KR20130104024A - Apparatus for searching image data - Google Patents

Abstract

PURPOSE: An apparatus for searching image data is provided to easily identify a desired section from the image data by searching a frame section same as or different from a reference frame from the image data. CONSTITUTION: A storage part (120) stores image data including first and second frames. A management part (130) manages the meta data of the image data. A searching part (140) determines whether or not the second frame is same as the first frame based on the first frame and the meta data. The searching part compares the pixels of the first and second frames. If the variation of pixel values is within a first range, the searching part determines that the pixels of the first and second frames are same. If a ratio of same pixels in the second frame is over a second range, the searching part determines that the first and second frames are same. [Reference numerals] (110) Input part; (120) Storage part; (130) Management part; (140) Searching part; (200) Video data; (AA) Search query; (BB) Search result output; (CC) Meta data

Description

Image Data Search Device {APPARATUS FOR SEARCHING IMAGE DATA}

The present invention relates to an image data retrieval apparatus, and more particularly, to an image data retrieval apparatus for retrieving a frame section identical or different from a reference frame among image data stored in a storage.

Image data is used in various fields, and as the technology develops, the density or the degree of integration of data is greatly increased. The storage capacity of storage devices continues to increase, and in the case of digital video or digital conversion video, the number of frames per second (FPS) of the entire video is increasing, and the resolution of each frame is also increasing. to be.

The image data can be used not only for the purpose of information transfer but also for security or crime prevention. Especially, in the case of the image data obtained by continuously photographing the same place or object for security purposes, the image data is not changed significantly. In addition, since shooting continues for a long time, a process of finding a desired video section from a large amount of video data is not easy.

Domestic Publication No. 2009-0027484 (released March 17, 2009) Domestic Publication No. 2003-0005908 (published 23 January 2003) Domestic Publication No. 2011-0076989 (July 6, 2011 released) Domestic Publication No. 2006-0040846 (released May 11, 2006)

If the administrator wants to search the video data of the section in which the abnormal situation occurs for the purpose of security, etc. from the video data recorded for hundreds of hours or more, the relevant section must be searched while checking the video data separately. There is no situation.

Accordingly, there is a need for a retrieval apparatus capable of easily identifying a desired section from a vast amount of image data and easily reproducing the image data of the corresponding section.

The present invention has been made in view of the above, and an object of the present invention is to provide an image data retrieval apparatus capable of easily identifying a desired section among a large amount of image data.

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

An image data retrieval apparatus according to an embodiment of the present invention for solving the above problems includes a storage unit for storing image data including a first frame and a second frame, a management unit for managing metadata of the image data; And a searcher to determine whether the second frame is the same as the first frame based on the metadata and the first frame, wherein the searcher is a pixel of the first frame and the second frame corresponding to each other. The pixels of the frames are compared to determine the same pixel when the pixel value variation is within the first range, and the search unit determines the same frame when the ratio of the same pixel in the second frame is greater than or equal to the second range.

Other specific details of the invention are included in the detailed description and drawings.

1 is a block diagram showing the configuration of an image data retrieval apparatus according to an embodiment of the present invention.
FIG. 2 is a conceptual diagram illustrating a configuration of image data of FIG. 1.
FIG. 3 is a diagram illustrating a pixel value change amount of a corresponding pixel between frames of the image data retrieval apparatus of FIG. 1.
FIG. 4 is a diagram illustrating a process of determining the same frame by calculating an amount of change in pixel values of the entire image data of FIG. 1.
FIG. 5 is a diagram illustrating a reference region between frames of the image data retrieval apparatus of FIG. 1.
FIG. 6 is a diagram illustrating a process of determining the same frame by calculating a pixel value change amount of a pixel in a reference region of FIG. 5.
FIG. 7 is a diagram illustrating a display unit that displays whether the image data of FIG. 1 is identical to a reference frame among all frames. FIG.
FIG. 8 is a diagram illustrating a status bar corresponding to all frames of the image data of FIG. 1.

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. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. The dimensions and relative sizes of layers and regions in the figures may be exaggerated for clarity of illustration.

In the present specification, the singular form includes plural forms unless otherwise specified in the specification. As used herein, the terms "comprises" and / or "made of" means that a component, step, operation, and / or element may be embodied in one or more other components, steps, operations, and / And does not exclude the presence or addition thereof.

