KR102282470B1 - Camera apparatus and method of object tracking using the same - Google Patents

Abstract

The present invention discloses a camera device capable of detecting and tracking an object.
A camera device according to an embodiment of the present invention includes: a camera that detects at least one object in a first direction of a monitoring area and generates metadata for the at least one object; and a camera controller configured to control at least one of pan, tilt, and zoom of the camera based on metadata of a target selected from among the at least one object.

Description

Camera apparatus and method of object tracking using the same

The present invention relates to a camera device capable of detecting and tracking an object.

An automatic tracking function of driving pan/tilt/zoom is used to identify a moving object through an image analysis device in an image acquired through an image sensor and continuously track the moving object.

An object of the present invention is to provide a camera device capable of reducing costs by driving pan/tilt/zoom of a camera without analyzing an image.

A camera device according to a preferred embodiment of the present invention includes: a camera that detects at least one object in a first direction of a monitoring area and generates metadata for the at least one object; and a camera controller configured to control at least one of pan, tilt, and zoom of the camera based on metadata of a target selected from among the at least one object.

The metadata may include coordinates of an object.

The camera control unit may calculate the size and center coordinates of the object from metadata generated while the camera maintains the first direction, and calculate vector information of the object from changes in the center coordinates of the object there is.

The vector information may include a moving distance, a moving direction, and a moving speed of the object.

The camera controller may filter the other object by comparing the size and vector information of the target with the size and vector information of the other object.

The camera controller may set an object having a preset size as a target.

The camera control unit sets a first area in the image obtained by the camera in the first direction, and when the target leaves the first area, the camera moves in a second direction toward the target. You can control the pan and tilt of

The camera controller may control the zoom of the camera so that the size of the target in the second direction is the same as the size of the target in the first direction.

The camera controller may set a second area in the target based on the moving speed of the target, and filter objects other than the second area by excluding metadata other than the second area.

The camera controller may filter the other object by comparing the size and vector information of the other object existing in the second area with the size and vector information of the target.

An object tracking method using a camera according to an embodiment of the present invention includes: generating, by the camera, metadata for at least one object detected in a first direction of a surveillance area; selecting, by a camera controller, a target among the at least one object based on a result of analyzing the metadata; and outputting a control signal for controlling at least one of pan, tilt, and zoom of the camera based on the metadata of the selected target.

The metadata may include coordinates of an object.

The outputting of the control signal may include: calculating the size and center coordinates of the object from metadata generated while the camera maintains the first direction; and calculating vector information of the object from a change in the center coordinates of the object.

The vector information may include a moving distance, a moving direction, and a moving speed of the object.

The outputting of the control signal may include filtering the other object by comparing the size and vector information of the target with the size and vector information of the other object.

The target selection step may include setting an object having a preset size as a target.

The step of outputting the control signal may include: setting, by the camera, a first region in the image acquired in the first direction; and calculating a pan and tilt movement amount of the camera so that the camera moves in a second direction toward the target when the target leaves the first area.

The outputting of the control signal may include outputting a control signal for controlling the zoom of the camera so that the size of the target in the second direction is the same as the size of the target in the first direction.

The step of outputting the control signal may include: setting a second area on the target based on the moving speed of the target; and filtering objects other than the second region by excluding metadata other than the second region.

The outputting of the control signal may include filtering the other object by comparing the size and vector information of the other object existing in the second area with the size and vector information of the target.

Embodiments of the present invention can reduce costs by tracking an object using only metadata of the object without image analysis, and provide a camera device capable of continuously tracking a moving object.

1 is a configuration diagram of a camera system according to an embodiment of the present invention.
2 is a block diagram schematically illustrating a configuration of a camera device according to an embodiment of the present invention.
3 is a diagram illustrating a virtual area setting for target tracking according to an embodiment of the present invention.
4 is a view for explaining an object tracking method of a camera device according to an embodiment of the present invention.
5 is a flowchart illustrating a method for controlling a posture of a camera according to an embodiment of the present invention.
6 is a flowchart illustrating a method of tracking an object according to an embodiment of the present invention.
7 is a view for explaining an object tracking method of a camera device according to another embodiment of the present invention.
8 is a flowchart illustrating an object tracking method according to another embodiment of the present invention.
9 is a flowchart illustrating an object identification method according to an embodiment of the present invention.

