KR100685134B1 - Security method and system based on camera - Google Patents

Abstract

The camera-based monitoring method according to the present invention comprises the steps of: registering a background image photographed at the point of time when the cleanup is completed with no moving object as a reference image of the surveillance region; In order to detect only objects that are determined to be left in the area of the background image except objects that temporarily move in and out of the area of the background image, they are previously determined as a criterion for determining that the difference region between the current image frame and the background image is left. Registering the difference area as a danger area when the period of time continues; And alerting the danger zone.

According to the camera-based surveillance method and surveillance system of the present invention, when dangerous goods deliberately placed by someone in an airport or a major public facility where many people come and go for a certain period of time, the object is detected and alerted, and preventive measures are taken in advance. Can be taken.

Description

Camera-based surveillance method and system {Security method and system based on camera}

1 is a flowchart illustrating a camera-based monitoring method according to an embodiment of the present invention.

FIG. 2 is a flowchart for explaining a preferred embodiment of the step S108 shown in FIG.

3 is a flowchart for explaining a preferred embodiment of the step S208 shown in FIG.

4 is a flowchart for explaining another preferred embodiment of the step S108 shown in FIG.

FIG. 5 is a flowchart for explaining a preferred embodiment of step S408 shown in FIG. 4.

6 is a flowchart for explaining a camera-based monitoring method according to another embodiment of the present invention.

FIG. 7 is a flowchart for explaining a preferred embodiment of the step S104 shown in FIG.

8 is a monitoring system according to a preferred embodiment of the present invention.

9A to 9F are image frames photographing a surveillance area for explaining the monitoring method of the present invention.

The present invention relates to a surveillance method and system based on a camera.

In most security surveillance systems, much research has been done on the tracking or recognition of moving objects.

By first examining the difference from the next image based on the image obtained by the camera, a changed image can be obtained. At this time, if there is no changed image, it means that nothing moves. If there is a changed image, it means that there is a moving object. Such motion tracking has been applied to various theft security systems, as well as to various tracking and recognition technologies.

Most of the prior arts focus on extracting and recognizing moving objects while being seen in front of the screen. For example, when taking a picture, most tend to focus on a person or a specific object regardless of changes in the background. In other words, the technical center of security surveillance system research is following this tendency, so there is little research on the change of background.

In the existing security and safety surveillance system, a surveillance camera system was constructed for the purpose of access, theft, or monitoring the working environment. However, this has been expensive because there is always a problem that requires the deployment of people for monitoring. Recently, an automatic monitoring system using a motion tracking technique or a sensor has been used.

However, there are almost no surveillance systems that can detect explosives or industrial dangerous goods through cameras in places where human traffic is frequent. In particular, with the recent increase in the risk of terrorism in major public facilities, it is necessary to develop a surveillance system that can detect such dangerous goods.

The technical problem to be solved by the present invention is that the dangerous goods placed deliberately placed by someone in an airport, a major public facility, where many people come and go, are left on the production line or floor inside a factory in an industrial site. It is to provide a monitoring method and a monitoring system for detecting and alarming such an object when left for a predetermined time or more.

