Method and system for selectively controlling multiple surveillance camera images
The system addresses operator fatigue in video security by using a video analysis server to identify events and a screening control server to manage high-resolution playback on a few screens, enhancing monitoring efficiency and reducing strain.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- KOREA ELECTRONICS TECH INST
- Filing Date
- 2025-06-30
- Publication Date
- 2026-07-02
AI Technical Summary
Existing video security systems cause operator fatigue due to the need to monitor large volumes of surveillance camera footage across multiple screens, and selective monitoring methods using grid-like playback screens still require significant attention, making detailed observation difficult.
A system and method for selective monitoring that uses a video analysis server to identify events and a screening control server to manage playback, allowing high-resolution display on a small number of screens by cycling through all feeds when no events are detected and focusing on event feeds when events occur.
Reduces operator fatigue by enabling efficient, detailed monitoring of surveillance camera footage through high-resolution playback on a few screens, improving monitoring efficiency and reducing operator strain.
Smart Images

Figure KR2025009180_02072026_PF_FP_ABST
Abstract
Description
Selective control method and system for multi-surveillance camera footage
[0001] The present invention relates to selective control of intelligent video security services.
[0002] In current video security services, the primary method used is to play back and allow operators to observe a large volume of surveillance camera footage across multiple screens. However, this method has the drawback of increasing operator fatigue.
[0003] To address these issues, recent intelligent video security services primarily utilize a selective monitoring method that identifies surveillance camera footage where an event (e.g., assault) occurred and displays it in a grid pattern across multiple screens.
[0004] While this existing selective monitoring method has the advantage of reducing operator fatigue by selectively monitoring only the footage where an event has been detected, compared to the method where operators simultaneously observe numerous surveillance camera feeds, it has the disadvantage that operator fatigue remains significant because monitoring is performed through small, grid-like playback screens, making it difficult for operators to observe the footage in detail at a glance.
[0005] Therefore, for more efficient selective monitoring than existing methods, a new method is needed to display surveillance camera footage where an event has been detected in high resolution using as few playback frames as possible.
[0006]
[0007] The present invention aims to provide a method and system for selective monitoring of multiple surveillance camera images, which enables selective monitoring through a small number of high-resolution playback screens in order to increase the monitoring efficiency of the controller and reduce the controller's fatigue.
[0008] The objectives of the present invention are not limited to those mentioned above, and other unmentioned objectives will be clearly understood by those skilled in the art from the description below.
[0009] A screening control system according to one embodiment of the present invention includes a video analysis server and a screening control server.
[0010] The above video analysis server includes a first memory and a first processor.
[0011] The first processor executes a computer-readable instruction stored in the first memory to collect surveillance camera images from a plurality of surveillance cameras, analyzes the surveillance camera images to generate an image analysis result, determines whether a new event has occurred and whether an existing event has ended based on the image analysis result, and generates an event message if a new event has occurred or an existing event has ended.
[0012] The above screening control server includes a second memory and a second processor.
[0013] The second processor executes a computer-readable command stored in the second memory to collect surveillance camera images from the surveillance camera, and upon receiving the event message from the image analysis server, updates an event list, which is a list of currently ongoing events, based on the event message, determines whether there is a currently ongoing event based on the event list, and if there is no currently ongoing event, sets the operation mode to a cyclical control mode, and if there is a currently ongoing event, sets the operation mode to an event control mode.
[0014] The above-mentioned cyclic control mode is a mode that cyclically plays back multiple surveillance camera videos, and the above-mentioned event control mode is a mode that plays back only the video in which an event occurred among the multiple surveillance camera videos.
[0015] In one embodiment of the present invention, the event control mode may be a mode that configures and outputs a control screen by dividing the screen by the number of video images in which an event occurs among a plurality of surveillance camera images.
[0016] In one embodiment of the present invention, the image analysis result may include the probability of occurrence of a target event.
[0017] In one embodiment of the present invention, the target event may include any one or a combination of collision, intrusion, assault, possession of a weapon, crowding, loitering, flooding, and fire.
[0018]
[0019] A screening control server according to one embodiment of the present invention plays surveillance camera images received from a plurality of surveillance cameras through a display device.
[0020] The above screening control server includes a memory for storing computer-readable commands; and a processor implemented to execute said commands.
