KR20150102286A - video surveillance system and method - Google Patents

Abstract

Disclosed are a video surveillance system and a method thereof. A video surveillance system according to the present invention includes at least one first camera which is fixed to photograph an image in a corresponding direction and recognizes an object from at least one key frame including the object among photographed images; a second camera which is rotatable, magnifies the object recognized by the first camera, and photographs the magnified image; and a data base part which receives the image photographed by the first camera and the magnified image photographed by the key frame and the second camera from the first camera and the second camera and stores the same.

Description

Technical Field [0001] The present invention relates to a video surveillance system and method,

The present invention relates to a video surveillance system and method, and more particularly, to a video surveillance system and method, in which a video camera and a key frame, which are captured in various directions using a first camera for capturing an image in a corresponding direction and a second camera, By enlarging the object recognized in the key frame and acquiring the enlarged image, the captured object can be clearly recognized, and the speed is improved by distributing the throughput to at least one of the first camera and the second camera, And more particularly, to a video surveillance system and a video surveillance method capable of performing a quick search of an image and an enlarged image.

Various types of security monitoring systems and monitoring devices have been developed and used to protect public or private property. The most commonly used system is to install equipment such as Closed Circuit Television (CCTV) in a place where security is required, and the situation of the place is recorded as video through the equipment, There is a video surveillance system that can check the image of the time of the incident or accident.

Such a conventional video surveillance system is dependent on the performance of the video recording server since processing and storage of images, key frames, and the like are performed in the video recording server in which video is recorded. Therefore, if the throughput of the video recording server increases, the speed of the video surveillance system as a whole slows down.

In addition, in the conventional video surveillance system, when the resolution of the camera itself is not high, it is difficult to identify the object captured on the camera, so that it is often difficult to solve the incident or accident. However, in order to solve such a problem, when all of the cameras installed in the video surveillance system are installed with high resolution cameras, a system having a high resolution is required to process the image and the storage device is required to store a large amount of data. There was a problem of rising.

SUMMARY OF THE INVENTION It is an object of the present invention to provide an image capturing apparatus and a method of capturing an image and a key frame captured in various directions using a first camera for capturing an image in a predetermined direction and a second camera arranged for rotation, By enlarging the object and acquiring the enlarged image, the captured object can be clearly recognized, and the speed is improved by distributing the throughput to at least one of the first camera and the second camera, And a video surveillance system and method capable of performing quick search of an enlarged image.

According to an embodiment of the present invention, an image surveillance system is provided with a fixed direction and captures an image in a corresponding direction, and at least one or more images, which recognize the object from one or more key frames, 1 camera; A second camera arranged to be rotatable and adapted to magnify the object recognized by the first camera to photograph an enlarged image; And a database unit receiving and storing the image captured by the first camera, the key frame, and the enlarged image captured by the second camera, from the first camera and the second camera.

The second camera tracks the object while rotating, and when the face of the object is confirmed, the second camera enlarges the object and photographs the enlarged image.

The first camera may extract feature points of the object from the key frame.

The database unit may store minutiae points of the object corresponding to each key frame.

The video surveillance system may further include a playback unit that plays back the image captured by the first camera, the key frame, and the enlarged image captured by the second camera.

The video surveillance system may further include a search unit for searching for a key frame including an object having a minutiae corresponding to the image search condition when an image search condition is input by a user's input. In this case, the reproducing unit may reproduce the image or the enlarged image from the key frame retrieved by the retrieving unit.

The video surveillance system includes: a picture storage unit for storing one or more pictures; And comparing the at least one photograph and the image photographed by the first camera or the enlarged image photographed by the second camera so that the photographed object among the at least one photograph matches the object of the image or the magnified image And a photograph comparing unit for checking whether there is a photograph and providing a result.

The first camera includes: a first photographing unit that photographs an image; A first controller for recognizing the object from one or more key frames including the object among the captured images; And a transmitting unit transmitting the image and the key frame to the database unit and transmitting an enlarged photographing command to enlarge and photograph the object.

The second camera includes: a second photographing unit for photographing an image; A communication unit for receiving the enlarged photographing instruction and transmitting the enlarged image to the database unit; And a second control unit for controlling the second photographing unit to photograph the enlarged image by enlarging the object recognized by the first camera by the received enlarged photographing command.

The first camera includes a first storage unit for storing images and key frames to be captured when communication with the database unit is impossible; And a first emergency power source for supplying an emergency power source when the power source is cut off.

