WO2019209027A1

WO2019209027A1 - Method and system for detecting and tracking video copy

Info

Publication number: WO2019209027A1
Application number: PCT/KR2019/004964
Authority: WO
Inventors: 이준영
Original assignee: 리마 주식회사
Priority date: 2018-04-24
Filing date: 2019-04-24
Publication date: 2019-10-31

Abstract

A method and a system for detecting and tracking a video copy are provided. The method performed by a computer comprises: a candidate frame extraction step of extracting one or more candidate frames from an original video, wherein the candidate frames include candidate areas in which identification information of a user having requested playing of an original video can be inputted; and a step of generating a corrected video in which the identification information has been inputted in the candidate area within a specific candidate frame, wherein the candidate area is a space having a specific range or more within a frame, and has a color within a reference value difference.

Description

Method and system for video copy detection and tracking

The present invention relates to a method and a system for detecting and tracking a moving picture copy, and more particularly, to a method and a system for preventing distribution of a moving picture by unauthorized copying and detecting and tracking a leaked copy of a moving picture.

As information and communication technologies and networks are developed, various contents, such as education, publication, music, movies, and games, which have been provided offline, are produced in digital data form and distributed and provided online.

Unlike the offline delivery method, contents produced in the form of digital data are easily acquired, copied, transformed, processed, modified and propagated, so that the original creator of the contents is often damaged due to illegal leakage. Is happening.

Therefore, in order to preserve the value of the produced contents and to create legitimate profits, the original producer prevents unauthorized copying and distribution of contents by unauthorized third parties, and traces leakers by reason of compensation and punishment if leaked. Means are required to enable the claim.

In particular, video content among digital contents is one of the most active illegal outflow. The reason is that the video content can easily obtain a URL containing the video, and illegal download is possible using various software and programs based on the obtained URL.

On the other hand, a current method for copy protection of video content is a method of encrypting the video itself using a digital rights rights (DRM, Digital Rights Management). DRM refers to a solution that encrypts digital content and makes it available only to customers who have purchased it normally. However, there are many ways to disable and avoid DRM, such as programs that can capture or record video as a whole.

The problem to be solved by the present invention is to provide a method and system that can generate a video capable of tracking the leak of unauthorized video.

In addition, the problem to be solved by the present invention is to provide a method and system that can detect whether or not unauthorized copying to the distributed video and track the leaker.

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

According to an aspect of the present invention, a method for detecting and tracking video duplication according to an aspect of the present invention includes extracting one or more candidate frames from an original video, which is performed by a computer, wherein the candidate frames request playback of the original video. A candidate frame extracting step comprising a candidate region into which identification information of a user can be inserted; And generating a corrected moving picture in which the identification information is inserted into a candidate region in a specific candidate frame, wherein the candidate region is a space over a specific range within the frame and is configured with a color within a difference of a reference value.

According to another aspect of the present invention, there is provided a method for detecting and tracking video duplication. The step of generating the corrected video includes setting an identification information input area as an average color of the candidate area in the candidate area. Doing; And inserting identification information of the user into a color that differs from the average color by a minimum value in the identification information input area.

According to another aspect of the present invention for solving the above-described problems, the method for detecting and tracking video duplication is composed of the average color of the candidate area in the candidate area, the average color area that can insert the user's identification information And extracting the identification information input area, wherein the identification information input area is located in the average color area.

According to another aspect of the present invention for solving the above-described problem, the method for detecting and tracking video duplication, the step of generating the corrected video, is composed of the average color of the candidate area in the candidate area, Extracting an average color area into which identification information can be inserted; And inserting identification information of the user in the average color area, wherein the identification information of the user is configured by a color that differs from the average color by a minimum value.

According to still another aspect of the present invention, there is provided a method for detecting and tracking video duplication, in which the first average color region and the second average color region are determined by a specific rule when the average color region is plural. Extracting; Separating the identification information of the user into a first portion and a second portion; And inserting the first portion and the second portion into the first average color region and the second average color region, respectively.