[0021] The processor is configured to set the initial operation mode of the screening control server to a cyclical control mode by executing the above commands, and when an event message is received from the video analysis server, to update an event list, which is a list of currently ongoing events, based on the event message, determine whether there is a currently ongoing event based on the event list, and if there is a currently ongoing event, to set the screening control server to an event control mode.
[0022] The above-mentioned circular control mode is a mode that cyclically plays back multiple surveillance camera videos.
[0023] The above event control mode is a mode that plays only the video where an event occurred among multiple surveillance camera videos.
[0024] In one embodiment of the present invention, the cyclic control mode is a mode that cyclically plays a plurality of surveillance camera images through a single playback screen at a constant period.
[0025] In one embodiment of the present invention, the event control mode is a mode that configures a control screen by dividing the screen by the number of video images in which an event occurs among a plurality of surveillance camera images, and outputs the control screen through the display device.
[0026] In one embodiment of the present invention, the event message may be either a new event occurrence message or an event termination message.
[0027]
[0028] According to the present invention, there is an effect of improving the efficiency of selective control and reducing the fatigue of controllers performing selective control.
[0029] The effects obtainable from the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below.
[0030]
[0031] FIG. 1 is a diagram illustrating conventional screening and control technology.
[0032] FIG. 2 is a block diagram showing the configuration of a screening control system according to one embodiment of the present invention.
[0033] FIG. 3 is a flowchart illustrating a screening control method according to a first embodiment of the present invention.
[0034] FIG. 4 is a flowchart for explaining a screening control method according to a second embodiment of the present invention.
[0035] FIG. 5 is a block diagram showing the configuration of a computer system for performing a screening control method according to the present invention.
[0036] The present invention is for selective monitoring of intelligent video security services. The present invention enables selective monitoring through a small number of high-resolution playback screens, thereby allowing the operator to observe the video in greater detail and reducing the operator's fatigue.
[0037] In conventional selective monitoring methods, a grid-like display of surveillance camera footage where an event occurred was primarily used; however, the method and system proposed in this invention perform selective monitoring through a single playback screen as much as possible, and use a method of splitting the playback screen to play surveillance camera footage only when events occur simultaneously in multiple surveillance cameras.
[0038] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Meanwhile, the terms used in this specification are for describing the embodiments and are not intended to limit the present invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. The terms "comprises" and / or "comprising" as used in this specification do not exclude the presence or addition of one or more other components, steps, actions, and / or elements in addition to the mentioned components, steps, actions, and / or elements.
[0039] Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. These terms may be used for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component.
[0040] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. Conversely, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions describing the relationship between components, such as "between" and "exactly between," or "adjacent to" and "directly adjacent to," should be interpreted in the same way.
[0041] In describing the present invention, detailed descriptions of related prior art are omitted if it is determined that such detailed descriptions may unnecessarily obscure the essence of the invention.
[0042] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In order to facilitate overall understanding in describing the present invention, the same reference numerals will be used for the same means regardless of the drawing number.
[0043]
[0044] Figure 1 is a diagram illustrating conventional screening and control technology.
[0045] Figure 1 is an example of selecting surveillance camera footage where an event occurred and displaying the selected footage in a grid pattern through multiple screens. Conventional selective monitoring technology follows a method of performing video monitoring through small playback screens displayed in a grid pattern, which makes it difficult for the operator to observe the footage in detail at a glance and still has the problem of significant monitoring fatigue.
[0046] To overcome the problems of such conventional selective monitoring technology, the present invention proposes a method of performing selective monitoring through a small number of playback screens and playing surveillance camera footage by splitting the playback screens only when an event occurs simultaneously in multiple surveillance cameras.
[0047]
[0048] FIG. 2 is a block diagram showing the configuration of a screening control system according to one embodiment of the present invention.
[0049] Referring to FIG. 2, a screening control system (100) according to one embodiment of the present invention includes a surveillance camera (110), an image analysis server (120), and a screening control server (130). The screening control system (100) may further include a display device (140). The surveillance camera (110) may be composed of a plurality of cameras.
[0050] The screening control system (100) illustrated in FIG. 2 is according to one embodiment, and the components of the screening control system (100) according to the present invention are not limited to the embodiment illustrated in FIG. 2 and may be added, changed, or deleted as needed.
