KR20120133645A - Security camera and Method of controlling thereof - Google Patents

Abstract

PURPOSE: A monitoring camera and a method for controlling an alarm through the target identification of the monitoring camera are provided to improve the accuracy of monitoring by identifying a target through the analysis of a moving target. CONSTITUTION: A camera unit derives an input image from light passing through an optical system. A moving target detecting unit(10) includes a comparison unit and a target detecting unit. The moving target detecting unit detects a moving target from the input image. A target identifying unit(20) identifies whether the moving target is a monitoring target or a disturbing target. If the target is the monitoring target, an alarm control unit(30) controls an alarm. [Reference numerals] (10) Moving target detecting unit; (11) Comparing unit; (12) Target detecting unit; (20) Target identifying unit; (21) Outline extracting unit; (23) First classifying unit; (30) Alarm control unit

Description

Alarm control method by identifying the surveillance camera and the target of the surveillance camera

One aspect of the present invention relates to an alarm control method through a surveillance camera and a target identification of the surveillance camera, and more particularly, a surveillance camera capable of identifying whether a movement target is a target or a disturbance target and its It relates to a control method.

Closed-circuit TV (hereinafter referred to as CCTV) surveillance system is to install at least one camera in the area to be monitored, to reproduce the video signal applied from the installed camera in real time, or to record the video signal to the recording medium The recorded video signal is reproduced and displayed on the display device. From this, the user can easily grasp the situation occurring in the monitored area.

Surveillance cameras included in such a surveillance system may notify the monitor by generating an alarm or warning when a movement of the surveillance object occurs. However, there are many cases where a surveillance camera incorrectly detects a motion of an object not being monitored and generates an alarm or warning, and thus a technique for improving the accuracy of the surveillance is required.

One aspect of the present invention is to provide a surveillance camera and a control method thereof that enables the identification of the object through the analysis of the object in which the movement occurred, thereby improving the accuracy of the surveillance.

In order to achieve the above object, the present invention comprises the steps of: detecting a target object is a motion camera is generated from the input image; Identifying whether the detected object is the object to be monitored or disturbed; And controlling an alarm when the identified object is a surveillance object. It includes a, provides an alarm control method by identifying the target of the surveillance camera.

According to one aspect of the invention, the step of detecting the target motion is generated, the step of extracting and comparing the previous frame and the current frame of the input image; And detecting a portion of the comparison result as the target where the movement occurs. It includes.

According to one feature of the invention, the step of identifying whether the movement target is a monitoring target or a disturbance target, using the size of the target movement generated.

According to one feature of the invention, the step of extracting the outer contour of the target object is generated; And if the extracted area value inside the outline is greater than or equal to a reference value, classifies it as the monitoring object, and if less than the reference value, classifies it as the disturbance object.

According to one aspect of the invention, the step of identifying whether the movement target is a monitoring target or a disturbance target, using the pattern of the target movement generated.

According to one feature of the invention, the step of extracting the outer contour of the target object is generated; Setting vertices at the bent portions of the extracted outlines; And when the number of vertices is greater than or equal to the reference number, classifies the object as the disturbance object.

In order to achieve the above object, the present invention, the imaging unit for deriving the input image from the light passing through the optical system; A moving object detection unit detecting a moving object generated from the input image; A target identification unit for identifying whether the detected target is a target of movement or a disturbance; And an alarm controller configured to control an alarm when the identified object is a surveillance object. It includes, providing a surveillance camera.

According to one aspect of the invention, the movement target detection unit, a comparison unit for extracting and comparing the previous frame and the current frame of the input image; And a target detection unit for detecting a portion of the comparison result of the comparison unit as a change generation target. It includes.

According to one feature of the invention, the target identification unit, the contour extraction unit for extracting the outer contour of the target movement is generated; And a first classifying unit classifying the monitored object when the extracted area value inside the outline is equal to or greater than a reference value, and classifying the detected object as the disturbance object. It includes.

According to one feature of the invention, the target identification unit, the contour extraction unit for extracting the outer contour of the target movement is generated; A vertex setting unit for setting a vertex in the bent portion of the extracted outer contour line; And a second classification unit classifying the disturbance object when the number of vertices is greater than or equal to the reference number, and classifying the monitoring object when the vertex is less than the reference number. It includes.