According to another aspect of the present invention for solving the above-described problem, a method for detecting and tracking video duplication extracts one or more candidate frames from a video to be detected, which is performed by a computer, wherein the candidate frames may be used to extract the original video. A candidate frame extracting step comprising a candidate region into which identification information of a user who has requested playback can be inserted; And searching for the identification information with respect to the candidate region within a specific candidate frame, wherein the candidate region is a space over a specific range within the frame and is configured with a color within a difference of a reference value.

According to still another aspect of the present invention, there is provided a method for detecting and tracking video duplication, wherein the searching for identification information includes searching for an area where a color differs from the candidate area by a minimum value. When the area where the color differs by the minimum value is detected, the identification information is extracted from the area where the color differs by the minimum value.

According to another aspect of the present invention for solving the above problems, a method for detecting and tracking video duplication is to extract identification information from each of the plurality of areas when a plurality of areas where the color differs by a minimum value is detected. step; And combining the extracted identification information.

According to another aspect of the present invention for solving the above problems, a system for detecting and tracking video duplication extracts one or more candidate frames from an original video, wherein the candidate frames contain identification information of a user who requested to play the original video. A candidate frame extractor comprising an insertable candidate region; And a generation unit for generating a corrected moving picture in which the identification information is inserted into a candidate region in a specific candidate frame, wherein the candidate region is a space over a specific range within the frame and is configured with a color within a reference value difference.

In accordance with another aspect of the present invention for solving the above problems, a system for detecting and tracking video duplication extracts one or more vvoframes from a duplicate video, wherein the candidate frame includes identification information of a user who requested to play the original video. A candidate frame extractor comprising an insertable candidate region; And a searcher for searching for the identification information with respect to the candidate region within a specific candidate frame, wherein the candidate region is a space over a specific range within the frame and is configured with a color within a difference of a reference value.

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

According to the present invention, the video author can create a corrected video to track the leaker in preparation for the unauthorized copying and leakage of the original video. Therefore, the video author can prepare for the damage caused by the video leakage in advance, and the video play requester can prevent unauthorized copying and distribution of the video.

In addition, according to the present invention, it is possible to determine whether the video is copied without permission for the distributed video, and if the video is unauthorized copying can detect and track the leaker. Therefore, the video author has the effect of tracking the leaker and requesting compensation for the leaker or requesting the leaker to be punished when damage occurs due to the leaking video.

In addition, according to the present invention, since the identification information of the user inserted into the corrected video is inserted in a way that the viewer is difficult to recognize with the naked eye, it is possible to prevent unauthorized copying of the video without inconvenience to the viewers watching the video. It works.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a block diagram schematically illustrating a configuration of a system for detecting and tracking a video copy according to an embodiment of the present invention.

2 is a flowchart schematically showing a method for generating a corrected moving picture that can be traced out according to an embodiment of the present invention.

3 is an exemplary view for explaining a step of extracting a candidate frame from a plurality of frames constituting a video according to an embodiment of the present invention.

4 is a flowchart schematically illustrating a process of inserting user identification information into an original video according to an embodiment of the present invention.

5 is an exemplary view showing a screen of an original video and a corrected video according to an embodiment of the present invention.

6 is an exemplary view for explaining how the user's identification information is inserted into the identification information input area according to another embodiment of the present invention.

FIG. 7 is a flowchart illustrating a method of generating a corrected moving picture that can be traced to a leaker, further comprising specifying an area in which identification information is inserted into an original video as an average color area according to another embodiment of the present invention.

8 is an exemplary view illustrating a candidate region and an average color region in a candidate frame according to another embodiment of the present invention.

9 is a flowchart schematically illustrating a method of dividing a user's identification information into a plurality of portions and inserting the identification information into a plurality of average color regions according to another embodiment of the present invention.

10 is an exemplary view showing a case where there are a plurality of average color areas according to another embodiment of the present invention.

11 is a flowchart schematically illustrating a video copy detection and tracking method according to an embodiment of the present invention.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but can be embodied in various different forms, and the present embodiments only make the disclosure of the present invention complete, and those of ordinary skill in the art to which the present invention belongs. It is provided to fully inform the skilled worker of the scope of the invention, which is defined only by the scope of the claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, "comprises" and / or "comprising" does not exclude the presence or addition of one or more other components in addition to the mentioned components. Like reference numerals refer to like elements throughout, and "and / or" includes each and all combinations of one or more of the mentioned components. Although "first", "second", etc. are used to describe various components, these components are of course not limited by these terms. These terms are only used to distinguish one component from another. Therefore, of course, the first component mentioned below may be a second component within the technical spirit of the present invention.

