KR101530255B1 - Cctv system having auto tracking function of moving target - Google Patents

Abstract

A CCTV system having an object auto-tracking function for capturing an image of the object so as to confirm the moving radius of the object entering the area of interest is disclosed. A user interface for setting a region of interest in the surveillance region; and a controller for storing close-up information in which a rotation angle and a zooming ratio of the surveillance camera are set according to coordinate values of the region of interest and storing coordinate value information of the region of interest, And a controller for analyzing the image data received from the surveillance camera to designate an object entering the ROI as a target and analyzing real time coordinate values of the object, And a control module for controlling the surveillance camera to capture an enlarged image of an object moving within the surveillance area by providing the surveillance camera with the close-up information through the wired / wireless network, And provides a CCTV system equipped with the apparatus. According to the present invention, since an enlarged image of an object that has entered a region of interest is acquired and stored among the objects that have entered the surveillance region, the reliability of the surveillance information on the region of interest can be enhanced.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a CCTV system equipped with an automatic object tracking device,

The present invention relates to a CCTV system having an object tracking function for capturing an image of the object so as to confirm the moving radius of the object entering the area of interest, and more particularly, And a CCTV system having an object tracking function for capturing an enlarged image by tracking an object entering the area of interest.

In recent surveillance systems, the importance of developing products or systems that can automatically recognize and track surveillance targets with video interpretation and tracking technology is increasing. Video interpretation and tracking technology can be applied to a variety of applications such as computation processing technology (image enhancement, image model, color image processing, motion analysis, video image synthesis), sensor control technology (combination of CCD, PTZ, IR, stereo, Interface technology (communication and control between sensor and computer, graphics).

The arithmetic processing technique is generally performed for the purpose of a monitoring target. That is, the object is defined, extracted, modeled, and tracked based on the object shape, shape, motion, and color information of the object to be monitored in the continuous image frame. Among these monitored components, the active model or the active contour model is divided into a plurality of blocks and a continuous image-based tracking and image frame which tracks the object to be monitored by the object shape, shape and behavior analysis, It is used in block matching based tracking to find small errors between blocks within a given image frame.

The sensor control technique includes a method using one camera and a method using a plurality of cameras to overcome the limitation of the visual range of the camera. At this time, there is a method of using a pan-tilt zoom (PTZ) camera to solve the limitation of the visual range of a single camera. Using PTZ camera, it is possible to obtain an effective and wide view angle in all directions of 360 degrees, but it is difficult to distinguish the background and the object in the image due to the motion characteristics of the camera. In addition, it is possible to separate background and object using adjacent images, but it is impossible to detect and track still objects. To solve this problem, we use a method of defining a background in advance and using a background difference method or a method of separating an object by stabilizing a background between adjacent images.

In most PTZ camera based object tracking systems, the tracking method depends on whether the object to be monitored exists in the image or the object enters into the region of interest of the image. In other words, it is classified into a method of tracking the object after stabilizing the background of the camera by estimating the movement of the camera in the image, a method of tracking the object when the camera is stopped, and moving the camera, assuming that the camera is moving. In this case, in the first method, a blur phenomenon may occur in the image depending on the moving speed of the camera, so that the object is tracked at a speed such that the deterioration phenomenon does not occur. In the second method, when an object is detected when the camera is stopped, the camera is moved so that the object is located at the center of the image, and the object is not tracked while the camera is moving.

In the object tracking system using PTZ camera, there is a need to create a background so as not to cause deterioration and move the camera accurately according to the movement of the object so that the object can be stably tracked while the object is positioned within the region of interest Do.

Korean Patent Laid-Open No. 10-2011-0023472 (published on March 8, 2011) Korean Patent Publication No. 10-2012-0124604 (published on November 14, 2012) Korean Patent No. 10-1153919 (published on May 31, 2012)

Accordingly, an object of the present invention is to provide an object tracking method and a tracking method for tracking an object moving into a predetermined area of interest while monitoring a wide area using a single PTZ camera, And a CCTV system having an automatic tracking function.

