JP2016090906A - Image processor, image processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable display of a video with a layout intended by a user, in an image processor for inputting a video divided into a plurality of parts to perform display.SOLUTION: An image processor for combining a plurality of partial videos obtained by dividing a video includes: first input means for inputting a first partial video; second input means for inputting a second partial video; acquisition means for acquiring a feature quantity which is the feature quantity in a boundary area in the case of combining the first partial video with the second partial video and is based on a plurality of images which are temporally different from one another; and control means for performing control so as to display the video with a layout in the case of combining the first partial video with the second partial video on the basis of the feature quantity acquired by the acquisition means.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program, and more particularly to a video display technique for inputting and displaying a video divided into a plurality of parts.

  In a video display device that displays a high-resolution video, a plurality of input interfaces may be used to input the video. For example, a case where a 1920 × 1080 pixel, 60 Hz signal is simultaneously input using four HDMI (High-Definition Multimedia Interface) cables to display a 4K2K moving image (content) will be described. Note that the 4K2K moving image indicates an image corresponding to a resolution four times that of full high-definition (resolution 1920 × 1080 pixels), that is, a resolution of about 4000 × 2000 pixels. Such a high-resolution content is transmitted by being divided into a plurality of parts on the transmission side (video distribution apparatus), and the content divided into a plurality of parts is displayed on the reception side (video display apparatus). On the receiving side, when the contents are combined and displayed, it is necessary to correctly set which input of the divided contents is displayed at which position.

  Conventionally, as a technique for synthesizing a plurality of divided images, an apparatus for reading and synthesizing a large-size original by dividing it into a plurality of partial images, synthesizes the partial images based on the image density at the edge of each partial image. There is a technique for determining an arrangement position in a composite image at the time (Patent Document 1).

JP-A-9-121277

  In Patent Document 1 described above, the arrangement position of each partial image in the composite image is determined based on the image density of the edge of each partial image. For example, there is a black belt around the composite image (up, down, left, and right). When combining divided images obtained by dividing a movie, there is a possibility of an unintended layout. That is, the black belt may be combined on the cross not at the periphery of the combined image but at the center of the combined image.

  In order to solve the above problems, an image processing apparatus of the present invention has the following configuration. That is, an image processing apparatus that synthesizes a plurality of partial videos obtained by dividing a video, a first input unit that inputs a first partial video, a second input unit that inputs a second partial video, An acquisition unit that acquires a feature amount in a boundary region when combining the first partial video and the second partial video, and based on a plurality of temporally different images, and the acquisition unit And control means for controlling to display the video in a layout when the first partial video and the second partial video are synthesized based on the acquired feature amount.

  In an image processing apparatus that inputs and displays a plurality of divided images, the images can be displayed in a layout intended by the user.

1 is a block diagram illustrating a configuration of an image processing apparatus according to a first embodiment. 5 is a flowchart illustrating processing in the image processing apparatus according to the first embodiment. Diagram showing an example of video data The figure which shows an example of the display area of the display part 109 Flow chart showing processing for calculating feature amount of video data Block diagram showing a configuration example of computer hardware applicable to an image processing apparatus A flowchart showing a method for determining the arrangement of video data The figure which shows the motion vector of each pixel in the boundary area | region of arrangement | positioning of each video data

  Hereinafter, the present invention will be described in detail based on an example of an embodiment with reference to the accompanying drawings. In addition, the structure shown in the following embodiment is only an example, and is not limited to the illustrated structure.

(Embodiment 1)
Hereinafter, an image processing apparatus according to the present embodiment will be described with reference to the drawings. First, FIG. 1 is a block diagram showing the configuration of the image processing apparatus of the present embodiment.

  In FIG. 1, an image processing apparatus 101 according to the present embodiment includes a first input unit 102, a second input unit 103, a third input unit 104, a fourth input unit 105, an acquisition unit 106, a determination unit 107, a display. A control unit 108 and a display unit 109 are included.

  The first input unit 102, the second input unit 103, the third input unit 104, and the fourth input unit 105 receive video data from the outside of the image processing apparatus 101 and send the video data to the acquisition unit 106. Is output. The video data is video data input to the image processing apparatus 101 via an interface for outputting video (image) such as HDMI (registered trademark) (High-Definition Multimedia Interface) and Display Port. In this embodiment, it is assumed that the image processing apparatus 101 inputs video data (partial video) obtained by dividing one video content (video data) having a high resolution simultaneously via a plurality of interfaces. The acquisition unit 106 receives each video data (partial video) from the first input unit 102, the second input unit 103, the third input unit 104, and the fourth input unit 105, and receives video data from each video data. Acquire (calculate) information on the feature amount of Details of the method for calculating the feature amount of the video data will be described later.