Since the present invention can apply various transformations and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and it should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention. In describing the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted.

In the following embodiments, terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

Terms used in the following examples are only used to describe specific examples, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the following examples, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification is present, but one or more It should be understood that this does not preclude the possibility of addition or presence of other features or numbers, steps, operations, components, parts, or combinations thereof.

Embodiments of the present invention may be represented by functional block configurations and various processing steps. These functional blocks may be implemented in any number of hardware and/or software configurations that perform specific functions. For example, embodiments of the present invention may be implemented directly, such as memory, processing, logic, look-up table, etc., capable of executing various functions by control of one or more microprocessors or other control devices. Circuit configurations may be employed. Similar to how components of an embodiment of the invention may be implemented as software programming or software elements, embodiments of the invention may include various algorithms implemented in combinations of data structures, processes, routines, or other programming constructs. , C, C++, Java, assembler, etc. may be implemented in a programming or scripting language. Functional aspects may be implemented in an algorithm running on one or more processors. Also, embodiments of the present invention may employ conventional techniques for electronic configuration, signal processing, and/or data processing, and the like. Terms such as mechanism, element, means, and configuration may be used broadly and are not limited to mechanical and physical configurations. The term may include the meaning of a series of routines of software in association with a processor or the like.

In addition, in this specification and drawing, about the component which has substantially the same structure, duplicate description is abbreviate|omitted by using the same code|symbol.

1 is a configuration diagram of a camera system according to an embodiment of the present invention.

Referring to FIG. 1 , the camera system according to the present embodiment may include a camera device 100 and a central management unit 700 including an integrated control unit 710 and a display unit 720 . The camera device 100 may be connected to the central management unit 300 through a wired or wireless network 600 .

The camera device 100 may continuously photograph the surrounding environment within the field of view by using the set pan/tilt/zoom to detect and track a plurality of objects within the field of view.

The camera device 100 may include at least one or more network cameras 110 and at least one analog camera 160 for capturing images. The network camera 110 may include a digital video recorder (DVR) or a network video recorder (NVR) that stores the captured image. The analog camera 160 may include an encoder for encoding the captured image. Here, the camera device 100 is not limited to the above description, and any device capable of transmitting an image to the central management unit 700 by being connected to the network 600 may be used.

The central management unit 700 may receive an image from the camera device 100 through the network 600 . The central management unit 700 may receive metadata generated according to object detection and tracking together with an image from the camera device 100 .

The central management unit 700 may display the received images of the camera device 100 and monitor the images being displayed. The central management unit 700 may control the camera device 100 by analyzing an object detection and tracking result of the camera device 100 and an image captured by the camera device 100 .

The integrated control unit 710 may control the operation of the central management unit 700 and display the control contents on the display unit 720 .

In this embodiment, the integrated control unit 710 may include a DSP or an image analysis unit (not shown) therein to detect an event from images of the camera device 100 received through the network 600 . The integrated control unit 710 may generate an event when a set event generation condition is satisfied by analyzing the image received from the camera device 100 .

2 is a block diagram schematically illustrating a configuration of a camera device according to an embodiment of the present invention.

Referring to FIG. 2 , the camera device 100 may include a camera 200 , a camera controller 300 , and a pan/tilt motor 400 .

The camera device 100 is integrally installed inside and outside of an office, house, hospital, as well as a bank or a public building requiring security, and is used for access control or crime prevention, and depending on the installation location and purpose of use, a straight-line type, a dome type, etc. It may have various forms.

The camera 200 includes an optical unit 201 , an image sensor 202 , an image processing unit 203 , an object detection unit 204 , a communication unit 205 , a transmission unit 206 , and a zoom control unit 207 , and , is accommodated in the first housing (not shown), and some components may be arranged to protrude out of the first housing for photographing.

The optical unit 201 may include an optical system such as a zoom lens, a focus lens, and an iris for adjusting the amount of light.