In the present specification, the "original video" is a final version that is a form for distributing a video produced by the original author of the video, and means a video as it is without any processing, modification, change, identification information insertion and duplication.

In the present specification, the 'correction video' refers to a video that is generated by inserting user's identification information in a specific way to the original video and tracking the leaked person.

In the present specification, 'frame' refers to a cut of an image used in a video.

In the present specification, a 'key frame' refers to a frame which is the center of the frame such as a start frame and an end frame of a single operation.

In the present specification, 'candidate frame' refers to a frame that satisfies a condition for inserting user's identification information by the method proposed in the present invention among a plurality of frames constituting the original video.

In the present specification, the "candidate area" means an area into which identification information of a user can be inserted in the candidate frame.

For example, according to an embodiment of the present invention, the candidate area is a space over a specific range within the frame, and is a region composed of colors within a difference of a reference value. However, the present invention is not limited thereto, and may be extracted using a feature that can distinguish a frame in the technical field to which the present invention pertains.

In the present specification, the 'average color region' means a region composed of an average color of candidate regions in the candidate region.

In the present specification, 'identification information' refers to identification information of a user who requested to play a video. For example, the identification ID of the user, the identification number of the playback device, the network IP address (Internet Protocol Address), the MAC address (Media Access Control Address), and the time of the playback request may be included, but are not limited thereto. Various information that can be included may be included.

In the present specification, the 'identification information input area' means an area where the user's identification information is located.

Unless otherwise defined, all terms used in the present specification (including technical and scientific terms) may be used in a sense that can be commonly understood by those skilled in the art. In addition, terms that are defined in a commonly used dictionary are not ideally or excessively interpreted unless they are specifically defined clearly.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

The present invention includes an invention related to a method for generating a corrected moving picture which can be traced to a leaker, and an invention related to a method of detecting a copy of a moving picture and tracking a leaker. First, an invention related to a method for generating a corrected video capable of tracking an leaker will be described.

Referring to FIG. 1, a system 1000 for detecting and tracking a video copy includes a corrected video generating server 100 and a copy video detecting and tracking server 200.

The corrected video generation server 100 and the duplicate video detection and tracking server 200 are not necessarily separate servers, but are also managed as one server.

The correction video generation server 100 receives the original video 10 and inserts the identification information 60 of the user who requested to play in the original video 10 to generate a correction video 20 for tracking the leaker. Play a role.

To this end, the corrected video generating server 100 extracts at least one candidate frame 30 into which the identification information 60 of the user can be inserted from a plurality of frames constituting the original video 10. The corrected video generating server 100 extracts the candidate region 40 from the extracted candidate frame 30 and inserts the identification information 60 of the user.

The duplicate video detection and tracking server 200 determines whether the corresponding video is a duplicate video with respect to the distributed video, and tracks a leaker if the video is unauthorized copying.

To this end, the duplicate video detection and tracking server 200 extracts at least one candidate frame 30 in which it is estimated that the user's identification information 60 has been inserted. The duplicate video detection and tracking server 200 extracts the candidate region 40 in the candidate frame 30 extracted from the detection target video. The duplicate video detection and tracking server 200 detects whether the identification information 60 of the user is inserted into the extracted candidate region 40, and extracts the detected identification information 60 of the user.

Detecting whether the identification information 60 of the user is inserted may be automatically performed by the server as described above, but the present invention is not limited thereto, and the detection requester may directly confirm the operation.

Referring to Figure 2, according to an embodiment of the present invention, a method for generating a corrected moving picture tracking, extracting the candidate frame 30 into which identification information can be inserted from the original video (10) (S100), And inserting identification information into the candidate region 40 (S200), and generating a corrected video 20 into which the identification information is inserted (S300). Hereinafter, a detailed description of each step will be described.

3 is an exemplary view for explaining a step (S100) of extracting a candidate frame from a plurality of frames constituting a video according to an embodiment of the present invention.