[0051]
[0052] The surveillance camera (110) generates multiple surveillance camera images and transmits them to the image analysis server (120) and the screening control server (130).
[0053]
[0054] The video analysis server (120) includes a first memory and a first processor. The first processor executes computer-readable commands stored in the first memory to collect a plurality of surveillance camera images from a surveillance camera (110) and analyzes the surveillance camera images to generate a video analysis result. The video analysis result may include whether a target event has occurred or the probability of the target event occurring. The target event may include any one or a combination of collision, intrusion, assault, possession of a weapon, crowd congestion, loitering, flooding, and fire.
[0055] The first processor determines whether a new event has occurred or whether an existing event has ended based on the image analysis results, and if a new event has occurred or an existing event has ended, generates an event message. The event message generated by the first processor is either a new event occurrence message or an event end message.
[0056]
[0057] The selection control server (130) is a computing device that selects surveillance camera images received from multiple surveillance cameras (110) according to a predetermined standard and plays them through a display device (140). The predetermined standard may be a period (timing) or whether an event occurs.
[0058] The screening control server (130) includes a second memory and a second processor. The second processor executes a computer-readable command stored in the second memory to collect multiple surveillance camera images from the surveillance camera (110).
[0059] When the operation of the screening control server (130) is initiated, the second processor sets the initial operation mode of the screening control server (130) to 'circulation control mode'.
[0060] In this specification, 'circular control mode' refers to a mode that circulates and plays back multiple surveillance camera videos, and 'event control mode' refers to a mode that plays back only the video in which an event occurred among the multiple surveillance camera videos.
[0061] Specifically, the cyclic control mode may be a mode that cyclically plays multiple surveillance camera videos through one (or a few) playback screens at a constant period.
[0062] Additionally, the above event control mode may be a mode that configures the control screen by dividing the screen by the number of video frames in which an event occurs among multiple surveillance camera images, and outputs the control screen through a display device (140).
[0063]
[0064] The operating mode of the selective control server (130) may vary depending on whether an event occurs based on the surveillance camera footage. That is, the selective control server (130) operates in a cyclical control mode when no event occurs, and operates in an event control mode when at least one event occurs.
[0065] The second processor can receive an event message from the video analysis server (120) through a communication device included in the screening control server (130). When the second processor receives an event message from the video analysis server (120), it updates an event list, which is a list of currently ongoing events, based on the event message.
[0066] The second processor determines whether there is a currently ongoing event based on the event list. If there is no currently ongoing event, the second processor sets the operation mode of the screening control server (130) to a cyclical control mode, and if there is a currently ongoing event, it sets the operation mode of the screening control server (130) to an event control mode.
[0067]
[0068] The display device (140) outputs surveillance camera images according to a screen configuration set by the screening control server (130). For example, the display device (140) may include any one of a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electro mechanical systems (MEMS) display, and an electronic paper display.
[0069]
[0070] Hereinafter, with reference to FIGS. 3 and FIGS. 4, the operation of the screening control system (100) will be explained in detail.
[0071] FIG. 3 is a flowchart illustrating a screening control method according to a first embodiment of the present invention. The screening control method of FIG. 3 can be performed by a screening control system (100).
[0072] Referring to FIG. 3, the screening control method according to the first embodiment of the present invention consists of steps S210 to S280. The screening control method illustrated in FIG. 3 is according to one embodiment, and the steps of the screening control method according to the present invention are not limited to the embodiment illustrated in FIG. 3 and may be added, changed, or deleted as necessary.
[0073]
[0074] S210 is the cyclic control stage.
[0075] When the operation of the screening control system (100) begins, the surveillance camera (110) transmits the surveillance camera images to the image analysis server (120) and the screening control server (130). There may be multiple surveillance cameras (110). In this embodiment, it is assumed that there are multiple surveillance cameras (110). The surveillance camera (110) transmits multiple surveillance camera images to the image analysis server (120) and the screening control server (130). The screening control server (130) starts cyclic monitoring using the surveillance camera images received from the surveillance camera (110).
[0076] In this specification, 'circular control' refers to a method or operation mode of playing back multiple surveillance camera images in a cyclic manner at a constant period. The selective control server (130) according to the present invention controls the output of the display device (140) in a manner that plays back multiple surveillance camera images in a cyclic manner through a single playback screen in a circular control mode.