  The determination unit 107 inputs from the first input unit 102, the second input unit 103, the third input unit 104, and the fourth input unit 105 based on the feature amount of the video data acquired by the acquisition unit 106. The arrangement of each piece of video data is determined. Details of the method for determining the arrangement of the video data will be described later.

  The display control unit 108 uses the first input unit 102, the second input unit 103, the third input unit 104, and the fourth input unit 105 based on the arrangement of the video data determined by the determination unit 107. The video data is synthesized and controlled to be displayed on the display unit 109.

  The display unit 109 displays the video data input to the input units 102 to 105 based on the control of the display control unit 108.

  Next, a processing flow of the image processing apparatus 101 in the present embodiment will be described with reference to FIG. FIG. 2 is a flowchart illustrating a procedure of processing executed by the image processing apparatus when four pieces of video data obtained by dividing the video data are input to the image processing apparatus 101 in the present embodiment. FIG. 2 shows a processing procedure in each processing unit of the image processing apparatus 101 until the display unit 109 displays video data.

  In step S <b> 201, the first input unit 102, the second input unit 103, the third input unit 104, and the fourth input unit 105 input and input video data from the outside of the image processing apparatus 101, respectively. Each video data is output to the acquisition unit 106.

  In step S <b> 202, the acquisition unit 106 calculates the feature amount of the video data based on the video data output from the input units 102 to 105, and outputs information regarding the calculated feature amount and each video data to the determination unit 107. . The details of the process in which the acquisition unit 106 calculates the feature amount of the video data will be described later. In step S202 of the present embodiment, the acquisition unit 106 calculates the feature amount of the video data. However, the present invention is not limited to this, and the feature of the video data calculated by another processing unit inside or outside the image processing apparatus 101 is not limited thereto. The configuration may be such that the acquisition unit 106 acquires the amount.

  In step S203, the determination unit 107 determines the arrangement of the video data input to each of the input units 102 to 105 based on the information regarding the feature amount calculated by the acquisition unit 106 in step S202. Then, the determination unit 107 outputs the information regarding the determined arrangement and the video data input to the input units 102 to 105 to the display control unit 108. Here, for example, the arrangement information is “upper left”, “upper right”, “lower left”, “lower right” in the display area of the display unit 109 for each video data input to the input units 102 to 105. Can be expressed respectively. Also, the upper left corner of the display area (display screen) is the origin, the right direction from the origin is x, the lower direction is y, and the display position and size (width and height) of each video data are expressed as coordinates (x, y ) May be used. Details of the process of determining the arrangement of the video data by the determination unit 107 will be described later.

  In step S204, the display control unit 108 synthesizes video data based on the information regarding the arrangement determined by the determination unit 107 in step S202, and generates video data to be displayed. Further, the display control unit 108 controls to display the generated video data on the display unit 109.

  Next, a method for calculating the feature amount of the video data by the acquisition unit 106 in step S202 of the present embodiment will be described in detail with reference to FIGS.

  FIG. 3 is a diagram illustrating an example of video data input from the first input unit 102, the second input unit 103, the third input unit 104, and the fourth input unit 105 to the acquisition unit 106.

  Reference numerals 301, 302, 303, and 304 denote the Nth frame of the video data input from the input units 102 to 105 to the acquisition unit 106, respectively. Reference numerals 305, 306, 307, and 308 respectively denote the (N + 1) th frame of video data input from the input units 102 to 105 to the acquisition unit 106. Here, the video 301 and the video 305 correspond to the video data input from the first input unit 102 to the acquisition unit 106, and the video 302 and the video 306 are input from the second input unit 103 to the acquisition unit 106. Corresponds to video data. The video 303 and the video 307 correspond to the video data input from the third input unit 104 to the acquisition unit 106, and the video 304 and the video 307 are the video input to the acquisition unit 106 from the fourth input unit 105. Corresponds to data.

  FIG. 4 is a diagram illustrating an example of a display area in which the display unit 109 displays video data. Reference numeral 401 denotes an area (LT) indicating the upper left position of the display area, and reference numeral 402 denotes an area (LB) indicating the lower left position of the display area. Reference numeral 403 denotes an area (RT) indicating the upper right position of the display area, and reference numeral 404 denotes an area (RB) indicating the lower right position of the display area.