A video is a video that makes it appear as if it is moving to the human eye by displaying a series of images called frames. Therefore, one video is composed of a plurality of frames, and the higher the frame, the smoother and clearer the video. On the other hand, the number of frames constituting one second of the video is expressed in x length per second, fps and the like.

Extracting the candidate frame 30 into which the identification information can be inserted in the original video 10 (S100) may insert the user's identification information 60 among a plurality of frames constituting the original video 10. Selecting and extracting a frame including the candidate region 40 satisfying the requirements.

The candidate area 40 is a space over a specific range in which the identification information in the frame can be inserted, and means the area composed of colors within the difference between the reference values.

According to an embodiment of the present invention, the reference value may be set differently according to the type of the original video, and means a difference value in which the color difference is not felt or is very fine when the frame is visually seen.

Referring to FIG. 3, by way of example, a part of the frame constituting the video is illustrated. Among the plurality of illustrated frames, the frames in the first half include the candidate area 40, which is an area composed of colors within a reference value difference at the same or similar position. The frames sharing the same feature are extracted as the candidate frame 30.

According to an embodiment of the present invention, the candidate frame 30 may form a plurality of candidate groups, and each candidate group includes a candidate frame 30 into which identification information of the same color may be inserted. The candidate group may be selected based on a key frame, but is not limited thereto. Various methods may be applied to extract a frame sharing a color below a reference value.

Inserting identification information into the candidate region 40 (S200), extracting the candidate region 40 from the candidate frame 30 of the original video 10 (S210), identification information input area 50 Setting the average color of the candidate area (S220), and inserting the user identification information 60 into the identification information input area 50 (S230).

The candidate region 40 refers to a region composed of colors within the difference between the reference values shared by the candidate frames 30. In other words, if the difference between the areas adjacent to the color of a specific area in the screen constituting the frame is within the reference value, the corresponding area becomes the candidate area 40. Accordingly, candidate frames 30 sharing the same candidate region 40 can insert identification information at the same position with the same color and size.

Unlike when the identification information is inserted at an arbitrary position, the candidate frame and the candidate region where the identification information may be inserted are selected and detected without the need to detect the identification information for all regions of all frames in the duplicate video detection and tracking step. You can do it. Therefore, according to the present invention, it is possible to efficiently and quickly detect duplicate video.

The identification information input area 50 means an area where the user's identification information 60 is substantially located. For example, it may be displayed as a background color of the user identification information 60 composed of characters.

The identification information input area 50 is set to the average color of the candidate area 40 (S220). This is for the viewer of the corrected video 20 to be difficult to find by the naked eye when the identification information input area 50 is inserted into the video, so as not to cause inconvenience to viewing.

The identification information 60 of the user is inserted to be located in the identification information input area 50 set as the average color of the candidate area 40. On the other hand, the user identification information 60 is composed of a color that differs by the minimum value from the average color.

According to an embodiment of the present invention, when the color is represented by an RGB (Red, Green, Blue) system, the color density is represented by a number from 0 to 255. The closer to 255, the higher the intensity of the color of the series, and the closer to 0, the lower the intensity of the color of the series. In this case, the minimum value means a difference of 1 in the RGB system.

On the other hand, the color of the user identification information 60 may be higher than the average color by one, or may be lower.

For example, if the average color of the candidate area 40 is the color of the green system among the three primary colors and the value of Green is 180, the color of the user identification information 60 is the value of the average color and the red color. And the value of Blue may be set to 181 or 179 which are the same but differ from the value of green by 180 and 1.

This corresponds to a color difference that is difficult to distinguish with the naked eye, and thus does not inconvenience viewing of the video play requester. On the other hand, the color difference by the minimum value plays a very important role in the detection step, a detailed description thereof will be described later.

The original video 10 is a video before inserting identification information, and means a final version that is a form for distributing a video produced by the original author of the video.

The corrected video 20 refers to a video generated by the identification information inserted into the candidate area 40 by the embedding method of the present invention.

According to the example illustrated in FIG. 5, the identification video 'USER' may be inserted into the corrected video 20 as the identification information 60 of the user. In addition to the identification ID, the identification information 60 of the user may include, but is not limited to, an identification number of a playback device, a network IP address (Internet Protocol Address), a MAC address (Media Access Control Address), and a time of a playback request. On the other hand, since the inserted identification ID 'USER' is not actually visible to the playback requester, the viewer cannot recognize this during video playback.

