KR20230056093A - A system and method for generating a ghost image including at least one image identified for each sequence for video comparison analysis - Google Patents

Abstract

The present invention relates to a technological idea for generating a ghost image generated by extracting only the motion of an object from a reference image for image comparison analysis. An image generating method according to an embodiment comprises the steps of: uploading, by a user terminal, the file or link information of a reference image including the continuous motion of an object to a server; generating, by the server, a ghost image, which is at least one image generated by extracting, from the background, only the pose of the object identified for each sequence in the reference image collected from the file or the link information; and providing, by the server, the generated ghost image to the user terminal. Therefore, the comparing efficiency of images can be increased.

Description

A system and method for generating a ghost image including at least one image identified for each sequence for video comparison analysis}

The present invention relates to an overall system and operation method for generating a ghost image obtained by extracting only motion of an object from a reference image for image comparative analysis.

Professional athletes use professional imaging equipment to film exercise videos and repeat the process of reviewing their own motion pictures.

In this review process, comparisons are made between reference images and sequence-by-sequence motions, and insufficient motions are supplemented.

Meanwhile, similar to professional athletes, ordinary people at the level of clubs can also repeat the process of reviewing after filming their own exercise videos through equipment such as mobile phones.

Similarly, in this process, the review process of correcting correctly is repeated while comparing its motion with the motion in the reference video for each sequence while contrasting with the reference images.

In this process, not only professional athletes but also the general public proceed with the review process by playing their own videos and reference videos side by side or playing them back at different times for comparison.

1 is a diagram illustrating a conventional method of comparing two images side by side for review of a golf swing.

Reference numeral 110 denotes an original image in which the swing of oneself (the first object, 111) is photographed, and reference numeral 120 corresponds to a reference image in which the swing of a professional player (the second object) is photographed.

When a playback command is input to the user terminal, the original video 110 and the reference video 120 are simultaneously played, and the user compares and reviews the swing of the first object 111 and the swing of the second object 121. proceeded to

This review method has a disadvantage in that image comparison is very inefficient because it is necessary to alternately check images reproduced in different frames. In addition, there is a problem in that system resources are wasted in that different images must be reproduced in their respective frames.

Korean Patent Publication No. 10-2008-0045359 "Interactive online golf game service method and recording medium through real-time analysis of physical condition, swing arc and speed" Korean Registered Patent No. 10-2010236 "Video 　 comparison 　 method and video 　 comparison 　 system using the same"

An object of the present invention is to increase image comparison efficiency by comparing the motions of two or more objects of interest in one image by sequence.

An object of the present invention is to prevent waste of system resources by reproducing only a single frame.

An image generating method according to an embodiment includes the steps of uploading, in a user terminal, a file or link information for a reference image including continuous motion of an object to a server, a reference image collected from the file or link information in the server. generating a ghost image in which only the poses of the objects classified by sequence are at least one or more images extracted from the background, and providing the created ghost image to the user terminal by the server. .

The providing of the generated ghost image to the user terminal may include providing link information in which the generated ghost image is stored to the user terminal in a push notification method.

Providing the generated ghost image to the user terminal may include transmitting a file of the generated ghost image to the user terminal using a push notification method.

An image generating method according to an embodiment includes storing an original image including a continuous motion of a second object in the user terminal, receiving a ghost image of a first object from the server, and adding the original image to the original image. The method may further include displaying a comparison image overlapping at least a portion of the ghost image.

The displaying of a comparison image by overlapping at least a portion of the ghost image with the original image may include adjusting at least one of transparency or color temperature of the ghost image differently from that of the original image. and displaying the ghost image, the transparency or color temperature of which is adjusted, by overlapping the original image.

Adjusting at least one of transparency or color temperature of the ghost image differently according to an embodiment includes adjusting transparency or color temperature of the ghost image compared to the original image based on control information received from a user. can do.

Adjusting at least one of transparency or color temperature of the ghost image differently according to an embodiment may include automatically adjusting transparency or color temperature of the ghost image compared to the original image using an artificial intelligence algorithm. .

The displaying of a comparison image in which at least a portion of the ghost image overlaps with the original image may include adding at least one thumbnail icon matching a sequence of the ghost image to the comparison image, and When a specific thumbnail icon is selected from among at least one or more thumbnail icons, a step of displaying a comparison image corresponding to a sequence matching the selected specific thumbnail icon may be included.

