WO2013183978A1

WO2013183978A1 - Image processing device and method

Info

Publication number: WO2013183978A1
Application number: PCT/KR2013/006896
Authority: WO
Inventors: 구선회
Original assignee: 주식회사 마이씨에프
Priority date: 2012-06-08
Filing date: 2013-07-31
Publication date: 2013-12-12
Also published as: KR101340308B1

Abstract

The present invention relates to an image processing device and method, and more specifically, to an image processing device and method capable of reducing a data capacity of a video without encoding the video and easily analyzing data of the video. An image processing device according to one embodiment of the present invention comprises: an image input unit for sequentially inputting image frames therethrough; a subject extraction unit for sensing and extracting a moving subject or a specific subject from the image frames inputted through the image input unit; a background image extraction unit for extracting, as an image, a background image that is the remaining area excluding the subject extracted by the subject extraction unit from the image frames; an object generation unit for objectizing the subject and the background image respectively extracted by the subject extraction unit and the background image extraction unit and generating combination information and frame information on the objectized subject and the background image; a first storage unit in which the objectized subject and the background image are stored; a second storage unit having a database in which the combination information and the frame information on the objectized subject and the background image are stored; and a control unit for controlling the subject extraction unit, the background image extraction unit, and the object generation unit to extract the subject and the background image from the image frames inputted through the image input unit, objectize the extracted subject and background image and generate the combination information and the frame information on the objectized subject and the background image, storing the objectized subject and the background image in the first storage unit, and storing the combination information and the frame information on the objectized subject and the background image in the database of the second storage unit.

Description

Image processing apparatus and method

The present invention relates to an image processing apparatus and a method, and more particularly, to an image processing apparatus and method that can reduce the video data capacity without having to encode a video, and can also facilitate data analysis of the video.

In general, large-capacity video files such as movies and animations are difficult to watch in real time over wired and wireless Internet because of the large file size, and are downloaded and watched for a long time. Downloading a large video file takes a lot of time and requires a lot of storage space on your computer.

In addition, in the case of a surveillance camera that is photographed for a long time, the longer the time, the larger the data capacity of the captured image, there is a limit in continuously storing the image file.

In order to solve this problem, a method of reducing the total file size by compressing all frame images of a video according to a compression protocol using a compression technique such as a moving picture expert group (MPEG) has been disclosed.

However, this technique has a limitation in reducing the data capacity of an image since it is a method of producing an finally encoded image file.

Disclosure of Invention The present invention has been made to solve the above problems, and an object of the present invention is to provide an image processing apparatus and a method capable of reducing video data capacity without encoding a video and facilitating data analysis of the video. There is this.

However, the objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, an image processing apparatus according to an embodiment of the present invention, the image input unit for sequentially inputting the image frame; A subject extracting unit which detects and extracts a moving subject or a specific subject from an image frame input through the image input unit; A background image extracting unit extracting a background image, which is a region other than the subject extracted by the subject extracting unit, from the image frame as an image; An object generator configured to objectize the subject and the background image extracted by the subject extractor and the background image extractor, respectively, and to generate combined information and frame information of the object and the subject image; A first storage unit storing the objectized subject and the background image; A second storage unit having a database storing combined information of the object and the background image and frame information; And extracting and subjecting the subject and the background image from the image frame input through the image input unit, and generating the combined information and the frame information of the objectized object and the background image. A controller configured to control an object generator and to store the objectized subject and the background image in the first storage unit and to store the combined information and the frame information of the objectized subject and the background image in the database of the second storage unit. do.

Here, the image combination unit for combining the objectized subject and the background image stored in the first storage unit according to the combined information and frame information stored in the database of the second storage unit; And a reproducing unit configured to receive and reproduce an image combined by the image combining unit, and wherein the controller is further configured to display the objectized subject and the background image stored in the first storage unit when the reproduction command is input. The image combination unit and the reproducing unit are preferably combined according to the combination information and the frame information stored in the control unit so as to reproduce the combined image.