According to another aspect of the present invention, there is provided a method of controlling a camera system including a user interface configured to set a region of interest within a surveillance region, A storage module for storing the coordinate value information of the ROI and storing the image received from the surveillance camera, and an object entering the ROI by analyzing the image data received from the surveillance camera as a target An image analysis module for analyzing real-time coordinate values of the object and extracting close-up information corresponding to the coordinate values; and an enlargement / reduction module for providing the close-up information to the surveillance camera through a wired / An object including a control module for controlling the surveillance camera A CCTV system equipped with an automatic tracking device is provided.

The CCTV system according to the present invention acquires and stores an enlarged image of an object through a zoom-in operation when the object being tracked enters the ROI, thereby enhancing the reliability of the monitoring information on the ROI, The details of the object (face of the person or license plate of the vehicle) can be easily acquired and used as evidence.

In addition, since the surveillance camera is rotated on the basis of the coordinate information in the coordinate space by presetting the surveillance region and the region of interest, the error can be reduced compared to the method of setting both the movement amount and the moving speed of the surveillance camera have.

In addition, the present invention can reduce the noise and concentrate the surveillance by classifying the region of interest in which the enlarged image of the surveillance target is obtained in advance, thereby enhancing the surveillance efficiency of the single surveillance camera.

1 is a block diagram for explaining a CCTV system according to the present invention.
2 is a schematic view showing a surveillance region in which a region of interest is set.
FIG. 3 is a view for explaining an image of the reference area of FIG. 2 taken; FIG.
4 is a diagram for explaining an image in a state where an object is detected before entering the region of interest.
FIG. 5 is a diagram for explaining an image in a state where an object entering a region of interest is detected. FIG.
6 is an enlarged view of a person who has entered the area of interest.
7 is a diagram for explaining an image in a state in which a vehicle entering a ROI is detected.
8 is an enlarged view of the vehicle of Fig.

Hereinafter, a CCTV system (hereinafter referred to as a CCTV system) having an object automatic tracking function according to preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram for explaining a CCTV system according to the present invention.

Referring to FIG. 1, the CCTV system according to the present invention includes a surveillance camera 100 installed in a surveillance area S and an object automatic tracking device 200 connected to the surveillance camera 100.

More specifically, the automatic object tracking apparatus 200 stores a user interface for setting a region of interest (A) in the surveillance region S and coordinate value information of the close-up information and the region of interest A An image analysis module 230 for extracting close-up information from the storage module 230 according to coordinate values of an object entering the region of interest A, a storage module 230 for storing an enlarged image of the object entering the region of interest A, (240), and a control module (250) for controlling the surveillance camera (100) according to the close-up information.

The object automatic tracking device 200 may be installed in a management server connected to the surveillance camera 100 through a wired / wireless network. At this time, the surveillance camera 100 uses an IP camera having an IP address, and a network video recorder (NVR) -based server is used as the management server.

Of course, the object automatic tracking device 200 may be installed in the surveillance camera 100 or may be installed in a communication terminal connected to the surveillance camera 100 through a wired / wireless network.

In other words, the surveillance camera 100 can be connected to a management server located at a remote location via a wired / wireless network. At this time, the surveillance camera 100 mainly takes only a photograph, and stores the image data on the management server side connected to each surveillance camera 100 via a wired / wireless network.

When the object automatic tracking device 200 is installed in a communication terminal or a management server, the object automatic tracking device 200 further includes a communication module 210 for transmitting / receiving data to / from the surveillance camera 100.

If necessary, the CCTV system according to the present invention includes a plurality of surveillance cameras 100, a communication terminal connected to each surveillance camera 100 via a wired / wireless network, and an object automatic tracking device 200 ) May be installed. At this time, one or more monitors may be connected to the management server so that image data generated by each surveillance camera 100 can be output.

Hereinafter, each component will be described in more detail with reference to the drawings.

FIG. 2 is a schematic view showing a surveillance region in which a region of interest is set, FIG. 3 is a view for explaining an image in which the reference region of FIG. 2 is photographed, FIG. 5 is a view for explaining an image in a state where an object entering the ROI is detected, and FIG. 6 is an enlarged view of a person entering the ROI.

Referring to FIG. 1, the CCTV system according to the present invention includes a surveillance camera 100.

The surveillance camera 100 is installed in a surveillance area S where continuous surveillance is required as shown in FIG. 2. The surveillance camera 100 generates video data by capturing an image of the surveillance area S, As shown in FIG.