The identification information input area 50 includes a space where the user's identification information 60 can be inserted. The color of the identification information input area 50 is set to the average color of the candidate area 40, and the user's identification information 60 is set to a color different from the average color by a minimum value.

In the exemplary diagram, the identification information input area 50 and the user identification information 60 are distinguished from each other for explanation. However, in the actual playback screen, the identification information may not be visually distinguished and the inserted identification information may not be recognized.

The step (S200) of inserting identification information into the candidate area 40 will be described focusing on the difference from FIG.

Referring to FIG. 7, the method further includes extracting the average color region 70 from the candidate region 40 as compared with FIG. 4.

The average color area is a specific area within the candidate area 40, which is composed of the average color of the candidate area 40, and means an area including a space into which the user identification information 60 can be inserted.

According to another embodiment of the present invention, the identification information input area 50 is located in the average color area 70. On the other hand, since the identification information input area 50 is set to the average color of the candidate area 40, the identification information input area 50 is substantially the same color as the color of the average color area 70.

When the identification information input area 50 is located in the average color area 70, it becomes more difficult to visually discriminate than when the identification information input area 50 is located in another space in the candidate area 40, so that the video is reproduced. There is an effect that can make the viewing of the requester more comfortable.

In the candidate frame 30, there is a candidate area 40 having a color difference less than or equal to a reference value. The candidate area 40 includes an area composed of colors that do not exactly match the average color of the candidate area 40 and an average color area 70 composed of an average color of the candidate area 40.

In the exemplary diagram, the candidate region 40 and the average color region 70 are distinguished from each other for explanation, but cannot be distinguished with the naked eye on the actual reproduction screen.

According to another embodiment of the present invention, the identification information 60 of the user may be inserted into the candidate area 40 in the candidate frame 30 of the video alone without the identification information input area 50. That is, the identification information input area 50 corresponds to a means used to facilitate searching for the identification information 60 of the user by creating an area where the color differs by the minimum value in the duplicate video detection and tracking step.

In addition, as another embodiment, even if the user's identification information 60 is inserted alone without the identification information input area 50, a method in which the color is different by the minimum value will be described.

The identification information 60 of the user may be inserted into the average color area 70 without being inserted into any area within the candidate area 40 of the candidate frame 30. At this time, the color of the user identification information 60 is composed of a color that differs from the average color by a minimum value. Accordingly, as in the case where the identification information input area 50 including the average color described above is located, it may be detected as an area where the color differs by a minimum value in the detection step.

Next, the case where the average color area 70 is plural will be described.

When there are a plurality of average color areas 70, the method of inserting the user identification information 60 is a method of inserting the entire user identification information 60 in duplicate, and selecting and inserting one average color area. And a method of separating and inserting the identification information 60 of the user into a plurality of parts, respectively.

In the method of dividing the user identification information 60 into a plurality of parts and inserting the identification information 60 into the plurality of average color areas 70, extracting the candidate area 40 from the candidate frame 30 of the original video (S210). Extracting the average color area 70 from the candidate area 40 (S211), extracting the first average color area 71 and the second average color area 72 from the average color area 70 ( S213), separating the identification information of the user into the first portion 61 and the second portion 62 (S215) and the first portion 61 and the second portion 62 of the identification information of the user in a first manner. And inserting into the average color area 71 and the second average color area 72, respectively (S217).

As an example, a method of extracting the first average color region 71 and the second average color region 72 from the plurality of average color regions 70 will be described. The plurality of average generation regions 70 basically consist of the average color of the candidate region 40, and are the same in that they include a space into which the identification information 60 of the user can be inserted. On the other hand, the width and position of each average color area 70 are all different. Therefore, the first average color gamut 71 and the second average color gamut 72 are extracted by a specific criterion. For example, the widest average color area may be selected as the first average color area 71 based on the area, and then the widest average color area may be selected as the second average color area 72. However, the present invention is not limited thereto, and various standards other than the width may be applied.

Referring to the example illustrated in FIG. 10, a plurality of average color areas 70 including the average color of the candidate areas 40 in the candidate area 40 and into which the identification information 60 of the user can be inserted are present. do.