Other aspects, features, and advantages other than those described above will become apparent from the following drawings, claims, and detailed description of the invention.

According to the surveillance camera and the control method according to an embodiment of the present invention, it is possible to distinguish between the monitoring target and the disturbing target through the analysis of the outer contour of the target in which the movement occurs, thereby improving the accuracy of the monitoring.

1 is a block diagram schematically illustrating a surveillance system.
FIG. 2 is a block diagram schematically illustrating a surveillance camera included in FIG. 1.
3 is a block diagram schematically illustrating an embodiment of a digital signal processor included in FIG. 2.
FIG. 4 is an explanatory diagram for explaining the operation of the object identifying unit of FIG. 3.
FIG. 5 is a block diagram schematically illustrating another embodiment of the digital signal processor included in FIG. 2.
FIG. 6 is an explanatory diagram for describing an operation of the object identifying unit of FIG. 5.
7 is a flowchart illustrating a method for controlling a surveillance camera according to an embodiment of the present invention.
8 is a flowchart illustrating a control method of a surveillance camera according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to be limited to the particular embodiment of the present invention, it should be understood to include all transformations, equivalents, and substitutes included in the spirit and scope of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by terms. Terms are used only for the purpose of distinguishing one component from another.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, the terms "comprise" or "have" are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and one or more other features. It is to be understood that the present invention does not exclude the possibility of the presence or the addition of numbers, steps, operations, components, components, or a combination thereof.

Hereinafter, with reference to the embodiments of the present invention shown in the accompanying drawings will be described in detail the configuration and operation of the present invention.

1 shows a surveillance system to which the surveillance cameras 1a, 1b and 1c of the present invention are applied. Referring to FIG. 1, each of the surveillance cameras 1a, 1b and 1c generates a live view image by capturing.

In addition, each of the surveillance cameras 1a, 1b, and 1c communicates with the digital video recorder (DVR) 2 as a recording device via the communication channel (DCOM), and outputs the live view image through the video signal channel (SVID). To 2).

FIG. 2 is a block diagram showing an internal configuration of any one surveillance camera 1a or 1b or 1c of FIG. 1. Referring to FIG. 2, the surveillance camera includes an optical system (OPS), a photoelectric conversion unit (OEC), a CDS-ADC (Correlation Double Sampler and Analog-to-Digital Converter, 101), a timing circuit 102, and a digital signal processor as a control unit. (DSP, Digital Signal Processor, 107), video-signal generator 108, aperture motor MA, zoom motor MZ, focus motor MF, filter motor MD, driver 110, and communication Interface 112.

The optical system OPS including the lens unit 301 and the filter unit 302 optically processes light from a subject.

The lens unit 301 of the optical system OPS includes a zoom lens ZL and a focus lens FL. In the filter unit 302 of the optical system OPS, an optical low pass filter (OLPF) used in the night mode of operation removes optical noise of high frequency content. Infra-Red cut filter (IRF) used in daytime operation mode cuts off the infrared component of incident light.

A photoelectric conversion unit (OEC) of a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) converts light from an optical system (OPS) into an electrical analog signal. Here, the digital signal processor 107 as the main controller controls the timing circuit 102 to control the operation of the photoelectric converter OEC and the Correlation Double Sampler and Analog-to-Digital Converter 101. .

The CDS-ADC 101 processes the analog video signal from the photoelectric converter (OEC), removes the high frequency noise, adjusts the amplitude, and converts the digital video data. This digital image data is input to the digital signal processor 107. In summary, the imaging unit 100 including the optical system, the photoelectric conversion unit and the CDS-ADC 101 inputs light into the digital signal processor 107 using digital image data as an input image.

The digital signal processor 107 performing overall control processes the digital signal from the CDS-ADC element 101 to generate digital image data classified into luminance and chroma signals.

The video-signal generator 108 converts the digital image data from the digital signal processor 107 into a video signal SVID which is an analog image signal.

The digital signal processor 107 communicates with the digital video recorder (DVR, 2 of FIG. 1) as a recording device via the communication interface 112 and the communication channel (DCOM in FIG. 1), and through the video signal channel (SVID). The video signal from the video-signal generator 108 is transmitted to the digital video recorder 2.