[0077] The screening control server (130) continuously performs cyclic monitoring when there is no video in which an event occurred among the multiple surveillance camera videos.
[0078]
[0079] Step S220 is the input waiting step.
[0080] The selective control server (130) waits for input from the video analysis server (120) or the user of the selective control server (130). The types of input received by the selective control server (130) are classified into 'new event occurrence', 'event termination', and 'selective control termination'.
[0081] Among these, 'new event occurrence' and 'event termination' are event messages indicating the occurrence or termination of an event, and are messages generated by the video analysis server (120). And, 'selective monitoring termination' is a command entered by the user of the selective monitoring server (130).
[0082]
[0083] Steps S230 to S240 represent the processing steps of the screening control system (100) when the input of step S220 is 'new event occurrence'.
[0084]
[0085] Step S230 is the screen splitting step.
[0086] When the screening control server (130) receives an event message of ‘new event occurrence’ from the video analysis server (120), it performs screen splitting.
[0087] The video analysis server (120) analyzes the surveillance camera video provided by the surveillance camera (110) to determine whether a specific target event has occurred or the probability of such event occurring, and if it determines that a new event that did not exist before has occurred, it sends a 'new event occurrence' message to the selection control server (130). Examples of the above target events may include collision, intrusion, assault, possession of a weapon, crowd density, loitering, flooding, fire, etc.
[0088]
[0089] Specifically, the selective control server (130) calculates the number of ongoing events and surveillance camera images ('event images') corresponding to the ongoing events in multiple surveillance camera images based on the current time. The selective control server (130) performs N screen divisions when N events have occurred or are continuing in multiple surveillance camera images based on the current time and each event corresponds one-to-one with a surveillance camera image. For example, the selective control server (130) divides the screen into 3 when there are 3 ongoing events and 3 corresponding surveillance camera images based on the current time.
[0090]
[0091] Step S240 is the event video playback step.
[0092] The screening control server (130) plays a surveillance camera video corresponding to the event, i.e., an event video, through a display device (140).
[0093] The screening control server (130) plays the event video through the display device (140) based on the screen divided according to step S230.
[0094]
[0095] And, while step S240 is in progress, the selection control server (130) returns to step S220 and waits for input. That is, step S240 can proceed as is, simultaneously with other steps, unless there is a separate adjustment (e.g., switching to circular control, changing the number of screen splits).
[0096]
[0097] Steps S250 through S270 represent the processing steps of the screening control system (100) when the input of step S220 is 'event termination'.
[0098]
[0099] Step S250 is the screen integration step.
[0100] When the screening control server (130) receives an event message of ‘event termination’ from the video analysis server (120), it performs screen integration.
[0101] The 'Event Ended' message means that at least one of the previously occurring or ongoing events has ended as of the current point in time.
[0102] The video analysis server (120) analyzes the surveillance camera video provided by the surveillance camera (110) to determine whether a predetermined target event has occurred or the probability of such event occurring, and if it is determined that an event that has previously occurred or has been ongoing is not currently occurring, it sends an 'event termination' message to the selection control server (130).
[0103] It is assumed that there is a one-to-one correspondence between the event and the surveillance camera footage, and that N events have previously occurred or continued. In this case, if the event termination message transmitted by the video analysis server (120) is a message notifying that one event has ended, the screening control server (130) performs screen integration into N-1. That is, an adjustment is made to reduce the number of screen divisions by one.
[0104] However, the selective control server (130) performs circular control (S210) without performing screen integration when N-1 is 0, that is, when there are no currently occurring or ongoing events due to the end of the event (see step S260).
[0105]
[0106] Step S260 is the step for determining whether an event exists.
[0107] The screening control server (130) determines whether there are any ongoing events. If there is one or more ongoing events, step S270 is performed, and if there are zero ongoing events, step S210 (circular control step) is performed because there are no ongoing events.
[0108]
[0109] Step S270 is the event video playback step.
[0110] Since there is an ongoing event, the screening control server (130) adjusts the number of screen divisions and plays the event video through the display device (140) based on the integrated screen. When step S270 is finished, it returns to step S220 (input waiting step). Step S270 can proceed as is, simultaneously with other steps, unless there is a separate adjustment (e.g., switching to cyclic control, changing the number of screen divisions).