Wherein the second camera further comprises: a second storage unit for storing a magnified image to be photographed when communication with the database unit is impossible; And a second emergency power source unit for supplying the emergency power source when the power source is shut off.

According to an embodiment of the present invention, an image surveillance method comprises: capturing an image in one direction by at least one first camera arranged in a fixed direction; The first camera recognizing the object from one or more key frames including an object of the image; Enlarging the object recognized by the first camera and photographing an enlarged image; And a database receiving and storing the image captured by the first camera, the key frame, and the enlarged image captured by the second camera from the first camera and the second camera.

The step of photographing the enlarged image may include: tracking the object while the second camera rotates; And if the face of the object is detected, the second camera magnifies the object and photographs the magnified image.

The video surveillance method may further include the step of the first camera extracting the minutiae point of the object from the key frame.

The video surveillance method may further include storing the minutiae points of the object corresponding to the key frame, respectively, by the database unit.

The video surveillance method may further include a step in which the playback unit reproduces the image captured by the first camera, the key frame, and the enlarged image captured by the second camera.

The video surveillance method may further include searching the key frame including the object having the minutiae corresponding to the image retrieval condition when the image retrieval condition is inputted according to the input of the user. In this case, the reproducing unit may reproduce the image or the enlarged image from the key frame retrieved by the retrieving unit.

The video surveillance method includes: storing one or more pictures; And comparing the at least one photograph and the image photographed by the first camera or the enlarged image photographed by the second camera so that the photographed object among the at least one photograph matches the object of the image or the magnified image Checking whether there is a photograph, and providing a result.

According to an aspect of the present invention, there is provided an image capture device including: an image captured in various directions using a first camera that captures an image in a predetermined direction and a second camera that is rotatably disposed, a key frame, By enlarging the recognized object and acquiring the magnified image, the photographed object can be clearly recognized, and the speed is improved by distributing the throughput to at least one of the first camera and the second camera, It is possible to provide a video surveillance system and method capable of performing quick search of a video image and an enlarged video image.

1 is a schematic view of a video surveillance system according to an embodiment of the present invention.
2 is a diagram illustrating an example of a configuration of a first camera and a second camera in a video surveillance system according to an embodiment of the present invention.
3 is a flowchart illustrating a video surveillance method according to an embodiment of the present invention.

The present invention will now be described in detail with reference to the accompanying drawings. Hereinafter, a repeated description, a known function that may obscure the gist of the present invention, and a detailed description of the configuration will be omitted. Embodiments of the present invention are provided to more fully describe the present invention to those skilled in the art. Accordingly, the shapes and sizes of the elements in the drawings and the like can be exaggerated for clarity.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise.

Further, the term "part" in the description means a unit for processing one or more functions or operations, which may be implemented by hardware, software, or a combination of hardware and software.

1 is a schematic view of a video surveillance system according to an embodiment of the present invention.

1, a video surveillance system according to an exemplary embodiment of the present invention includes at least one first camera 110, a second camera 120, a database unit 130, a playback unit 140, and a search unit 150 ). ≪ / RTI > The video surveillance system 100 shown in FIG. 1 is according to one embodiment, and the blocks shown in FIG. 1 are not all blocks are mandatory components, and in some embodiments some of the blocks may be added, changed or deleted .

Here, the database unit 130, the playback unit 140, and the search unit 150 may be implemented in the form of a server device or a client device, or may be included in a server device or a client device. The server device or client device may be one or more of a server computer, a personal computer, a smart phone, a personal digital assistant (PDA), a tablet computer, and a laptop computer.

The first camera 110 captures an image in a predetermined direction and recognizes the object from one or more key frames including the object among the captured images. In FIG. 1, the first camera 110 is shown as four, but this is according to the embodiment, and may be three or less or five or more as necessary. The first camera 110 is fixedly disposed so that its direction can not be adjusted, so that only the image in the corresponding direction can be captured. Each of the first cameras 110-1, 110-2, 110-3, and 110-4 is installed so that there is no blind spot in the corresponding place, and can photograph the corresponding place in each direction. The key frame is a frame including an object, and may be an image captured by the first camera 110 according to a predetermined time period. The object may be a moving object such as a person, an animal, or a car.

In one embodiment, the first camera 110 may extract feature points of the object from the key frame. The feature point may be a color or a pattern of a top or bottom of a person, if the object is a person. In this case, the database unit 130 may store minutiae points of the object corresponding to the key frames.

