KR102243922B1 - Electronic device that enables video summarization by measuring similarity between frames and operating method thereof - Google Patents

Abstract

Disclosed are an electronic device for enabling video summarization by measuring a similarity between frames and an operation method thereof. According to the present invention, the operation method repeats the following steps of: setting a first frame among a plurality of frames forming a video as a reference frame; sequentially extracting and storing the n number of first frames including the reference frame in a data storage; and measuring a frame similarity between an n^th frame, which is the last frame among the n number of first frames, and the remaining frames to reset a frame having a frame similarity less than a reference value among the remaining frames as the reference frame and sequentially re-extracting and additionally storing the n number of second frames including the reset reference frame in the data storage. Accordingly, the operation method can support in implementing the video summarization.

Description

Electronic device that enables summary of video by measuring similarity between frames and its operation method {ELECTRONIC DEVICE THAT ENABLES VIDEO SUMMARIZATION BY MEASURING SIMILARITY BETWEEN FRAMES AND OPERATING METHOD THEREOF}

The present invention relates to an electronic device that enables a summary of a moving picture by measuring the similarity between frames, and a method of operating the same.

Video content platform apps have been counted as the apps that domestic smartphone users have used for the longest time, and considering that the usage time of these video content platform apps continues to increase, recently, a video that provides a variety of videos among people. Content platforms are gaining explosive popularity.

Since the video content platform provides numerous video content that can deliver useful information in various fields, people who want to search for necessary information gradually enter search terms on the portal site to browse related posts, but instead use the video platform to provide necessary information. I try to get information by watching videos related to. For example, information can be obtained by searching for vivid reviews of products of interest to purchase, or by watching videos of road views or parking lots of places to be visited.

Relatedly, learning information through watching videos has the advantage that it is easy to understand, memorable for a long time, and you can find fun with little attention, but you cannot grasp the entire contents of the video at a glance, so you can get the information you want. The downside is that you have to watch the video from start to finish. Specifically, if the video has been watched until the end, but it is not a video about the desired content, it may result in wasting time, and if the playing time of the video is long, there is a disadvantage in that a lot of time must be spent watching the video until the end.

In this case, if the video can be summarized by removing frames with high similarity by measuring the similarity between frames of the video, and extracting and storing only dissimilar frames in which new objects or large movements are detected, the user Even if you do not watch the video until the end, you can determine whether it is a video related to the information you are looking for within a short time, so it will be efficient in terms of user cost and time.

Furthermore, it can be used to designate a thumbnail to be displayed on the screen by reducing it so that it can be recognized at a glance before playing the video content.

Therefore, there is a need for a study on a technology that enables the summary of moving pictures by measuring the similarity between frames.

An electronic device that enables summarization of a video by measuring similarity between frames according to the present invention and an operating method thereof include setting a first frame among a plurality of frames constituting a video as a reference frame, and n First frames are sequentially extracted and stored in a data storage, and a frame similarity among the remaining frames is measured by measuring a frame similarity between the n-th frame, which is the last frame of the n first frames, and the remaining frames, and the frame similarity among the remaining frames is less than a reference value. It is intended to support the summary of the video by repeating the process of re-extracting n second frames including the reset reference frame after resetting to the reference frame and storing it in the data storage. .

According to an embodiment of the present invention, when a video summary command is received from a user by measuring similarity between frames, the electronic device sets the first frame among a plurality of frames constituting the video as a reference frame. A reference frame setting unit and n (n is a natural number of 2 or more) first frames including the reference frame among the plurality of frames-the n first frames are consecutive frames from the reference frame Is extracted and stored in a data storage, and frame similarity between the nth frame, which is the last frame of the n first frames, and the frames consecutive from the nth frame, are calculated, respectively, and a frame with the nth frame When a dissimilar frame having a similarity value less than a preset reference value is identified, the dissimilar frame is reset to the reference frame, and then n second frames including the reset reference frame are sequentially re-read. It includes a video summary unit that summarizes the video by repeating the process of extracting and additionally storing the video in the data storage.