[0111]
[0112] Step S280 is the termination step.
[0113] In step S220, when the user inputs 'selection control termination' to the selection control server (130), that is, when the user commands the selection control server (130) to terminate selection control, the operation of the selection control system (100) is terminated.
[0114]
[0115] FIG. 4 is a flowchart illustrating a screening control method according to a second embodiment of the present invention.
[0116] The second embodiment of FIG. 4 specifically describes the operation of the image analysis server (120) and the screening control server (130) based on the first embodiment of FIG. 3. The second embodiment has the same basic technical concept as the first embodiment. Therefore, the matters described in the second embodiment can be applied to the first embodiment, and the matters described in the first embodiment can be applied to the second embodiment.
[0117] Referring to FIG. 4, the screening control method according to the second embodiment of the present invention consists of steps S310 to S450. The screening control method illustrated in FIG. 4 is according to one embodiment, and the steps of the screening control method according to the present invention are not limited to the embodiment illustrated in FIG. 4 and may be added, changed, or deleted as necessary.
[0118] Furthermore, in this specification, steps S310 to S330 may be referred to as a "method of operation of a video analysis server," and steps S410 to S450 and step S330 may be referred to as a "method of operation of a screening control server." Accordingly, the screening control method according to the present invention includes a method of operation of a video analysis server and a method of operation of a screening control server.
[0119] Hereinafter, with reference to FIG. 4, a screening control method according to a second embodiment of the present invention will be described.
[0120] First, the operation method of the video analysis server (S310 to S330) will be explained.
[0121] Step S310 is the video analysis step.
[0122] The video analysis server (120) collects surveillance camera images from the surveillance camera (110) and analyzes the surveillance camera images to generate a video analysis result. The surveillance camera images may consist of multiple images.
[0123] The video analysis server (120) analyzes surveillance camera footage to determine whether a pre-set analysis target event (hereinafter 'target event') has occurred (type of event that has occurred) or calculates the probability of the target event occurring. The video analysis result includes the type of event, information on the probability of event occurrence (probability of occurrence by event type), or whether the event has occurred. The target event may include any one or a combination of collision, intrusion, assault, possession of a weapon, crowd density, loitering, flooding, and fire.
[0124] In step S310, the artificial intelligence-based video analysis techniques that the video analysis server (120) can use to determine whether or not each target event occurs or the probability of occurrence are examples of those in Table 1. Examples of artificial intelligence models that the video analysis server (120) can use to analyze surveillance camera footage include a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and a Transformer.
[0125] Supplementary Explanation of Event AI-based Video Analysis Techniques Collision Object Detection / Recognition, Object Tracking, Motion Recognition Detects and tracks objects such as vehicles and people to determine their position, speed, and direction at the moment of collision. Determines whether a collision has occurred or the probability of a collision by assessing movement and deformation of the object's shape during the collision. Intrusion Object Detection / Recognition, Facial Recognition Detects objects moving within a defined surveillance area or objects crossing the boundary between a surveillance area and a non-surveillance area. Determines the probability of intrusion based on the detection results. Assault Object Detection / Recognition, Posture Estimation, Motion Recognition, Facial Expression Analysis Determines whether the detected object is a person. If it is a person, analyzes posture or movements of arms or legs to determine whether a violent act has occurred, whether the individual is a perpetrator or victim, or the probability. Adjusts the probability of occurrence by analyzing the facial expressions of the perpetrator or victim. Weapon-carrying Object Detection / Recognition, Image Classification, Posture Estimation, Motion Recognition Detects and classifies weapons such as knives, guns, steel pipes, and baseball bats. Specifically, the type of weapon is identified by analyzing its shape, size, color, etc. It is determined whether the object connected to the weapon is a person. The probability of weapon possession is determined by multiplying the probability that the detected object is a weapon by the probability that the connected object is a person. Risk is assessed by analyzing the posture and behavior of the person possessing the weapon. Crowd density object detection / recognition, object tracking, behavioral pattern analysis, motion recognition, area estimation, and density analysis determine whether an object within the video is a person. The area of the captured region is estimated based on the object within the video. The number of people within the video is calculated, and density is calculated by dividing the calculated number of people by the estimated area. Congestion is estimated by analyzing the movement of people included in the video based on behavioral pattern analysis or motion recognition, and risk is predicted based on density, behavioral patterns, and motion recognition results. The probability of crowd density is determined based on the probability that the object within the video is a person and the probability distribution of the captured region area.Loitering Object Detection / Recognition, Object Tracking, Behavioral Pattern Analysis, Motion Recognition: Detects individuals who stay in a specific area for longer than a threshold time or engage in repetitive behaviors. Calculates the probability that the detected person is a suspicious individual based on the detection results and the frequency of interactions with other people over a predetermined period. Flooded Object Detection / Recognition, Object Tracking, Image Classification, Area Analysis, Area Estimation: Determines whether the detected object is water. If the detected object is water, analyzes the flooded area through area analysis. Distinguishes water from other objects based on color and texture. Estimates the area of the region captured in the image based on objects within the image. Estimates the flooded area by comparing the estimated image area with the flooded area. Generates and analyzes time-series data representing changes in the flooded area over time. Calculates the probability of flooding occurrence based on the analysis of the flooded area or time-series data. Fire Thermal Imaging Camera Image Analysis, Object Detection / Recognition, Image Classification: Analyzes temperature changes based on thermal imaging camera images. Determines whether the detected object is smoke or flames. Determining whether a fire has occurred or the probability of its occurrence by analyzing the color, shape, and movement of the flames.