As shown in FIG. 10, when a plurality of average color regions 70 exist, each region is referred to as a first average color region 71 and a second average color region 72. The first average color area 71 and the second average color area 72 may correspond to the two widest areas among the plurality of average color areas 70.

In the first average color region 71 and the second average color region 72, a first portion 61 and a second portion 62 which separate the user identification information 60 are inserted.

Referring to FIG. 10, when the identification information 60 of the user is 'USER', the first and second

average color areas

71 and 72 are separated into a 'US' part and an 'ER' part. You can insert each one.

In this case, if any one of the plurality of average color areas 70 does not have enough space to insert the identification information 60 of the user alone, by inserting the identification information 60 of the user is still separated Implementation through the embodiment becomes possible.

The following describes an invention related to a method for detecting and tracking video copies.

Referring to FIG. 11, in the method of detecting and tracking a video copy, extracting the candidate frame 30 from the detected video (S400) and identifying the user with respect to the candidate area 40 in the extracted candidate frame 30. Searching (60) (S500) and extracting the identification information 60 of the inserted user (S600).

According to the present invention, it is not necessary to search the entire area of all of the plurality of frames constituting the video to be detected for video duplication detection and tracking, and only the specific candidate area 40 is searched by extracting the specific candidate frame 30. . Therefore, there is an effect that more efficient and economical duplicate video detection and outflow tracking can be performed.

Extracting the candidate frame 30 from the detection target video (S400) is the same as the content of step (S100) of extracting the candidate frame 30 from the original video 10 described in the method for generating the corrected video 20 above. Do.

A step S500 of searching for the identification information 60 of the user with respect to the candidate region 40 in the extracted candidate frame 30 will be described.

Searching for the user identification information 60 (S500) targets the candidate area 40 existing in the specific candidate frame 30 extracted in step S400.

According to an embodiment of the present invention, the identification information input area 50 in the candidate area 40 is set to the average color of the candidate area 40. Meanwhile, the inserted user identification information 60 includes colors that differ by the minimum value from the average color.

The duplicate video detection and tracking server 200 is inserted into the candidate area 40 by using the feature that the color value of the identification information input area 50 and the color value of the user identification information 60 differ by a minimum value. Search for the identification information 60 of the user. That is, the step (S500) of searching for the identification information 60 of the user may include detecting an area where the color differs by a minimum value and extracting the identification information 60 of the user from the detected area. .

When the color is represented by the RGB system, the minimum value of the color means 1 as the color value represented by 0 to 255. Accordingly, the duplicate video detection and tracking server 200 searches for an area in which the difference in color values differs by one, which is the minimum value, in the candidate area 40 to be detected. The duplicate video detection and tracking server 200 extracts and obtains the identification information 60 of the user from the corresponding area when a region where the difference in the color value is different by the minimum value 1 is detected.

For example, the case where the color value of the identification information input area 50 is the average color of the candidate area 40 and the color value of the green series of the average color is 180 will be described. In this case, the color of the identification information 60 of the user may be the same as the color value of the identification information input area 50 of the red series and the blue series, and the color value of the green series may be 181 (or 179). May be). The duplicate video detection and tracking server 200 searches for an area where the difference in color values of the green series differs by a minimum value of 1. The color values of the green series of the identification information input area 50 and the user identification information 60 are 180 and 181, respectively, and are different from each other by a minimum value of 1, and thus are detected by the duplicate video detection and tracking server 200.

As described above, when an area in which the difference in color values differs by a minimum value of 1 is detected, the duplicate video detection and tracking server 200 extracts and obtains the user identification information 60 from the detected area.

On the other hand, in one embodiment, when the area of the difference between the color value is not found by the minimum value of 1 is found, another search for a new candidate frame, or the difference in the color value is changed by the minimum value of 1 The search may not stop until the region is found.

According to another embodiment of the present invention, after extracting the candidate frame 30 from the detection target video (S400), the step of extracting the average color region 70 may be further included. This is a case where the region into which the identification information 60 of the user is inserted is specified as the average color region 70 composed of the average color of the candidate region 40 existing in the candidate region 40 in the process of generating the corrected moving image. In this case, the duplicate video detection and tracking server 200 searches only the extracted average color region 70 without searching the entire candidate candidate region 40. Therefore, the search target area becomes narrower, which enables faster and more efficient search.