The second camera 120 is rotatably disposed to magnify the object recognized by the first camera 110 to photograph an enlarged image. The second camera 120 can freely rotate in various directions and can be enlarged, and can be freely enlarged and photographed at any place of the installed location. In one embodiment, when the object is a human being or an animal, the second camera 120 may track the object while rotating, and if the face of the object is confirmed, the second camera 120 may magnify the object to take the magnified image. As described above, the video surveillance system 100 according to an embodiment of the present invention can easily check the object by capturing an enlarged image of the object by the second camera 120.

The database unit 130 stores the image captured by the first camera 110 and the key frame and the enlarged image captured by the second camera 120 from the first camera 110 and the second camera 120 And stores it. In one embodiment, the database unit 130 may be configured as a storage device for storing various data. For example, the database unit 130 may be a storage device such as a hard disk drive.

The playback unit 140 plays back the image captured by the first camera 110, the key frame, and the enlarged image captured by the second camera 120. The reproducing unit 140 reproduces the image, the key frame, and the enlarged image and provides the reproduced image to the user so that the user can check the image or enlarged image when an event or an accident occurs at the place.

The search unit 150 searches for a key frame including an object having a minutia corresponding to the image search condition when an image search condition is input in response to a user's input. As described above, the first camera 110 extracts the minutiae points of the object from the key frame, and the database unit 130 stores the minutiae points of the object corresponding to the respective key frames. Accordingly, when the image retrieval condition is inputted by the user, the retrieval unit 150 searches for a key frame including an object having a minutia corresponding to the image retrieval condition. The reproduction unit 140 reproduces the image or the enlarged image from the key frame searched by the search unit 150. [ For example, when the user sets a blue checkered image and a white bottom under the image search condition, the search unit 150 searches for a key frame including an object having a feature point matching the condition, and the playback unit 140 Reproduces the image or the enlarged image from the searched key frame. As described above, the video surveillance system 100 according to an embodiment of the present invention can search for images by inputting image search conditions, so that it is possible to search for images conveniently and quickly.

The photograph storage unit 160 and the photograph comparing unit 170 may be configured to check if a specific person such as a child or a suspect is photographed in an image or an enlarged image photographed by the first camera 110 and the second camera 120 .

The picture storage unit 160 stores one or more pictures. Here, the one or more photographs may be photographs in which a specific person such as a child or an incident suspect is photographed.

The photograph comparator 170 compares the at least one photograph and the image photographed at the first camera 110 or the enlarged image photographed at the second camera 120, Whether or not there is a picture matching the object of the image or the enlarged image, and provides a result. Here, the image captured by the first camera 110 or the enlarged image captured by the second camera 120 used for comparison may be provided directly by the first camera 110 or the second camera 120, And may be provided in the database unit 130. In one embodiment, the photograph comparing unit 170 can check whether or not the objects are matched by comparing the minutiae points of the object extracted from the first camera 110 with the minutiae points of the photographic object.

2 is a diagram illustrating an example of a configuration of a first camera and a second camera in a video surveillance system according to an embodiment of the present invention.

2, a first camera 110 of a video surveillance system according to an embodiment of the present invention includes a first photographing unit 111, a first control unit 112, a transmitter 113, a first storage unit 114 and a first emergency power supply unit 115. [ The first camera 110 shown in FIG. 2 is according to one embodiment, and the blocks shown in FIG. 2 are not all blocks are mandatory components, and in some embodiments some of the blocks may be added, changed or deleted .

The first photographing unit 111 photographs an image. In the case of the first camera 110, since the direction is fixed, the first photographing unit 111 is fixed in the corresponding direction and photographs the image in the corresponding direction.

The first controller 112 recognizes the object from one or more key frames including the object among the captured images. Also, in one embodiment, the first controller 112 may extract feature points of the object from the key frame.

The transmitting unit 113 transmits the image and the key frame to the database unit 130 and transmits an enlarged photographing instruction to the second camera 120 to enlarge and photograph the object. In one embodiment, when there is a wireless communication function, the transmission unit 113 can communicate via wireless communication such as mobile communication, Wi-Fi, Bluetooth, etc., and can use the wireless communication function It can communicate via wired communication such as USB (Universal Serial Bus) or Ethernet (Ethernet).

The first storage unit 114 stores images and key frames to be photographed when communication with the database unit 130 is not possible. When the communication with the database unit 130 is restored and communication becomes possible again, the stored image and key frame are transmitted to the database unit 130 through the transmission unit 113.