  FIG. 5 is a flowchart showing the procedure of the video data feature quantity calculation process executed by the acquisition unit 106 in step 202 of FIG. In this embodiment, the acquisition unit 106 calculates a motion vector as a feature amount of video data.

  In step S <b> 501, the acquisition unit 106 records (saves) the video data of the Nth playback order input from the input units 102 to 105 in the memory. Here, the video data of the Nth frame are the videos 301 to 304 shown in FIG.

  Next, in step S502, the acquisition unit 106 records the video data of the (N + 1) th frame input from the input units 102 to 105. Here, the video data of the (N + 1) th frame corresponds to each of the videos 305 to 308 shown in FIG. Note that the present embodiment is not limited to step S501 and step S502, and the acquisition unit 106 is not limited to calculating the feature amount of video data using video data of the Nth frame and video data of the (N + 1) th frame. Absent. That is, the acquisition unit 106 may perform step S501 and step S502 in one step, and may be any unit that calculates the feature amount of video data using video data of a plurality of frames.

Next, in step S503, the acquisition unit 106 acquires a list indicating combinations of video data and arrangements based on the number of input video data (number of inputs). Note that the acquisition unit 106 may calculate (create) the list, acquire the calculated list, or hold the acquired list. In the present embodiment, since video data is connected from four input units, the maximum number of list elements calculated by the acquisition unit 106 is 24, and LIST [i] = (LT, LB, RT, RB) is set. Use the following combinations. As described above, the video data input from each of the first input unit 102, the second input unit 103, the third input unit 104, and the fourth input unit 105 are 1, 2, 3, 4 As a list.
LIST [0] = (1,2,3,4), LIST [1] = (1,2,4,3),
LIST [2] = (1, 3, 4, 2), LIST [3] = (1, 3, 2, 4),
LIST [4] = (1, 4, 2, 3), LIST [5] = (1, 4, 3, 2)
...
LIST [18] = (4, 1, 2, 3), LIST [19] = (4, 1, 3, 2),
LIST [20] = (4,2,1,3), LIST [21] = (4,2,3,1),
LIST [22] = (4,3,1,2), LIST [23] = (4,3,2,1)
As described above, the list calculated by the acquisition unit 106 can be indicated using LIST [i] = (LT, LB, RT, RB). For example, when LIST [3] = (1, 3, 2, 4), the input (1) of the first input unit 102 is displayed on the upper left (LT) of the display area, and the third input unit 104 is displayed on the lower left (LB). Indicates that the input (3) is placed. Furthermore, the input (2) of the second input unit 103 is arranged in the upper right (RT), and the input (4) of the fourth input unit 105 is arranged in the lower right (RB).

In the present embodiment, the acquisition unit 106 calculates feature amounts for all combinations of input video data and their arrangement. The number of combinations of video data and arrangement is 1 for video data input from each of the first input unit 102, the second input unit 103, the third input unit 104, and the fourth input unit 105. , 2, 3 and 4 are equal to the permutation calculation results for selecting four from the quaternion set. Note that the total number of combinations when the number of input video data is n is calculated by Equation 2. That is, the total number of combinations when the input video data is four is ₄ P ₄ = 4! = 4 × 3 × 2 × 1 = 24.
_n P _n (Formula 2)
In the above description, the permutation for extracting four elements from the quaternary set has been described. However, the present invention is not limited to this, and the present embodiment is applicable to a permutation for extracting k elements from the n-element set. A permutation calculation algorithm for extracting k elements from an n-element set is a general known technique, and thus description thereof is omitted.

  Next, in step S504, the acquisition unit 106 sets an initial value (i = 0).

  In step S505, the acquisition unit 106 acquires (determines) a processing target combination (a combination for which a feature value is calculated) from among the combinations of the video data recorded in steps S501 and S502 and the arrangement in the display area. To do. The acquisition unit 106 receives information (hereinafter referred to as a selection command) instructing to select a combination of input video data and arrangement. Based on the acquired selection command, the acquisition unit 106 determines the combination LIST [i] = (LB, LT, RB, RT) to be processed from the list acquired in step S503. In step S505 immediately after the initial value is set in step S504, the acquisition unit 106 determines LIST [0] as a combination of processing targets.