In addition, according to an embodiment of the present invention, the method of operating an electronic device that enables a summary of a video by measuring similarity between frames is a first frame among a plurality of frames constituting a video when a video summary command is received from a user. A data storage by sequentially extracting n first frames including the reference frame among the plurality of frames-the n first frames are consecutive frames from the reference frame And a frame similarity between the n-th frame, which is the last frame of the n-th frames, and the frames consecutive from the n-th frame, respectively, and a frame similarity with the n-th frame is a preset reference value. When a dissimilar frame having a value less than is identified, the dissimilar frame is reset to the reference frame, and then n second frames including the reset reference frame are sequentially re-extracted to the data storage. And summarizing the video by repeating the storing process.

An electronic device that enables summarization of a video by measuring similarity between frames according to the present invention and an operating method thereof include setting a first frame among a plurality of frames constituting a video as a reference frame, and n First frames are sequentially extracted and stored in a data storage, and a frame similarity among the remaining frames is measured by measuring a frame similarity between the n-th frame, which is the last frame of the n first frames, and the remaining frames, and the frame similarity among the remaining frames is less than a reference value. After resetting to the reference frame, n second frames including the reset reference frame may be sequentially re-extracted and additionally stored in the data storage by repeating the process to enable summary of the video. .

1 is a diagram illustrating a structure of an electronic device that enables a summary of a moving picture by measuring similarity between frames according to an embodiment of the present invention.
2 and 3 are diagrams for explaining an electronic device that enables a summary of a video by measuring a similarity between frames according to an embodiment of the present invention.
4 is a flowchart illustrating a method of operating an electronic device enabling a summary of a moving picture by measuring similarity between frames according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. This description is not intended to limit the present invention to a specific embodiment, it is to be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention. While describing each drawing, similar reference numerals have been used for similar elements, and unless otherwise defined, all terms used in the present specification including technical or scientific terms refer to common knowledge in the technical field to which the present invention pertains. It has the same meaning as commonly understood by someone who has it.

In this document, when a part "includes" a certain component, it means that other components may be further included rather than excluding other components unless otherwise stated. In addition, in various embodiments of the present invention, each component, function blocks, or means may be composed of one or more sub-components, and the electrical, electronic, and mechanical functions performed by each component are electronic. A circuit, an integrated circuit, or an application specific integrated circuit (ASIC) may be implemented with various known devices or mechanical elements, and may be implemented separately or two or more may be integrated into one.

On the other hand, the blocks of the attached block diagram and the steps in the flowchart are computer program instructions that are mounted on a processor or memory of equipment capable of processing data such as general-purpose computers, special computers, portable notebook computers, and network computers to perform specified functions. It can be interpreted as meaning. Since these computer program instructions can be stored in a memory provided in a computer device or in a memory readable by a computer, the functions described in the blocks in the block diagram or in the steps in the flowchart are produced as a product containing the instruction means for performing this. It could be. In addition, each block or each step may represent a module, segment, or part of code containing one or more executable instructions for executing the specified logical function(s). In addition, it should be noted that in some alternative embodiments, functions mentioned in blocks or steps may be executed in a different order. For example, two blocks or steps shown in succession may be performed substantially simultaneously or may be performed in reverse order, and in some cases, some blocks or steps may be omitted.

1 is a diagram illustrating a structure of an electronic device that enables a summary of a moving picture by measuring similarity between frames according to an embodiment of the present invention.

Referring to FIG. 1, an electronic device 110 that enables a summary of a video by measuring similarity between frames according to an embodiment of the present invention includes a reference frame setting unit 111 and a video summary unit 112. .

When a video summary command is received from the user, the reference frame setting unit 111 sets the first frame among a plurality of frames constituting the video as a reference frame.