The first emergency power supply unit 115 supplies the emergency power supply when the power supply is cut off. In one embodiment, the first emergency power supply unit 115 may be configured as an uninterruptible power supply system (UPS).

The first storage unit 114 and the first emergency power supply unit 115 may be provided to prevent the storage of images photographed through the first camera 110 from being interrupted even when an error occurs in the system.

2, the second camera 120 of the video surveillance system according to an embodiment of the present invention includes a second photographing unit 121, a communication unit 122, a second control unit 123, a second storage unit 124 and a second emergency power source unit 125. [ The second camera 120 shown in FIG. 2 is according to one embodiment, and the blocks shown in FIG. 2 are not all blocks are mandatory components, and in some embodiments some of the blocks may be added, changed or deleted .

The second photographing unit 121 photographs an image. In the case of the second camera 120, since the rotation and enlargement are possible, the second photographing unit 121 rotates or magnifies the direction to photograph the image.

The communication unit 122 receives the enlarged image capturing command transmitted from the first camera 110 and transmits the enlarged image to the database unit 130. [ In one embodiment, when the communication unit 122 has a wireless communication function, the communication unit 122 can communicate through wireless communication such as mobile communication, Wi-Fi, and Bluetooth. When the wireless communication function is not used or the wireless communication function is not used, It can communicate via wired communication such as USB or Ethernet.

The second control unit 123 controls the second photographing unit 121 to enlarge the object recognized from the first camera 110 by the received enlarged photographing instruction and photograph the enlarged image. In addition, in one embodiment, the second control unit 123 tracks the object while the second photographing unit 121 rotates, and when the face of the object is confirmed, the second control unit 123 enlarges the object, 2 photographing unit 121 can be controlled.

The second storage unit 124 stores a magnified image to be photographed when communication with the database unit 130 is impossible. When communication with the database unit 130 is restored and communication becomes possible again, the stored enlarged image is transmitted to the database unit 130 through the communication unit 122.

The second emergency power source unit 125 supplies the emergency power source when the power source is cut off. In one embodiment, the second emergency power supply section 125 may be configured as a UPS.

The second storage unit 124 and the second emergency power supply unit 125 may be provided to prevent the storage of the image photographed through the second camera 120 from being interrupted even when an error occurs in the system.

3 is a flowchart illustrating a video surveillance method according to an embodiment of the present invention.

Referring to FIG. 3, when the video surveillance method according to an embodiment of the present invention is started, at least one first camera arranged in a fixed direction captures an image in a corresponding direction (S201) And recognizes the object from one or more key frames included (S202).

Then, the second camera arranged to be rotatable magnifies the object recognized by the first camera and shoots an enlarged image (S203). In step S203, if the face of the object is detected by tracking the object while the second camera rotates, the second camera may magnify the object to photograph the magnified image.

After the second camera has taken an enlarged image (S203), the database stores the image captured by the first camera, the key frame, and the enlarged image captured by the second camera in the first camera and the second camera (S204).

The reproducing unit reproduces the image captured by the first camera, the key frame, and the enlarged image captured by the second camera (S205).

In one embodiment, after step S202, the first camera extracts minutiae points of the object from the key frame (S206), and the database stores the minutiae points of the object corresponding to the respective key frames (S207 ).

Then, when a user inputs an image search condition, the search unit searches for a key frame including an object having a minutia corresponding to the image search condition (S208). The reproducing unit reproduces the image or the enlarged image from the key frame retrieved by the retrieving unit (S209).

In one embodiment, the video surveillance method further comprises the steps of: storing one or more photographs; comparing the at least one photograph and the image photographed by the first camera or the enlarged image photographed by the second camera; And checking whether there is a photograph in which at least one of the at least photographs matches the object of the image or the enlarged image, and providing a result. Through this process, when a specific person such as a child or a suspect is photographed in an image or an enlarged image photographed by the first camera and the second camera, it can be confirmed.

The video surveillance method shown in FIG. 3 is similar to the video surveillance system according to an embodiment of the present invention shown in FIGS. 1 and 2, so that the description of FIGS. 1 and 2 The detailed description will be omitted. In Fig. 3, as in Figs. 1 and 2, each step of the flowchart shown in Fig. 3 is not a necessary step in all steps, and in other embodiments, some steps may be added, changed or deleted.