The image sensor 202 converts the light passing through the optical unit 201 into an electrical image signal. The image sensor 202 includes an image pickup device such as a Charge Coupled Device (CCD) or a Complementary Metal-Oxide-Semiconductor (CMOS).

The image processing unit 203 performs image signal processing such as noise removal on the digital image signal obtained by changing the digital image signal from the image sensor 202 or the analog image signal from the image sensor 202, and the signal-processed image signal is transmitted to the object detection unit 204 and the transmission unit 206 , respectively. The image processing unit 203 may transmit a signal-processed digital image signal or convert it into an analog image signal and transmit it.

The object detection unit 204 may detect an object from an image signal (hereinafter, referred to as “image”) received from the image processing unit 203 . For example, the object detecting unit 204 may detect the local motion of the object as a difference image between the current image and the reference image obtained while the camera 200 gazes in one direction. The reference image is captured and determined at the moment the motion detection function for object detection is activated. The current image is an image taken after the reference image is determined. The reference image and the current image are determined by the angle of view of the camera 200 . The object detecting unit 204 may detect an object by simple comparison of a reference image and a current image generated in the same direction. The method of detecting the local motion of the object by the object detecting unit 204 of the present invention is not limited to the method using the above-described image difference, and of course, various known methods may be applied.

The object detection unit 204 may generate metadata that is a set of object detection results. The metadata may include the number of objects detected in the image and coordinates of each object. The coordinates of the object may include upper-left coordinates and lower-right coordinates of the object block.

The communication unit 205 transmits the generated metadata to the camera control unit 300 .

The transmission unit 206 may transmit the image received from the image processing unit 203 to the remote central management unit 300 .

The zoom control unit 207 generates a zoom control signal based on the zoom movement amount received from the camera control unit 300 and adjusts the zoom lens and the focus lens of the optical unit 201 to zoom (Zooming, Zoom-in, or Zoom-out). ) can be done.

The camera acquires an image and transmits it to a digital signal processor (DSP) or an image analyzer to detect and track an object. The DSP analyzes the image to determine the camera's posture. For example, in an image, a global motion generated by a camera movement and a local motion of an object exist at the same time, and the entire screen may be detected as a motion due to the camera movement. The DSP may estimate a global motion between two consecutive previous images and a current image input at a predetermined time interval, and obtain a previous image in which the global motion is compensated. The DSP may detect an object by extracting feature points between the compensated previous image and the current image (eg, luminance information, color depth, edge information, location information, etc.). That is, the DSP has a large amount of computation by detecting motion on the entire screen, and also increases the cost when a DSP with good performance is used for real-time application.

In an embodiment of the present invention, the camera control unit 300 does not have a DSP, and the camera 200 generates metadata by detecting a local motion of an object with a small amount of computation from an input image while maintaining a set posture, Only metadata, not an image, is transmitted to the camera controller 300 . The camera controller 300 may control the posture of the camera 200 by analyzing and processing metadata. Accordingly, the camera device 100 according to an embodiment of the present invention can reduce the amount of computation and processing time for object tracking, reduce costs, and simultaneously track the object in real time.

The camera controller 300 may be accommodated in a first housing or a second housing (not shown) coupled to the first housing. The camera controller 300 may control the pan/tilt/zoom control of the camera 200 , that is, the posture.

The camera control unit 300 may include a communication unit 301 , a metadata processing unit 303 , and a motor control unit 305 .

The communication unit 301 may be connected to the communication unit 205 of the camera 200 through a serial port or the like, and may receive metadata for each object from the communication unit 205 of the camera 200 .

The metadata processing unit 303 analyzes the received metadata and the zoom magnification of the camera 200 . The metadata processing unit 303 may calculate the size (width and height) and center coordinates (X,Y) of the object from the coordinates of the object included in the metadata. The metadata processing unit 303 may calculate vector information from a change in the coordinates of the object, that is, a change in the center coordinates of the object. The vector information may include a moving distance, a moving direction, and a moving speed of the object. Hereinafter, the size and vector information of the object is referred to as motion information of the object.