Specifically, the surveillance camera 100 uses a PTZ (Pan Tilt Zoom) camera having a pan / tilt module and a zoom module for continuously tracking and photographing an object, It is better to use a speed dome camera. At this time, depending on the type of the surveillance camera 100, there may be a difference in angle of forward and backward, left and right rotation, and degree of zoom function.

Also, the surveillance camera 100 uses the PTZ coordinate value. Here, the PTZ coordinate value means coordinate values by three factors of pan, tilt, and zoom.

These fan coordinate values are coordinates for horizontally rotating left and right, and generally have coordinate values of 0 to 360 degrees. The tilt coordinate value is a coordinate for rotating forward and backward along the vertical axis, and generally has a coordinate value of 0 to 360 degrees. Finally, the zoom coordinate value is used to optically magnify an object and can be enlarged up to several tens of times depending on the performance of the surveillance camera 100. FIG.

In addition, the zoom coordinate value is obtained by equally dividing the screen into a predetermined size and setting a zoom magnification for each part in advance, so that when the object is captured at a position farthest from the shooting direction of the surveillance camera 100, And when the object is captured near the surveillance camera 100, the zoom of the camera is reduced. At this time, the previously set zoom magnification may be changed according to the place where the surveillance camera 100 is installed and the situation.

Meanwhile, when the object is not designated, the surveillance camera 100 photographs the moving image of the reference region, which is a space including the region of interest A, of the surveillance region S as shown in FIG. 3, As shown in FIG. 5, when an object designated as a target enters the region of interest A, an enlarged image of the object is captured while tracking the object to generate image data. At this time, the surveillance camera 100 photographs an enlarged image of the vehicle so that the license plate of the vehicle can be recognized when the object is a vehicle. When the object is a person, The enlarged image is photographed.

When the object automatic tracking device 200 is installed at a remote location, the surveillance camera 100 transmits image data to the object automatic tracking device 200 through a wired / wireless network, Signal.

The surveillance camera 100 basically enters the area of interest A and shoots an enlarged image of the object until the object designated as the target exits the surveillance area S. However, when the surveillance camera 100 exits the surveillance area S An enlarged image of another object may be photographed according to the selection of the manager.

Referring to FIG. 1, the CCTV system according to the present invention may further include a communication module 210.

The communication module 210 is provided to transmit and receive signals to and from the object automatic tracking device 200 and the surveillance camera 100 installed at a remote location. The communication module 210 transmits a wired / wireless network to the surveillance camera 100 installed in the surveillance area S And transmits / receives data to / from the surveillance camera 100.

Referring to FIG. 1, the CCTV system according to the present invention includes a user interface.

The user interface 220 is configured to set a region of interest A within the surveillance region S, and may be a mouse, a keyboard, a touch pad, or the like.

Here, the area of interest (A) is an area to be used as a reference for photographing an enlarged image of an object in the surveillance area (S), and can be set by the administrator through the user interface (220).

The user interface 220 inputs a selection signal of the second object from the manager so that the enlarged image of the second object located in the surveillance area S can be captured even before the arbitrary first object leaves the surveillance area S And provide it to the image analysis module 240.

If necessary, the user interface 220 can set the core area B in the surveillance area S in addition to the area of interest A from the manager. The core region B is a space located inside the surveillance region S and is located inside the region of interest A or outside the region of interest A as shown in FIG.

This core area B is the area with the highest importance among the surveillance area S and it is required to generate an enlarged image of the object in order to collect information (appearance, car number, etc.) of the entered object.

Referring to FIG. 1, the CCTV system according to the present invention includes a storage module 230.

The storage module 230 stores the close-up information in which the rotation angle and the zooming ratio of the surveillance camera 100 are set according to the coordinate value of the ROI A and stores the coordinate value information of the ROI A And stores the image received from the surveillance camera 100, and is connected to the control module 250 and the image analysis module 240.

Here, the zooming ratio can be adjusted according to the type of the object. For example, when the zoom ratio is set on the basis of an automobile because the size of the person and the vehicle are different from each other, the zoom of the surveillance camera 100 is adjusted to be reduced when the object is recognized as a person.

The storage module 230 includes all kinds of recording devices in which data that can be read by a computer is stored. More specifically, the storage module 230 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD A random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM) , A magnetic memory, a magnetic disk, or an optical disk may be used.