In addition, the image analysis information generation unit for generating image analysis information associated with the object and the subject image; And an image analyzer configured to analyze characteristics of an image reproduced through the playback unit based on the image analysis information, wherein the controller is configured to store the image analysis information generated by the image analysis information generator in the database of the second storage unit. If the image analysis command is input to the image analysis command, the image analysis unit may be controlled to analyze characteristics of the image reproduced through the reproduction unit based on the image analysis information stored in the database of the second storage unit.

The image combination unit may combine the images by substituting the combination information and the frame information into attribute values of the object and the background image.

The combining information includes at least one of an arrangement order of framed object and a background image, frame position, size, brightness, exposure time, and other effects, and the frame information should be combined with some image elements at any position during image reproduction. Contains information indicating whether or not

The image analysis information includes at least one of a title, a shooting time, a shooting period, a color, a position, and a movement direction of the object and the background image.

In order to achieve the above object, the image processing method according to an embodiment of the present invention, the step of sequentially inputting the image frame; Detecting and extracting a moving subject or a specific subject from the image frame; Extracting a background image, which is a region other than the extracted subject, from the image frame as an image; Objectifying the extracted subject and background image, respectively, and generating combination information and frame information of the objectized subject and background image; And storing the objectized subject and the background image in a first storage unit, and storing the combined information and the frame information in a database of the second storage unit.

Here, when a reproduction command is input, combining the objectized subject and the background image stored in the first storage unit according to the combination information and the frame information stored in the database of the second storage unit; And reproducing the combined image.

The method may further include generating image analysis information related to the objectized object and the background image; Storing the image analysis information in a database of the second storage unit; And when the image analysis command is input, analyzing a feature of the reproduced image based on the image analysis information stored in the database of the second storage unit.

The combining may include combining the combination information and the frame information by substituting the attribute values of the object and the background image.

According to the image processing apparatus and method according to the present invention as described above, it is possible to reduce the video data capacity without having to encode the video, and to facilitate the data analysis of the video.

1 is a control block diagram of an image processing apparatus according to an exemplary embodiment of the present invention.

2 is a flowchart illustrating an image processing method according to an exemplary embodiment of the present invention.

Specific details of other embodiments are included in the detailed description and drawings, and the advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings.

However, the present invention is not limited to the embodiments disclosed below, but may be embodied in various different forms, and the present embodiments merely make the disclosure of the present invention complete and common knowledge in the technical field to which the present invention belongs. It is provided to fully inform the person having the scope of the invention, which is defined only by the scope of the claims. Like reference numerals refer to like elements throughout.

Hereinafter, an image processing apparatus and a method according to an exemplary embodiment of the present invention will be described with reference to the accompanying block diagram or the drawings of the processing flowchart.

As illustrated in FIG. 1, an image processing apparatus according to an exemplary embodiment of the present invention may include an image input unit 110, a subject extractor 120, a background image extractor 130, an object generator 140, and image analysis information. The generator 150, the first storage unit 160, the second storage unit 170, the image combiner 180, the playback unit 190, the image analyzer 210, and the controller 220 are included.

Such an image processing device converts an analog image signal input through a camera into a digital image signal, and compresses / restores the image using MPEG (Moving Picture Experts Group), an international video compression method, to record and play back for a long time. Digital Video Recorder (hereinafter referred to as DVR). In addition to recording, DVR has various selection menu functions such as motion detection, connection recording, camera control, image magnification, editor, etc., and has the function to save data semi-permanently. In particular, DVR can be applied to video conferencing, video education or remote medical examination. Especially, it is installed in security buildings such as banks, military areas, etc., and it is a security surveillance system that captures and compresses and saves images from a specific location. Widely used. Unlike conventional CCTV (Closed Circuit Television) using the DVR, such a DVR can easily store and manage an image, and also can easily search for a necessary image and check the image stored in a desired time frame in a short time. Of course, the image processing apparatus may be applied to a personal computer, a personal digital assistant (PDA), a portable multimedia player (PMP), a mobile communication terminal, and the like, in addition to a DVR.

The image input unit 110 is a portion in which an image frame is input, and the images photographed from a moving image photographing means (not shown) such as a video camera, a digital camera, and a camera phone are sequentially input. Here, the image includes both an analog image or a digital image, but it is assumed that the image is converted into a digital image signal and input. The image signals converted into digital signals are sequentially input through the image input unit 110 in units of frames.