For example, the metadata processing unit 303 may calculate the movement distance and movement direction of the X-axis and Y-axis between the previous coordinates and the current coordinates of the object. Vector information may be extracted with the first center coordinates (X1, Y1) and the second center coordinates (X2, Y2) of the object input at predetermined time intervals. In this case, the movement distance along the X-axis becomes (X2-X1), and the movement direction can be estimated in the forward direction when the calculated value is greater than 0, and in the reverse direction when the calculated value is less than 0. Similarly, the movement distance along the Y axis becomes (Y2-Y1), and the movement direction can be estimated in the forward direction when the calculated value is greater than 0, and in the reverse direction when the calculated value is less than 0.

In addition, the metadata processing unit 303 may calculate the moving speed of the object. The moving speed may vary depending on the moving distance and zoom magnification. The movement speed increases in proportion to the movement distance, and the movement speed decreases by the rate at which the angle of view decreases as the zoom magnification increases.

In addition, the metadata processing unit 303 may calculate vector information by applying an X-axis and Y-axis interpolation method for synchronization when the pan and the tilt TILT are simultaneously driven.

The metadata processing unit 303 may select a tracking target, that is, a target based on the size of the object. The target selection criterion may be set to a predetermined ratio of a vertical length or a predetermined ratio of a horizontal length of the image. When at least one of a horizontal length (width) and a vertical length (height) of the object corresponds to the target selection criterion, the metadata processing unit 303 may select the object as a target. The width of the object may be calculated from the difference between the x value of the upper left coordinate and the lower right coordinate of the object. The height of the object may be calculated from a difference between the y value of the upper left coordinate and the lower right coordinate of the object. For example, the metadata processing unit 303 determines that an object having a vertical length (height) of 1/4, 1/2, or 3/4 of the vertical length of the image is displayed for a certain period of time (eg, 10 image frames). It can be selected as a target when it is detected as moving continuously during a period of time. The target selection criterion is not limited to the above-described ratio.

The metadata processing unit 303 may control the pan/tilt/zoom of the camera 200 to prevent the target from departing from the range of the camera's angle of view. The metadata processing unit 303 may calculate a pan/tilt/zoom movement amount for moving the camera 200 so that the center coordinates of the target are located in the center of the image.

The metadata processing unit 303 may set a first virtual region in the first image captured in the first direction. The first region is a critical region for pan/tilt movement of the camera 200 set based on the center of the first image. The range of the first area can be adjusted according to a user's setting or a target (type of target, moving speed of the target, etc.). When the target located at the center of the first image deviates from the first area, the metadata processing unit 303 may calculate a pan and tilt movement amount for moving the camera 200 in the second direction. The second direction is a direction in which the target is positioned at the center of the second image acquired in the second direction. The metadata processing unit 303 may calculate a zoom movement amount for controlling the zoom of the camera 200 so that the size of the target located in the center of the second image is the same as the size when the target is located in the center of the first image. . The metadata processing unit 303 may transmit the zoom movement amount of the camera 200 to the camera 200 through the communication unit 301 .

The metadata processing unit 303 may set a second virtual region in the target. The second area is a movable range of the target determined in consideration of the target's moving speed. The metadata processing unit 303 may filter out non-target objects outside the movable range of the target by excluding metadata other than the second area and analyzing only the metadata of the second area.

When the target is out of the first area, the metadata processing unit 303 may track the target by comparing the previous metadata analysis result of the target with the current metadata analysis result of another object to identify the target. If the center coordinates of the target do not belong to the first area, it may be determined that the target is out of the first area. The metadata processing unit 303 may identify the target by comparing the size, movement distance, and movement direction of the target with the size, movement distance, and movement direction of other objects. The metadata processing unit 303 may compare some or all of the size, movement distance, and movement direction. For example, the metadata processing unit 303 may compare sizes first, compare the movement distances if the sizes are the same, and compare the movement directions if the movement distances are the same.

The metadata processing unit 303 may track the target by identifying the target by comparing the previous metadata analysis result of the target with the current metadata analysis result of the other object even when another object exists in the second area set in the target. .

