WO2014200137A1 - 핑거프린트에 기반한 광고 검출 시스템 및 방법 - Google Patents
핑거프린트에 기반한 광고 검출 시스템 및 방법 Download PDFInfo
- Publication number
- WO2014200137A1 WO2014200137A1 PCT/KR2013/005805 KR2013005805W WO2014200137A1 WO 2014200137 A1 WO2014200137 A1 WO 2014200137A1 KR 2013005805 W KR2013005805 W KR 2013005805W WO 2014200137 A1 WO2014200137 A1 WO 2014200137A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- section
- fingerprint
- advertisement
- unit
- segment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/454—Content or additional data filtering, e.g. blocking advertisements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
- H04H60/35—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users
- H04H60/37—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users for identifying segments of broadcast information, e.g. scenes or extracting programme ID
- H04H60/375—Commercial
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/61—Network physical structure; Signal processing
- H04N21/6106—Network physical structure; Signal processing specially adapted to the downstream path of the transmission network
- H04N21/6125—Network physical structure; Signal processing specially adapted to the downstream path of the transmission network involving transmission via Internet
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/835—Generation of protective data, e.g. certificates
- H04N21/8358—Generation of protective data, e.g. certificates involving watermark
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8455—Structuring of content, e.g. decomposing content into time segments involving pointers to the content, e.g. pointers to the I-frames of the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/854—Content authoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
- H04H60/56—Arrangements characterised by components specially adapted for monitoring, identification or recognition covered by groups H04H60/29-H04H60/54
Definitions
- the present invention relates to an advertisement detection system and method, and more particularly, to a system and method capable of detecting an advertisement included in broadcast content based on a fingerprint.
- TV broadcast content can be largely divided into TV program section and advertising section.
- the advertising section is regarded as a low importance or unnecessary section from the viewer's point of view, and many researches have been conducted on technologies for automatically detecting and removing or reprocessing it to provide TV contents to users. lost.
- the program section and the advertisement section are mostly distinguished by manual humans, and research to automatically distinguish them has been conducted.
- the efficiency is very low.
- a black screen is often inserted at the beginning and the end of the advertisement, there is a method of detecting the advertisement section by detecting the black screen.
- Republic of Korea Patent Publication No. 10-2011-0129325 (2011.12.01. Disclosure) relates to "advertising image detection method and apparatus", the monitoring target image mixed with the broadcast content and the advertising image played through the image playback device Dividing each of the plurality of frames into partial blocks of a predetermined size; Calculating feature information for each of the partial blocks corresponding to a preset position among the partial blocks of the predetermined size; Converting the feature information into a feature information vector; And detecting the reference advertisement image by comparing the feature information vector of the reference advertisement image to be detected previously stored in the database with the feature information vector.
- this technique should be stored in advance in advance the feature information of the advertising video, and also can be applied only when the feature information of the monitored video and the advertising video is completely matched, so it is applicable when the advertising section is only partly the same There is a limit that cannot be. Moreover, there is a fundamental limitation with this technique that the database is fixed and the database cannot be updated dynamically over time.
- the present invention is to solve the above limitations, an advertisement detection system and method that can accurately and effectively detect the advertising section by repeating the process of detecting the advertising section that appears continuously in the broadcast content and database the same. It aims to provide.
- the present invention is continuously received by continuously storing the broadcast content in real time and by selecting the reference section and the test section for the stored broadcast content to detect the advertising section and to change the reference section and the test section according to the result.
- Another object of the present invention is to provide a system and method capable of efficiently selecting a comparison target section of broadcast content and dynamically coping with it.
- the present invention is more accurate by detecting the repeated advertising section based on the fingerprint, segmenting and storing the detected advertising section in the database, and then divide the stored advertising sections into more detailed advertising sections. It is yet another object to provide a system and method that can perform efficient advertisement detection.
- a fingerprint-based advertising detection system the content stream storage unit for storing broadcast content in real time;
- a section selector which selects a reference section and a test section from the broadcast content stored by the content stream storage;
- a fingerprint extractor configured to extract a fingerprint in at least one manner with respect to the reference interval and the test interval selected by the interval selector;
- a fingerprint matching unit configured to perform matching by comparing a fingerprint of a test section extracted from the fingerprint extractor and a fingerprint of a reference section;
- An advertisement section determiner configured to determine an advertisement segment from a test section based on a matching result performed by the fingerprint matching unit;
- An advertisement database manager configured to store segment information about advertisement segments determined by the advertisement section determiner in an advertisement database and manage an advertisement database;
- a section updater configured to change the reference section and the test section selected by the section selector.
- the interval dividing unit may select a predetermined time interval as a test interval from a most recently stored time point among broadcast contents stored by the content stream storage unit, and select a predetermined time interval as a reference interval from an end point of the test interval.
- test section may be configured to have a shorter time length than the reference section.