The camera-based monitoring method according to the present invention for achieving the above technical problem comprises the steps of: (a) registering a background image photographed at the time when the cleanup is completed with no moving object as a reference image of the surveillance region; (b) In order to detect only an object that is determined to be left in the area of the background image except for an object temporarily moving in and out of the area of the background image, the difference region between the current image frame and the background image is left unattended. Registering the difference area as a danger area if it continues for a preset period of time as a criterion for determining that it is determined to And (c) alerting the dangerous area.
Step (b) may include: (b1) capturing a current image frame; (b2) detecting a movement region in the current image frame by obtaining a deviation between a previous image frame and a current image frame; (b3) comparing the background image with the image excluding the movement area in the current image frame; (b4) if it is determined that there is no difference region as a result of the comparison, proceeding to step (b1); And (b5) if it is determined that there is a difference region, in order to detect only an object determined to be left in the area of the background image for more than a predetermined period, the difference region is defined only when the difference region is maintained for a predetermined frame period. And registering the dangerous area.
Step (b5) may include: (b51) registering the difference area as a preliminary dangerous area; (b52) determining whether the preliminary dangerous area has been repeated for the frame period corresponding to the preset period, and if not repeated during the frame period, proceeding to step (b1); And (b53) registering the preliminary dangerous zone as a dangerous zone when the preliminary dangerous zone is repeated during the frame period.
Step (b) may include: (b1) capturing a current image frame; (b6) detecting and storing a difference area between the current image frame and the background image; (b7) comparing the difference region between the current image frame and the stored background image and the difference region between the background image stored in the previous image frame; (b8) if there is no identical part as a result of the comparison, proceeding to step (b1); And (b9) if there is a same part as a result of the comparison, registering the same part as a dangerous area when the same part is maintained for a frame period corresponding to the preset period.
Step (b9) may include: (b91) registering the same portion as a preliminary dangerous area; (b92) determining whether the preliminary dangerous area has been repeated during the frame period, and proceeding to step (b1) if it has not been repeated during the frame period; And (b93) registering the preliminary dangerous zone as a dangerous zone when the preliminary dangerous zone is repeated during the frame period.
The step (c) may include: (c1) obtaining information on the danger zone by calculating the position and size of the danger zone; (c2) magnifying the dangerous area; And (c3) alerting the dangerous area information.
Surveillance system according to the present invention for achieving the above technical problem, a surveillance camera for taking an image; A controller connected to the surveillance camera by wire / wireless to store a background image photographed by the surveillance camera and having a computer executing the surveillance method of any one of claims 1 to 5; And an alarm unit configured to alert the registered dangerous area output from the controller.
The camera-based monitoring method may be recorded as a program on a computer-readable recording medium.

delete

delete

delete

delete

delete

delete

delete

delete

delete

Hereinafter, with reference to the accompanying drawings the configuration and operation of the camera-based monitoring method and monitoring system according to a preferred embodiment of the present invention will be described in detail as follows. Like reference numerals in the drawings denote components that perform the same function.

The basic concept of the present invention is to construct a monitoring system that helps to take appropriate measures by alerting a person in charge of an object that is different from the first background image of an area to be monitored for a predetermined time. .

8 is a surveillance system according to an exemplary embodiment of the present invention, which includes a surveillance camera 102 photographing a surveillance region 100 and a surveillance controller 106 connected to the surveillance camera 102 by wire / wireless 104. The monitor 108 is connected to the monitoring control unit 106. In addition, the monitoring system of the present invention may alert the monitored situation through the monitor 108, the speaker 110, or the mobile terminal 112 of the security personnel as needed.

1 is a flowchart illustrating a camera-based monitoring method according to an embodiment of the present invention.

Referring to FIG. 1, the camera-based monitoring method according to the present invention first registers a background image (S100).

The background image is an image frame that is captured and stored when the initial surveillance system is installed or when the cleanup is completed without moving objects in the surveillance area. It can be viewed based on the image acquired through the camera after the traffic check is completed and no human traffic is completed.

Such a background image is updated and registered when a surveillance area is changed or when the initial layout of the surveillance area is changed.

After the step S100, if the difference region between the current image frame and the background image continues for a predetermined period, the difference region is registered as a dangerous region (S102). In step S102, an object that was not initially present but left unattended in the monitoring area is detected.

In this case, the moving object is excluded from the detection object, although there is a difference from the background image due to a condition lasting for a predetermined period of time.

Industrial sites can detect objects that are left outside the product line or on the floor, objects that are outside of the product moving on the conveyor, and objects suspected of explosives in facilities such as airports.

The information on the registered dangerous area may be utilized as backup data for observing the trend of the surveillance area, and alarm data provided to the surveillance personnel.