The video summary unit 112 sequentially extracts n (n is a natural number of 2 or more) first frames including the reference frame among the plurality of frames and stores them in a data storage, and among the n first frames By calculating the frame similarity between the last frame, the n-th frame, and the frames consecutive from the n-th frame, respectively, a dissimilar frame having a frame similarity with the n-th frame is less than a predetermined reference value. When it is confirmed, the dissimilar frame is reset to the reference frame, and then the n second frames including the reset reference frame are sequentially re-extracted and additionally stored in the data storage, thereby repeating the process of storing the video. Summarize. Here, the n first frames are frames that are continuous from the reference frame.

For example, referring to FIG. 2, when a video summary command is received from a user, the reference frame setting unit 111 uses the first frame 212 of the plurality of frames 211 constituting the video as a reference frame. Can be set.

At this time, assuming that n is 5, the video summary unit 112 sequentially extracts five frames 1 213 including the first frame 212 that is the reference frame among the plurality of frames 211 Can be stored in data storage.

In addition, the video summary unit 112 calculates a frame similarity between frames consecutive from the fifth frame 214 and the fifth frame 214, which is the last frame among the five frames 1 213, respectively, and the drawing Assuming that the frame indicated by reference numeral 215 is identified as a dissimilar frame 215 having a value less than a preset reference value, the frame similarity with the fifth frame 214 is reset, the dissimilar frame 215 is reset to the reference frame. After that, by repeating the process of sequentially re-extracting the five frames 2 216 including the dissimilar frame 215 that is the reset reference frame and storing it in the data storage, the video can be summarized. I can. Here, the five frames 1 213 and the five frames 2 216 may be consecutive frames from the reference frame.

In this case, according to an embodiment of the present invention, the moving picture summarizing unit 112 may include a frame similarity calculating unit 113 as a configuration that calculates a frame similarity to identify dissimilar frames.

When the n first frames including the reference frame are stored in the data storage, the frame similarity calculating unit 113 continues from the n-th frame, which is the last frame of the n first frames, and the n-th frame. The frame similarity between the frames to be used is calculated.

In this case, according to an embodiment of the present invention, the frame similarity calculating unit 113 may include a divided region extracting unit 114, an average value calculating unit 115, and a similarity calculating unit 116.

The divided region extracting unit 114 applies a window of a preset size to a target frame to be compared among the n-th frame and the frames consecutive from the n-th frame in a preset direction, so that the n-th frame and the From each of the target frames, t (t is a natural number of 2 or more) divided regions are extracted.

The average value calculating unit 115 checks pixel values of pixels constituting each of the t divided regions extracted from the n-th frame and the target frame, and then for each of the n-th frame and the target frame. , An average value of pixel values for pixels constituting each of the t divided regions is calculated.

Here, the pixel value may be a value composed of color codes such as RGB, HSB, and CMYK. In the case of black and white, a value specified by one number can be checked as a pixel value. By selecting one channel, the numeric value of the selected channel can be checked as a pixel value.

For example, in the case of an RGB channel, one of an R channel, a G channel, and a B channel may be selected and the numeric value of the selected channel may be checked as a pixel value.

The similarity calculating unit 116 generates a t-dimensional first vector having t average values composed of the average values of each of the t divided regions calculated for the n-th frame as respective components, and After generating a t-dimensional second vector having t average values consisting of the average values of each of the t divided regions calculated for each component, the vector similarity between the first vector and the second vector is determined by the n A frame similarity is calculated between the first frame and the target frame.

In this case, according to an embodiment of the present invention, the vector similarity may be calculated according to Equation 1 below.

Here, M is a vector similarity between two vectors, D is a Euclidean distance between two vectors, and a Euclidean distance D between the two vectors can be calculated according to Equation 2 below.

In Equation 2, D denotes the Euclidean distance, and p _i and q _i denote the i-th components included in the two vectors. As the Euclidean distance between two vectors is smaller, the two vectors can be regarded as similar vectors, and as the Euclidean distance between the two vectors is larger, the two vectors can be regarded as dissimilar vectors.