The motor controller 305 may generate a motor control signal for controlling the driving of the pan/tilt motor 400 based on the amount of pan and tilt movement. The motor controller 305 may convert the amount of pan and tilt movement into a pulse signal for driving the motor in consideration of the motion information of the object and conditions of the camera device 100 such as a motor step angle, a gear ratio, and a micro step.

The pan/tilt motor 400 includes a pan motor and a tilt motor, and the pan motor and the tilt motor may be accommodated in the first housing or the second housing, respectively. The pan motor and the tilt motor may be implemented as a step motor or a pulse motor. The pan motor rotates the camera 200 in the left and right directions according to the fan motor driving pulse signal, and the tilt motor may control the camera 200 in the vertical direction according to the tilt motor driving pulse signal. The pan motor and tilt motor can each be controlled separately or simultaneously.

3 is a diagram illustrating a virtual area setting for target tracking according to an embodiment of the present invention.

As shown in FIG. 3A , the metadata processing unit 303 may set a virtual first area LA in the image. The metadata processing unit 303 calculates the pan/tilt movement amount of the camera 200 when the target A leaves the first area LA, and the motor control unit 305 outputs a pan/tilt control signal to the camera (200) is moved. Accordingly, the target (A) is again located in the center (P) of the image. The metadata processing unit 303 may control the zoom magnification of the camera 200 so that the size of the target A is constant after the pan/tilt of the camera 200 is controlled.

As illustrated in FIG. 3B , the metadata processing unit 303 may set a virtual first area LA in the image and set a virtual second area MA in the target. The metadata processing unit 303 calculates the pan/tilt movement amount of the camera 200 when the target A leaves the first area LA, and the motor control unit 305 outputs a pan/tilt control signal to the camera (200) is moved. Accordingly, the target (A) is again located in the center (P) of the image. The metadata processing unit 303 may control the zoom magnification of the camera 200 so that the size of the target A is constant after the pan/tilt of the camera 200 is controlled. By using only metadata within the second area MA, the metadata processing unit 303 may reduce errors in recognizing and tracking other objects existing in areas other than the second area MA as targets.

4 is an example for explaining an object tracking method of a camera device according to an embodiment of the present invention.

The camera controller 300 receives metadata for the plurality of objects A, B, and C from the camera 200 . The camera controller 300 analyzes metadata of the plurality of objects A, B, and C. The camera controller 300 selects, as a target, an object A matching a target selection criterion among a plurality of objects A, B, and C. As shown in FIG. 4( a ), the camera control unit 300 controls the camera 200 so that the target A among the plurality of objects A, B, and C is located at the center P of the image. Tilt/zoom control.

The camera controller 300 transmits the zoom movement amount of the camera 200 to the camera 200 and generates an attitude control value corresponding to the pan/tilt movement amount of the camera 200 . The pan/tilt motor 400 controls the pan/tilt of the camera 200 by panning and tilting according to the attitude control value. The camera 200 maintains the size of the target A constant by adjusting the zoom lens and the focus lens according to the zoom movement amount.

While the target A exists in the first area LA, the pan/tilt/zoom of the camera 200 is fixed. That is, the camera 200 acquires an image of the front in a certain posture, generates metadata of a plurality of objects A, B, and C from the acquired image, and the camera controller 300 analyzes the received metadata Thus, the calculated motion information for each object may be stored in a memory (not shown).

As shown in FIG. 4(b) , when the target A leaves the first area LA, the camera 200 pans/tilts according to a pan/tilt/zoom control signal from the camera controller 300 . and the camera 200 moves to a new posture. The camera controller 300 controls the target A based on the motion information (magnitude and vector information) calculated while the target A is in the first area LA, particularly just before the target A leaves the first area LA. Based on the motion information of , the target A may be tracked by identifying the target A among a plurality of objects existing outside the first area LA. The camera control unit 300 determines the target A's metadata from among the metadata received in real time with respect to the plurality of objects based on the motion information calculated while the target A exists in the first area LA. can be selected. For example, the camera control unit 300 may estimate the next moving distance and moving direction in consideration of the moving distance and moving direction of the target A calculated while the target A is present in the first area LA. Also, it is possible to select metadata that gives an analysis result that is closest to the size of the target A, the estimated movement distance, and the movement direction from among the analysis results of the received metadata.