The subject extractor 120 detects and extracts a moving subject or a specific subject (eg, a person) from an image frame input through the image input unit 110.

The moving subject may be extracted by motion tracking. Motion tracking calculates a motion vector by determining a difference between two consecutive frame images, and tracks a subject by the motion vector. Specifically, in order to obtain a motion vector, a feature point is set in a currently input image frame, and how much data in which direction the feature point coordinates are moved is compared with a previously input image frame. In this case, the feature point may be set by the user, or may be automatically set by comparison with a previously input image frame.

The method of extracting a specific subject includes setting a feature point in a currently input image frame and extracting a specific subject region based on data of feature point coordinates.

The background image extractor 130 extracts a background image, which is a region other than a subject extracted by the object extractor 120, from an image frame input through the image input unit 110 as an image. To this end, a process of subtracting the subject from the entire image frame is included.

The object generator 140 may objectize the subject and the background image extracted by the subject extractor 120 and the background image extractor 130, respectively, and generate combination information and frame information of the object and the subject image. Here, the combined information is information for generating an image frame by combining the object and the background image, for example, the arrangement order or frame position, size, brightness, exposure time, and other effects of the subject and the background image. Information. The frame information is information indicating which image elements should be combined at which position during image playback. For example, the frame and the number of frames to which the subject and the background image, which are the components of the image, should be connected, and which of the screens of the frame are used. Information such as whether to be located in the area.

The image analysis information generator 150 generates specific information related to the objectized subject and the background image. The specific information includes a title characterizing a subject and a background image, a shooting time, a shooting period, a color of the subject, a position, a direction of movement, and the like, and is used for image analysis.

The first storage unit 160 stores the object and the background image objectified by the object generator 140, and the second storage unit 170 combines the information, the frame information, and the image analysis information of the object and the background image. Has a database that is stored.

The image combination unit 180 reads the objectized subject and background image stored in the first storage unit 160 and the combined information and frame information stored in the database of the second storage unit 170, and reads the combined information and frame. The object and the background image objectified according to the information are combined. Specifically, an image frame is generated by substituting the read combination information and frame information into corresponding attribute values of the objectized object and the background image.

The playback unit 190 plays a role of receiving and playing the image combined by the image combination unit 180. The playback unit 190 may generally be a FlashPlayer, SilverlightRuntime, or a web browser itself. In addition, a program serving as the play unit 190 may be separately manufactured by a program such as C ++, C ＃, VisualBasic, or the like.

The image analyzer 210 analyzes the characteristics of the image reproduced through the playback unit 190 based on the image analysis information stored in the second storage unit 170. That is, the image capturing time, the shooting period, the color of the subject, the position, the movement direction, etc., as well as the title characterizing the image reproduced by the playback unit 190 can be analyzed.

The controller 220 controls the overall operation of the device. The controller 220 controls the subject extractor 120 and the background image extractor 130 to extract the subject and the background image from the image frame input through the image input unit 110.

The controller 220 controls the object generator 140 to objectize the extracted subject and the background image and to generate the combined information and the frame information of the object and the background image.

The controller 220 stores the objectized subject and the background image in the first storage unit 160, and stores the combined information and the frame information of the objectized subject and the background image in a database of the second storage unit 170. That is, the controller 220 does not store the entire image frame as one file, but separately stores the objectized object and the background image, combined information, and frame information.

In addition, the controller 220 controls the image analysis information generation unit 150 to generate image analysis information such as a title associated with the object and the background image, a shooting time, a shooting period, a color, a position, and a movement direction of the subject. The generated image analysis information is stored in a database of the second storage unit 170.

When the playback command is input, the controller 220 does not control to play the entire image frame as one file, but instead of controlling the objectized object and the background image stored in the first storage unit 160 of the second storage unit 170. The image combination unit 180 is controlled to generate an image frame by combining the combination information and the frame information stored in the database. In addition, the controller 220 allows the combined image frame to be played back through the playback unit 190.