[0126]
[0127] Step S320 is the step for determining whether an event has occurred or ended.
[0128] The video analysis server (120) determines whether a new event that did not previously exist has occurred and whether an existing event has ended based on the video analysis results generated in step S310. That is, the video analysis server (120) determines whether a new event has occurred and whether an existing event has ended based on the video analysis results. If a new event occurs, the video analysis server (120) assigns a predetermined identifier (event identifier) to the event.
[0129] If the video analysis server (120) determines that a new event has occurred or that an existing event has ended, it proceeds to step S330, and otherwise, it performs step S310.
[0130] Step S330 is the event message transmission step.
[0131] The video analysis server (120) generates an event message based on surveillance camera footage and video analysis results and transmits it to the selective control server (130). When a new event occurs, the video analysis server (120) generates a 'new event occurred' message and transmits it to the selective control server (130). Additionally, when an existing event ends, the video analysis server (120) generates an 'event ended' message and transmits it to the selective control server (130).
[0132] A new event occurrence message includes an event identifier of the new event and an identifier of the surveillance camera image corresponding to the new event. Additionally, an event termination message includes an event identifier assigned to the existing event being terminated and an identifier of the surveillance camera image corresponding to the existing event.
[0133]
[0134] Next, the operation method (S410 to S450) of the screening control server (130) is described.
[0135] Step S410 is the cyclic control step.
[0136] When the selective control server (130) has started operation, or when it is determined at step S440 that there are no currently ongoing events, the selective control server (130) is set to a rotational control mode. That is, the initial operation mode of the selective control server (130) is 'rotational control mode', and the selective control server (130) continues to operate in rotational control mode when there are no currently ongoing events.
[0137] For reference, the selective control server (130) performs cyclic control or event control based on the surveillance camera footage received from the surveillance camera (110).
[0138] In this specification, 'circular control' or 'circular control mode' refers to a method or operation mode for playing back multiple surveillance camera images in a cyclic manner at a constant period. The selective control server (130) according to the present invention controls the output of the display device (140) in a manner that plays back multiple surveillance camera images in a cyclic manner through a single playback screen in the circular control mode. The selective control server (130) maintains the circular control mode until it is switched to the event control mode.
[0139]
[0140] Step S420 is the message reception waiting step.
[0141] The screening control server (130) monitors whether an event message is received from the video analysis server (120). If an event message is received from the video analysis server (120), the screening control server (130) performs step S430.
[0142]
[0143] Step S430 is the step for updating the event list.
[0144] As described above, the event message is either a new event occurrence message or an event termination message. The selective control server (130) updates the event list based on the event message. For example, in a situation where there is no event in the event list, if the event message received by the selective control server (130) from the video analysis server (120) is a new event occurrence message and there is only one event identifier included in the new event occurrence message, the selective control server (130) updates the event list by recording the event identifier and the corresponding surveillance camera image identifier in the event list. In addition, as another example, in a situation where there is an event in the event list, if the event message received by the selective control server (130) from the video analysis server (120) is an event termination message and there is only one event identifier included in the event termination message, the selective control server (130) updates the event list by deleting the identifier of the terminated event and the corresponding surveillance camera image identifier from the event list.
