KR20190092227A - System for Serarching Using Intelligent Analyzing Video - Google Patents

Abstract

According to one embodiment of the present invention, provided is a system for searching a real video and a recorded video by intelligent video analysis, which receives CCTV videos from a plurality of CCTV cameras; classifies and stores each CCTV video by channel; and applies a predetermined video analysis condition to the CCTV videos of the plurality of CCTV cameras to analyze videos of multiple channels at the same time, so as to search a search condition set as an event in a photographed CCTV video, and thus multiple channels can be searched at the same time and unnecessary manpower and time waste can be prevented.

Description

Real and recorded video retrieval system by intelligent video analysis {System for Serarching Using Intelligent Analyzing Video}

The present invention relates to a system for retrieving a real image and a recorded image using preset image analysis conditions. More particularly, the present invention relates to receiving a CCTV image from a plurality of CCTV cameras, classifying each CCTV image by channel, and storing the same. Random image condition as needed for video retrieval system by intelligent image analysis and multi-channel CCTV cameras by applying set image analysis condition to CCTV images of multiple CCTV cameras The present invention relates to a system for expressing images according to conditions in real time.

CCTV (Closed Circuit Television) is widely used for industrial, educational, medical, traffic control, disaster prevention, and in-house image information transmission. And since CCTV has proved to be effective in preventing crimes, suppressing crimes, finding criminals, ease of arrest, reducing anxiety of citizens, and supplementing limited police personnel, crimes have been established by installing CCTVs in hotspots such as alleys. Is preventing.

Therefore, CCTV has been installed and operated in many devices due to its effectiveness.

On the other hand, the CCTV system according to the prior art allows the image taken through the CCTV to be displayed on the monitor installed in the management center, such as building management office or police station.

Therefore, the CCTV system according to the prior art performs a visual search manually while replaying the recorded surveillance video so that the police or safety officers can analyze the incident and use it for collecting evidence after an accident or crime occurs. It takes a long time to find.

In order to solve such a long time image search, a conventional video player uses a double speed search function to play an image recorded at a speed of 2 times, 4 times, 8 times, 16 times, etc. Finding the scene.

However, when using the double speed search function, the desired scene may be excessive, and screen truncation may occur, thereby preventing proper image search.

Republic of Korea Patent Publication No. 10-2017-0096838

An object of the present invention is to receive a CCTV image from a plurality of CCTV cameras, and to classify and store each CCTV image by channel, and to apply a predetermined video analysis condition to the CCTV image of a plurality of CCTV cameras to simultaneously display a multi-channel image The present invention provides a system for retrieving real and recorded video by intelligent video analysis.

Another object of the present invention is to provide an image analysis condition to a plurality of cameras in order to search for CCTV camera images in real time by intelligent video analysis to display a plurality of CCTV camera images in accordance with the conditions on a monitor in real time The present invention provides a real image and a recorded image retrieval system.

In order to solve the above problems,

According to an embodiment of the present invention, a real image and a recorded image retrieval system using intelligent image analysis may include a plurality of CCTV (Closed Circuit Television) cameras for capturing images from different locations; And

A CCTV image database unit for receiving a CCTV image to be periodically or aperiodically transmitted from the plurality of CCTV cameras, and classifying and storing each CCTV image by each CCTV camera, and a photographed object type, an object color option, and a vehicle number. A user interface for providing a setting menu for inputting one or more image analysis conditions or emergency event detection conditions among the options; and a CCTV image of each CCTV camera stored in the CCTV image database unit according to the input image analysis conditions. An image retrieval server having a control unit which analyzes the images at the same time by applying all of them;

Including,

The setting menu may include an object type including a check box for checking a person, a vehicle, and an event function;

An event setting including an image analysis option for setting at least one image analysis condition and an emergency function option for setting an emergency event detection condition for detecting a specific event using the image analysis condition;

An object color option comprising a check box for recognizing the object color and a selection menu for selecting the object color;

A vehicle number option comprising a check box for performing a vehicle number search and keyword input means for inputting a vehicle number;

An emergency function mode of capturing an event image to correspond to the emergency event detection condition;

An image analysis mode comprising a check box for performing a stop function upon object recognition; And

An event list comprising a check box for performing initialization when the image analysis starts;

Including;

The emergency event detection conditions are set by using the setting menu, and added to the local conditions applied to the CCTV camera of the desired area,

The emergency event detection condition includes one or more condition information among an object type set in the setting menu, the event setting, the object color option, the vehicle number option, the image analysis mode, and a setting menu of the event list.

