KR20190114276A - Method for processing composite video and apparatus for the same - Google Patents

Abstract

Disclosed are a composite video processing method, capable of minimizing a problem occurring in an overlap area, and an apparatus thereof. According to one embodiment of the present invention, the composite video processing method comprises the following processes: generating a reference composite video combining a plurality of reference source videos based on the reference source videos inputted from a plurality of camera devices with synchronization, and generating reference stitching information defining a position relation between a pixel area included in the reference source videos and a pixel area included in the reference composite video; confirming a plurality of source videos inputted from the camera devices with synchronization; generating a stitched video in which the source videos are combined based on the reference stitching information; confirming a time difference generation area from which a time difference among the source videos is generated from the stitching video; and reflecting phase relation information of the source videos based on the time difference generation area to generate a composite video.

Description

METHOD FOR PROCESSING COMPOSITE VIDEO AND APPARATUS FOR THE SAME}

The present disclosure relates to a video or video processing technology, and more particularly, to a method and apparatus for processing a composite video combining a plurality of synchronized video or video.

Due to the dissemination of displays capable of playing high resolution images and virtual reality (VR) playback devices, research on the production of related contents (eg, high resolution video contents, panoramic video contents, VR contents, etc.) has been actively conducted. ought.

Dedicated devices for capturing high-definition video content, panoramic video content, VR content, etc. are being distributed, but they are being distributed at high prices because they have dedicated camera modules and parts. In addition, since most of these equipments match images using post-processing software after the shooting is completed, there is a limit that it is impossible to check and match the images at the same time.

Many improvements are required for real-time panorama image production, but the first of these is optimization of the matching method of source videos. Conventional video matching methods are mainly based on still images, not videos taken in real time, and the research focuses on quality of video rather than execution time, so it is difficult to match high resolution videos in real time.

An object of the present disclosure is to provide a method and apparatus for processing a composite video, which can minimize a problem occurring in an overlapped area while generating a composite video using a plurality of source videos.

Technical problems to be achieved in the present disclosure are not limited to the above-mentioned technical problems, and other technical problems not mentioned above will be clearly understood by those skilled in the art from the following description. Could be.

According to an aspect of the present disclosure, a method for processing a composite video is provided. The method may generate a reference composite video combining the plurality of reference source videos based on a plurality of reference source videos inputted in synchronization from a plurality of camera apparatuses, and include a pixel area included in the plurality of reference source videos. Generating reference stitching information that defines a positional relationship between pixel regions included in the reference synthesized video, checking a plurality of source videos that are respectively synchronized from the plurality of camera devices, and the reference stitching information. A step of generating a stitching image combining the plurality of source videos, a step of identifying a parallax generating region where parallaxes of the plurality of source videos are generated in the stitching image, and based on the parallax generating region Reflecting phase correlation information of the plurality of source videos and It may include the process of creating a movie.

The features briefly summarized above with respect to the present disclosure are merely exemplary aspects of the detailed description of the present disclosure described below, and do not limit the scope of the present disclosure.

According to the present disclosure, there may be provided a composite video processing method and apparatus capable of minimizing a parallax problem occurring in an overlapped area while generating a composite video using a plurality of source videos.

In addition, the method and apparatus for processing a composite video according to the present disclosure may be variously applied and applied to an apparatus for generating content by using a source video obtained from a multi-camera that cannot physically have one origin.

The effects obtainable in the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned above may be clearly understood by those skilled in the art from the following description. will be.

1 is a diagram illustrating an operation of generating a synthesized moving image by the synthesized moving image processing apparatus according to an embodiment of the present disclosure.
2 is a block diagram illustrating a configuration of a synthesized video processing unit included in the synthesized video processing apparatus according to an exemplary embodiment.
3 is a diagram illustrating a reference source video and a reference composite video processed by the composite video processing apparatus according to an embodiment of the present disclosure.
4 is a diagram illustrating reference stitching information generated by a composite video processing apparatus according to an embodiment of the present disclosure.
5A is a diagram illustrating a stitching image generated by the composite video processing apparatus according to an embodiment of the present disclosure.
5B is a diagram illustrating a composite video generated by the composite video processing apparatus according to an embodiment of the present disclosure.
6 is a flowchart illustrating a procedure of a composite video processing method according to an embodiment of the present disclosure.
7 is a block diagram illustrating a computing system executing a composite video processing apparatus and method according to an embodiment of the present disclosure.