The terms spatially relative, "below", "beneath", "lower", "above", "upper" and the like, Lt; / RTI > can be used to easily describe the correlation between the two. Like reference numerals refer to like elements throughout.

Hereinafter, an image data retrieval apparatus according to an embodiment of the present invention will be described with reference to FIG. 1. 1 is a block diagram showing the configuration of an image data retrieval apparatus according to an embodiment of the present invention.

The apparatus for searching image data according to an embodiment of the present invention includes a storage unit 120 for storing image data 200 including a first frame and a second frame, And a search unit (140) for determining whether the second frame is the same as the first frame based on the meta data and the first frame, wherein the search unit (140) And determines that the pixel of the second frame is the same pixel when the amount of change in the pixel value is within the first range, and the searching unit 140 determines the same pixel in the second frame When the ratio of the pixels is equal to or larger than the second range, the same frame is determined.

Referring to FIG. 1, the input unit 110 may receive predetermined image data 200. The image data 200 received by the input unit 110 may be transmitted from an external photographing apparatus (not shown), or may be an image obtained by the camera module itself including the image data retrieval apparatus according to the present embodiment. .

The predetermined image data 200 may be image data including a plurality of frames, and may be data captured by a surveillance camera or a network camera and transmitted. The above-listed cameras may be a closed-circuit television (CCTV), but are not limited thereto, and may include all known camera units including a plurality of optical lenses, imaging devices such as CCDs, and the like.

Such a camera module acquires an image of the inside or the outside of a building or a specific area, converts the image into image data, and transmits the image data to the input unit 110.

The camera module for transmitting the image data 200 includes a camera unit for photographing an actual image, an encoder unit connected to the camera unit to generate analog or digital image data, and image data retrieval according to the present embodiment. It may include a transmitting and receiving unit for transmitting to the device. As described above, when the camera module for capturing the image data 200 is included in the image data retrieval apparatus according to the present embodiment, the transmission / reception unit or the like may be omitted.

As such, the image data 200 obtained by repeatedly photographing a predetermined region is composed of images of the same region, and thus a plurality of frames may be identical without change.

Accordingly, in order to quickly search for this, the image data retrieval apparatus according to the present embodiment may display to the user a frame in which a pixel is changed by a predetermined ratio or more relative to a previous frame or a predetermined reference frame as described below. The unnecessary frames that are repeated among the image data 200 can be quickly accessed to the important frames in a skipped state.

Description of the plurality of frames constituting the image data 200 will be described later in detail with reference to FIGS. 2 to 6.

Referring back to FIG. 1, the input unit 110 may receive various setting values desired by a user used to search for the image data 200 in addition to the image data 200.

Specifically, as described below, the input unit 110 determines whether the same pixel is the same pixel based on an amount of change in pixel values between pixels existing at the same position of a plurality of frames. You can receive the range setting value to decide whether or not. Since the range of change in the pixel value for determining the same pixel for each image data 200 is different from each other, the user can select and input appropriately according to the type of the image data 200.

The setting value input through the input unit 110 may be stored in the management unit 130 and used to retrieve the image data 200 stored in the search unit 140.

In addition, the input unit 110 may include an interface module for appropriately converting when the format of the input image data 200 is different.

The storage unit 120 stores the input image data 200. The storage unit 120 may mean a physical storage space such as a server, or may mean a logical storage space such as a database. When the received image data 200 is stored and required by a playback unit (not shown), the image data 200 may be loaded and displayed on the display unit 150 (see FIG. 7).

The management unit 130 manages setting values input by the user by the input unit 110, and extracts metadata of the image data 200 stored in the storage unit 120 and separately manages the metadata.

The extraction of the metadata may be performed simultaneously with or at the same time as the operation of storing the image data 200 in the storage 120, and the metadata may be important information of the image data 200, for example, size information and pixels. One or more of coordinate information and color information may be included. In addition, information about a pixel of the image data 200 may be indexed and stored so that the searcher 140 may search the image data 200 quickly. .

The searcher 140 searches for the same frame or a different frame from the image data 200 based on a predetermined reference frame.