The digital signal processor 107 controls the driving unit 110 to drive the aperture motor MA, the zoom motor MZ, the focus motor MF, and the filter motor MD. The aperture motor MA drives the aperture (not shown), the zoom motor MZ drives the zoom lens ZL, and the focus motor MF drives the focus lens FL. The filter motor MD drives the optical low pass filter OLPF and the infrared cut filter IRF in the filter unit 302.

3 is a detailed block diagram of a digital signal processor 107 according to an embodiment of the present invention.

Referring to FIG. 3, the digital signal processor 107 includes a motion target detector 10, a target identifier 20, and an alarm controller 30.

The motion object detector 10 detects an object in which a motion is generated from the input image. In detail, the movement object detector 10 may include a comparator 11 and an object detector 12.

The comparison unit 11 extracts and compares the previous frame and the current frame of the input image. Although the front and rear frames may be compared in various ways, for example, the background and the object may be distinguished from each frame, and the front and rear frames may be compared based on the background. However, the operation of the comparison unit is not limited to this, and various known methods may be used.

The object detecting unit 12 detects a portion in which the amount of change is generated as a result of the comparison by the comparing unit 11 as the object in which the movement is generated. For example, when the position of the object is changed or the shape of the object is changed in the front and rear frame, there is a part where the amount of change is generated. This part is defined and detected as the object where the motion is generated.

According to the exemplary embodiment of the present invention, the movement target detection unit 10 may detect the movement target. The method of detecting the object from which the motion is generated is not limited to the above description, and various known motion detection methods may be used. For example, the live view image may be used as the input image instead of the front and rear frames.

Referring back to FIG. 3, the object identifying unit 20 identifies whether the object in which the motion detected by the moving object detecting unit 10 is generated is a monitoring object or a disturbing object. Here, the monitoring target is a target for which the observer wants to monitor the intrusion, change and movement of the target. For example, the object to be monitored may be a man, an animal, or an artificial object including various objects to be monitored. On the other hand, the disturbance target is not an object to be monitored by the monitor and may be an object that mainly disturbs the monitor during the monitoring period and acts as a noise. For example, the disturbance may be natural matter such as trees, snow, rain or hail.

According to an embodiment of the present invention, the object identifying unit 20 may distinguish whether the object is to be monitored or disturbed by using the size of the object on which the motion is generated. In this case, the object identifying unit 20 may include a contour extracting unit 21 and a first classification unit 23.

The contour extracting unit 21 extracts the outer contour of the target in which the motion is generated. There are various ways to extract the contour. For example, the magnitude of the brightness change and the phase of the brightness change of each pixel forming the object in which the motion is generated in the current frame are calculated, and the plurality of contour points are extracted according to the magnitude of the brightness change. After marking the positions of the contour points forming a single contour in the center, a method of completing the contour may be used. As another example, a method of detecting a figure similar to the object in which the motion is generated from the database, and correcting the figure based on the outline of the contour of the figure may be used to extract the contour of the object in which the motion is generated.

The first classifying unit 23 derives an area value inside the outer contour line extracted by the contour extracting unit 21 and compares the area value with the reference value. As a result of the comparison, if the area value is above the reference value, it is classified as a monitoring object. If the area value is less than the reference value, it is classified as a disturbance object. Here, when the extracted outer contour is a closed loop, the first classification unit 23 derives an area value inside the closed curve. If the extracted outer contour is not a closed curve, the first classifying unit 23 may form a closed curve by connecting an open portion of the outer contour to a random line and then derive an area value inside the closed curve. On the other hand, in the present embodiment, the surveillance camera is for distinguishing the disturbance target such as snow, rain, hail and the like from the monitoring target. Accordingly, the reference value may be an arbitrary value or a value using size information such as snow, rain, and hail. For example, the reference value may be a value representing an average size of snow, rain, hail, or the like, or the size of a representative value.

Referring to FIG. 4, when comparing the previous frame (a) and the current frame (b), it can be seen that the positions of the butt ends and eyes have changed. For example, assuming that the reference area value is the middle value between the butt end area value and the snow area value, the contour area value is larger than the reference value for the butt end, so it is classified as monitored. do. However, in the case of eyes, butt end is classified as a disturbance object because the contour area value is smaller than the reference value.