FIG. 2 is a flowchart for explaining a preferred embodiment of the step S108 shown in FIG.

Referring to FIG. 2, in step S108, a current image frame is photographed (S200).

After operation S200, a movement region is detected in the current image frame (S202).

The motion region of the current image frame may be detected by a general motion detection technique for obtaining a deviation between the previous image frame and the current image frame.

After the step S202, the background image is compared with the image excluding the movement area in the current image frame (S204). In order to detect an object that has been left for a predetermined period or more, the movement area detected in the current image frame is excluded. And compare this with background image.

After step S204, it is determined that there is no difference region as a result of the comparison. If it is determined that there is no difference region as a result of the comparison, the process proceeds to step S200 (S206).

However, if it is determined that there is a difference area as a result of the comparison, if the difference area is maintained for a predetermined frame period, the difference area is registered as a dangerous area (S208).

The embodiment of FIG. 2 will be described using the captured image frames of FIGS. 9A to 9F.

9A is an initial background image at time T. FIG.

9B to 9D are image frames photographed at time T + 1 to time T + 3, respectively, in which only moving objects appear.

FIG. 9E is an image frame photographed at time T + 4, and has an image left by someone.

9F is an image frame photographed at a time T + 5, and is an image in which a bag which is left for a predetermined time and is an alarm target exists.

First, at time T + 1, a current image frame is photographed (S200), and motion is detected (S202). Compared to the background image T except for a bag of man-1, man-1 and man-2, which are moving regions in the current image frame T + 1 (S204), there is no difference (S206). .

Similarly to T + 2 in time T + 2 and T + 3, there is no difference compared to the background image (T) except for the bag of man-1 and man-1 and man-2, which are moving areas (S204). S206) Proceeds to step S200.

Referring to FIG. 9E, at time T + 4, a bag left by someone is next to the pot on the right side of the image. Photograph the current image frame (S200) and detect the movement (S202). Compared with the background image T except for the man-3 which is the movement region in the current image frame T + 4 (S204), the bag next to the right flowerpot is detected as the difference region.

Referring to FIG. 9F, the bag next to the right pollen is detected as a difference region when compared to the background image T except for the man-4 which is the movement region at time T + 5 (S204).

Bag regions repeatedly detected in FIGS. 9E and 9F are registered as dangerous areas.

3 is a flowchart for explaining a preferred embodiment of the step S208 shown in FIG.

Referring to FIG. 3, in step S208, a difference region between an image and a background image excluding a movement region in a current image frame is registered as a preliminary danger region (S300).

After step S300, it is determined whether the preliminary dangerous area is repeated for a predetermined frame period (S302). If it is determined that the preliminary danger area has not been repeated for a predetermined frame period, the process proceeds to step S200 to capture a new image frame.

If it is determined that the reserve danger zone is repeated for a predetermined frame period, the reserve danger zone is registered as a danger zone (S304).

4 is a flowchart for explaining another preferred embodiment of the step S108 shown in FIG.

Referring to FIG. 4, in step S108, a current image frame is captured (S400).

The difference region between the current image frame and the background image is detected and stored (S402).

After operation S402, the difference region between the current image frame and the stored background image is compared with the difference region between the background image stored in the previous image frame (S404).

If there is no identical part as a result of the comparison in step S404 (S406), all of the difference areas between the current image frame and the background image are determined as motion regions. In this case, the process proceeds to step S400 to shoot a new image frame.

If there is the same part as a result of the comparison in step S404 (S406), if the same part is maintained for a predetermined frame period, the same part is registered as the dangerous area (S408).

The embodiment of FIG. 4 will be described using the captured image frames of FIGS. 9A to 9F.

9A is an initial background image at time T. FIG.

First, at time T + 1, when the current image frame is photographed (S400) and the difference between the current image frame and the background image is detected, the bags of man-1 and man-1 and man-2 are detected and stored (S402).