The predetermined reference frame may be a specific frame in the image data 200, but is not limited thereto and may be an image separately input by a user. When the user separately inputs an image to be searched in the image data 200, the searcher 140 may search for the same frame as the image and return a section including the frame to the user. In addition, the search unit 140 may receive a search query from a user. For example, when a frame included in the image data 200 is to be searched, a search may be performed by inputting a specific condition, for example, a pixel position and an RGB value, without inputting an image.

Also, the reference frame may mean one or more frames. For example, a plurality of reference frames may be set, and a frame corresponding to one of the plurality of reference frames may be detected among a plurality of frames constituting the image data 200.

The searcher 140 does not search the frame of the image data 200 by directly accessing the storage 120 to improve the search speed, and may refer to the indexing information of the metadata stored in the manager 130 to display the image data ( 200).

Hereinafter, a detailed process of the searcher 140 searching for the image data 200 will be described with reference to FIGS. 2 to 4. FIG. 2 is a conceptual diagram illustrating the configuration of the image data of FIG. 1. FIG. 3 is a diagram illustrating a pixel value change amount of a corresponding pixel between frames of the image data retrieval apparatus of FIG. 1, and FIG. 4 is an image of FIG. 1. A diagram for describing a process of determining the same frame by calculating an amount of change in pixel values for the entire data.

Referring to FIG. 2, a conceptual form of the image data 200 is illustrated. Image data 200 is composed of a plurality of frames (200_1 to 200_N) in the form of a static image, a plurality of frames are continuously reproduced for a predetermined time to implement a moving image. When the number of frames per second (FPS) is high when the image data 200 is reproduced, more frames may be included in the image data 200 having the same amount of time. Capacity will also increase.

In particular, when the image data 200 according to the present exemplary embodiment is composed of an image obtained by photographing a long time at a predetermined angle at the same point, a large part of the frames constituting the image data 200 are identical within the error range without change. It may consist of an image. Accordingly, in order to efficiently search for the image data 200, it is necessary to skip the same repeated frame in which a special event does not occur and access a frame having a predetermined change or more.

The search unit 140 of the image data retrieval apparatus according to the present embodiment may generate a frame including an image that is the same as or different from the image of the reference frame 210 based on the reference frame 210 set by the user or preset in the system. Search.

As shown in the illustrated example, the reference frame 210 may be one of the frames constituting the image data 200, but is not limited thereto. As described above, the reference frame 210 may be an image separately input from the outside. In addition, without the reference frame 210, a user may input a search condition as the pixel position and color condition.

Referring to FIG. 3, the search unit 140 performs a task of determining whether the frame is identical to another frame based on one reference frame 210. As shown in the illustrated example, the searcher 140 may compare the reference frame 210 and the predetermined frame 200_3 of the image data 200, and the pixel P1 of the reference frame 210 at a position corresponding to each other. The pixel P2 of the predetermined frame 200_3 may be compared to determine the same pixel when the pixel value change amount is within a predetermined range.

That is, the searcher 140 compares the pixel value of the pixel of the reference frame 210 with the pixel value of the pixel of another frame 200_1 to 200_N to be compared, and one pixel in the frame to be compared is one. It may be a plurality of pixels or all pixels constituting the frame of, but is not limited thereto.

The searcher 140 determines whether the same pixel is the same based on the change amount of the pixel value. The same pixel does not necessarily have to match the pixel value, and the pixel included in the error range set in advance by the user or the system is the same pixel. You can judge.

For example, when the pixel value of the RGB form of the first pixel of the reference frame 210 is (200, 200, 200) and the error range is set to ± 10, the other frame 200_1 to 200_N to be compared is compared. In addition to (200, 200, 200) pixel values of the corresponding pixel, pixel values of (190, 190, 210), (200, 210, 190), etc. may be determined to be the same pixel.

Such an error range may vary according to the image data 200 and may be appropriately selected by the user.

4, whether the plurality of pixels of the predetermined frame 200_3 of the image data 200 compared with the plurality of pixels of the reference frame 210 are the same.

That is, the searcher 140 may extract information about pixels determined to be the same pixel by comparing the pixel value of each pixel of the predetermined frame 200_3 with the pixel value at the corresponding position of the reference frame 210.

The illustrated figure shows an exemplary situation for the same pixel distribution, where 0 means a pixel determined to be the same pixel within an error range, and 1 means a pixel determined to be deformed beyond the error range.