[0145]
[0146] Step S440 is the step for determining whether an event exists.
[0147] The selective control server (130) determines whether there is an event currently in progress based on the event list. The selective control server (130) performs step S410 (circular control) if there is no event in the event list, and performs step S450 if there is an event.
[0148]
[0149] The S450 stage is the event control stage.
[0150] If it is determined at step S440 that there is an ongoing event, the selective control server (130) enters the event control mode. Specifically, the selective control server (130) maintains the existing event control mode or switches from the existing cyclical control mode to the event control mode. In the event control mode, the selective control server (130) performs event control by outputting only the video corresponding to the ongoing event among the surveillance camera videos received from the surveillance camera (110) through the display device (140).
[0151] In this specification, 'event control' or 'event control mode' refers to a method or operation mode for playing only the video in which an event has occurred among multiple surveillance camera videos. The selective control server (130) according to the present invention configures a control screen by dividing the screen by the number of surveillance camera videos in which an event has occurred in the event control mode, and outputs the configured control screen through a display device (140). The selective control server (130) maintains the event control mode until there are no ongoing events.
[0152] For example, the selective control server (130) adjusts the control screen configuration based on event messages. For example, when the selective control server (130) receives a message indicating a new event has occurred, it divides the screen, and when it receives a message indicating an event has ended, it integrates the screen.
[0153] As another example, the selective control server (130) can determine the configuration of the control screen based on the event list. That is, the selective control server (130) calculates the number of surveillance camera images to be output through the display device (140) based on the identifier of the surveillance camera image corresponding to one or more events included in the event list, and adjusts the configuration of the control screen by dividing the screen by the number of images calculated. For example, if there are 3 events included in the event list and 3 surveillance camera images corresponding to them, the selective control server (130) configures the control screen divided into 3 areas and controls the display device (140) to display each of the 3 surveillance camera images in the divided areas.
[0154] After step S450, the screening control server (130) returns to step S420 (waiting for message reception). However, the screening control server (130) maintains the event monitoring mode until all events are terminated and it switches to the cyclic monitoring mode.
[0155]
[0156] The screening control method according to the present invention has been described with reference to the flowcharts shown in FIGS. 3 and 4. For simplicity of explanation, the method has been illustrated and described in a series of blocks; however, the present invention is not limited to the order of said blocks, and some blocks may occur in a different order or simultaneously with other blocks as illustrated and described herein, and various other branches, flow paths, and sequences of blocks that achieve the same or similar results may be implemented. Furthermore, not all illustrated blocks may be required for the implementation of the method described herein.
[0157]
[0158] Meanwhile, in the description with reference to FIGS. 3 and 4, each step may be further divided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Also, some steps may be omitted as necessary, and the order between steps may be changed. Furthermore, even if other omitted details are included, the contents of FIG. 2 or FIG. 5 may be applied to the contents of FIG. 3 and 4. Also, the contents of FIG. 3 and 4 may be applied to the contents of FIG. 2 or FIG. 5.
[0159]
[0160] FIG. 5 is a block diagram showing the configuration of a computer system for performing a screening control method according to the present invention. A screening control system (100) or a component included in the screening control system (100) according to one embodiment of the present invention (e.g., image analysis server (120), screening control server (130)) may be implemented in a form such as the computer system (1000) of FIG. 5.
[0161] Referring to FIG. 5, a computer system (1000) may include at least one of a processor (1010), memory (1030), an input interface device (1050), an output interface device (1060), and a storage device (1040) that communicate via a bus (1070). The computer system (1000) may also further include a communication device (1020) coupled to a network. The processor (1010) may be a central processing unit (CPU) or a semiconductor device that executes computer-readable instructions stored in memory (1030) or storage device (1040). Memory (1030) and storage device (1040) may include various forms of volatile or non-volatile storage media. For example, memory (1030) may include read-only memory (ROM) and random access memory (RAM). In the embodiment of the present description, the memory (1030) may be located inside or outside the processor (1010), and the memory (1030) may be connected to the processor (1010) through various known means. The memory (1030) is a volatile or non-volatile storage medium of various forms, and for example, the memory (1030) may include read-only memory (ROM) or random access memory (RAM).