In step S506, the acquisition unit 106 calculates the feature amount of the video data based on the combination of processing targets acquired in step S505. That is, in this embodiment, the acquisition unit 106 calculates a motion vector in the Nth frame video data and the N + 1th frame video data as the feature amount of the video data. Note that the method for calculating the motion vector is not limited. As a motion vector calculation method generally used, there is a block matching method. In the block matching method, one frame of video data is divided into grid-like blocks, and a motion vector is obtained by correlating each block with video data within a search range in a frame temporally different from that frame. is there. In the present embodiment, the acquisition unit 106 calculates a motion vector from the Nth frame video data and the N + 1th frame video data. The acquisition unit 106 calculates a motion vector (vector value) for all the pixels of the video data of the (N + 1) th frame, and calculates a vector indicating where each pixel has moved between the Nth frame and the (N + 1) th frame. Various methods can be applied to represent the motion vector. For example, the motion vector P at the coordinates (x, y) of the video data has a movement amount a in the x direction and b in the y direction. If the base vector in the x direction is Z _x and the base vector in the y direction is Z _y , it can be expressed by Equation 1.

  In step S507, the acquisition unit 106 stores the motion vector, which is the feature amount of the video data calculated in step S506, in association with the video data and the arrangement.

  In step S508, the acquisition unit 106 determines whether the calculation processing of the motion vector that is the feature amount of the video data has been completed for all combinations of the input video data and the arrangement. That is, it is determined whether or not the combination LIST [i] to be processed acquired in step S505 is the last data in the list acquired in step 503, and if it is determined that it is not the last data in the list, The process proceeds to step S509. In step S509, the acquisition unit 106 increments i and advances the combination to be processed to the next combination. On the other hand, if it is determined in step S508 that the motion vector calculation processing has been completed for all combinations of video data and arrangement, the feature amount calculation processing ends. Here, when i = 23, it is determined that the data is the last data in the list (YES in step S606), and the combination selection process is terminated.

  As described above, the acquisition unit 106 can calculate the motion vector as the feature amount of the video data based on the Nth frame video and the N + 1th frame video that are temporally different.

  In the present embodiment, the acquisition unit 106 calculates a motion vector as a feature amount of video data, but the present invention is not limited to this. In other words, the acquisition unit 106 may calculate information regarding changes between a plurality of frames of an object in the video as a feature amount of the video data.

  Next, details of the process in which the determination unit 107 determines the arrangement of the video data in step S203 will be described with reference to FIG. FIG. 7 is a flowchart illustrating a method for determining the arrangement of the video data input to the input units 102 to 105 by the determination unit 107 in step S203 of FIG.

  In step S701, the determination unit 107 acquires a motion vector that is a feature amount of the video data calculated and stored by the acquisition unit 106 in step S505. Here, the determination unit 107 acquires motion vectors in all combinations of video data and arrangement calculated and stored by the acquisition unit 106.

  In step S <b> 702, the determination unit 107 acquires and holds information regarding the similarity between the motion vectors of pixels corresponding to the boundary regions of the regions 401 to 404 among all combinations of video data and arrangement.

  Details of the method for calculating the similarity of the motion vectors corresponding to the boundary regions of the regions 401 to 404 acquired by the determination unit 107 in step S702 will be described with reference to FIG. FIG. 8 is a diagram showing a motion vector of each pixel in a boundary region of each video data arrangement. FIG. 8 shows an example in which each video data shown in FIG. 3 is arranged in the display area shown in FIG. 8, the same reference numerals are assigned to the same areas and video data as the areas shown in FIG. 4 and the video data shown in FIG. 3, and the description thereof is omitted.

  Reference numerals 801, 802, 803, and 804 denote motion vector vectors. The end point of the arrow of each motion vector 801 to 804 indicates the pixel position of the (N + 1) th frame, and the start point of the arrow indicates the pixel position of the Nth frame.

  Reference numeral 805 denotes a boundary area of the arrangement of each video data. The boundary region indicates a pixel group included in a region between the sides in contact with the other regions and a predetermined distance T (for T pixels) in each of the regions 401 to 404. Here, in the present embodiment, T is represented by the number of pixels, but is not limited thereto, and may be a value indicating a boundary region. Since the region 401 (LT) is in contact with the region 403 (RT) and the region 402 (LB), the right side of the region 401 (LT) in contact with the region 403 (RT) and the region 401 (LT) in contact with the region 402 (LB) The region for T pixels from the lower side is a boundary region. Similarly, since the region 403 (RT) is in contact with the region 401 (LT) and the region 404 (RB), the left side of the region 403 (RT) in contact with the region 401 (LT) and the region 404 (RB) are in contact with each other. A region corresponding to T pixels from the lower side of 403 (RT) is a boundary region.