The image search server sets the emergency event detection condition through the setting menu before using the emergency function mode, periodically determines whether the emergency function mode is activated, and if the emergency function mode is activated, the emergency event. Search for a detection condition, generate an image processing signal according to the detected emergency event detection condition and transmit it to a control module for controlling the plurality of CCTV cameras, and emergency to display different colors in the area where the emergency event detection condition is set Monitoring unit;

If the check box of the vehicle number search is checked, the image processing unit for receiving the image image from the CCTV image database unit to determine the position of the license plate by clustering of numbers; And

A number recognition unit for correcting the license plate extracted from the license plate area determined by the image processor and recognizing a number from the license plate;

More,

The image search server is collectively applied to the plurality of CCTV cameras linked, when the image analysis condition or the emergency event detection condition is selected,

The control module for controlling each CCTV camera takes an image in a general mode without capturing an event image at ordinary times, and when an image processing signal including the emergency event detection condition is received, an event according to the emergency event detection condition Image capturing is performed, and the event image capturing is performed to correspond to at least one condition information among an object type, an event setting, an object color option, a vehicle number option, an image analysis mode, and an event list set in the image analysis condition.

The controller receives an image image captured by the vehicle black box, stores the image in the CCTV image database, sets the image analysis condition with respect to the stored image image, and analyzes the image information according to the set image analysis condition. ,

The image search server sequentially displays the first CCTV image searched according to the first video analysis condition, the second CCTV video searched according to the second video analysis condition, and the third CCTV video searched according to the third video analysis condition. The display may be controlled by screen division, and the first image analysis condition, the second image analysis condition, and the third image analysis condition may be differently set by the image analysis condition or the emergency event detection condition.

Such solutions will become more apparent from the following detailed description for carrying out the invention according to the accompanying drawings.

Prior to this, the terms or words used in this specification and claims should not be interpreted in a conventional and dictionary sense, and the inventors will be required to properly define the concepts of terms in order to best describe their invention. On the basis of the principle that it can be interpreted as meaning and concept corresponding to the technical idea of the present invention.

According to an embodiment of the present invention, by searching a search condition set as an event in the captured CCTV image, it is possible to simultaneously search for multiple channels, and there is an effect of preventing unnecessary manpower and time consumption.

1 is a block diagram of a system for retrieving a real image and a recorded image by intelligent image analysis according to an embodiment of the present invention.
2 is a block diagram schematically illustrating an internal configuration of an image search server according to an exemplary embodiment of the present invention.
3 is a view showing the configuration of a setting menu according to an embodiment of the present invention.
4 is a diagram illustrating an example of object color recognition and vehicle number search according to an embodiment of the present invention.
5 is a view showing a state in which the CCTV image searched for the display unit is output according to an embodiment of the present invention.
6 is a view showing an example of a screen configuration that can simultaneously retrieve CCTV images from a plurality of CCTV cameras according to an embodiment of the present invention.
7 is a view showing a state of analyzing an image of the black box according to an embodiment of the present invention.
8 is a view showing a state in which an emergency monitoring zone is applied according to an embodiment of the present invention.

Specific aspects and specific technical features of the present invention will become more apparent from the following detailed description and embodiments related to the accompanying drawings. In the present specification, in adding reference numerals to the components of each drawing, it should be noted that the same reference numerals are used to refer to the same components, even if displayed on different drawings. In addition, in describing an embodiment of the present invention, when it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description thereof will be omitted.