When the image analysis command is input, the controller 220 analyzes the characteristics of the image reproduced through the playback unit 190 based on the image analysis information stored in the second storage unit 170. To control.

Referring to FIG. 2, first, image frames are sequentially input through the image input unit 110 (S110).

Then, the subject extractor 120 detects and extracts a moving subject or a specific subject from sequentially input image frames, and the background image extractor 130 extracts a background image, which is a region other than the subject (S120). Since a specific extraction method has been described above, a description thereof will be omitted.

The object generator 140 objectizes the extracted subject and the background image, respectively (S130), and generates combination information and frame information of the objectized subject and the background image (S140).

The controller 220 stores the objectized subject and the background image in the first storage unit 160, and stores the combined information and the frame information of the objectized subject and the background image in a database of the second storage unit 170 ( S150).

On the other hand, the image analysis information generation unit 150 generates image analysis information such as a title associated with the object and the background image, the shooting time, the shooting period, the color of the subject, the position, the movement direction, etc. (S160). Then, the controller 220 stores the generated image analysis information in the database of the second storage unit 170 (S170).

When the play command is input (S180), the image combination unit 180 may convert the objectized subject and the background image stored in the first storage unit 160 according to the combined information and frame information stored in the database of the second storage unit 170. Combination generates an image frame (S190). In addition, the controller 220 allows the combined image frame to be played back through the playback unit 190 (S210).

Meanwhile, when an image analysis command is input (S220), the image analyzer 210 may analyze the image analysis information such as the title stored in the second storage unit 170, the shooting time, the shooting period, the color of the subject, the position, and the movement direction. Based on the analysis of the characteristics of the image reproduced through the playback unit 190 (S230).

As described above, the present invention provides a plurality of images to an image processing apparatus, such as a case where a video must be continuously recorded for a predetermined time through a video recording means such as a video camera, a digital camera, a camera phone, or a large video file must be downloaded. When the frames are sequentially input, the subject and the background image are first detected and extracted from the image frame. The extracted subject and the background image are respectively objectized and stored, and the combined information and the frame information are separately stored in the database. As a result, video data capacity can be reduced without encoding an image, and a separate decoding process is not required even when playing an image. In addition, there is an advantage that can easily analyze the data of the image by generating the image analysis information and stored in the database together.

The invention can also be embodied as computer readable code on a computer readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, optical data storage devices, and the like, which are also implemented in the form of carrier waves (for example, transmission over the Internet). Include.

Although described above based on the preferred embodiments of the present invention, those skilled in the art will understand that the present invention may be implemented in other specific forms without changing the technical spirit or essential features of the technical field to which the present invention belongs.

Therefore, the embodiments described above are to be understood as illustrative in all respects and not as restrictive. The scope of the present invention is defined by the appended claims rather than the foregoing description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims

An image input unit configured to sequentially input image frames;

A subject extracting unit which detects and extracts a moving subject or a specific subject from an image frame input through the image input unit;

A background image extracting unit extracting a background image, which is a region other than the subject extracted by the subject extracting unit, from the image frame as an image;

An object generator configured to objectize the subject and the background image extracted by the subject extractor and the background image extractor, respectively, and to generate combined information and frame information of the object and the subject image;

A first storage unit storing the objectized subject and the background image;

A second storage unit having a database storing combined information of the object and the background image and frame information; And

The subject extracting unit, the background image extracting unit, and the object to extract and subject the subject and background image from the image frame input through the image input unit, and generate the combined information and the frame information of the objectized subject and the background image. And a controller configured to control the generation unit, and to store the objectized subject and the background image in the first storage unit, and to store the combined information and the frame information of the objectized subject and the background image in the database of the second storage unit. Image processing device.
Sequentially inputting image frames;

Detecting and extracting a moving subject or a specific subject from the image frame;

Extracting a background image, which is a region other than the extracted subject, from the image frame as an image;

Objectifying the extracted subject and background image, respectively, and generating combination information and frame information of the objectized subject and background image; And

And storing the objectized object and the background image in a first storage unit and storing the combined information and the frame information in a database of the second storage unit.