KR20230142171A - Method and apparatus for cctv screening surveillance based on metaverse - Google Patents

Abstract

The metaverse-based CCTV screening and control method according to an embodiment of the present invention includes the steps of mapping the area that can be monitored by each CCTV in the form of a polygon on the metaverse space, analyzing past crime data to determine the crime time, It includes obtaining location, coordinates, and circumstances, and setting priorities of the CCTV based on analysis results of surveillance video and past crime data obtained from the CCTV.

Description

Metaverse-based CCTV screening control method and device {METHOD AND APPARATUS FOR CCTV SCREENING SURVEILLANCE BASED ON METAVERSE}

The present invention relates to image recognition-based physical security technology.

Specifically, the present invention relates to technology for predicting crime risk by detecting objects in images such as CCTV and recognizing the properties of the objects.

In smart cities, the goal is to provide various application services, including security services such as crime prevention and disaster prevention, by establishing CCTV as an urban infrastructure. Although the pace of development of intelligent CCTV is rapid, operator intervention is also frequent, requiring a large investment of human and material resources to safely control the entire city.

Therefore, a CCTV screening control system is needed that accurately recommends CCTVs that need to be controlled with increased priority to users monitoring video through CCTV. If a priority is recommended after an incident occurs on the CCTV to be screened or after the incident is recognized, post-processing such as dispatching the police or 119 is possible, but it incurs a large cost to recover the damage.

Therefore, a method is needed to prevent crime in advance, which is one of the purposes of CCTV. To achieve this, it is necessary to select CCTV with a high risk of an incident occurring, and this can be presented statistically through past crime history. However, current crime statistics are compiled on a per-dong basis, so there are limitations in singling out a single CCTV.

Domestic Registered Patent Publication No. 10-2024149 (Title of invention: Intelligent smart screening control system)

The purpose of the present invention is to provide a technology that can determine whether a crime will occur based on images obtained through CCTV.

Additionally, the purpose of the present invention is to provide a technology that can define the video surveillance area of CCTV and map it to spatiotemporal information of past crimes.

In addition, the purpose of the present invention is to provide a technology for recommending CCTV that should be prioritized and a method for calculating weights for selective control.

The metaverse-based CCTV screening and control method according to an embodiment of the present invention to achieve the above purpose includes mapping the area that can be monitored by each CCTV in the form of a polygon on the metaverse space, including past crimes. It includes analyzing data to obtain crime time, location, coordinates, and circumstances, and setting priorities for the CCTV based on analysis results of surveillance video and past crime data obtained from the CCTV.

At this time, the mapping step may map buildings and roads in the video obtained from the CCTV onto the metaverse space.

At this time, the analysis result of the past crime data may include Born-to-Attributes and Belong-to-Attributes information of the object based on contextual data composed of natural language.

At this time, in the step of setting the priority of the CCTV, if the properties in the image obtained from the first CCTV include the properties in the analysis result of the past crime data, the priority of the first CCTV can be set high.

At this time, the step of setting the priority of the CCTV includes performing re-recognition on the surveillance video obtained from the CCTV, calculating the moving direction of the object in the surveillance video, and based on the moving direction of the object It may include a step of adjusting the priority of CCTV.

In addition, the metaverse-based CCTV screening and control device according to an embodiment of the present invention for achieving the above object includes a memory in which at least one program is recorded, and a processor that executes the program, and the program Mapping the area that can be monitored by CCTV in the form of a polygon on the metaverse space, analyzing past crime data to obtain crime time, location, coordinates, and circumstances, and monitoring obtained from the CCTV It includes commands for performing the step of setting the priority of the CCTV based on analysis results of video and past crime data.

At this time, the mapping step may map buildings and roads in the video obtained from the CCTV onto the metaverse space.

At this time, the analysis result of the past crime data may include Born-to-Attributes and Belong-to-Attributes information of the object based on contextual data composed of natural language.

At this time, in the step of setting the priority of the CCTV, if the properties in the image obtained from the first CCTV include the properties in the analysis result of the past crime data, the priority of the first CCTV can be set high.

At this time, the step of setting the priority of the CCTV includes performing re-recognition on the surveillance video obtained from the CCTV, calculating the moving direction of the object in the surveillance video, and based on the moving direction of the object It may include a step of adjusting the priority of CCTV.

According to the present invention, it is possible to provide technology that can determine whether a crime will occur based on images obtained through CCTV.

In addition, the present invention can provide a technology that can define the video surveillance area of CCTV and map it to spatiotemporal information of past crimes.