In addition, in describing the components of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are only to distinguish the components from other components, and the nature, order, order, etc. of the components are not limited by the terms. If a component is described as being "connected", "coupled" or "connected" to another component, that component may be directly connected or connected to that other component, but there may be another configuration between each component. It is to be understood that the elements may be "connected", "coupled" or "connected".

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

As shown in FIGS. 1 and 2, the real image and recorded image retrieval system 100 by intelligent image analysis according to an embodiment of the present invention is connected to the image retrieval server 200 and connected to the image at different locations. Consists of a plurality of CCTV (Closed Circuit Television) camera 300 to shoot the.

The image retrieval server 200 of the present invention includes an image storage unit 210, a user interface unit 220, a control unit 230, an image processing unit 240, a number recognition unit 250, a display unit 260, and emergency monitoring. The unit 270 includes an arbitrary image analysis condition input unit 280, an arbitrary image analysis transmission unit 282, and an arbitrary condition image display unit 290.

The image storage unit 210 includes a CCTV image database unit 212 and an event database unit 214.

The image storage unit 210 receives CCTV images transmitted periodically or aperiodically from a plurality of closed circuit television (CCTV) cameras 300, and classifies each CCTV image into channels to the CCTV image database unit 212. Save it. Here, the channel means each CCTV camera 300 for transmitting CCTV images.

The user interface 220 is an input interface such as a keyboard, a mouse, and a touch screen formed in the user terminal, and receives an image analysis condition of an image to be analyzed through this.

The user interface 220 provides a setting menu for inputting an image analysis condition or an emergency event detection condition.

As shown in FIG. 3, the setting menu according to an embodiment of the present invention is provided as a screen of the user interface unit 220. Object type 221, event setting 222, object color option 223, vehicle number option 224, image analysis mode 225, setting menu of event list 226, image analysis start button 227, Emergency function mode 228 is included.

The object type 221 consists of a check box for checking the function of the person 221a, the vehicle 221b, the other 221c, and the event 221d. The object color option 223 checks to recognize the object color. A box 223a, and a selection menu 223b for selecting the object color.

The vehicle number option 224 includes a check box 224a for performing a vehicle number search and keyword input means 224b for inputting a vehicle number.

When the check box 224a of the vehicle number search is checked, the image processor 240 receives the image image from the CCTV image database unit 212 and determines the position of the license plate by clustering of numbers.

The number recognition unit 250 corrects the license plate extracted from the vehicle license plate area determined by the image processor 240 and recognizes the number from the license plate.

As shown in FIG. 4, for example, when 'blue' is designated as the object color option 223, a vehicle having blue may be extracted.

The image analysis mode 225 includes a check box 225a for performing a stop function when recognizing an object, and the event list 226 includes a check box 226a for performing initialization at the start of image analysis.

The event setting 222 includes a setting option 222a including an image analysis option for setting an image analysis condition as an event and an emergency function option for setting an emergency event detection condition as an event.

When the image analysis condition is received through the setting menu of the user interface 220, the controller 230 sets all the received image analysis conditions to a plurality of CCTV images stored in the CCTV image database unit 212 to establish a multi-channel. Simultaneously analyze the image.

The control unit 230 searches for CCTV images of each CCTV camera 300 stored in the CCTV image database unit 212 according to image analysis conditions, and classifies the searched CCTV images by channel (by CCTV) for an event database. The data may be stored in the unit 214 or output through the display unit 260 as shown in FIG. 5.

When the image search server 200 of the present invention selects a keyword input, a color selection, and an object type as an image analysis condition, the image search server 200 may be collectively applied to all the CCTV cameras 300 to be linked.

The image retrieval server 200 detects illegal intruders, detects prone areas, detects illegal parking, border or safety line violations, reverse driving vehicle detection, theft detection, unauthorized dumping objects, classifies and detects objects in the image, etc. Image analysis function can be performed.

As shown in FIG. 6, the controller 230 according to an embodiment of the present invention simultaneously retrieves CCTV images of up to four CCTV cameras 300 through the display unit 260 and displays the screen on the display unit 260. The output can be divided and can be searched quickly by supporting x2, x4 and x8 speeds for each camera.