In the processing to display a comparison image in which at least a portion of the ghost image overlaps with the original image, a sequence of continuous motion of the first object is matched with a sequence of the second object. It may include processing synchronization, and displaying a comparison image in which the first object and the second object in which the sequence is matched overlap each other.

The processing to display a comparison image in which at least a portion of the ghost image overlaps with the original image may include extracting a time interval for each sequence of the continuous movement of the first object, and the second object. Extracting time intervals for each sequence of objects, and displaying a difference value of time intervals for each sequence of the first object based on the time interval for each sequence of the second object in the comparison image. there is.

An image generation system according to an embodiment includes a user terminal for uploading a file for a reference image including continuous motion of an object or transmitting link information for the reference image, and a reference image collected from the file or link information. may include a server that generates a ghost image, which is at least one image extracted from a background of only the poses of the objects classified by sequence, and provides the generated ghost image to the user terminal.

According to an embodiment, the server may provide link information in which the generated ghost image is stored or a file of the generated ghost image to the user terminal using a push notification method.

A user terminal according to an embodiment stores an original image including continuous motion of a second object, receives a ghost image of a first object from the server, and overlaps at least a portion of the ghost image with the original image. It can be processed to display a comparison image.

An image generating program according to an embodiment is an image generating program stored in a recording medium, and the image generating program is executed in a computing system and, in a user terminal, file or link information for a reference image including continuous movement of an object. A command set for uploading to a server, a command set for generating a ghost image, which is at least one image extracted from a background of only the pose of the object identified by sequence in the reference image collected from the file or link information in the server. , and a command set for providing the generated ghost image to the user terminal in the server.

According to an embodiment, by comparing motions of two or more objects of interest in one image for each sequence, image comparison efficiency may be increased.

According to one embodiment, it is possible to prevent waste of system resources by reproducing only a single frame.

1A is a diagram illustrating a conventional method of comparing two images side by side for review of a golf swing.
1B is a diagram showing a comparison image obtained by overlapping a ghost image with an original image according to an embodiment of the present invention.
2 is a diagram illustrating an image generating system according to an embodiment of the present invention.
3A and 3B are diagrams illustrating a ghost image generated by an image generating system according to an exemplary embodiment.
4 is a diagram illustrating ghost images generated in different poses classified by sequence.
5 is a diagram for explaining an embodiment in which a comparison image is generated by overlapping a ghost image with an original image in an image generating system according to an embodiment.
6 is a diagram for explaining an embodiment in which a comparison image is generated by overlapping a ghost image as it is with an original image in an image generating system according to an embodiment.
7 is a diagram illustrating comparison images in which ghost images of different transparency overlap each other.
8 is a diagram illustrating comparison images in which ghost images of different color temperatures overlap each other.
9 is a diagram for explaining an embodiment in which a thumbnail of a ghost image is included in a comparison image.
10 is a diagram explaining an image generating method according to an embodiment of the present invention.

Specific structural or functional descriptions of the embodiments according to the concept of the present invention disclosed in this specification are only illustrated for the purpose of explaining the embodiments according to the concept of the present invention, and the embodiments according to the concept of the present invention These may be embodied in various forms and are not limited to the embodiments described herein.

Embodiments according to the concept of the present invention can apply various changes and can have various forms, so the embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosures, and includes modifications, equivalents, or substitutes included in the spirit and scope of the present invention.

Terms such as first or second may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another component, for example, without departing from the scope of rights according to the concept of the present invention, a first component may be named a second component, Similarly, the second component may also be referred to as the first component.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when an element is referred to as “directly connected” or “directly connected” to another element, it should be understood that no other element exists in the middle. Expressions describing the relationship between components, such as "between" and "directly between" or "directly adjacent to" should be interpreted similarly.

Terms used in this specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate that the described feature, number, step, operation, component, part, or combination thereof exists, but one or more other features or numbers, It should be understood that the presence or addition of steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in this specification, it should not be interpreted in an ideal or excessively formal meaning. don't

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, the scope of the patent application is not limited or limited by these examples. Like reference numerals in each figure indicate like elements.

The present invention can be used for review to compare postures, and can be utilized in various fields such as tennis, golf, soccer, and sports dance.

Hereinafter, the characteristic configurations of the present invention will be described through embodiments used in golf.

1B is a diagram showing a comparison image 110 in which a ghost image 121 overlaps an original image 110 according to an embodiment of the present invention.