Hereinafter, a detailed description of the content overlapping with the above-described content will be omitted.

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

Referring to FIG. 5 , the camera may detect at least one object from an image obtained by photographing a monitoring area in a direction the camera is currently looking at ( S52 ).

The camera may generate metadata representing information of the object (S54). The metadata may include the number of objects detected in the image and coordinates of each object. The coordinates of the object may include upper-left coordinates and lower-right coordinates of the object block. The camera may transmit metadata of the object to the camera controller.

The camera controller may receive the metadata of the object, and calculate motion information of the object based on the metadata and the zoom magnification (S56). The size and center coordinates of the object may be calculated from the coordinates of the object. Vector information of the object can be calculated from the change of the coordinates of the center of the object. The object motion information indicates a local motion of the object in an image captured by a camera that maintains the current PTZ value, and may include object size and vector information. The vector information may include a moving distance, a moving direction, and a moving speed of the object. The camera controller may select a target based on the size of each object.

The camera controller may control pan/tilt/zoom (PTZ) of the camera based on the motion information of the object (S58). The camera controller may control the pan/tilt/zoom (PTZ) of the camera so that the selected target is located in the center of the image. The camera controller may control the pan/tilt/zoom (PTZ) of the camera so that the target is again located in the center of the image when the target is out of the first area of the image.

6 is a flowchart illustrating a method for tracking an object according to an embodiment of the present invention.

Referring to FIG. 6 , the camera controller determines the posture control value and zoom magnification of the camera so that the selected target is located in the center of the image, and the PTZ of the camera is controlled by the generated posture control value and zoom magnification (S62) .

The camera controller may set the first area in the image captured by the camera in the current PTZ state, and calculate the target's motion information by analyzing the metadata of the target received from the camera while the target is in the first area. (S64).

When the target leaves the first area of the image, the camera control unit may track the target based on pre-calculated motion information (S66). The camera controller may identify a target among a plurality of objects among a plurality of objects existing outside the first area based on motion information calculated while the target exists in the first area. The camera controller may identify the target among the plurality of objects by comparing the size, movement distance, and movement direction of the target with the size, movement distance, and movement direction of the objects in a predetermined order. The camera controller determines the posture control value and zoom magnification of the camera so that the identified target is located in the center of the image, and the PTZ of the camera is controlled by the determined posture control value and zoom magnification. The size of the target may be kept constant by the zoom control.

7 is a view for explaining an object tracking method of a camera device according to another embodiment of the present invention.

As shown in FIG. 7A , the camera controller 300 receives metadata for a plurality of objects 11 to 14 detected in the monitoring area from the camera 200 . The camera controller 300 sets the virtual first area LA in the image corresponding to the angle of view of the camera 200 .

The camera controller 300 may select an object having a preset size among the plurality of objects 11 to 14 as a target. For example, an object having a predetermined ratio of a horizontal length or a vertical length of an image may be selected as a target. In the example of FIG. 7( a ), the object 13 is selected as a target.

As shown in FIG. 7B , the camera controller 300 controls the pan/tilt of the camera 200 so that the target object 13 is located in the center of the image. The camera controller 300 generates an attitude control value corresponding to the pan/tilt movement amount. The pan/tilt motor 400 controls the pan/tilt of the camera 200 by panning and tilting according to the attitude control value. The camera controller 300 determines the size of the target 13 by controlling the zoom magnification of the camera 200 .

The camera control unit 300 analyzes the metadata of the target 13 moving in the first area LA of the image captured by the camera 200 while maintaining the PTZ, and the size and center coordinates of the target 13 . to calculate The camera controller 300 may calculate the size and vector information of the target based on the current coordinates and the previous coordinates of the target 13 . The vector information includes the moving speed, moving direction, and moving distance of the object.

The camera controller 300 may set the second region MR on the target 13 in consideration of the moving speed and the moving direction of the target 13 . The faster the moving speed of the target, the wider the second area MA, and the slower the moving speed, the smaller the second area MA. By setting the second area MA, it is possible to filter disturbances caused by the surrounding environment or a plurality of objects. As shown in FIG. 7(c) , as the second area MR of the target 13 is set, the background and other surrounding objects 12 and 14 other than the second area MR may be filtered. .