Accordingly, as the vector similarity between the first vector and the second vector increases, the first vector can be regarded as a vector similar to the second vector, and as the vector similarity decreases, the first vector is the second vector It can be seen as a vector similar to.

In connection with this, FIG. 3 is a diagram illustrating a process of extracting t divided regions from the n-th frame and the target frame in order to calculate a frame similarity between the n-th frame and the target frame.

Assuming that there is a frame such as the picture shown at 310 of FIG. 3, and assuming that t is 8, the divided area extracting unit 114 moves the window 311 of a preset size in a preset direction from the lower left. By applying in the diagonal direction 312, it is possible to extract eight divided regions. Specifically, the divided region extracting unit 114 applies the window 311 of a preset size to the frame shown in reference numeral 310 in a diagonal direction 312 from the lower left, so that the eight divisions as indicated by reference numeral 320 Regions can be extracted.

Then, the average value calculating unit 115 checks the pixel values of the pixels constituting each of the eight divided areas 320, and then the pixel values of the pixels constituting each of the eight divided areas 320 are determined. You can calculate the average value.

In addition, when the eight average values composed of the average values for each of the eight divided regions 320 are t1, t2, t3, t4, t5, t6, t7 and t8, the similarity calculating unit 116 An 8-dimensional vector having average values t1, t2, t3, t4, t5, t6, t7, and t8 as each component can be generated.

In this way, the divided region extracting unit 114, the average value calculating unit 115, and the similarity calculating unit 116 according to the present invention calculate the first vector for the n-th frame and the second vector for the target frame. Can be generated.

At this time, the first vector is called (t1, t2, t3, t4, t5, t6, t7, t8), and the second vector is called (t9, t10, t11, t12, t13, t14, t15, t16). In this case, the similarity calculation unit 116 includes the first vector (t1, t2, t3, t4, t5, t6, t7, t8) and the second vector (t9, t10, t11, t12, t13, t14, t15, The vector similarity between t16) may be calculated as a frame similarity between the n-th frame and the target frame.

In this way, the frame similarity calculating unit 112 calculates the frame similarity between the n-th frame and frames consecutive from the n-th frame, and then the frame similarity with the n-th frame is less than a preset reference value. When a dissimilar frame having a value is identified, a process of summarizing the video may be repeatedly performed by resetting the dissimilar frame to a reference frame.

According to an embodiment of the present invention, the video summary unit 112 may include a reference value correction unit 118 to adjust the playback time of the summary video according to the length of the video.

When the playing time of the video is less than a preset first time, the reference value correcting unit 118 corrects the reference value by multiplying the reference value by a preset first weight of more than 1 and less than 2, and the playing time of the video is preset. When the second time is exceeded, the reference value is corrected by multiplying the reference value by a preset second weight of greater than 0 and less than 1. Here, the second time is a value exceeding the first time.

In relation to the reference value correction unit 118, when the playback time of the video is less than the first time, in order to prevent the playback time of the summary video generated as the video with a relatively short playback time is summarized from being too short, By multiplying the reference value, which is a criterion for determining the dissimilar frame, by the first weight to increase the reference value, the criterion identified as the dissimilar frame may be relaxed. In this way, when the size of the reference value is largely adjusted, the length of the summary video is too short due to the short length of the original video because it is treated as the dissimilar frame and included as a frame of the summary video even when the frame similarity is relatively high. Can be solved.

On the other hand, when the playback time of the video exceeds the second time, in order to prevent the playback time of the summary video generated as the video with a relatively long playback time from being summarized become too long, the reference value correction unit 118 ) Is a criterion for determining the dissimilar frame by multiplying the reference value by the second weight to make the reference value smaller, thereby making the criterion identified as the dissimilar frame strict.

In this way, if the size of the reference value is adjusted to be small, it is treated as the dissimilar frame only when the frame similarity is low, and is included as a frame of the summary video, thus solving the problem that the length of the summary video is too long due to the long original video. I can.