The original image 110 includes the first object 111, and the ghost image may be interpreted as an image obtained by extracting only the second object from the reference image 120.

In this specification, the first object means an object that represents a series of movements in an original image, and as a specific example, it means an ordinary person trying to correct the motions of professional players. In addition, the second object means an object included in the reference image, and may specifically mean a professional player compared to a normal person.

The comparison image 110 according to the present invention is based on the frame of the original image 110, and thus may include the background included in the original image 110 as it is.

The first object 111 of the original image 110 may perform distinct and continuous motions, and among the respective motions, significant motions may be classified as sequences.

For example, according to the movement of the first object 111 in the original video 110, viewpoints such as address, takeback, half swing, takeback, impact, and follow-through may be designated as respective sequences.

Meanwhile, the ghost image 121 may be interpreted as a still image stored in several sequences of the reference image 120 . For example, the reference image 120, like the original image 110, may display viewpoints such as address, takeback, half swing, takeback, impact, and follow-through as sequences according to the movement of the second object 121. can be specified. In addition, a ghost image may be generated by extracting only the image 121 of the second object from a still image captured in a sequence such as a designated address, takeback, half swing, takeback, impact, and follow-through.

Specific sequences for generating ghost images may be directly input by the user or set through a machine learning algorithm through big data analysis.

In FIG. 1A, reference numeral 121 denotes a second object, but in FIG. 1B, a ghost image, which is an image created by extracting only the second object, is identified.

Reference numeral 110 denotes a comparison image 110 in which the original image 110 and the ghost image 121 are overlapped and displayed in consideration of the sequence. The movement of the first object 111 in the impact sequence and the ghost image Movements of the second object identified as 121 may be displayed in an overlapping manner.

2 is a diagram illustrating an image generating system 200 according to an embodiment of the present invention.

An image generating system 200 according to an embodiment may include a user terminal and a server.

First, the user terminal may upload a file for a reference image including continuous movement of an object or transmit link information for the reference image to the server.

Accordingly, the server generates a ghost image, in which only the pose of an object classified by sequence is at least one image extracted from a background in a reference image collected from a file or link information, and provides the generated ghost image to the user terminal. can do.

In FIG. 2 , reference numerals 201 , 202 , 207 , and 208 denote operations on the user terminal side, and the remaining reference numerals may be interpreted as operations on the server side, information generated on the server side, and commands related to the server.

First, the user terminal may select a reference image including the continuous motion of the object (201), and provide a file or link information for the selected reference image to the server (202).

Next, the server may collect the reference image using the file or link information provided from the user terminal. If the user terminal transmits a file, a reference image may be included in the corresponding file.

In addition, if the user terminal transmits link information for accessing the reference image, the server can download the reference image by accessing the corresponding link information.

The server may generate and record information about the request status, request date, requested ID, country, app, request type, file name, etc. for each reference image as shown by reference numeral 204 .

In addition, the generated ghost image 205 can be interpreted as an image from which the background has been removed from the original image, and can be transmitted to the requesting terminal in the form of a notification alarm (206).

For example, the server may upload the generated ghost image to the database and provide link information for accessing the uploaded ghost image in the form of a notification alarm.

Reference numeral 207 denotes images recorded in the user terminal, and an original image, a comparison image obtained by overlapping the original image with a ghost image, and a reference image obtained by extracting the ghost image may be recorded.

In this case, the images may be recorded in various image quality such as normal quality, ghost sequence, and high quality.

Next, the user terminal may download the ghost image, overlap the original image, and display it in the form of a comparison image (208).

In an image generating method according to an embodiment, a sequence for generating a ghost image may be directly selected from a reference image in a user terminal.

The user terminal may input sequences to generate a ghost image from a reference image according to a user's input.

Accordingly, the user terminal may transmit the still images captured from the reference images in the generated sequences to the server and request generation of a ghost image.

In another embodiment, the user terminal transmits the reference video to the server, but may also transmit the reference video and information on generated sequences to the server together.

In this case, the server may generate a ghost image by capturing a still image from a reference image in the generated sequence, removing a background from the captured still image, and extracting only an object.

A user terminal according to another embodiment may select a sequence to generate a ghost image from a reference image by using an artificial intelligence algorithm instead of directly selecting a sequence.

At this time, the artificial intelligence algorithm may be driven in the server or in the user terminal.

For example, an artificial intelligence algorithm identifies sequences corresponding to address, takeback, half swing, back swing top, impact, and follow-through from a reference image through artificial intelligence that has learned golf images, and in the identified sequence You can capture still images.