As shown in FIG. 7( d ), when the target 13 is out of the first area LA, the camera control unit 300 again moves the fan of the camera 200 so that the target 13 is located in the center of the image. You can change the posture by controlling /tilt. When the size of the target 13 is decreased or increased due to the movement of the target 13 , the camera controller 300 zooms in or out the camera 200 so that the size of the target 13 becomes the size when the target 13 is selected.

As shown in FIG. 7( e ), when a plurality of objects exist in the second region MR set in the target 13 , the camera control unit 300 controls the size of the continuously monitored target 13 and By comparing the vector information with the size and vector information of other objects to identify the target 13, it is possible to track the target 13 without missing it. Although not shown, even when a plurality of objects exist in an area outside the first area LA while the target 13 is outside the first area LA, the camera control unit 300 controls the continuously monitored target ( By comparing the size and vector information of 13) with the size and vector information of other objects to identify the target 13, it is possible to track the target 13 without missing it.

7(f), when the target 13 is missed, the camera control unit 300 pans/tilts the camera 200 so that the camera 200 faces in the direction in which the target 13 was last positioned. control The camera controller 300 generates an attitude control value corresponding to the pan/tilt movement amount. The pan/tilt motor 400 controls the pan/tilt of the camera 200 by panning and tilting according to the attitude control value. Then, the camera control unit 300 controls the camera 200 to zoom out to restart the detection of the target 13 .

8 is a flowchart illustrating an object tracking method according to another embodiment of the present invention.

Referring to FIG. 8 , the camera may capture an image in a direction that the camera is looking at in the current PTZ state, and may detect at least one object ( S81 ).

The camera may generate metadata representing information about the object (S82). The metadata may include coordinates of the object.

The camera controller may receive metadata to identify an object and calculate motion information for each object ( S83 ). The object motion information indicates a local motion of the object in an image captured in the current PTZ state of the camera, and may include object size and vector information. The size and center coordinates of the object may be calculated from the coordinates of the object. Vector information of the object can be calculated from the change in the center coordinates of the object. The vector information may include a moving distance, a moving direction, and a moving speed of the object.

The camera controller may select a target based on the size of the object (S84). The target selection criterion may be set to a predetermined ratio of a vertical length or a predetermined ratio of a horizontal length of the image.

The camera controller may control the pan/tilt/zoom (PTZ) of the camera so that the target is located at the center of the image (S85). The camera controller may set the first area in the image.

The camera control unit determines whether the target is out of the first area (S86). When the target is out of the first area, the target is tracked using vector information of the target, and the pan/tilt/zoom (PTZ) of the camera can be controlled so that the target is again located in the center of the image ( S87 ). The camera controller may identify the target among the plurality of objects by comparing the size, movement distance, and movement direction of the objects outside the first area with the previously calculated size, movement distance, and movement direction of the target in a predetermined order.

Meanwhile, the camera controller may set the second area on the target. The camera controller may filter the object outside the movement range of the target by using only the metadata of the second area. In addition, when another object exists in the second area set in the target, the camera controller compares the size, movement distance, and movement direction of the other object with the size, movement distance and movement direction of the target in a predetermined order to identify the target. there is.

9 is a flowchart illustrating an object identification method according to an embodiment of the present invention.

When the target leaves the first area and a plurality of objects exist outside the first area, or when a plurality of objects exist in the second area set in the target, the camera control unit identifies the target by comparing the motion information between the target and the object. can

Referring to FIG. 9 , the camera controller may analyze the metadata for each object received from the camera to calculate motion information of each object ( S91 ).

The camera controller compares the size of the target with the size of the object (S93), compares the movement distance if the sizes match (S95), and compares the movement direction when the movement distances match (S97).

The camera controller may identify an object having the same size, moving distance, and moving direction of the target as the target (S99). That is, the camera controller may filter and exclude objects having different at least one of a size, a movement distance, and a movement direction of the target.