At time T + 2, when the current image frame is photographed (S400) and a difference between the current image frame and the background image is detected, the bags of man-1 and man-1 and man-2 are detected and stored (S402). If you compare man-1 and man-1 stored in T + 1, man-2 and man-1 and man-1 stored in T + 2, man-2 (S404), they do not exist in the same area. It is determined (S406). Therefore, the process proceeds to step S400 to shoot a new image.

The same is true for T + 3 as for T + 2.

In T + 4, when the current image frame is photographed (S400) and a difference between the current image frame and the background image is detected, the bag next to man-3 and the flowerpot is detected and stored (S402). Comparing man-1, bag and man-2 stored in T + 3 with man-3 and bag stored in T + 4 (S404), it is determined that the bag exists in the same area (S406).

Referring to FIG. 9F, when the difference between the current image frame and the background image is detected at time T + 5, the man-4 and the bag next to the flowerpot are detected and stored (S402). Comparing this with the man-3 and the bag stored at T + 4 (S404), it is determined that the bag exists in the same area (S406).

The bag area repeatedly detected in FIGS. 9E and 9F is registered as a dangerous area (S408).

FIG. 5 is a flowchart for explaining a preferred embodiment of step S408 shown in FIG. 4.

Referring to FIG. 5, in step S408, the same part is registered as a preliminary dangerous area (S500).

It is determined whether the preliminary dangerous area is repeated for a predetermined frame period, and if it is not repeated for a predetermined frame period, the process proceeds to step S400 (S502).

If the spare danger zone is repeated for a predetermined frame period, the spare danger zone is registered as a danger zone (S504).

6 is a flowchart for describing a camera-based monitoring method according to another exemplary embodiment of the present invention, in which the step S104 is further included in the embodiment of FIG. 1.

Referring to FIG. 6, the background image is registered (S100), and if the difference region between the current image frame and the background image lasts for a predetermined period of time, the difference region is registered as a study region (S102). After step S102, the danger zone is alerted (S104).

FIG. 7 is a flowchart for explaining a preferred embodiment of the step S104 shown in FIG.

Referring to FIG. 7, in step S104, first, the location and size of the danger area are calculated to obtain information of the danger area (S700). The dangerous area is enlarged and photographed (S702). Then, the information of the acquired danger zone is alerted (S704).

Alarms may be displayed on the monitor of the monitoring system and notified, a voice message may be notified through the loudspeaker of the monitoring system, and a danger zone may transmit information to the portable terminal of the security officer.

8 is a surveillance system according to an exemplary embodiment of the present invention, which includes a surveillance camera 102 photographing a surveillance region 100 and a surveillance controller 106 connected to the surveillance camera 102 by wire / wireless 104. The monitor 108 is connected to the monitoring control unit 106.

The surveillance controller 106 stores the initial background image photographed by the surveillance camera 102, and if the difference between the current image frame and the background image photographed by the surveillance camera 102 lasts for a predetermined period of time, the difference is detected in the danger zone. Register with

In addition, the monitoring control unit 106 may alert the monitored situation through the monitor 108, the speaker 110, or the mobile terminal 112 of the security personnel.

The camera-based monitoring method according to the present invention can be embodied as computer readable codes on a computer readable recording medium. Computer-readable recording media include any type of recording device that stores programs or data that can be read by a computer system. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, hard disk, floppy disk, flash memory, optical data storage, and the like. Here, the program stored in the recording medium refers to a series of instruction instructions used directly or indirectly in an apparatus having an information processing capability such as a computer to obtain a specific result. In addition, the term computer is used to mean all devices having information processing capability for performing a specific function by a program having a memory, an input / output device, and an arithmetic device despite the fact that the name is actually used. Therefore, the computer includes a control system wired / wirelessly connected to the surveillance camera shown in FIG. 8, and a program stored as a program on a recording medium is read by the control system so that the monitoring method of the present invention can be implemented.