From this, nine pixels among the entire pixels 10x7 of the predetermined frame 200_3 are the same pixels with image change, and the remaining 61 pixels are change pixels with substantially no image change.

Based on this, when the ratio of the same pixels in the predetermined frame 200_3 to be determined is within a predetermined range, the search unit 140 may determine the same frame as the reference frame 210 and exceeds the predetermined range. A change frame different from the reference frame 210 may be determined.

The same pixel ratio may be expressed as a ratio of the number of identical pixels to the total number of pixels constituting the frame. In the illustrated example, since 61 pixels of the total 70 pixels are the same pixel, the same pixel ratio represents 87.14%.

The criteria for determining the same frame may be arbitrarily set by the user according to the type of the image data 200, similarly to the criteria for determining the same pixel described above. For example, in the case of the image data 200 having a lot of motion, a predetermined range for determining the same frame may be set low, and the image data 200 in the static section may be set high. no.

Hereinafter, an image data search apparatus according to another embodiment of the present invention will be described with reference to FIGS. 5 to 6. FIG. 5 is a diagram illustrating a reference region between frames of the image data retrieval apparatus of FIG. 1, and FIG. 6 is a diagram illustrating a process of determining the same frame by calculating an amount of change in pixel values of pixels in the reference region of FIG. 5. .

According to another embodiment of the present invention, the manager 130 may set a predetermined area A1 of the reference frame 210 as the first area and manage color data of pixels included in the first area. The predetermined area A1 may vary according to the main monitoring area of the image data 200.

That is, the predetermined area A1 set on the reference frame 210 may be set as a main area necessary for detecting a change of a frame when searching for the entire area of the frame. For example, when the image data 200 is an image near the door, the area near the door is specified from the entire image to search for a case where the image near the door is changed by the person. Can be determined.

In this way, special monitoring of the reference frame 210 is required or the main point is set to the predetermined area A1. Although the management unit 130 may determine the predetermined area A1, the present invention is not limited thereto, and the management area 130 may set the predetermined area A1 in a process of inputting information and range through the input unit 110.

As such, when the pixels of the specific predetermined area A1 are defined among all the pixels of the reference frame 210, the searcher 140 compares the areas existing at positions corresponding to the predetermined area A1 based on the pixels. The comparison target area A2 of the frame 200_3 may be set as the second area.

That is, as shown in FIG. 6, the searcher 140 may determine whether the same pixel is the same for all pixels corresponding to each other in the first area and the second area, and then determine the same frame based on the same pixel.

As such, when the same pixel is determined based on the pixels included in the limited area, and the same frame is determined based on the same pixel, the same pixel is determined based on the total pixels, and based on the ratio of the same pixels to the entire pixels. Compared to the case of determining the same frame, the search speed can be greatly reduced.

Referring to FIG. 6, a result of determining whether the same pixels are the same for all 16 pixels included in the second area A2, which is the area to be compared. The process of determining the same pixel is as described above, and the process of determining the same frame is determined based on the ratio of the number of the same pixel to the total number of pixels in the region to be compared. In the illustrated example, 11 pixels are the same among all 16 pixels in the second area A2 of the frame 200_3 to be compared with the pixels of the reference frame 210, and since 5 pixels are changed, the same is the same. The ratio of pixels represents 68.75%. In this case, assuming that the range of the same pixel ratio for determining the same frame is 80% or more, the comparison target frame 200_3 having a value of 80% or less may be excluded from the same frame.

As described above, when searching the pixels within the limited region without searching the entire pixels of the reference frame 210, the search speed can be greatly improved.

Hereinafter, an image data search apparatus according to another embodiment of the present invention will be described with reference to FIGS. 7 to 8. FIG. 7 is a diagram illustrating a display unit displaying whether the frame of the image data of FIG. 1 is the same as the reference frame, and FIG. 8 is a view illustrating a status bar corresponding to the entire frame of the image data of FIG. 1.

The image data retrieval apparatus according to another embodiment of the present invention is the same as the previous embodiment, but further includes a display unit 150 and / or playback unit 160.

Referring to FIG. 7, the display unit 150 further includes a display unit 150 displaying the image data 200 in units of all frames, and the display unit 150 displays the same frame as the reference frame 210 among all the frames.