In addition, the present invention can provide a technology for recommending CCTV that should be prioritized and a method for calculating weights for selective control.

Figure 1 is a flowchart showing a metaverse-based CCTV screening and control method according to an embodiment of the present invention.
Figure 2 is a diagram showing an example of an environment where multiple CCTV cameras are installed and a space with a high risk of crime.
Figure 3 is a diagram conceptually showing a priority assignment method considering whether control is possible through a camera.
Figure 4 is a diagram conceptually showing a method of assigning priority through calculating the distance to a place where a past dangerous incident occurred.
Figure 5 is an example of a CCTV installation environment to illustrate the limitations of the prior art.
Figure 6 is a diagram illustrating a method of mapping CCTV surveillance areas to spatial coordinates.
Figure 7 is a diagram showing a method of configuring a metaverse to provide a space capable of video surveillance.
Figure 8 is a diagram conceptually showing an intelligent CCTV screening and control method based on the video surveillance metaverse space.
Figure 9 is a diagram showing a method of selectively controlling CCTV in the metaverse space based on the current situation recognized by AI CCTV.
Figure 10 is a diagram showing a CCTV screening and control method that provides the movement flow of people in the metaverse space in intelligent CCTV.
Figure 11 shows the configuration of a screening control device through the metaverse provision of intelligent CCTV and a crime risk prediction model.
Figure 12 is a diagram showing the configuration of a computer system according to an embodiment.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and will be implemented in various different forms. The present embodiments only serve to ensure that the disclosure of the present invention is complete and that common knowledge in the technical field to which the present invention pertains is not limited. It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

Although terms such as “first” or “second” are used to describe various components, these components are not limited by the above terms. The above terms may be used only to distinguish one component from another component. Accordingly, the first component mentioned below may also be the second component within the technical spirit of the present invention.

The terms used in this specification are for describing embodiments and are not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” or “comprising” implies that the mentioned component or step does not exclude the presence or addition of one or more other components or steps.

Unless otherwise defined, all terms used in this specification can be interpreted as meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. When describing with reference to the drawings, identical or corresponding components will be assigned the same reference numerals and redundant description thereof will be omitted. .

Figure 1 is a flowchart showing a metaverse-based CCTV screening and control method according to an embodiment of the present invention.

The metaverse-based CCTV selection and control method according to the embodiment can be performed in a metaverse-based CCTV selection and control device such as a computing device.

Referring to FIG. 1, the metaverse-based CCTV selection and control method according to an embodiment of the present invention maps the area that can be monitored by each CCTV in the form of a polygon on the metaverse space (S110).

At this time, the mapping step may map buildings and roads in the video obtained from the CCTV onto the metaverse space.

Next, past crime data is analyzed to obtain crime time, location, coordinates, and circumstances (S120).

At this time, the analysis results of past crime data may include Born-to-Attributes and Belong-to-Attributes information of the object based on contextual data composed of natural language.

Next, CCTV priorities are set based on the analysis results of surveillance video and past crime data obtained from CCTV (S130).

At this time, in the step of setting the priority of the CCTV, if the properties in the image obtained from the first CCTV include the properties in the analysis result of the past crime data, the priority of the first CCTV can be set high.

At this time, the step of setting the priority of the CCTV includes performing re-recognition on the surveillance video obtained from the CCTV, calculating the moving direction of the object in the surveillance video, and based on the moving direction of the object It may include a step of adjusting the priority of CCTV.

Figure 2 is a diagram showing an example of an environment where multiple CCTV cameras are installed and a space with a high risk of crime.

Referring to Figure 2, (a, b, c, d, e, f, g, h, i) represents the place where a crime occurred in the past, and (A, B, C, D) represents the place where CCTV was installed. indicates.

In places where crimes have occurred in the past, if the time, space, and environment are similar, there is a high probability that similar incidents will occur again. Therefore, if CCTV control installed based on past crime data is selectively performed in consideration of times and places with a high probability of crime occurring, limited human and material environments can be overcome.

Figure 3 is a diagram conceptually showing a priority assignment method considering whether control is possible through a camera.

Referring to FIG. 3, if many of the places of past crimes that occurred in the current time are included within a certain range from the installation location of the control CCTV, a method of increasing the priority of selective control can be applied. In the example of Figure 3, CCTVs B and C are selected first because they are adjacent to the two crimes in time and space.

Figure 4 is a diagram conceptually showing a method of assigning priority through calculating the distance to a place where a past dangerous event occurred.