As shown in FIG. 7, the control unit 230 supports an image format (AVI, MP4, etc.) photographed in a vehicle black box, and receives the image image photographed in the vehicle black box. After storing and setting the image analysis condition through the setting menu, the image information may be analyzed according to the set image analysis condition.

The emergency monitoring unit 270 periodically determines whether an emergency function mode for capturing an event image is activated according to the emergency event detection condition, and when the emergency function mode is activated, searches for an emergency event detection condition and applies the detected emergency event detection condition. Accordingly, the image processing signal is generated and transmitted collectively to a control module (not shown) that controls the plurality of CCTV cameras 300.

Before using the emergency function mode, the emergency event detection condition can be set through the setting menu or the function menu.

Emergency event detection conditions can be set using a setting menu, in addition to the addition of the local conditions can be applied to the emergency event detection conditions to the CCTV camera 300 of the desired area.

When the control module of each CCTV camera 300 receives an image processing signal including an emergency event detection condition, the control module of the CCTV camera 300 performs event image capture corresponding to the emergency event detection condition.

In other words, as shown in Figure 8, the control module of each CCTV camera 300 is to shoot the video signal in two modes, usually do not take the event video recording in normal mode to shoot the image, emergency event When the image processing signal including the detection condition is received, the event image photographing is performed by displaying a different color in an area where the emergency event detection condition is set according to the emergency event detection condition.

The event image shooting is a setting menu of an object type 221, an event setting 222, an object color option 223, a vehicle number option 224, an image analysis mode 225, and an event list 226 set in a setting menu. Photographing is performed so as to correspond to one or more pieces of condition information.

Meanwhile, the controller 230 according to an embodiment of the present invention may search for the first CCTV image searched according to the first video analysis condition, the second CCTV video searched according to the second video analysis condition, and the third video search condition searched according to the second video analysis condition. 3 CCTV images can be controlled to be displayed in a screen division on the display unit 260 in sequence.

Here, the first image analysis condition, the second image analysis condition, and the third image analysis condition indicate image analysis conditions that are differently set through the setting menu.

The arbitrary image analysis condition input unit 280 receives a CCTV image transmitted periodically or aperiodically from the plurality of CCTV cameras in a real image and a recorded image retrieval system using intelligent image analysis, and performs an arbitrary image analysis condition on a real time image. It performs the function of granting.

The random image analysis transmitter 282 transmits the random image analysis condition to the user interface 220 in real time.

The arbitrary condition image display unit 290 detects and displays an image matching the condition on the screen according to the arbitrary image analysis condition.

Although the present invention has been described in detail with reference to one embodiment, this is to explain the present invention in detail, and the real image and the recorded image retrieval system by intelligent image analysis according to the present invention are not limited thereto. The terms "comprise", "comprise", or "have" described above mean that a corresponding component may be included unless specifically stated to the contrary, and therefore, excludes other components. Rather, it should be construed that it may further include other components, all terms including technical or scientific terms are to be generally understood by one of ordinary skill in the art unless otherwise defined Has the same meaning as

In addition, the above description is merely illustrative of the technical idea of the present invention, and those skilled in the art to which the present invention pertains various modifications and variations without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention but to describe the present invention, and the scope of the technical idea of the present invention is not limited by the one embodiment. The protection scope of the present invention should be interpreted by the following claims, and all technical ideas within the equivalent scope should be interpreted as being included in the scope of the present invention.