[0162] Accordingly, embodiments of the present invention may be implemented as a method implemented on a computer or as a non-transient computer-readable medium in which computer-executable instructions are stored. In one embodiment, when executed by a processor (1010), the computer-readable instructions may perform a method according to at least one aspect of the present description.
[0163] The communication device (1020) can transmit or receive wired or wireless signals.
[0164] In addition, the screening control method according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computer means and may be recorded on a computer-readable medium.
[0165] The above computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the computer-readable medium may be specially designed and configured for embodiments of the present invention, or they may be known and available to a person skilled in the art of computer software. The computer-readable recording medium may include a hardware device configured to store and execute program instructions. For example, the computer-readable recording medium may be magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; ROM; RAM; flash memory, etc. The program instructions may include not only machine code, such as that generated by a compiler, but also high-level language code that can be executed by a computer through an interpreter, etc.
[0166] The processor (1010) can perform the selection control method according to the present invention by executing computer-readable commands stored in memory (1030) or storage device (1040).
[0167]
[0168] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims.
[0169]
[0170] [Explanation of the symbol]
[0171] 100: Selective Control System
[0172] 110: Surveillance camera
[0173] 120: Video Analysis Server
[0174] 130: Screening Control Server
[0175] 140: Display device
[0176] 1000: Computer System
[0177] 1010: Processor
[0178] 1020: Communication device
[0179] 1030: Memory
[0180] 1040: Storage device
[0181] 1050: Input interface device
[0182] 1060: Output interface device
[0183] 1070: Bus
Claims
1. A video analysis server comprising a first memory and a first processor, wherein the first processor executes a computer-readable command stored in the first memory to collect surveillance camera images from a plurality of surveillance cameras, analyzes the surveillance camera images to generate a video analysis result, determines whether a new event has occurred and whether an existing event has ended based on the video analysis result, and generates an event message if a new event has occurred or an existing event has ended; and A screening control server comprising a second memory and a second processor, wherein the second processor executes computer-readable commands stored in the second memory to collect surveillance camera images from the surveillance camera, and upon receiving the event message from the image analysis server, updates an event list, which is a list of currently ongoing events, based on the event message, determines whether there is a currently ongoing event based on the event list, and if there is no currently ongoing event, sets the operation mode to a cyclical control mode, and if there is a currently ongoing event, sets the operation mode to an event control mode. The above-mentioned cyclic control mode is a mode that cyclically plays back multiple surveillance camera images, and The above event control mode is a mode that plays only the video where an event occurred among multiple surveillance camera videos. Person selection control system.
2. In paragraph 1, the event control mode is, A mode that configures and outputs a control screen by dividing the screen according to the number of video feeds where an event occurred among multiple surveillance camera feeds. Person selection control system.
3. In paragraph 1, the image analysis result is, Including the probability of occurrence of the target event Person selection control system.
4. In Paragraph 3, the above-mentioned target event is, Includes any one or a combination of collision, intrusion, assault, possession of a weapon, crowding, loitering, flooding, and fire. Person selection control system.
5. In a selective control server that plays surveillance camera images received from multiple surveillance cameras through a display device, Memory for storing computer-readable instructions; and It includes a processor implemented to execute the above commands, and The above processor, by executing the above instructions, Set the initial operation mode of the above screening control server to cyclic control mode, and When an event message is received from the video analysis server, the event list, which is a list of currently ongoing events, is updated based on the event message, and Based on the above event list, determine whether there is a currently ongoing event, and If there is a currently ongoing event, the above screening control server is configured to be set to event control mode, and The above-mentioned cyclic control mode is, It is a mode that cycles through multiple surveillance camera videos, and The above event control mode is, A mode that plays only the video where an event occurred among multiple surveillance camera footage. Person selection control server.
6. In paragraph 5, the above-mentioned cyclic control mode is, A mode that cycles through multiple surveillance camera videos on a single playback screen at a regular interval. Person selection control server.
7. In paragraph 5, the above event control mode is, A mode for configuring a control screen by dividing the screen according to the number of video feeds in which an event occurs among multiple surveillance camera feeds, and outputting the control screen through the display device. Person selection control server.
8. In paragraph 5, the above event message is, Either the new event occurrence message or the event end message Person selection control server.