The alarm control unit 30 controls to generate an alarm or a warning when the object identified by the object identification unit 20 is a monitoring target. Although described herein as an alarm, it is not limited to an alarm and includes operating all devices that a monitor can recognize, such as pop-ups, a warning sound, or a warning device. The alarm controller 30 controls not to generate an alarm or a warning when the object identified by the object identifying unit 20 is a disturbing object. Meanwhile, although not shown in FIG. 2, the alarm generating unit or the warning generating unit may generate a control signal for generating an alarm in the alarm control unit 30 and apply the generated alarm signal to the alarm generating unit or the warning generating unit.

According to an embodiment of the present invention, after extracting the outer contour of the object in which the movement occurs, a disturbance object such as snow, rain, hail, etc. may be detected by comparing the inner area value of the outer contour with a reference value. In the conventional surveillance cameras, when the snow, rain, hail, and the like fall from the sky is recognized as the movement of the monitoring object, a lot of false alarms. From this, there was a problem that the accuracy of the surveillance system was reduced. However, according to one embodiment of the present invention, snow, rain, hail, etc. are detected as a disturbing object to increase the accuracy of the monitoring system and more precise monitoring is possible.

5 is a detailed block diagram of a digital signal processor 107 according to another embodiment of the present invention.

Referring to FIG. 5, similar to FIG. 3, the digital signal processor 107 includes a movement target detector 10, an object identifier 20, and an alarm controller 30. However, the digital signal processor 107 of FIG. 5 is different from the digital signal processor 107 of FIG. 3 and the object identifying unit 20. In detail, the object identifying unit 20 of FIG. 5 identifies the monitoring object and the disturbing object according to the pattern, not the size of the object detected by the motion object detecting unit 10. Accordingly, the object identifying unit 20 of FIG. 5 includes a contour extracting unit 21, a vertex setting unit 22, and a second classifying unit 24. Hereinafter, a description of the functions and actions of the elements overlapping with FIG. 3 will be omitted.

The object identifying unit 20 of FIG. 5 includes a contour extracting unit 21. The contour extracting unit 21 functions and functions the same as the contour extracting unit described with reference to FIG.

The vertex setting unit 22 sets a vertex on the outer contour line extracted by the contour extraction unit 21. Here, the vertices may be set in various ways. For example, when the degree of warp of the extracted outline contour is a predetermined angle, for example, a right angle or more, a portion where the inclination of the tangent of the degree of warp is greatest is set as the first vertex. The above-described first vertex setting process is repeated with respect to the extracted outer contour, and the second vertex, the third vertex, and the like are set.

Next, the second classification unit 24 compares the number of vertices set by the vertex setting unit 22 with the reference number, and when the number of vertices set is greater than or equal to the reference number, classifies the corresponding object as a disturbing object and sets the number of vertices. If the number is less than the standard number, the object is classified as a monitored object. If a vertex is more than a predetermined number for one object, the object has a complex pattern, and if the vertex is less than a predetermined number, the object may have a simple pattern. In the case of the above-mentioned disturbing objects, trees often have a complex pattern by leaves. On the other hand, surveillance objects such as people, animals and objects often have simpler patterns than trees. Accordingly, the second classification unit 24 may classify the disturbance target and the monitoring target based on the statistical fact.

Referring to FIG. 6, when comparing the previous frame (a) and the current frame (b), it can be seen that the position of the butt end and the tree is changed. If it is assumed that the reference number is 10, the butt end is classified as being monitored because it is smaller than the reference number because the four vertices on the contour are four. However, trees are classified as disturbances because there are more than 10 vertices on the outline due to the complex pattern of the leaves.

According to an embodiment of the present invention, after extracting the outer contour of the object in which the movement occurs, a disturbance object such as a tree can be detected by detecting a pattern of the outer contour. In the conventional surveillance cameras, when a leafy tree is shaken by the wind, the movement is recognized as the movement of the surveillance target, and a false alarm is often emitted. From this, there was a problem that the accuracy of the surveillance system was reduced. However, according to one embodiment of the present invention, the movement of the tree is detected as the movement of the disturbing object to increase the accuracy of the monitoring system and more precise monitoring is possible.