  Hereinafter, as an example, a method for calculating the similarity of motion vectors corresponding to the boundary region between the region 401 (LT) and the region 403 (RT) will be described. In the region 401 (LT) and the region 403 (RT), the right side of the region 401 (LT) and the left side of the region 403 (RT) are in contact with each other as a boundary. Then, the determination unit 107 calculates the difference value of the motion vector in the boundary region between the region 401 and the region 403 indicated by the thick rectangular region in FIG.

First, the sum _SLT of motion vectors in the boundary region on the right side of the region 401 (LT) can be calculated using the equation shown in Equation 3. In Equation 3, the width S of the input video data is set to w and the height is set to h, and the total motion vector S _LT of the boundary region on the right side of the region 401 is expressed by y-coordinate from w-T to w. It can be calculated by adding the motion vector of each pixel in the range from 0 to h in coordinates. A sum S _RT the motion vectors of the left side of the boundary region of the region 403 (RT) also can be calculated similarly.

Then, the similarity of the motion vectors in the boundary region (the portion surrounded by a thick frame) between the region 401 and the region 403 is expressed by the sum S of the motion vectors in the boundary region on the right side of the region 401 as shown in Expression 4. and _LT, expressed by the sum _{S RT} and differential motion vectors left side of the boundary region of the region 403. In Equation 4, the smaller the difference between the sum _{S RT} the sum _{S LT} is a high similarity of motion vectors of the boundary area between the region 401 and the region 403, a large difference between the sum _{S RT} the sum _{S LT} is It shows that the similarity of the motion vector in the boundary region between the region 401 and the region 403 is low.
S _LT -S _RT (Equation 4)
Here, in FIG. 8 of the present embodiment, reference numeral 806 (oval) indicates an object included in the video data. When the object 806 moves from the Nth frame to the (N + 1) th frame, the motion vector at the edge portion of the object 806 is a non-zero value, and the motion vector = 0 in the area other than the object 806. That is, based on the information about the object (person, thing) extracted by the extraction unit (not shown), only the motion vector at the edge portion of the object in the boundary region is obtained from the boundary region between the region 401 and the region 403. You may use as a similarity degree of a motion vector.

Further, the sum of motion vectors can be similarly calculated for the boundary region of the region 402 (LB) and the boundary region of the region 401 (RB). The similarity of motion vectors in all boundary regions (shaded portions in FIG. 8) can be expressed by Equation 5. In Equation 5, the smaller the calculated value is, the higher the similarity of the motion vectors in all the boundary regions is, and the larger the calculated value is, the lower the similarity of the motion vectors in all the boundary regions is.
_{(S LT -S RT) + (} S LT -S LB) + (S RB -S RT) + (S RB -S LB) ( Equation 5)
In step S702 in FIG. 7, the determination unit 107 acquires and holds the similarity between the motion vectors in the boundary area calculated using the above-described formula. In the present embodiment, the determination unit 107 calculates the similarity of the motion vectors in the boundary region using the equations 3 to 5. However, the present invention is not limited to this, and other calculation methods may be used.

  In step S703, the determination unit 107 determines the arrangement of each video data based on the information regarding the feature amount acquired and held in step S702. In other words, in the present embodiment, the determination unit 107 determines the combination having the highest similarity of motion vectors among the combinations of all input video data and arrangement as the arrangement of each video data. In other words, in the present embodiment, the determination unit 107 determines a combination having the smallest value calculated using the calculation method shown in Expression 5 of step S702 as the arrangement of each video data.

  By synthesizing and displaying the video data using the arrangement of the video data determined in each step of FIG. 7 described above, the layout can be appropriately set based on the feature amount of each input video data. .

  According to the present embodiment, in an image processing apparatus that inputs and displays a plurality of divided images, the images can be used in a layout intended by the user. In other words, even when a divided image obtained by dividing a movie having a black band around the combined image (up, down, left, and right) can be combined with an appropriate layout, the black band is crossed at the center of the combined image. It can be prevented from being synthesized on top. As described above, the content can be output in the layout intended by the user according to the present embodiment, so that the setting of the output device is changed, the input terminal is reconnected to the display device, and the setting of the display position on the display device is changed. There is no need.

(Embodiment 2)
In FIG. 1 of the first embodiment described above, the image processing apparatus 101 has the configuration including the display unit 109. However, the display unit 109 may be configured outside the image processing apparatus 101. Further, an overall control unit (not shown) may be provided inside the image processing apparatus 101 so that the overall control unit controls each processing unit of the image processing apparatus 101. For example, the configuration may be such that the overall control unit instructs the acquisition unit 106 to acquire the feature amount of the video data, and the acquisition unit 106 acquires the feature amount of the video data based on the instruction from the overall control unit. .