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present disclosure. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention.

In describing the embodiments of the present disclosure, when it is determined that a detailed description of a known structure or function may obscure the gist of the present disclosure, a detailed description thereof will be omitted. In the drawings, parts irrelevant to the description of the present disclosure are omitted, and like reference numerals designate like parts.

In the present disclosure, when a component is "connected", "coupled" or "connected" with another component, it is not only a direct connection, but also an indirect connection in which another component exists in the middle. It may also include. In addition, when a component "includes" or "having" another component, it means that it may further include another component, without excluding the other component unless otherwise stated. .

In the present disclosure, terms such as first and second are used only for the purpose of distinguishing one component from other components, and do not limit the order or importance between the components unless specifically mentioned. Accordingly, within the scope of the present disclosure, a first component in one embodiment may be referred to as a second component in another embodiment, and likewise, a second component in one embodiment may be referred to as a first component in another embodiment. It may also be called.

In the present disclosure, components that are distinguished from each other are for clearly describing each feature, and do not necessarily mean that the components are separated. That is, a plurality of components may be integrated into one hardware or software unit, or one component may be distributed and formed into a plurality of hardware or software units. Therefore, even if not mentioned otherwise, such integrated or distributed embodiments are included in the scope of the present disclosure.

In the present disclosure, components described in various embodiments are not necessarily required components, and some may be optional components. Therefore, an embodiment composed of a subset of components described in an embodiment is also included in the scope of the present disclosure. In addition, embodiments including other components in addition to the components described in the various embodiments are included in the scope of the present disclosure.

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings.

1 is a diagram illustrating an operation of generating a synthesized moving image by the synthesized moving image processing apparatus according to an embodiment of the present disclosure.

The composite video processing apparatus 10 may include a plurality of camera devices 11-1, 11-2, and 11-3. In particular, the lens units included in the plurality of camera apparatuses 11-1, 11-2, and 11-3 are arranged to photograph subjects existing in different directions, respectively, and the plurality of camera apparatuses 11-1, 11-2 are provided. , 11-3) may acquire a plurality of source videos of capturing different photographing areas. In this case, each of the plurality of source videos may overlap the source video obtained from a neighboring camera device and a partial region.

In addition, the composite video processing apparatus 10 may include a composite video processing unit 15, and the composite video processing unit 15 may include a plurality of camera devices 11-1, 11-2, and 11-3. Synchronize the source video of the video, and combine and synchronize the plurality of source video to generate and store the composite video in real time.

For example, as the plurality of camera apparatuses 11-1, 11-2, and 11-3 provide a plurality of source videos 100-1, 100-2, and 100-3 obtained at the same time, the synthesis is performed. The video processing unit 15 considers an arrangement relationship of the plurality of camera devices 11-1, 11-2, and 11-3, and overlaps regions from the plurality of source videos 100-1, 100-2, and 100-3. (101-1, 101-2) is detected. Then, the composite video processor 15 stitches the first source video 100-1 and the second source video 100-2 based on the first overlapped area 101-1, and the second overlapped area 101. The stitching image may be configured by stitching the second source video 100-2 and the third source video 100-3 based on -2).

In addition, the composite video processor 15 may generate a composite video by correcting the stitching image by reflecting phase correlation information of the first internal third source video 100-1, 100-2, and 100-3. Can be.

Hereinafter, an operation of generating a composite video by reflecting phase correlation information by the synthesized video processor 15 will be described in detail.

2 is a block diagram illustrating a configuration of a synthesized moving picture processing unit included in the synthesized moving picture processing device according to an embodiment of the present disclosure.

Referring to FIG. 2, the composite video processing unit 20 may include a reference stitching information generation unit 21, a stitching image generation unit 23, a parallax generation area check unit 25, and a composite video generation unit 27. It may include.