The camera posture control and object tracking method according to the present invention can be implemented as computer-readable codes on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. In addition, the computer-readable recording medium is distributed in a computer system connected through a network, so that the computer-readable code can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers in the art to which the present invention pertains.

Aspects of the present invention have been described with reference to the embodiments shown in the accompanying drawings, which are merely exemplary, and that various modifications and equivalent other embodiments are possible therefrom by those skilled in the art. point can be understood. Accordingly, the true protection scope of the present invention should be defined only by the appended claims.

Claims (20)

a camera for detecting at least one object in a first direction of the monitoring area and generating metadata for the at least one object; and
a camera controller for controlling at least one of pan, tilt, and zoom of the camera based on metadata of a target selected from among the at least one object; and
The camera control unit,
The camera sets a first area based on the center of the image in the image acquired in the first direction,
setting a second region in the image obtained in the first direction to have a size and a direction varying according to the speed and movement direction of the target;
Excluding metadata other than the second area, by analyzing the metadata in the second area to filter objects outside the second area to track the target;
when the target leaves the first area, controlling at least one of pan and tilt of the camera to move the camera in a second direction toward the target;
The first area is a critical area for pan and tilt movement of the camera;
The second area has a larger size as the speed of the target increases, and has a smaller size as the speed of the target decreases. According to claim 1,
The metadata includes coordinates of the object. According to claim 2, wherein the camera control unit,
The camera device, which calculates the size and center coordinates of the object from metadata generated while the camera maintains the first direction, and calculates vector information of the object from changes in the center coordinates of the object. 4. The method of claim 3,
The vector information is a camera device including a moving distance, a moving direction, and a moving speed of the object. According to claim 3, wherein the camera control unit,
Filtering the other object by comparing the size and vector information of the target with the size and vector information of the other object, the camera device. According to claim 1, wherein the camera control unit,
A camera device for setting an object having a preset size as a target. delete According to claim 1, wherein the camera control unit,
and controlling the zoom of the camera so that the size of the target in the second direction is the same as the size of the target in the first direction. delete According to claim 1, wherein the camera control unit,
and filtering the other object by comparing the size and vector information of the other object existing in the second area with the size and vector information of the target. generating, by the camera, metadata for at least one object detected in a first direction of the surveillance area;
selecting, by a camera controller, a target among the at least one object based on a result of analyzing the metadata; and
outputting a control signal for controlling at least one of pan, tilt, and zoom of the camera based on the metadata of the selected target;
The control signal output step,
setting, by the camera, a first area in the image acquired in the first direction based on the center of the image;
setting a second region in the image acquired in the first direction to have a size and a direction variable according to the speed and movement direction of the target;
tracking a target by excluding metadata outside the second area, analyzing metadata within the second area, and filtering objects outside the second area; and
When the target leaves the first area, controlling at least one of pan and tilt of the camera so that the camera moves in a second direction toward the target;
The first area is a critical area for pan and tilt movement of the camera,
The second area has a larger size as the speed of the target increases, and has a smaller size as the speed of the target decreases. 12. The method of claim 11,
The metadata includes the coordinates of the object, an object tracking method using a camera. The method of claim 12, wherein the outputting of the control signal comprises:
calculating the size and center coordinates of the object from the metadata generated while the camera maintains the first direction; and
Calculating vector information of the object from a change in the center coordinates of the object; object tracking method using a camera comprising a. 14. The method of claim 13,
The vector information is an object tracking method using a camera including a moving distance, a moving direction, and a moving speed of the object. The method of claim 13, wherein the outputting of the control signal comprises:
and filtering the other object by comparing the size and vector information of the target with the size and vector information of the other object. According to claim 11, wherein the target selection step,
Object tracking method using a camera comprising; setting an object having a preset size as a target. delete The method of claim 11, wherein the outputting of the control signal comprises:
and outputting a control signal for controlling the zoom of the camera so that the size of the target in the second direction is the same as the size of the target in the first direction. delete The method of claim 11, wherein the outputting of the control signal comprises:
and filtering the other object by comparing the size and vector information of the other object existing in the second area with the size and vector information of the target.

Images