7 is a flowchart illustrating a method for controlling a surveillance camera according to an embodiment of the present invention.

Referring to FIG. 7, first, an object in which motion is generated from an input image is detected by various motion detection methods. (S11)

Next, the outline of the detected object is extracted. (S12)

Next, the area value inside the outer contour and the reference value are compared (S13), and if the area value is larger than the reference value, the detected object is classified as a monitoring object (S14), and if the area value is smaller than the reference value, the detected object is disturbed. The object is classified (S15).

Finally, if the identified object is a watch target, the alarm is controlled so that the watcher can recognize it. (S16)

8 is a flowchart illustrating a method for controlling a surveillance camera according to another embodiment of the present invention.

Referring to FIG. 8, first, a target in which a motion is generated from an input image is detected by various motion detection methods. (S21)

Next, the outline of the detected object is extracted. (S22)

Next, a vertex is set on the outer contour (S23). In this case, the vertex may be set through the shape of bending the outline. Next, the number of vertices and the reference number are compared (S24), and if the number of vertices is larger than the reference number, the detected object is classified as a disturbance object (S25). If the number of vertices is less than the reference number, the detected object is determined. Classify it to be monitored (S26).

Finally, if the identified object is a watch target, the alarm is controlled so that the watcher can recognize it. (S27)

It will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Accordingly, the true scope of the present invention should be determined by the technical idea of the appended claims.

100: imaging unit 107: digital signal processor

Claims (10)

Detecting, by the surveillance camera, a target in which a motion is generated from the input image;
Identifying whether the detected object is the object to be monitored or disturbed; And
Controlling an alarm when the identified object is a surveillance object;
Including, alarm control method through the target identification of the surveillance camera. The method of claim 1,
The detecting of the object in which the movement occurs,
Extracting and comparing a previous frame and a current frame of the input image; And
Detecting a portion of the comparison result as a change generation target;
Including, alarm control method through the target identification of the surveillance camera. The method of claim 1,
Identifying whether the movement target is a monitoring target or a disturbing target,
Alarm control method through the object identification of the surveillance camera, using the size of the object in which the movement is generated. The method of claim 3,
Identifying whether the movement target is a monitoring target or a disturbing target,
Extracting an outer contour of the object on which the movement occurs; And
And classifying the surveillance object as the surveillance object when the extracted area value of the outer contour is greater than or equal to a reference value, and classifying the disturbance object as less than the reference value. The method of claim 1,
Identifying whether the movement target is a monitoring target or a disturbing target,
Alarm control method through the object identification of the surveillance camera, using the pattern of the object in which the movement is generated. The method of claim 5,
Identifying whether the movement target is a monitoring target or a disturbing target,
Extracting an outer contour of the object on which the movement occurs;
Setting vertices at the bent portions of the extracted outlines; And
When the number of the vertices is more than the reference number is classified as the disturbance target, if less than the reference number, the alarm control method through the object identification of the surveillance cameras. An imaging unit for deriving an input image from the light passing through the optical system;
A moving object detection unit detecting a moving object generated from the input image;
A target identification unit for identifying whether the detected target is a target of movement or a disturbance; And
An alarm controller for controlling an alarm when the identified object is a surveillance object;
Including, surveillance cameras. The method of claim 7, wherein
The moving object detection unit,
A comparator for extracting and comparing a previous frame and a current frame of the input image; And
A target detection unit for detecting a portion of the comparison result of the comparison unit, in which a change amount is generated, as the target in which the movement occurs;
Including, surveillance cameras. The method of claim 7, wherein
The target identification unit,
Contour extraction unit for extracting the outer contour of the target object is generated; And
A first classifying unit classifying the monitored object when the extracted area value inside the outline is equal to or greater than a reference value, and classifying the disturbance object when the extracted area value is less than the reference value;
Surveillance camera comprising a. The method of claim 7, wherein
The target identification unit,
Contour extraction unit for extracting the outer contour of the target object is generated;
A vertex setting unit for setting a vertex in the bent portion of the extracted outer contour line; And
A second classification unit classifying the disturbance object when the number of vertices is greater than or equal to the reference number and classifying the monitoring object when the vertex is less than the reference number;
Surveillance camera comprising a.

Images