First, the reference stitching information generation unit 21 checks a plurality of reference source videos captured by the plurality of camera devices 11-1, 11-2, and 11-3, respectively, and combines the plurality of reference source videos. A reference synthetic video may be generated. The reference stitching information generator 21 may generate reference stitching information that defines a positional relationship between the pixel areas included in the plurality of reference source videos and the pixel areas included in the reference synthesized video.

For example, the reference stitching information generating unit 21 requests the plurality of camera apparatuses 11-1, 11-2, and 11-3 to shoot the reference source video, and the plurality of camera apparatuses 11-1 and 11-2. , 11-3) may receive a plurality of reference source videos 301-1, 301-2, 301-3,. The reference stitching information generation unit 21 considers a plurality of reference source moving images 301-1 and 301-2 in consideration of the photographing direction, the arrangement state, etc. of the plurality of camera apparatuses 11-1, 11-2, and 11-3. , 301-3,... May be generated. In this case, the reference stitching information generation unit 21 includes pixels included in the plurality of reference source videos 301-1, 301-2, 301-3,..., And pixels included in the reference synthesized video 350. Reference stitching information indicating a positional relationship therebetween can be generated.

For example, the reference stitching information may be information indicating coordinates at which the coordinates of each pixel included in the plurality of reference source videos 301-1, 301-2, 301-3, ... are positioned in the reference synthesized video 350. Can be.

The reference stitching information 400 (refer to FIG. 4) indicates coordinates of each pixel included in the reference source videos 301-1, 301-2, 301-3, and ... and coordinates of the pixels included in the reference composite video. A mapped look-up table may be included. In addition, the reference stitching information is for the overlapped areas 360-1, 360-2,... Where the plurality of reference source videos 301-1, 301-2, 301-3, ... overlap. Information indicating a method of combining values of pixels included in the plurality of reference source videos 301-1, 301-2, 301-3,... (Ie, blending indication information (Blending Mask)) 420. ) May be further included.

In addition, the reference stitching information generator 21 divides the reference source videos 301-1, 301-2, 301-3, ... into a predetermined unit, and divides the reference source videos 301-1, 301-2, 301-3 into a control point 310. Reference stitching information may be constructed using corresponding pixels. For example, when the reference source video has a resolution of 1920 ×× 1080 units and the predetermined unit is set to '60', the reference stitching information generation unit 21 may use the reference source videos 301-1, 301-2, and 301. -3, ...) by dividing the horizontal and vertical regions into '60' and the pixel corresponding to the divided point 310, that is, the pixel located in the 32nd unit dividing 1920 units of the horizontal region into 60 and The region of the 18th pixel in which the 1080 unit of the vertical region is divided into 60 may be set as the division point 310. The reference stitching information generator 21 may generate a look-up table in which the split point 310 maps coordinates of pixels located in the reference synthesized video.

In addition, the predetermined unit for dividing the reference source videos 301-1, 301-2, 301-3,... By the reference stitching information generator 21 may be variously changed. For example, when the predetermined unit is set to '1', the reference stitching information generation unit 21 may generate a look-up table for 1920 × 1080 split points.

The reference stitching information generation unit 21 checks the scene transitions of the input source video, reconstructs the reference stitching information using the source video where the scene change occurs, and provides a reference for the source video where scene switching does not occur. The operation of updating the value of the lookup table included in the stitching information may be performed.

The reference stitching information generator 21 may generate reference stitching information based on information obtained during compression or encoding of a plurality of input source videos. For example, the type of frame (I frame, P frame, B frame, etc.) checked in the compression or encoding process of the input source video may be checked, and the scene transition may be determined.

The reference stitching information generator 21 may provide the stitching image generator 23 with reference stitching information generated through the above-described operation.

The stitching image generator 23 may identify a plurality of source videos input from the plurality of camera devices 11-1, 11-2, and 11-3, respectively. The stitching image generator 23 may generate a stitching image 500 (refer to FIG. 5A) by combining a plurality of source videos based on the reference stitching information.

The stitching image generating unit 23 may provide the stitching image 500 generated through the above-described operation to the parallax generating region checking unit 25. Correspondingly, the parallax generating region checking unit 25 may detect the parallax generating region 520 from the stitched image.