  Each processing unit shown in FIG. 1 has been described in the above embodiment as being configured by hardware. However, the processing performed by each processing unit shown in these drawings may be configured by a computer program. Hereinafter, the present embodiment will be described with reference to FIG. FIG. 6 is a block diagram illustrating a configuration example of computer hardware applicable to the image processing apparatus according to each of the embodiments.

  The CPU 601 controls the entire computer using computer programs and data stored in the RAM 602 and the ROM 603, and executes each process described above as performed by the image processing apparatus according to each of the above embodiments. That is, the CPU 601 functions as each processing unit shown in FIG.

  The RAM 602 has an area for temporarily storing computer programs and data loaded from the external storage device 606, data acquired from the outside via an I / F (interface) 607, and the like. Further, the RAM 602 has a work area used when the CPU 601 executes various processes. That is, the RAM 602 can be allocated as, for example, a picture memory or can provide various other areas as appropriate.

  The ROM 603 stores setting data and a boot program for the computer. The operation unit 604 is configured by a keyboard, a mouse, and the like, and can input various instructions to the CPU 601 by operation of a user of the computer. The output unit 605 displays the processing result by the CPU 601. Further, the output unit 605 is constituted by a liquid crystal display, for example.

  The external storage device 606 is a mass information storage device represented by a hard disk drive device. The external storage device 606 stores an OS (Operating System) and computer programs for causing the CPU 601 to realize the functions of the units illustrated in FIG. Furthermore, each image data as a processing target may be stored in the external storage device 606.

  Computer programs and data stored in the external storage device 606 are appropriately loaded into the RAM 602 under the control of the CPU 601 and are processed by the CPU 601. The I / F 607 can be connected to a network such as a LAN or the Internet, other devices such as a projection device or a display device, and the computer can acquire and send various information via the I / F 607. Can be. Reference numeral 608 denotes a bus connecting the above-described units.

  The operation having the above-described configuration is controlled by the CPU 601 centering on the processing described in the above flowchart.

(Other embodiments)
The present invention supplies a program that realizes one or more functions of the above-described embodiments to a system or apparatus via a network or a storage medium, and one or more processors in a computer of the system or apparatus read and execute the program This process can be realized. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

DESCRIPTION OF SYMBOLS 101 Image processing apparatus 102 1st input part 103 2nd input part 104 3rd input part 105 4th input part 106 Acquisition part 107 Determination part 108 Display control part 109 Display part

Claims (8)

An image processing device for combining a plurality of partial videos obtained by dividing a video,
First input means for inputting a first partial video;
Second input means for inputting a second partial video;
Acquisition means for acquiring feature quantities in a boundary region when combining the first partial video and the second partial video, and based on a plurality of temporally different images;
Control means for controlling to display the video in a layout when the first partial video and the second partial video are combined based on the feature amount acquired by the acquisition unit. A featured image processing apparatus. The acquisition unit acquires information on a motion vector in the boundary region as the feature amount,
The image processing apparatus according to claim 1, wherein the control unit displays the video in the layout based on information on the motion vector acquired by the acquisition unit. The acquisition means acquires information on the similarity between motion vectors in the boundary region as the feature amount,
The image processing apparatus according to claim 1, wherein the control unit displays the video in the layout based on information on the similarity of the motion vectors acquired by the acquisition unit. .   The image according to any one of claims 1 to 3, further comprising a combining unit that combines the first partial video and the second partial video based on the layout. Processing equipment. Furthermore, it has an extracting means for extracting an object included in the video,
The image processing apparatus according to claim 1, wherein the acquisition unit acquires the feature amount based on the object extracted by the extraction unit.   The image processing apparatus according to claim 5, wherein the acquisition unit acquires a motion vector at an edge of the object extracted by the extraction unit as the feature amount. An image processing method for combining a plurality of partial videos obtained by dividing a video,
A first input step of inputting a first partial video;
A second input step of inputting a second partial video;
An acquisition step of acquiring a feature amount in a boundary region when combining the first partial video and the second partial video;
And a control step of controlling to display the video in a layout when the first partial video and the second partial video are synthesized based on the feature amount acquired in the acquisition step. A featured image processing method.   The program for functioning a computer as each means of the image processing apparatus as described in any one of Claims 1 thru | or 6.

Images