Referring to Figure 4, CCTV D is close to four crimes (a, b, c, d) in time and space, so it is selected first.

Figure 5 is an example of a CCTV installation environment to illustrate the limitations of the prior art.

In the case of a camera capable of 360-degree observation, the selection target can be determined based on whether or not there is a crime within a certain range, as shown in Figure 3. In the case of cases where the control range of CCTV is uncertain or a crime outside the control range occurs, the distance as shown in Figure 4 You can judge priority.

However, considering the existing CCTV installation environment, in both cases, it may not be possible to control the crime scene through video surveillance from selected CCTV. For example, if you look in a specific direction from the location where the camera is installed, the opposite direction becomes a shaded area, making it impossible to control selected locations with similar time and space. Alternatively, if CCTV is installed to control other locations at certain times using the camera PTZ function, a problem may occur where the selected location cannot be detected.

Figure 6 is a diagram illustrating a method of mapping CCTV surveillance areas to spatial coordinates.

If the video surveillance area of each camera is aligned with the spatial coordinates (street name address, GPS location, etc.) provided as the location of a past crime, it becomes a polygon area on the map as shown in FIG. 6. Whether or not selective control is possible is determined based on whether the locations of similar events in time and space belong to each CCTV Polygon.

Looking at the example in Figure 6, the frequency of A:B:C:D=3:2:4:1 indicates whether video surveillance of similar events in time and space is possible. In the case of high frequency, it is judged that many similar risk events have occurred, so the priority of screening control is C, A, B, and D.

The CCTV Metaverse is provided by constructing meta information such as Point (latitude, longitude, possible.

Figure 7 is a diagram showing a method of configuring a metaverse to provide a space capable of video surveillance.

Referring to FIG. 7, when video is monitored by camera A, video A is viewed. In the video, each point in the area that can be recognized by humans or Vision AI technology is mapped to each location corresponding to the metaverse space. For example, if the landmark building seen in the video is in common in the metaverse space (including map information), the two locations are mapped. The lanes of the road are also mapped. The recognizable area from the vanishing point of the image is mapped into the metaverse space.

Figure 8 is a diagram conceptually showing an intelligent CCTV screening and control method based on the video surveillance metaverse space.

As shown in Figure 7, when a space where CCTV video surveillance is possible is provided through the metaverse, time, location, coordinates, and crime circumstances are provided as additional data to the metaverse using past crime data learned by Predictive Crime AI. AI CCTV also provides coordinates, attributes (Attributes, Actions, etc.) and re-recognition information of objects (people, cars, etc.) in the metaverse space through CCTV image recognition. Intelligent CCTV screening control presents spatiotemporal information on high-risk CCTV using data from the established metaverse. For example, in the case of C CCTV, theft incidents occur frequently, so the priority of selective control is raised at a certain time.

Figure 9 is a diagram showing a method of selectively controlling CCTV in the metaverse space based on the current situation recognized by AI CCTV.

In Figure 8, data provided additionally in the metaverse space may include context composed of natural language, such as past criminal history data, court rulings, investigation records, and case logs. For example, “a theft case in which a drunk adult man was sitting at a bus stop, dozing off with his backpack down, and an elderly man wandering around grabbed the backpack and left the property,” “an assault in which a man who was fighting took out a weapon,” Like “incident”, the object’s born-to-attributes include gender/age, the possessed attributes include backpack/weapon, and the object’s actions include drunkenness/wandering, etc. . This property is recognized by AI CCTV as the current video situation through video surveillance.

If the recognized result is similar to the above circumstances and time and space, the priority of screening control increases. For example, if attributes such as “weapon,” “backpack,” “drunk,” “adult male,” and “bus stop” are recognized in CCTV A, it is judged to be similar to past crimes i and c and is selected first as the risk increases. It becomes a controlled CCTV.

Figure 10 is a diagram showing a CCTV screening and control method that provides the movement flow of people in the metaverse space in intelligent CCTV.

Referring to Figure 10, AI CCTV performs re-recognition. If re-recognition is performed, the movement flow of objects can be determined at the location where CCTV is installed. For example, objects detected in CCTV B are often re-recognized in CCTV C, indicating that people frequently move from B to C. Using this, in the case of crimes that occur while moving, the movement path can be predicted and the weight can be reflected.

For example, in the case of incident h that occurred in B in the past, “a sexual crime in which a man followed a woman walking unsteadily and then took her by the shoulder,” it was controlled in B, but if a similar situation occurred on the current CCTV, it would move to C and put the woman by the shoulder. Considering the case where a person is taken, the priority of screening control can be increased by giving weight to CCTV C.