In addition, the server may generate a ghost image in which the background is deleted from the still image captured for each sequence and only the object is extracted.

3A and 3B are diagrams illustrating a ghost image 320 generated from a reference image 310 .

3A shows a reference image 310 in a sequence in which the second object 301 takes an address, and a ghost image 320 in which only the second object 301 is extracted by deleting the background part in the sequence in which the address operation is taken. ).

Next, in FIG. 3B, the reference image 330 in the sequence in which the second object 301 is performing the follow-through operation is shown, and the background part is deleted from the sequence in which the follow-through operation is being performed, and only the second object 301 is displayed. The extracted ghost image 340 is shown.

The ghost image 320 and the ghost image 340 correspond to images in which part of the continuous motion of the same second object is captured, and may be images generated in different sequences.

Also, according to the golf swing mechanism, the ghost image 320 has a sequence ahead of the ghost image 340 in time.

4 is a diagram illustrating ghost images 400 generated in different poses classified by sequence.

As shown in FIG. 4, the ghost image 400 may be a set of still images captured from reference images in the address sequence 401, the backswing top sequence 402, the impact sequence 403, and the follow-through sequence 404. there is.

The ghost image 400 according to the present invention may further include information on time intervals that have elapsed from the previous sequence to the current sequence, along with the still images captured in each sequence.

For example, if the first ghost image is generated 1 second after the start of the reference image and the second ghost image is generated 3 seconds, the second ghost image includes a second ghost image 1 second after the first ghost image was generated. This may include a time interval of 2 seconds up to 3 seconds.

Information on the time interval may be additionally displayed in a comparison image in which the original image and the ghost image overlap.

For example, with respect to the time interval from address to the top of the backswing during the operation of the golf swing, a general person's time and a professional player's time can be compared.

To this end, a time interval of the first object from the address to the backswing top of the original image and a time interval of the ghost image from the address to the backswing top may be compared with each other.

If the time interval of the first object is 2 seconds and the time interval of the ghost image by the second object is 1 second, the user who monitored the comparison video will perform core exercise and swing trajectory to reduce the time from address to back swing top. You may want to consider checking.

The image processor according to an embodiment may display a difference value of a time interval of each sequence of the first object based on a time interval of each sequence of the second object in the comparison image.

5 is a diagram for explaining an embodiment in which a comparison image is generated by overlapping a ghost image with an original image in a user terminal.

Combining the foregoing descriptions, the comparison image 530 can be generated by overlapping the original image 510 with the ghost image 520 .

The ghost image 520 may be generated by capturing the entire reference image including the movement of the second object for each specific sequence, removing the background, and extracting only the second object.

The comparison image 530 may be generated by synchronizing the sequences of the original image 510 and the ghost image 520 with each other, and in FIG. 5, the portion corresponding to the impact sequence of the first object and the second object overlaps. indicate

6 is a diagram for explaining an embodiment in which a comparison image is generated by overlapping a ghost image 602 on a first object 601 of an original image in a user terminal as it is.

The ghost image 602 may be freely arranged at a position adjacent to the first object 601 in the original image. For example, at least a portion of the first object 601 may overlap or may not overlap, and may be freely disposed anywhere on the top, bottom, left, and right sides of the first object 601 .

The greater the overlap between the first object 601 and the ghost image 602, the shorter the movement distance of the user's gaze, enabling quick comparison between the two images, thereby increasing the efficiency of comparison.

However, when the first object 601 and the ghost image 602 overlap, it may be difficult to distinguish the two images. That is, it may be difficult to distinguish which image is a ghost image and which is the first object of the original image.

To this end, FIGS. 7 and 8 describe an embodiment of processing a ghost image to distinguish between two images.

7 is a diagram 700 illustrating comparison images in which ghost images of different transparency overlap each other.

First, in the original image 710, the transparency of the ghost image may be differently overlapped in the order of reference numerals 720 to 740.

The ghost image included in the comparison image 720 is more transparent than the ghost image included in the comparison image 740 .

In addition, the ghost image included in the comparison image 730 is more opaque than the ghost image included in the comparison image 720 and can be displayed with a degree of transparency that is more transparent than the ghost image included in the comparison image 740 .

The user terminal according to an embodiment may differently adjust the transparency of the ghost image compared to the original image. In addition, the user terminal according to an embodiment may display the ghost image whose transparency is adjusted by overlapping the original image.