For example, when the first time is referred to as '5 minutes' and the second time is referred to as '15 minutes', the reference value correcting unit 118 determines the reference value when the playing time of the video is less than '5 minutes'. The reference value can be largely corrected by multiplying '1.5', which is a preset weight of more than 1 and less than 2, and when the playing time of the video exceeds '15 minutes', the preset weight of more than 0 and less than 1 is' By multiplying by 0.5', the reference value can be corrected to be small.

According to an embodiment of the present invention, the electronic device 110 that enables a summary of a video by measuring similarity between frames may further include a summary video playback unit 117.

After the video is summarized, the summary video playback unit 117 sequentially connects the frames stored in the data storage and starts playback from the first frame when a summary video playback command for the video is received from the user. do.

4 is a flowchart illustrating a method of operating an electronic device enabling a summary of a moving picture by measuring similarity between frames according to an embodiment of the present invention.

In step S410, when a video summary command is received from the user, the first frame among a plurality of frames constituting the video is set as a reference frame.

In step S420, n first frames including the reference frame from among the plurality of frames (the n first frames are consecutive frames from the reference frame) are sequentially extracted and stored in a data storage. , A frame similarity with the n-th frame is less than a preset reference value by calculating a frame similarity between the n-th frame, which is the last frame of the n-th frames, and the frames consecutive from the n-th frame, respectively. When a dissimilar frame having a is confirmed, resetting the dissimilar frame to the reference frame, sequentially re-extracting the n second frames including the reset reference frame, and additionally storing it in the data storage By repeating, the video is summarized.

At this time, according to an embodiment of the present invention, in step S420, when the n first frames including the reference frame are stored in the data storage, the n-th frame, which is the last frame among the n first frames, is stored in the data storage. It may include calculating a frame similarity between a frame and frames consecutive from the n-th frame, and calculating the frame similarity is a comparison between the n-th frame and the frames consecutive from the n-th frame. Extracting t divided regions from each of the n-th frame and the target frame by applying a window of a preset size to the target frame as a target in a preset direction, and extracting from each of the n-th frame and the target frame After checking the pixel values of the pixels constituting each of the t divided areas, for each of the n-th frame and the target frame, the pixel values of the pixels constituting each of the t divided areas Computing an average value and generating a t-dimensional first vector having t average values consisting of the average values of each of the t divided regions calculated for the n-th frame as respective components, and the target frame After generating a t-dimensional second vector having t average values composed of the average values of each of the t divided regions calculated for each component, the vector similarity between the first vector and the second vector is calculated. It may include calculating a frame similarity between the n-th frame and the target frame.

In this case, according to an embodiment of the present invention, the vector similarity may be calculated according to Equation 1 above.

In addition, according to an embodiment of the present invention, the operation method of the electronic device is, after the video is summarized, when a summary video playback command for the video is received from the user, frames stored in the data storage are sequentially connected. Thus, it may further include starting playback from the first frame.

Further, according to an embodiment of the present invention, in step S420, when the playback time of the video is less than a preset first time, the reference value is corrected by multiplying the reference value by a preset first weight of more than 1 and less than 2, , When the playing time of the video exceeds a preset second time (the second time is a value exceeding the first time), the reference value is multiplied by a preset second weight of greater than 0 and less than 1 to the reference value. It may include the step of correcting.

In the above, with reference to FIG. 4, a method of operating an electronic device that enables a summary of a video by measuring similarity between frames according to an embodiment of the present invention has been described. Here, in an operation method of an electronic device that enables a summary of a video by measuring a similarity between frames according to an embodiment of the present invention, a summary of a video is possible through a similarity measurement between the frames described with reference to FIGS. 1 to 3. Since it may correspond to the configuration of the operation of the electronic device 110, a more detailed description thereof will be omitted.

An operation method of an electronic device that enables a summary of a moving picture by measuring a similarity between frames according to an embodiment of the present invention may be implemented as a computer program stored in a storage medium for execution through a combination with a computer.