100: video search system 200: video search server
210: video storage unit 212: CCTV video database unit
214: event database unit 220: user interface unit
221: Object type 221a: person
221b: vehicle 221c: other
221d: Event 222: Event Settings
222a: setup options 223: object color options
223b: Select Menu 224: Car Number Options
225: video analysis mode 226: event list
227: start image analysis button 228: emergency function mode
230: control unit 240: image processing unit
250: number recognition unit 260: display unit
270: emergency monitoring unit 300: CCTV camera

Claims (3)

A plurality of CCTV cameras for capturing images at different positions; And
A CCTV image database unit for receiving a CCTV image to be periodically or aperiodically transmitted from the plurality of CCTV cameras, and classifying and storing each CCTV image by each CCTV camera, and a photographed object type, an object color option, and a vehicle number. A user interface for providing a setting menu for inputting one or more image analysis conditions or emergency event detection conditions among the options; and a CCTV image of each CCTV camera stored in the CCTV image database unit according to the input image analysis conditions. An image retrieval server having a control unit which analyzes the images at the same time by applying all of them;
Including,
The setting menu may include an object type including a check box for checking a person, a vehicle, and an event function;
An event setting including an image analysis option for setting at least one image analysis condition and an emergency function option for setting an emergency event detection condition for detecting a specific event using the image analysis condition;
An object color option comprising a check box for recognizing the object color and a selection menu for selecting the object color;
A vehicle number option comprising a check box for performing a vehicle number search and keyword input means for inputting a vehicle number;
An emergency function mode of capturing an event image to correspond to the emergency event detection condition;
An image analysis mode comprising a check box for performing a stop function upon object recognition; And
An event list comprising a check box for performing initialization when the image analysis starts;
Including;
The emergency event detection conditions are set by using the setting menu, and added to the local conditions applied to the CCTV camera of the desired area,
The emergency event detection condition includes one or more condition information among an object type set in the setting menu, the event setting, the object color option, the vehicle number option, the image analysis mode, and a setting menu of the event list.
The image search server sets the emergency event detection condition through the setting menu before using the emergency function mode, periodically determines whether the emergency function mode is activated, and if the emergency function mode is activated, the emergency event. Search for a detection condition, generate an image processing signal according to the detected emergency event detection condition and transmit it to a control module for controlling the plurality of CCTV cameras, and emergency to display different colors in the area where the emergency event detection condition is set Monitoring unit;
If the check box of the vehicle number search is checked, the image processing unit for receiving the image image from the CCTV image database unit to determine the position of the license plate by clustering of numbers; And
A number recognition unit for correcting the license plate extracted from the license plate area determined by the image processor and recognizing a number from the license plate;
More,
The image search server is collectively applied to the plurality of CCTV cameras linked, when the image analysis condition or the emergency event detection condition is selected,
The control module for controlling each CCTV camera takes an image in a general mode without capturing an event image at ordinary times, and when an image processing signal including the emergency event detection condition is received, an event according to the emergency event detection condition Image capturing is performed, and the event image capturing is performed to correspond to at least one condition information among an object type, an event setting, an object color option, a vehicle number option, an image analysis mode, and an event list set in the image analysis condition.
The controller receives an image image captured by the vehicle black box, stores the image in the CCTV image database, sets the image analysis condition with respect to the stored image image, and analyzes the image information according to the set image analysis condition. ,
The image search server sequentially displays the first CCTV image searched according to the first video analysis condition, the second CCTV video searched according to the second video analysis condition, and the third CCTV video searched according to the third video analysis condition. The intelligent image analysis is performed by controlling the display to be divided by the screen, and setting the first image analysis condition, the second image analysis condition, and the third image analysis condition differently according to the image analysis condition or the emergency event detection condition. Video and recorded video search system.
The method according to claim 1,
The video search server,
An arbitrary image analysis condition input unit configured to receive a CCTV image transmitted periodically or aperiodically from the plurality of CCTV cameras and to assign a certain image analysis condition to a real-time image;
An arbitrary image analysis transmission unit configured to transmit an arbitrary image analysis condition to a user interface unit in real time; And
An arbitrary condition image display unit configured to detect an image corresponding to the condition and display the image according to the arbitrary image analysis condition;
Real and recorded video retrieval system by intelligent video analysis further comprising a.
The method according to claim 1,
The control unit searches the real-time and recorded video search system by intelligent video analysis, characterized in that the control to search for the CCTV video of the four CCTV cameras searched according to the video analysis conditions to display the screen divided by the display unit.

Images