The best embodiments have been disclosed in the drawings and specification above. Although specific terms have been used herein, they are used only for the purpose of describing the present invention and are not used to limit the scope of the present invention as defined in the meaning or claims. Therefore, those skilled in the art will understand that various modifications and equivalent other embodiments are possible from this. Therefore, the true technical protection scope of the present invention will be defined by the technical spirit of the appended claims.

As described above, according to the camera-based surveillance method and surveillance system of the present invention, when dangerous goods placed by someone intentionally left in a public airport, a major public facility with a lot of people, such objects are detected and Alerts can be taken beforehand.

In addition, the present invention can be used as a system for warning the safety of workers by detecting such unattended objects in the industrial field, such as when the product is left in the factory for more than a certain time on the production line or the floor.

In addition, the present invention can be used as illegal parking detection system and garbage illegal dumping monitoring system.

The invention is not limited to the examples described above and represented in the drawings. Those skilled in the art taught by the above-described embodiments, many modifications to the above-described embodiments are possible by substitution, erasure, merging, etc. within the scope and object of the present invention described in the following claims.

Claims (10)

(a) registering a background image photographed at the point of time when the cleanup is completed with no moving object as a reference image of the surveillance region; (b) In order to detect only an object that is determined to be left in the area of the background image except for an object temporarily moving in and out of the area of the background image, the difference region between the current image frame and the background image is left unattended. Registering the difference area as a danger area if it continues for a preset period of time as a criterion for determining that it is determined to And and (c) alerting the dangerous area. The method of claim 1, wherein step (b) (b1) photographing a current image frame; (b2) detecting a movement region in the current image frame by obtaining a deviation between a previous image frame and a current image frame; (b3) comparing the background image with the image excluding the movement area in the current image frame; (b4) if it is determined that there is no difference region as a result of the comparison, proceeding to step (b1); And (b5) If it is determined that there is a difference region as a result of the comparison, the difference region is dangerous only when the difference region is maintained for a predetermined frame period in order to detect only an object that is determined to be left in the area of the background image for more than the preset period. Camera-based monitoring method comprising the step of registering as an area. The method of claim 2, wherein step (b5) (b51) registering the difference area as a preliminary dangerous area; (b52) determining whether the preliminary dangerous area has been repeated for the frame period corresponding to the preset period, and if not repeated during the frame period, proceeding to step (b1); And and (b53) registering the preliminary dangerous zone as a dangerous zone when the preliminary dangerous zone is repeated during the frame period. According to claim 1, wherein step (b), (b1) photographing a current image frame; (b6) detecting and storing a difference area between the current image frame and the background image; (b7) comparing the difference region between the current image frame and the stored background image and the difference region between the background image stored in the previous image frame; (b8) if there is no identical part as a result of the comparison, proceeding to step (b1); And (b9) a camera-based monitoring method comprising registering the same part as a dangerous area when the same part is maintained for a frame period corresponding to the preset period when there is a same part as a result of the comparison. Way. The method of claim 4, wherein step (b9) (b91) registering the same portion as a preliminary dangerous area; (b92) determining whether the preliminary dangerous area has been repeated during the frame period, and proceeding to step (b1) if it has not been repeated during the frame period; And (b93) registering the preliminary dangerous zone as a dangerous zone when the preliminary dangerous zone is repeated during the frame period. delete The method of claim 1, wherein step (c) (c1) obtaining information of the danger zone by calculating the position and size of the danger zone; (c2) magnifying the dangerous area; And and (c3) alerting the dangerous area information. A surveillance camera for capturing an image; A controller connected to the surveillance camera by wire / wireless to store a background image photographed by the surveillance camera and having a computer executing the surveillance method of any one of claims 1 to 5; And And a warning unit for alarming the registered dangerous area outputted from the control unit. delete A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 5 and 7.

Images