In addition, the method of operating an electronic device that enables summarization of a moving picture by measuring the similarity between frames according to an embodiment of the present invention is implemented in the form of a computer program command for execution through a combination with a computer, Can be recorded. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded in the medium may be specially designed and configured for the present invention, 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. -A hardware device 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 not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, in the present invention, specific matters such as specific components, etc., and limited embodiments and drawings have been described, but this is provided only to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , If a person of ordinary skill in the field to which the present invention belongs, various modifications and variations are possible from these descriptions.

Therefore, the spirit of the present invention is limited to the described embodiments and should not be defined, and all things that are equivalent or equivalent to the claims as well as the claims to be described later fall within the scope of the spirit of the present invention. .

110: An electronic device that enables a summary of a video by measuring the similarity between frames
111: reference frame setting unit 112: video summary unit
113: frame similarity calculating unit 114: divided region extracting unit
115: average value calculation unit 116: similarity calculation unit
117: summary video playback unit 118: reference value correction unit

Claims (12)

A reference frame setting unit configured to set a first frame among a plurality of frames constituting a video as a reference frame when a video summary command is received from a user; And
When the first frame is set as the reference frame, the following steps 1) and 2) are repeatedly performed to store only some frames among the plurality of frames in the data storage, thereby summarizing the partial frames. Video summary section to create video
An electronic device that enables a summary of a moving picture by measuring similarity between frames including a.
Step 1) Of the plurality of frames, n (n is a natural number of 2 or more) frames including the reference frame-the n frames are consecutive frames from the reference frame-are sequentially extracted and stored in the data storage. Save
Process 2) When the n frames are stored in the data storage, frame similarity between the n-th frame, which is the last frame of the n-th frames, and frames consecutively present after the n-th frame, are sequentially calculated. Thus, the frame similarity among frames consecutively present after the n-th frame is the reference value until a dissimilar frame having a frame similarity with the n-th frame is confirmed to have a value less than a predetermined reference value. If all frames having the above values are removed and the dissimilar frame having a value of the frame similarity less than the reference value is identified, the dissimilar frame is reset to the reference frame, and then the process is performed based on the reset reference frame. 1) perform the operation again The method of claim 1,
The video summary unit
When the n frames including the reference frame are stored in the data storage through the process 1), in the process 2), the n-th frame, which is the last frame among the n frames, and after the n-th frame A frame similarity calculator that calculates the frame similarity between frames that are consecutively present in
Including,
The frame similarity calculation unit
By applying a window of a preset size to a target frame to be compared among the n-th frame and the frames consecutive from the n-th frame in a preset direction, t(t) from each of the n-th frame and the target frame is applied. A divided region extracting unit that extracts two or more natural numbers) divided regions;
After checking pixel values of pixels constituting each of the t divided regions extracted from each of the n-th frame and the target frame, for each of the n-th frame and the target frame, the t divided regions An average value calculating unit that calculates an average value of pixel values for each of the pixels constituting each; And
A t-dimensional first vector having t average values composed of the average values of each of the t divided regions calculated for the n-th frame as each component is generated, and the t-dimensional first vectors calculated for the target frame are generated. After generating a t-dimensional second vector having t average values consisting of the average values of each of the divided regions as each component, the vector similarity between the first vector and the second vector is determined from the n-th frame and the target frame. Similarity calculator that calculates the frame similarity between frames
An electronic device that enables a summary of a moving picture by measuring similarity between frames including a. The method of claim 2,
The vector similarity is an electronic device that enables a summary of a moving picture by measuring the similarity between frames calculated according to Equation 1 below.
[Equation 1]