In detail, the parallax generating area checking unit 25 preferably detects the parallax generating area 520 based on the overlap area 510. To this end, the parallax generating area checking unit 25 may check the overlapping area 510 included in the stitching image based on the reference stitching information. In addition, the parallax generating region checking unit 25 may determine the parallax generating region 520 with respect to the overlapping region 510. Here, the parallax generating area checking unit 25 calculates a difference value between the reference composite video generated by the reference stitching information generating unit 21 and the stitching image, and determines the parallax generating area 520 using the calculated result. Can be.

The composite video generator 27 may generate the composite video by reflecting phase correlation information of the plurality of source videos based on the parallax generating region 520.

In detail, the composite video generator 27 may check phase correlation information on the source video corresponding to the overlapped area 510. For example, the composite video generator 27 may calculate x and y translation values in a corresponding region of the source video, and may determine this as phase correlation information. The composite video generator 27 may apply the phase correlation information to the splitting points 550 (see FIG. 5B) around the parallax generating region 520.

In addition, the composite video generator 27 may classify the overlapped region 510 and the non-overlapping region 515 to reflect the phase correlation information.

In detail, the composite video generator 27 may apply the above-described phase correlation information to the splitting point 550 existing in the overlap area 510. Then, the composite video generator 27 extracts the object 560 causing parallax in the parallax generating area 520 through image analysis, and the size of the object or motion information (eg, motion) for the object. Vector, etc.) can be estimated.

The composite video generating unit 27 may apply the above-described phase correlation information by reflecting the size of the object 560 or the motion information of the object. For example, as the composite video generation unit 27 confirms that the object 560 moves in the right direction, the composite video generation unit 27 targets the source video 570 located in the right direction and corresponds to the size of the object 560 that was requested. The coordinates of the dividing point 550 of the area to be moved can be moved.

That is, the composite video generator 27 may divide the non-overlapping region 575 of the source video 570 into a predetermined number, and apply the above-described phase correlation information at a ratio corresponding to the divided number. For example, the composite video generator 27 divides the non-overlapping area 575 of the source video 570 into 10 areas, and 90% of the phase correlation information is located at the splitting point of the partition area 575a closest to the overlapping area. Is applied, and a value of 80% of the phase correlation information may be applied to the dividing point of the second divided region 575b in the overlapped region. Similarly, the synthesized video generating unit 27 may start at 70% of the phase correlation information at the divided points of the divided regions 575c, 575d, 575e, 575f, 575g, 575h, and 575i which are the 3rd to 10th adjacent regions in the overlapped region. A value of 10% can be applied and the value of the stitching image generated based on the reference stitching information is not applied to the splitting point of the partition 575j closest to the 10th overlapping region. Can be.

Furthermore, the composite video generator 27 may provide the parallax generating region detected through the above-described operation to the reference stitching information generating unit 21, and the reference stitching information generating unit 21 reflects the parallax generating region. The value of the lookup table included in the aforementioned standard stitching information may be updated.

Although the above-described composite video processing apparatus 10 will be described based on the operation of generating the panoramic video, the present disclosure is not limited thereto. One of ordinary skill in the art may generate a composite video of various formats based on a method of generating a panoramic video.

6 is a flowchart illustrating a procedure of a composite video processing method according to an embodiment of the present disclosure.

The composite video processing method according to an embodiment of the present disclosure may be performed by the above-described composite video processing apparatus.

First, in operation S601, the composite video processing apparatus may identify a plurality of reference source videos respectively captured by the plurality of camera apparatuses, and generate a reference composite video combining the plurality of reference source videos. The synthesized video processing apparatus may generate reference stitching information that defines a positional relationship between the pixel areas included in the plurality of reference source videos and the pixel areas included in the reference synthesized video.

For example, the composite video processing apparatus requests photographing of a reference source video from a plurality of camera devices, and the plurality of reference source videos 301-1, 301-2, 301-3,... , See FIG. 3). The synthesized video processing apparatus is configured to synthesize a plurality of reference source videos 301-1, 301-2, 301-3, ... in consideration of the recording direction and the arrangement state of the plurality of camera devices. ) Can be created. In this case, the synthesized video processing apparatus may include a positional relationship between pixels included in the plurality of reference source videos 301-1, 301-2, 301-3, and pixels included in the reference synthesized video 350. Reference stitching information indicating may be generated.