The user terminal according to an embodiment may adjust the transparency of the ghost image compared to the original image based on control information received from the user, or may automatically adjust the transparency of the ghost image compared to the original image using an artificial intelligence algorithm. there is.

8 is a diagram 800 illustrating comparison images in which ghost images of different color temperatures overlap each other.

Comparison images denoted by reference numerals 810 and 820 are images obtained by overlapping two different ghost images extracted from a reference image.

Reference numeral 810 indicates that ghost images having the same color temperature are overlapped, and a ghost image generated from an address sequence and a ghost image generated from an impact sequence are overlapped with the same color temperature.

In this case of overlapping at the same color temperature, it may be ambiguous which ghost image belongs to a minute body part.

In order to distinguish them, at reference numeral 820, the ghost image generated from the address sequence and the ghost image generated from the impact sequence are overlapped with different color temperatures to distinguish them.

Referring to the fact that the comparison efficiency increases according to the color temperature, the user terminal according to an embodiment may adjust the color temperature of the ghost image differently compared to the original image and display the ghost image with the adjusted color temperature overlapped with the original image. there is.

For example, a user terminal according to an embodiment may adjust a color temperature of a ghost image compared to an original image based on control information received from a user.

In addition, the user terminal according to an embodiment may automatically adjust the color temperature of the ghost image compared to the original image using an artificial intelligence algorithm.

9 is a diagram for explaining an embodiment in which a thumbnail of a ghost image is included in a comparison image.

The user terminal according to an embodiment may add at least one thumbnail icon 911 matching the sequence of the ghost image to the comparison image 910 .

In addition, when a specific thumbnail icon is selected from among at least one or more thumbnail icons 911, the user terminal according to an embodiment may display a comparison image corresponding to a sequence matching the selected specific thumbnail icon.

When a thumbnail icon corresponding to the backswing top sequence is selected in the comparison image 910, the user terminal according to an embodiment controls to branch to the corresponding image so that a scene corresponding to the backswing top is displayed in the original image and the ghost image. .

Meanwhile, when a specific thumbnail icon is selected from among at least one thumbnail icon 921, the user terminal according to an embodiment may display a comparison image corresponding to a sequence matching the selected specific thumbnail icon.

That is, when a thumbnail icon corresponding to an impact sequence is selected in the comparison image 920, the user terminal according to an embodiment controls the source image and the ghost image to branch to the corresponding image so that a scene corresponding to the impact is displayed. .

10 is a diagram explaining an image generating method according to an embodiment of the present invention.

In the image generating method according to an embodiment of the present invention, a user terminal may upload a file or link information for a reference image including continuous motion of an object to a server (step 1001).

The server may generate a ghost image from a reference image collected from file or link information (step 1002). As described above, the ghost image may include at least one image extracted from the background of only the pose of the object identified for each sequence in the collected reference image.

In an image generating method according to an embodiment of the present invention, a server may provide a generated ghost image to the user terminal (step 1003).

For example, the server may provide link information in which the created ghost image is stored to the user terminal in a push notification method. In addition, the server may directly transmit the created ghost image file to the user terminal in a push notification method.

In an image generating method according to an embodiment of the present invention, a ghost image having adjusted transparency or color temperature may be displayed overlapping an original image in a user terminal (step 1004).

The user terminal may store the original image including the continuous movement of the second object. Also, a ghost image of the first object may be received from the server, and a comparison image obtained by overlapping at least a portion of the ghost image with the original image may be displayed.

In the image generation method according to an embodiment of the present invention, in displaying a comparison image, at least one of transparency or color temperature of the ghost image may be differently adjusted compared to the original image. In addition, a ghost image whose transparency or color temperature is adjusted may be overlapped with the original image and displayed.

An image generating method according to an embodiment of the present invention adjusts the transparency or color temperature of the ghost image compared to the original image based on control information received from a user, or controls the ghost image compared to the original image using an artificial intelligence algorithm. Transparency or color temperature can be adjusted automatically.

Meanwhile, in the image generating method according to an embodiment, at least one thumbnail icon matching a sequence of ghost images may be added to the comparison image in order to display the comparison image. In addition, when a specific thumbnail icon is selected from among at least one or more thumbnail icons, a comparison image corresponding to a sequence matching the selected specific thumbnail icon may be displayed.