The above-described video surveillance method has been described with reference to the flowcharts shown in the drawings. While the above method has been shown and described as a series of blocks for purposes of simplicity, it is to be understood that the invention is not limited to the order of the blocks, and that some blocks may be present in different orders and in different orders from that shown and described herein And various other branches, flow paths, and sequences of blocks that achieve the same or similar results may be implemented. Also, not all illustrated blocks may be required for implementation of the methods described herein.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be taken as limitations. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

110: First camera
120: Second camera
130:
140:
150:
160:
170:

Claims (18)

At least one first camera for capturing an image in a predetermined direction and recognizing the object from one or more key frames including an object among the captured images;
A second camera arranged to be rotatable and adapted to magnify the object recognized by the first camera to photograph an enlarged image; And
And a database unit for receiving and storing the image captured by the first camera, the key frame, and the enlarged image captured by the second camera from the first camera and the second camera, . The method according to claim 1,
Wherein the second camera comprises:
Wherein when the face of the object is detected by tracking the object while rotating, the object is magnified to photograph the magnified image. The method according to claim 1,
Wherein the first camera comprises:
And extracts feature points of the object from the key frame. The method of claim 3,
The database unit,
And stores the minutiae points of the object corresponding to each of the key frames. 5. The method of claim 4,
Further comprising: a playback unit for playing back the image captured by the first camera, the key frame, and the enlarged image captured by the second camera. 6. The method of claim 5,
Further comprising a search unit for searching for a key frame including an object having a minutiae corresponding to the image search condition when an image search condition is input by receiving a user input,
Wherein,
And reproduces the image or the enlarged image from the key frame retrieved by the retrieving unit. The method according to claim 1,
A picture storage unit for storing one or more pictures; And
Comparing the at least one photograph, the image photographed by the first camera, or the enlarged image photographed by the second camera, and comparing a photographed object of the at least one photograph with an object of the image or the magnified image Further comprising: a picture comparison unit for checking whether there is a picture or not and providing a result. The method according to claim 1,
Wherein the first camera comprises:
A first photographing unit for photographing an image;
A first controller for recognizing the object from one or more key frames including the object among the captured images; And
And a transmitting unit transmitting the image and the key frame to the database unit and transmitting an enlarged photographing command to enlarge and photograph the object. 9. The method of claim 8,
Wherein the second camera comprises:
A second photographing unit for photographing an image;
A communication unit for receiving the enlarged photographing instruction and transmitting the enlarged image to the database unit; And
And a second control unit for controlling the second photographing unit to photograph the enlarged image by enlarging the object recognized by the first camera by the received enlarged photographing command. 9. The method of claim 8,
Wherein the first camera comprises:
A first storage unit for storing images and key frames to be photographed when communication with the database unit is impossible; And
Further comprising a first emergency power supply unit for supplying emergency power when the power supply is cut off. 10. The method of claim 9,
Wherein the second camera comprises:
A second storage unit for storing a magnified image to be photographed when communication with the database unit is impossible; And
Further comprising a second emergency power supply for supplying emergency power when the power supply is cut off. The method comprising the steps of: one or more first cameras arranged in a fixed direction to photograph an image in a corresponding direction;
The first camera recognizing the object from one or more key frames including an object of the image;
Enlarging the object recognized by the first camera and photographing an enlarged image; And
The database receiving and storing the image captured by the first camera and the enlarged image captured by the key frame and the second camera from the first camera and the second camera, Monitoring method. 13. The method of claim 12,
Wherein the step of photographing the magnified image comprises:
Tracking the object while the second camera rotates; And
And when the face of the object is detected, the second camera magnifies the object and photographs the magnified image. 13. The method of claim 12,
Wherein the first camera extracts feature points of the object from the key frame. 15. The method of claim 14,
And storing the minutiae points of the object corresponding to the key frame in the database unit. 16. The method of claim 15,
Further comprising the step of the reproducing unit reproducing the image captured by the first camera, the key frame, and the enlarged image captured by the second camera. 17. The method of claim 16,
Further comprising the step of, when the image search condition is input in response to a user input, the search unit searches for a key frame including an object having a minutia corresponding to the image search condition,
The method of claim 1,
Wherein the reproducing unit reproduces the image or the enlarged image from the key frame retrieved by the retrieving unit. 13. The method of claim 12,
Storing one or more pictures; And
Comparing the at least one photograph, the image photographed by the first camera, or the enlarged image photographed by the second camera, and comparing a photographed object of the at least one photograph with an object of the image or the magnified image Determining whether there is a video signal, and providing a result.

Images