Next, a case where a plurality of areas where the difference in color values is the minimum value in the video copy detection and tracking step is found will be described.

Referring to FIG. 10, the identification ID of the user 'USER' as the identification information is divided into 'US', which is the first part 61, and 'ER,' which is the second part 62, and the first average color area 71. Is inserted into the second average color area 72, and 'ER' is inserted into the second average color area 72, respectively. The duplicate video detection and tracking server 200 extracts and acquires portions of identification information 'US' and 'ER' from the first average color region 71 and the second average color region 72, respectively, To obtain the entire identification information.

In one embodiment, the order of combining the detected pieces of identification information is applied in the same manner as the criteria for selecting the first average color area 71 and the second average color area 72. As in the above-described example, among the plurality of average cutting areas 70, the widest average color area is defined as the first average color area 71, and the next widest average color area is defined as the second average color area 72. If you choose), the order of combining will follow. That is, the identification information detected in the first average color area 71 is used as the first part 61 and the identification information detected in the second average color area 72 is the second part 62. 61) The second part 62 is then combined to complete the entire identification information.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, in a software module executed by hardware, or by a combination thereof. Software modules may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those skilled in the art to which the present invention pertains may implement the present invention in other specific forms without changing the technical spirit or essential features. I can understand that. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive.

Claims

Performed by a computer,

Extracting at least one candidate frame from an original video, wherein the candidate frame includes a candidate area into which identification information of a user who has requested to play the original video can be inserted; And

Generating a corrected video including the identification information inserted in a candidate region within a specific candidate frame;

The candidate region is a space over a specific range within a frame, and composed of colors within a difference of a reference value.
The method of claim 1, wherein generating the corrected video comprises:

Setting an identification information input area in the candidate area to an average color of the candidate area; And

And inserting identification information of the user into a color that differs from the average color by a minimum value in the identification information input area.
The method of claim 2,

The method may further include extracting an average color area formed of an average color of the candidate area within the candidate area and inserting user identification information.

And the identification information input area is located in the average color area.
The method of claim 1, wherein generating the corrected video comprises:

Extracting an average color area formed of an average color of the candidate area within the candidate area and into which user identification information can be inserted; And

And inserting identification information of the user into the average color area.

The identification information of the user is composed of a color that differs by the minimum value from the average color, outgoing traceable correction video generation method.
The method of claim 4, wherein

Extracting a first average color area and a second average color area according to a specific rule when the average color area is plural;

Separating the identification information of the user into a first portion and a second portion; And

And inserting the first portion and the second portion into the first average color region and the second average color region, respectively. 2.
Performed by a computer,

Extracting at least one candidate frame from the detection target video, wherein the candidate frame includes a candidate area into which identification information of a user who has requested to play the original video can be inserted; And

Searching for the identification information about a candidate region within a specific candidate frame;

The candidate area is a space over a specific range within a frame and is composed of colors within a reference value difference.
The method of claim 6, wherein the identifying information search step,

Searching for an area in which color differs from the candidate area by a minimum value;

And if the region where the color differs by the minimum value is detected, extracting the identification information from the region where the color differs by the minimum value.
The method of claim 7, wherein when a plurality of areas where the color differs by a minimum value is detected,

Extracting identification information from each of the plurality of areas; And

Combining the extracted identification information, characterized in that it further comprises, moving picture detection and tracking method.
Extracting at least one candidate frame from an original video, wherein the candidate frame includes a candidate area into which identification information of a user who has requested to play the original video can be inserted; And

And a generator configured to generate a corrected video including the identification information in a candidate region within a specific candidate frame.

The candidate region is a space over a specific range within the frame, and composed of colors within the difference between the reference value, the outflow tracking can be corrected video generation system.
Extracting at least one candidate frame from the detection target video, wherein the candidate frame includes a candidate area into which identification information of a user who has requested to play the original video can be inserted; And

And a searcher for searching for the identification information on the candidate region within a specific candidate frame.

The candidate region is a space over a specific range within a frame, and is composed of colors within a reference value difference.