In addition, the image generation method according to an embodiment may perform synchronization by matching a sequence of continuous motion of the first object with a sequence of the second object in order to display a comparison image.

In addition, the image generating method according to an embodiment may extract a time interval for each sequence of a continuous movement of a first object and extract a time interval for each sequence of a second object in order to display a comparison image. .

In this case, the difference value of the time interval of each sequence of the first object based on the time interval of each sequence of the second object may be processed to be displayed in the comparison image.

After all, according to an embodiment of the present invention, comparison efficiency of images can be increased by comparing motions of two or more objects of interest within one image for each sequence. Also, waste of system resources can be prevented by reproducing only a single frame.

The devices described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (14)

Uploading, in a user terminal, a file or link information for a reference image including continuous movement of an object to a server;
generating, in the server, a ghost image in which only the pose of the object classified by sequence is at least one image extracted from a background in the reference image collected from the file or link information; and
Providing, by the server, the generated ghost image to the user terminal
An image generating method comprising a. According to claim 1,
In the server, the step of providing the generated ghost image to the user terminal,
Providing link information in which the generated ghost image is stored to the user terminal in a push notification method
An image generating method comprising a. According to claim 1,
In the server, the step of providing the generated ghost image to the user terminal,
Transmitting the created ghost image file to the user terminal in a push notification method
An image generating method comprising a. According to claim 1,
In the user terminal,
Storing the original image including the continuous movement of the second object;
receiving a ghost image of a first object from the server;
processing to display a comparison image overlapping at least a portion of the ghost image with the original image;
Image generating method characterized in that it further comprises. According to claim 4,
The step of displaying a comparison image overlapping at least a portion of the ghost image with the original image,
adjusting at least one of transparency and color temperature of the ghost image to be different from that of the original image; and
Displaying the ghost image whose transparency or color temperature is adjusted by overlapping the original image
An image generating method comprising a. According to claim 5,
The step of differently adjusting at least one of transparency or color temperature of the ghost image,
Adjusting transparency or color temperature of the ghost image compared to the original image based on control information received from a user
An image generating method comprising a. According to claim 5,
The step of differently adjusting at least one of transparency or color temperature of the ghost image,
Automatically adjusting the transparency or color temperature of the ghost image compared to the original image using an artificial intelligence algorithm
An image generating method comprising a. According to claim 4,
The step of displaying a comparison image overlapping at least a portion of the ghost image with the original image,
Adding at least one thumbnail icon matching the sequence of the ghost image to the comparison image;
When a specific thumbnail icon is selected from among the at least one thumbnail icon,
Processing a comparison image corresponding to a sequence matching the selected specific thumbnail icon to be displayed
Image generating method characterized in that it comprises a. According to claim 4,
The step of displaying a comparison image overlapping at least a portion of the ghost image with the original image,
processing synchronization by matching a sequence of continuous motions of the first object with a sequence of the second object; and
Processing to display a comparison image overlapping the first object and the second object in which the sequence is matched
Image generating method characterized in that it comprises a. According to claim 4,
The step of displaying a comparison image overlapping at least a portion of the ghost image with the original image,
extracting time intervals for each sequence of the continuous movement of the first object;
extracting a time interval for each sequence of the second object;
Displaying a difference value of a time interval of each sequence of the first object based on a time interval of each sequence of the second object in the comparison image.
Image generating method characterized in that it comprises a. A user terminal for uploading a file for a reference image including continuous movement of an object or transmitting link information for the reference image; and
A server generating a ghost image, wherein only the pose of the object classified by sequence in the reference image collected from the file or link information is at least one image extracted from a background, and providing the generated ghost image to the user terminal.
An image generating system comprising a. According to claim 11,
The image generating system, characterized in that the server provides the link information in which the generated ghost image is stored or the file of the generated ghost image to the user terminal in a push notification method. According to claim 11,
The user terminal stores an original image including the continuous movement of the second object, receives a ghost image of the first object from the server, and produces a comparison image obtained by overlapping at least a portion of the ghost image with the original image. An image generating system characterized by processing to display. An image generating program stored on a recording medium, wherein the image generating program is executed in a computing system:
In a user terminal, a command set for uploading a file or link information for a reference image including continuous motion of an object to a server;
In the server, a command set for generating a ghost image, wherein only the pose of the object classified by sequence in the reference image collected from the file or link information is at least one image extracted from a background; and
In the server, a command set for providing the generated ghost image to the user terminal
An image generating program that includes.

Images