For example, the reference stitching information may be information indicating coordinates at which the coordinates of each pixel included in the plurality of reference source videos 301-1, 301-2, 301-3, ... are positioned in the reference synthesized video 350. Can be.

The reference stitching information 400 (refer to FIG. 4) indicates coordinates of each pixel included in the reference source videos 301-1, 301-2, 301-3, and ... and coordinates of the pixels included in the reference composite video. A mapped look-up table may be included. In addition, the reference stitching information is for the overlapped areas 360-1, 360-2,... Where the plurality of reference source videos 301-1, 301-2, 301-3, ... overlap. Information indicating a method of combining values of pixels included in the plurality of reference source videos 301-1, 301-2, 301-3,... (Ie, blending indication information (Blending Mask)) 420. ) May be further included.

Furthermore, the composite video processing apparatus divides the reference source videos 301-1, 301-2, 301-3, ... into predetermined units, and divides the pixels corresponding to the divided control points 310. Can be used to construct reference stitching information. For example, when the reference source video has a resolution of 1920 ×× 1080 units and the predetermined unit is set to '60', the reference stitching information generation unit 21 may use the reference source videos 301-1, 301-2, and 301. -3, ...) by dividing the horizontal and vertical regions into '60' and the pixel corresponding to the divided point 310, that is, the pixel located in the 32nd unit dividing 1920 units of the horizontal region into 60 and The region of the 18th pixel in which the 1080 unit of the vertical region is divided into 60 may be set as the division point 310. The composite video processing apparatus may generate a look-up table in which the split point 310 maps coordinates of pixels located in the reference composite video.

Furthermore, the predetermined unit for dividing the reference source videos 301-1, 301-2, 301-3,... By the synthesized video processing apparatus may be variously changed. For example, when the predetermined unit is set to '1', the reference stitching information generation unit 21 may generate a look-up table for 1920 × 1080 split points.

The composite video processing apparatus checks the scene transitions of the input source video, reconstructs the reference stitching information using the source video where the scene transition occurs, and includes the reference stitching information for the source video where scene switching does not occur. The operation of updating a value of the lookup table may be performed.

The synthesized video processing apparatus may generate reference stitching information based on information obtained during the compression or encoding process of the input source video. For example, the type of frame (I frame, P frame, B frame, etc.) checked in the compression or encoding process of the input source video may be checked, and the scene transition may be determined.

In operation S602, the composite video processing apparatus may identify a plurality of source videos input from the plurality of camera devices, respectively. In operation S603, the composite video processing apparatus may generate a stitching image 500 (see FIG. 5A) by combining a plurality of source videos based on the reference stitching information.

In operation S604, the composite video processing apparatus may detect a parallax generating region 520 from the stitched image.

In detail, the composite video processing apparatus preferably detects the parallax generating area 520 based on the overlap area 510. To this end, the composite video processing apparatus may identify the overlapped area 510 included in the stitching image based on the reference stitching information. The synthesized video processing apparatus may determine the parallax generating area 520 with respect to the overlapping area 520. Here, the synthesized video processing apparatus may calculate a difference value between the reference synthesized video and the stitched image generated in operation S601, and determine the parallax generating region 520 using the calculated result.

In operation S605, the composite video processing apparatus may generate the composite video by reflecting phase correlation information of the plurality of source videos based on the parallax generating region 520.

In detail, the composite video processing apparatus may check phase correlation information on the source video corresponding to the overlapped area 510. For example, the composite video processing apparatus may calculate x and y translation values in a corresponding region of the source video, and may determine this as phase correlation information. The synthesized video processing apparatus may apply the phase correlation information to the splitting points 550 (see FIG. 5B) around the parallax generating region 520.

Furthermore, the composite video processing apparatus may classify the overlapped region 510 and the non-overlapping region 515 to reflect the phase correlation information.

In detail, the composite video processing apparatus may apply the above-described phase correlation information to the splitting point 550 existing in the overlapped area 510. Then, the composite video processing apparatus extracts the object 560 that causes parallax within the parallax generating region 520 through image analysis, and the size of the object and motion information (eg, a motion vector) of the object. Can be estimated.