Referring to FIG. 1, the CCTV system according to the present invention includes an image analysis module 240.

The image analysis module 240 analyzes the image data received from the surveillance camera 100 and detects the object 10 entering the surveillance area S as shown in FIG. The object 20 which has entered the region of interest A among the located objects is secondarily detected and designated as a target. The image analysis module 240 analyzes real-time coordinate values of the object designated by the target 20 and extracts close-up information corresponding to the coordinate values from the storage module 230.

More specifically, the image analysis module 240 analyzes the image data to detect whether there is an object in the surveillance area S from the outside. Then, the image analysis module 240 tracks and designates an object entering the region of interest A as a target, extracts the characteristics of the object, temporarily stores the extracted feature in a buffer or a register, And analyzes coordinate values of the object.

If necessary, the image analysis module 240 analyzes the image data to determine whether the object is an object to be tracked. For example, when the object 20 designated as the target suddenly rotates or is hidden by another object and then reappears, the characteristic of the object extracted beforehand is compared with any first object located at the same or similar coordinate value as the existing object It is determined whether the first object is an object to be tracked. If it is determined that the first object is different from the object designated as the tracking target, the second object closest to the coordinate where the existing object is located is detected to determine whether the second object corresponds to the object to be tracked.

In addition, the image analysis module 240 tracks the movement of the object. Since the object can move, the image analysis module 240 tracks the movement of the object and analyzes the coordinates of the object in real time.

When the object is out of the surveillance area S or the object is not moving for a set time and is stopped, the image analysis module 240 ends the extraction of the close-up information for the object, Up information of the object from the storage module 230. At this time, the image analysis module 240 analyzes the image data generated during the rotation process to the initial position by the surveillance camera 100, and enlarges the first detected object through the image data among the objects that have entered inside the region of interest (A) Designate a new target to generate the image.

When the extraction of the close-up information for the object designated as the target is completed, the image analysis module 240 generates a rotation signal of the surveillance camera 100 so that the surveillance camera 100 can photograph the reference area described above, (250).

When the photographing time of the enlarged image is input through the user interface 220, the image analyzing module 240 photographs the enlarged image of the object for a preset time and then controls the surveillance camera 100 to rotate to the initial position And provides it to the control module 250.

Meanwhile, the image analysis module 240 may include an object recognition data table and an ambient object data table to distinguish the objects from the surrounding objects using the image data.

The object recognition data table is configured to store setting data for object shape detection, biometrics, and coordinate recognition in order to distinguish objects. At this time, the setting data for the shape sensing is setting data for recognizing a shape of a complex figure, such as a license plate of a vehicle, such as an automobile or a motorcycle, which is an object in which motion occurs. In addition, the setting data for biometrics is setting data for recognizing the eyes, nose, mouth, and the like based on the characteristics of the human body, particularly, the face of the human body.

The surrounding object data table is configured to store setting data for geographical information, shape detection, and coordinate recognition of surrounding objects so as to be able to distinguish surrounding objects in the image analysis module 240. At this time, the setting data for the geographical information of the surrounding object is setting data for the terrain, the ground, etc. of the predetermined area, and the setting data for the shape sensing corresponds to the setting data for the shape sensing of the object recognition data table.

In particular, setting data for coordinate recognition, which should be commonly recognized, is linked with virtual space coordinates or geographic information through the image data generated by the surveillance camera 100, So that the location can be grasped.

In addition, the image analysis module 240 extracts predetermined close-up information according to the coordinate value so that the enlarged image of the object can be captured according to the coordinate value of the object that has entered the region of interest (A). Here, the close-up information is a control signal designated to control the pan, tilting, and zoom of the surveillance camera 100 to preset values according to the coordinate values.

In addition, the image analysis module 240 analyzes the image data to specify the type of the object, and can change the close-up information so that the zoom-in position of the surveillance camera 100 is changed according to the object type. For example, when the outline of the object is analyzed as a person, the image analysis module 240 changes the close-up information so that the face is zoomed in on the full body of the person as shown in FIG. When the external shape of the object is analyzed as a vehicle through the image data including the image as shown in FIG. 7, the image analysis module 240 changes the close-up information so that the enlarged image of the license plate of the vehicle can be photographed as shown in FIG.