The display unit 150 displays the same frame 200B and the different change frame 200A differently from the reference frame 210 so that the user visually checks the list of the same frames determined by the searcher 140. can do.

In the illustrated example, the section including the same frame 200B and the section including the change frame 200A are distinguished from each other in a state in which the entire frames are arranged in chronological order, but the present invention is not limited thereto. For example, it may be displayed as a list of section information of the same frame 200B, or an image of the changed frame 200A may be output.

Referring to FIG. 8, the image data retrieval apparatus according to the present embodiment further includes a reproducing unit 160 reproducing the image data 200, and the reproducing unit 160 includes the image data 200 arranged in chronological order. ) And outputs a status bar 300 corresponding to the entire frame and displaying the playback status.

As shown, the status bar 300 displays an identification mark so that the section 300A including the same frame as the comparison frame 210 and the section 300B including the different change frame are identified. There is no limitation on the type of identification display, and a marking for generating a predetermined mark in a corresponding section of the status bar 300 or a coloring method for changing the color of the corresponding section may be used.

In addition, the identification mark may include a playback link for playing the section including the same frame of the image data 200 when clicked. Accordingly, the user can search for an image through the status bar 300, and when the user clicks the identification mark, the corresponding frame is played to immediately check the desired image.

In addition, the status bar 300 may display an identification mark different from the identification mark to identify a section including a frame in which a ratio of the same pixel is within a range different from a predetermined range among the remaining frames except for the same frame.

That is, as described above, the same frame is determined according to the ratio of the same pixel, and when the similar frame including the same pixel as well as the same frame is searched for, the search unit 140 uses the ratio of the same pixel. After determining differently, a similar frame period may be further determined based on this.

For example, the searcher 140 may determine that the same frame is 80% or more of the same pixel in one frame, and may determine the similar frame when it is within 70 to 80%.

In order to identify the section including the similar frame determined as described above, an identification mark and another identification mark of the same frame may be added so that the user may easily search for the similar frame.

In addition, it may be configured to be identified in the status bar 300 according to the similarity with the reference frame 210. For example, as the ratio of the same pixel to the reference frame 210 is higher, the status bar 300 of the corresponding section is displayed in darker color, and as the ratio of the same pixel to the reference frame 2100 is lower, the status bar of the corresponding section ( 300 may be displayed in light color.

Therefore, the user can intuitively identify the similarity of the same frame or similar frame through the status bar 300, and click the corresponding identification mark on the status bar 300 to go directly to the frame to perform additional operations. can do.

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, You will understand. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive.

110: input unit
120:
130: management
140: search unit
200: image data
300: Status bar

Claims (10)

A storage unit which stores image data including a first frame and a second frame;
A management unit managing metadata of the image data; And
A search unit which determines whether the second frame is the same as the first frame based on the metadata and the first frame,
The searcher compares the pixels of the first frame and the pixels of the second frame at positions corresponding to each other, and determines the same pixel when the amount of change in pixel value is within the first range.
And the searching unit determines the same frame when the ratio of the same pixel in the second frame is greater than or equal to the second range. The method of claim 1,
Wherein,
Setting a predetermined region of the first frame as a first region,
Image data retrieval apparatus for managing the color data of the pixels included in the first area. The method of claim 2,
And the first region is varied according to a main surveillance region of the image data. The method of claim 2,
The search unit may search,
An area existing at a position corresponding to the first area is set as a second area of the second frame,
And determining the same pixel and the same frame for all pixels corresponding to each other in the first area and the second area. The method of claim 1,
And the first range or the second range is varied according to the image data. The method of claim 1,
Further comprising a display unit for displaying the image data in units of whole frames,
And the display unit displays the same frame as the first frame among the entire frames to be identified. The method of claim 1,
Further comprising a playback unit for playing the video data,
And the reproduction unit outputs a status bar corresponding to all frames of the image data arranged in chronological order and displaying a reproduction state. The method of claim 7, wherein
And a first identification mark is displayed on the status bar to identify a section including the same frame among the entire frames. 9. The method of claim 8,
And the first identification mark includes a playback link for playing the section including the same frame of the video data when clicked. The method of claim 7, wherein
And a second identification mark is displayed on the status bar to identify a section including a frame in which a ratio of the same pixel is within a third range different from the second range among the other frames except for the same frame. .

Images