The composite video processing apparatus may apply the above-described phase correlation information by reflecting the size of the object 560 or the motion information of the object. For example, when the composite video processing apparatus determines that the object 560 moves in the right direction, the composite video processing apparatus may be configured to target the source video 570 located in the right direction, and to determine the area of the region corresponding to the size of the object 560 that is being sought. The coordinates of the split point 550 may be moved.

That is, the composite video processing apparatus may divide the non-overlapping region 575 of the source video 570 into a predetermined number, and apply the above-described phase correlation information at a ratio corresponding to the divided number. For example, the composite video processing apparatus divides the non-overlapping area 575 of the source video 570 into 10 areas, and a 90% value of the phase correlation information is divided at the splitting point of the partition area 575a closest to the overlapping area. In addition, a value of 80% of the phase correlation information may be applied to a split point of the split area 575b that is second closest to the overlapped area. Similarly, the composite video processing apparatus has 70% to 10% of the phase correlation information at the divided points of the divided regions 575c, 575d, 575e, 575f, 575g, 575h, and 575i which are the 3rd to 10th closest overlap regions. A value may be applied, and the value of the stitching image generated based on the reference stitching information may be applied to the splitting point of the partition 575j closest to the 10th overlapping region without reflecting the phase correlation information.

Furthermore, the composite video processing apparatus may update the value of the lookup table included in the above-described reference stitching information by reflecting the parallax generating region detected through the above-described operation.

7 is a block diagram illustrating a computing system executing a composite video processing apparatus and method according to an embodiment of the present disclosure.

Referring to FIG. 7, the computing system 1000 may include at least one processor 1100, a memory 1300, a user interface input device 1400, a user interface output device 1500, and storage connected through a bus 1200. 1600, and network interface 1700.

The processor 1100 may be a central processing unit (CPU) or a semiconductor device that executes processing for instructions stored in the memory 1300 and / or the storage 1600. The memory 1300 and the storage 1600 may include various types of volatile or nonvolatile storage media. For example, the memory 1300 may include a read only memory (ROM) and a random access memory (RAM).

Thus, the steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, software module, or a combination of the two executed by the processor 1100. The software module resides in a storage medium (ie, memory 1300 and / or storage 1600), such as RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs. You may. An exemplary storage medium is coupled to the processor 1100, which can read information from and write information to the storage medium. In the alternative, the storage medium may be integral to the processor 1100. The processor and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal.

Exemplary methods of the present disclosure are represented as a series of operations for clarity of description, but are not intended to limit the order in which the steps are performed, and each step may be performed simultaneously or in a different order as necessary. In order to implement the method according to the present disclosure, the illustrated step may further include other steps, may include other steps except some, or may include additional other steps except some.

The various embodiments of the present disclosure are not an exhaustive list of all possible combinations and are intended to describe representative aspects of the present disclosure, and the matters described in the various embodiments may be applied independently or in combination of two or more.

In addition, various embodiments of the present disclosure may be implemented by hardware, firmware, software, or a combination thereof. For hardware implementations, one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), General Purpose It may be implemented by a general processor, a controller, a microcontroller, a microprocessor, and the like.

It is intended that the scope of the disclosure include software or machine-executable instructions (eg, an operating system, an application, firmware, a program, etc.) to cause an operation in accordance with various embodiments of the method to be executed on an apparatus or a computer, and such software or Instructions, and the like, including non-transitory computer-readable media that are stored and executable on a device or computer.

Claims (1)

In the method of processing a composite video,
Generating a reference composite video combining the plurality of reference source videos based on a plurality of reference source videos inputted in synchronization from a plurality of camera devices, respectively, and including a pixel area included in the plurality of reference source videos, Generating reference stitching information defining positional relationships between pixel regions included in the composite video,
Checking a plurality of source videos inputted in synchronization with each other from the plurality of camera apparatuses;
Generating a stitching image combining the plurality of source videos based on the reference stitching information;
Identifying a parallax generating region where parallaxes of the plurality of source videos are generated in the stitching image;
And generating the composite video by reflecting phase correlation information of the plurality of source videos based on the parallax generating region.

Images