However, the attributes such as “man,” “woman,” “elderly,” and “child” described above are only examples to explain the present invention, and AI does not assume that people of a specific gender or age are criminals or victims. That is not the case.

Figure 11 shows the configuration of a screening control device through the metaverse provision of intelligent CCTV and a crime risk prediction model.

Referring to Figure 11, past crime history (Crime Events, 210) is used as learning data for a crime risk prediction model (Predictive Crime AI, 220) and is provided as spatiotemporal crime data in the metaverse.

CCTV 230 is distributed through VMS (Video Management System, 240), and a polygon, which is the CCTV video surveillance range, is created through projection mapping 250 between the streamed video and the metaverse space. Basic screening control (Screening CCTV, 280) is provided with this surveillance range and spatiotemporal information of the event. In addition, in the present invention, AI CCTV (260) recognizes and generates circumstances from the video, and Predictive Crime AI (220) ) dynamically assigns weights (Criminal Weights) to the selected control CCTV (280) from the received circumstances. In addition, the object properties and re-recognition information recognized by the AI CCTV 260 are provided as additional data to the metaverse 270 to give weights (spatio-temporal weights) reflecting adjacent CCTVs and movement flows. The given weight is reflected in past crime incidents, so users can check CCTVs with a high risk of crime and receive feedback. The user modifies the circumstances of the incident or modifies and confirms the crime risk predicted by Predictive Crime AI (220) and includes it in Crime Events (210).

Figure 12 is a diagram showing the configuration of a computer system according to an embodiment.

The metaverse-based CCTV screening and control device according to the embodiment may be implemented in a computer system 1000 such as a computer-readable recording medium.

Computer system 1000 may include one or more processors 1010, memory 1030, user interface input device 1040, user interface output device 1050, and storage 1060 that communicate with each other via bus 1020. You can. Additionally, the computer system 1000 may further include a network interface 1070 connected to the network 1080. The processor 1010 may be a central processing unit or a semiconductor device that executes programs or processing instructions stored in the memory 1030 or storage 1060. The memory 1030 and storage 1060 may be storage media including at least one of volatile media, non-volatile media, removable media, non-removable media, communication media, and information transfer media. For example, memory 1030 may include ROM 1031 or RAM 1032.

The metaverse-based CCTV screening and control device according to an embodiment of the present invention includes a memory 1030 in which at least one program is recorded, and a processor 1010 that executes the program, and the program is monitored by each CCTV. Mapping the possible area in the form of a polygon on the metaverse space, analyzing past crime data to obtain crime time, location, coordinates, and circumstances, and surveillance video and past footage obtained from the CCTV It includes commands for performing the step of setting the priority of the CCTV based on the analysis results of crime data.

At this time, the mapping step may map buildings and roads in the video obtained from the CCTV onto the metaverse space.

At this time, the analysis result of the past crime data may include Born-to-Attributes and Belong-to-Attributes information of the object based on contextual data composed of natural language.

At this time, in the step of setting the priority of the CCTV, if the properties in the image obtained from the first CCTV include the properties in the analysis result of the past crime data, the priority of the first CCTV can be set high.

At this time, the step of setting the priority of the CCTV includes performing re-recognition on the surveillance video obtained from the CCTV, calculating the moving direction of the object in the surveillance video, and based on the moving direction of the object It may include a step of adjusting the priority of CCTV.

The specific implementations described in the present invention are examples and are not intended to limit the scope of the present invention in any way. For the sake of brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connections or connection members of lines between components shown in the drawings exemplify functional connections and/or physical or circuit connections, and in actual devices, various functional connections or physical connections may be replaced or added. Can be represented as connections, or circuit connections. Additionally, if there is no specific mention such as “essential,” “important,” etc., it may not be a necessary component for the application of the present invention.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all scopes equivalent to or equivalently changed from the scope of the claims are within the scope of the spirit of the present invention. It will be said to belong to

1000: computer system 1010: processor
1020: Bus 1030: Memory
1031: Rom 1032: RAM
1040: User interface input device
1050: User interface output device
1060: Storage 1070: Network Interface
1080: Network

Claims (1)

Mapping the area that can be monitored by each CCTV in the form of a polygon on the metaverse space;
Analyzing past crime data to obtain crime time, location, coordinates, and circumstances; and
Setting priorities of the CCTV based on analysis results of surveillance video and past crime data obtained from the CCTV;
A metaverse-based CCTV screening and control method comprising:

Images