Here, M is the vector similarity between two vectors, and D is the Euclidean distance between the two vectors. The method of claim 1,
After the video is summarized, when a summary video playback command for the video is received from the user, a summary video playback unit sequentially connects frames stored in the data storage and starts playback from the first frame
An electronic device that enables summarization of the moving picture by measuring similarity between frames further comprising a. The method of claim 1,
The video summary unit
When the playback time of the video is less than a preset first time, the reference value is multiplied by a preset first weight of more than 1 and less than 2 to correct the reference value, and the playback time of the video is preset second time-the second Time is a value exceeding the first time-When exceeding -, a reference value correcting unit for correcting the reference value by multiplying the reference value by a preset second weight of greater than 0 and less than 1
An electronic device that enables a summary of a moving picture by measuring similarity between frames including a. When a video summary command is received from a user, setting a first frame among a plurality of frames constituting the video as a reference frame; And
When the first frame is set as the reference frame, the following steps 1) and 2) are repeatedly performed to store only some frames among the plurality of frames in the data storage, thereby summarizing the partial frames. Steps to create a video
A method of operating an electronic device that enables a summary of a moving picture by measuring similarity between frames, including.
Step 1) Of the plurality of frames, n (n is a natural number of 2 or more) frames including the reference frame-the n frames are consecutive frames from the reference frame-are sequentially extracted and stored in the data storage. Save
Process 2) When the n frames are stored in the data storage, frame similarity between the n-th frame, which is the last frame of the n-th frames, and frames consecutively present after the n-th frame, are sequentially calculated. Thus, the frame similarity among frames consecutively present after the n-th frame is the reference value until a dissimilar frame having a frame similarity with the n-th frame is confirmed to have a value less than a predetermined reference value. If all frames having the above values are removed and the dissimilar frame having a value of the frame similarity less than the reference value is identified, the dissimilar frame is reset to the reference frame, and then the process is performed based on the reset reference frame. 1) perform the operation again The method of claim 6,
The step of generating the summary video
When the n frames including the reference frame are stored in the data storage through the process 1), in the process 2), the n-th frame, which is the last frame among the n frames, and after the n-th frame Calculating frame similarity between frames consecutively present in
Including,
The step of calculating the frame similarity is
By applying a window of a preset size to a target frame to be compared among the n-th frame and the frames consecutive from the n-th frame in a preset direction, t(t) from each of the n-th frame and the target frame is applied. Extracting 2 or more natural numbers) divided regions;
After checking pixel values of pixels constituting each of the t divided regions extracted from each of the n-th frame and the target frame, for each of the n-th frame and the target frame, the t divided regions Calculating an average value of pixel values for each of the pixels constituting each; And
A t-dimensional first vector having t average values composed of the average values of each of the t divided regions calculated for the n-th frame as each component is generated, and the t-dimensional first vectors calculated for the target frame are generated. After generating a t-dimensional second vector having t average values consisting of the average values of each of the divided regions as each component, the vector similarity between the first vector and the second vector is determined from the n-th frame and the target frame. Step of calculating the frame similarity between
A method of operating an electronic device that enables a summary of a moving picture by measuring similarity between frames, including. The method of claim 7,
The vector similarity is a method of operating an electronic device that enables a summary of a moving picture by measuring a similarity between frames calculated according to Equation 1 below.
[Equation 1]

Here, M is the vector similarity between two vectors, and D is the Euclidean distance between the two vectors. The method of claim 6,
After the video is summarized, when a summary video playback command for the video is received from the user, sequentially connecting frames stored in the data storage and starting playback from the first frame
The method of operating an electronic device for enabling a summary of a moving picture by measuring a similarity between frames further comprising a. The method of claim 6,
The step of generating the summary video
When the playback time of the video is less than a preset first time, the reference value is multiplied by a preset first weight of greater than 1 and less than 2 to correct the reference value, and the playback time of the video is preset second time-the second Time is a value exceeding the first time-If exceeds, correcting the reference value by multiplying the reference value by a preset second weight of greater than 0 and less than 1
A method of operating an electronic device that enables a summary of a moving picture by measuring similarity between frames, including. A computer-readable recording medium recording a computer program for executing the method of any one of claims 6 to 10 through combination with a computer. A computer program stored in a storage medium for executing the method of claim 6 through a combination with a computer.

Images