As described above, the image analysis module 240 corrects the close-up information so that the enlarged image is photographed on an element (face, license plate) most suitable for tracking the object in the future.

If necessary, the image analysis module 240 analyzes the image data and if an object passing through the region of interest A is read out of the surveillance region S, The image data of the object which does not enter the image data can be deleted. This is to minimize the capacity of the image data stored in the storage module 230 by deleting the image data for the object that does not enter the core area B having the highest security level.

Also, during the extraction of the close-up information of the first object designated as the target, the image analysis module 240 may detect that the first object leaves the surveillance area S even though the presence of the second object that has entered the area of interest A is detected Up information of the first object until the time when the first object is located.

When a selection signal for an object other than the object designated as the target among the objects located in the region of interest A is inputted through the user interface 220, the image analysis module 240 stops extracting the close-up information of the object designated as the target , And extracts close-up information of a new object to which the selection signal is input. Accordingly, the surveillance camera 100 generates image data of an enlarged image of an object designated as a target, and then generates image data of an enlarged image of a new object.

As such, the object that captures the magnified image may be selected by the administrator through the user interface 220. [

Referring to FIG. 1, the CCTV system according to the present invention includes a control module 250.

The control module 250 controls the operation of the surveillance camera 100 according to the close-up information extracted from the image analysis module 240 and receives image data from the surveillance camera 100 and stores the received image data in the storage module 230 And is connected to the image analysis module 240, the storage module 230, the user interface 220, and the communication module 210.

More specifically, the control module 250 generates a control signal based on the close-up information, provides the control signal to the surveillance camera 100 through the wired / wireless network, And controls the surveillance camera 100 to capture an enlarged image. When the video data of the object designated as the target is transmitted from the surveillance camera 100 to the control module 250, the control module 250 stores the video data in the storage module 230.

The control module 250 provides the image analysis module 240 with a selection signal of a new object through the user interface 220.

In addition, the control module 250 controls the surveillance camera 100 so that the surveillance camera 100 is rotated to the initial position when a rotation signal is transmitted from the image analysis module 240.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention as defined in the appended claims. It can be understood that it is possible.

100: Surveillance camera 200: Object automatic tracking device
210: communication module 220: user interface
230: storage module 240: image analysis module
250: Control module

Claims (6)

A user interface for setting a region of interest within the surveillance region;
Up information in which a zooming ratio adjusted according to a rotation angle of a surveillance camera and a type of an object is set according to a coordinate value of the ROI, stores coordinate value information of the ROI, A storage module for storing;
An image analyzing module for analyzing image data received from the surveillance camera to designate an object entering the ROI as a target, analyzing real-time coordinate values of the object, and extracting close-up information equivalent to the coordinate values; And
And a control module for providing the close-up information to the surveillance camera through a wired / wireless network and controlling the camera to photograph an enlarged image of the object in accordance with the movement of the object in a close-
The image analysis module extracts close-up information of a newly detected object through the image data from the storage module after finishing the close-up information extraction for the object if the object is not moving for a set time, Wherein the first object detected through the image data among the objects entering the inside of the ROI is designated as a new target for generating an enlarged image by analyzing the image data generated during the rotation process to the initial position, Gt; CCTV < / RTI > delete The apparatus of claim 1, wherein the image analysis module
Wherein the close-up information is changed so that the face is zoomed in close-up in a full body view of the person when the object is a person. The apparatus of claim 1, wherein the image analysis module
Up information of the first object until the first object is out of the surveillance area even if a second object that has entered the region of interest is detected while extracting the close-up information of the first object, The CCTV system comprising: The apparatus of claim 1, wherein the image analysis module
And generating a rotation signal for controlling the surveillance camera so as to rotate the mirror to an initial position after capturing an enlarged image of the object for a preset time when the photographing time of the enlarged image is inputted through the user interface, A CCTV system equipped with an automatic object tracking device. The apparatus of claim 1, wherein the image analysis module
Wherein when the selection signal of the object located in the region of interest is inputted in addition to the object designated as the target, extraction of the close-up information of the object designated as the target is stopped and the close-up information of the object to which the selection signal is inputted is extracted. Gt; CCTV < / RTI >

Images