entered the dangerous area, the edge calculation module detects the person's movement coordinates to determine their direction of movement. Based on this direction, it can be determined whether the person is moving towards the dangerous edge side. If it is determined that the person is indeed moving towards the dangerous edge side, the alarm system is activated, and a controllable barrier facing the dangerous edge side is erected to provide auxiliary protection for the person, thereby ensuring their safety.

[0086] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A means for specifying the method in one or more boxes.

[0087] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The method specified in one or more boxes.

[0088] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the method specified in one or more boxes.

[0089] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations. The above descriptions are merely specific embodiments of this invention, but the scope of protection of this invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this invention should be included within the scope of protection of this invention. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A rooftop security system based on edge computing, characterized in that, include: The camera is installed on the roof of the target building to collect real-time images of the roof. An edge computing module, connected to the camera, is used to identify whether there are people in the target rooftop image information and whether the identified target people have entered a pre-set danger zone. The alarm module, connected to the edge computing module, is used to trigger an alarm when a target person identified by the edge computing module from the target rooftop image information enters a dangerous area. The edge computing module is also used to determine whether the target person is moving toward the preset danger edge side of the target rooftop; The system also includes: A controllable baffle control module, connected to the edge computing module, is used to control the controllable baffle on the dangerous edge side to rise when the edge computing module determines that the target person is moving towards the dangerous edge side of the roof plane of the target building, so as to prevent the target person from falling from the dangerous edge side; The edge computing module includes: The personnel identification unit is used to identify whether there are personnel in the target rooftop image information; A personnel positioning unit is used to locate the position information of the target personnel identified by the personnel identification unit within the rooftop plane. The intrusion danger zone determination unit is used to determine whether the target person is in a pre-set danger zone based on the target person's location information on the roof plane; The movement determination unit is used to determine the movement direction of the target person based on the position information of the target person located in the roof plane at each consecutive moment within a certain period of time by the personnel positioning unit, and to determine whether the target person is moving towards the danger edge. The movement determination unit includes: The movement direction vector calculation subunit is used to calculate the movement direction vector of the target person on the target rooftop according to the second formula; The control value calculation subunit is used to calculate the control value of the controllable baffle on the danger edge side according to the third formula; The second judgment subunit is used to determine whether the control value of the controllable baffle on the dangerous edge side is equal to 1. If it is, it determines that the target person is moving towards the dangerous edge side. The second formula is: In the second formula, [X(t),Y(t)] represents the movement direction vector of the target personnel on the rooftop of the target building over a period of time; 'a' represents an integer variable with a value of [x(ta×T),y(ta×T)] represents the coordinates of the target person in the preset two-dimensional rectangular coordinate system at time ta×T; {x[t-(a-1)×T],y[t-(a-1)×T]} represents the coordinates of the target person in the preset two-dimensional rectangular coordinate system at time t-(a-1)×T; t0 represents the initial time when the target person is identified to appear on the rooftop; T represents the calculation and detection period of the edge computing module; S(a) represents the distance the target person moves in the rooftop image information from time t-(a-1)×T to time ta×T; Indicates rounding down; The third formula is: In the third formula, E(t) represents the controllable baffle value on the danger edge side at the current moment; else represents the value of the controllable baffle value other than the controllable baffle value at the current moment. and All other cases.

2. The rooftop security system based on edge computing as described in claim 1, characterized in that, The rooftop plane has a safe edge side for personnel access; the dangerous edge side is any other side of the rooftop plane that is not a safe edge side.

3. The rooftop security system based on edge computing as described in claim 1, characterized in that, The camera is specifically installed on the safe edge side of the target building's roof, with the camera's shooting direction facing the entire roof, including the non-safe edge side.

4. The rooftop security system based on edge computing as described in claim 1, characterized in that, The location information of the target person on the roof plane is the coordinates of the target person in a preset two-dimensional rectangular coordinate system on the roof plane; wherein, the preset two-dimensional rectangular coordinate system takes the safe edge side of the roof plane as the bottom end, the left edge point of the bottom end as the origin of the coordinate system, the rightward direction of the bottom end as the X-axis, and the direction perpendicular to the X-axis from the origin as the Y-axis; The intrusion danger zone determination unit includes: The judgment value calculation subunit is used to calculate the judgment value of whether the target personnel have entered the danger zone according to the first formula; The first judgment subunit is used to determine whether the judgment value of whether the target person has entered the danger zone is equal to 1. If yes, it is determined that the person has entered the danger zone; otherwise, it is determined that the person has not entered the danger zone. The first formula is: In the first formula, W(t) represents the judgment value of whether the target personnel have entered the danger zone at the current moment; [x(t),y(t)] represents the coordinates of the target personnel in the preset two-dimensional rectangular coordinate system at the current moment; X0 represents the length value of the safe edge side; Y0 represents the length value of the danger edge side perpendicular to the safe edge side; L represents the maximum vertical distance between the nearest edges in the danger zone; ∨[,,] indicates the existence of a function, and the overall function is valid if one or more of the formulas in the parentheses are true; ∧[] indicates all functions, and the overall function is valid when all the formulas in the parentheses are true, otherwise the overall function is not true.

5. The rooftop security system based on edge computing as described in claim 1, characterized in that, The system also includes: a mobile terminal carried by the administrator; The alarm module is specifically used to send alarm information to the mobile terminal when the edge computing module identifies a target person entering a dangerous area from the target rooftop image information; the alarm information includes at least: target rooftop identification information and target rooftop image information; The mobile terminal is used to display the received alarm information.

Images