- the fingerprint extractor may divide the reference section and the test section into unit sections each having a preset time length, and extract a fingerprint by any one of a fingerprint extraction method for each unit section.
- the fingerprint matching unit performs matching by comparing the extracted fingerprint for each unit section of the test section with the extracted fingerprint for all unit sections of the reference section for all unit sections of the test section. It can also be configured to.
- the starting point of the unit interval may be configured to have an interval by the time length (S).
- time length (S) between the start point of the unit section is preferably shorter than the time length of the unit section.
- the advertisement section determiner may determine successive unit sections of the test section matching the unit sections of the reference section as the advertisement segment based on a matching result of the fingerprint matching unit.
- the fingerprint extracting unit may divide a section corresponding to the advertisement segment among the advertisement segment and the reference interval into unit sections each having a preset time length, thereby fingerprinting the reference section and the test section for each unit section. Extracting a fingerprint by at least one other method other than the extracted method, wherein the fingerprint matching unit, all of the fingerprint extracted for each unit section of the advertising segment and the corresponding reference segment of the reference section The matching may be performed by comparing the extracted fingerprints with respect to the unit section for all the unit sections of the advertisement segment.
- the advertisement section determiner may finally determine successive unit sections of the advertisement segment matching the unit sections corresponding to the advertisement segment among the reference sections based on a matching result of the fingerprint matching unit. have.
- the advertisement section determiner may compare the fingerprint of the advertisement segment with the advertisement segments already registered in the advertisement database and finally determine the advertisement segment.
- the fingerprint may be a fingerprint by at least one other method other than a method in which a fingerprint is extracted for the reference period and the test period.
- the advertisement database manager may store at least one fingerprint of the advertisement segments determined by the advertisement section determiner and time information of the advertisement segment as segment information in the advertisement database.
- the section updater may be configured to change the reference section by including the reference point up to the end point of the advertisement segment determined from the test section.
- the reference interval may be changed by including the end point of the last advertisement segment as a reference interval.
- the total length of the reference section may be constant by changing the position of the start point of the reference section by the length newly included in the reference section.
- the interval updating unit may be configured to extend the length of the test interval by the length of the position of the start point of the reference interval.
- the section update unit may be configured to change the reference section by including the reference section up to the start point of the advertisement segment determined from the test section.
- the reference section may be changed by including the reference section up to the start point of the first advertising segment.
- the entire length of the reference section may be constant by changing the position of the start point of the reference section by the length newly included in the reference section.
- the section updater may store time information of a start point of a reference section corresponding to the advertisement segment determined by the advertisement section determiner, in the advertisement segment history, and identify a search section of a preset advertisement segment history every predetermined time. A section corresponding to a point before the minimum value among time information included in the search section may be removed from the reference section.
- the advertisement database manager may select two advertisement segments from among the advertisement segments stored in the advertisement database, compare the fingerprints of the selected advertisement segments, detect the same interval, and then select the same interval from the selected advertisement segment. By segmenting the section, a new advertisement segment forming process may be performed.
- the ad segments before the split may be removed from the ad database.
- the new advertisement segment forming process may be repeated for a predetermined number N for any two advertisement segments.
- the new advertising segment forming process may be performed for two segments whose time length is equal to or greater than a predetermined time length K.
- the process of forming a new advertisement segment may be repeatedly performed until there are no advertisement segments having the same section among all the advertisement segments included in the advertisement database.
- the advertisement database manager may update the fingerprint and time information for the formed new advertisement segments.
- a fingerprint-based advertisement detection method comprising: a first step of storing broadcast content in real time; Selecting a reference section and a test section from the stored broadcast contents; Extracting a fingerprint in at least one manner with respect to the selected reference interval and the test interval; A fourth step of performing matching by comparing the fingerprint of the extracted test interval with the fingerprint of the reference interval; A fifth step of determining an advertisement segment from a test section based on the matching result; A sixth step of storing segment information on the determined advertisement segments in an advertisement database; And a seventh step of changing the reference section and the test section.
- an advertisement detection system and method capable of accurately and effectively detecting an advertisement section by repeatedly detecting the advertisement section continuously appearing in the broadcast content and making a database thereof.
- the present invention is continuously received by continuously storing the broadcast content in real time and by selecting the reference section and the test section for the stored broadcast content to detect the advertising section and to change the reference section and the test section according to the result.
- the present invention by detecting the repeated advertising section based on the fingerprint, and segmented and stored in the database to detect the detected advertising section, by segmenting the segment into more granular unit advertising section It is possible to provide a system and method capable of performing accurate and efficient advertisement detection.
- FIG. 1 is a view showing the overall configuration of the advertisement detection system 100 based on the fingerprint according to an embodiment of the present invention.
- FIG. 2 is a view for explaining an example of a method for selecting a reference section and a test section in the section selector 20.
- 3 is a diagram for describing operations of the fingerprint extractor 30 and the fingerprint matcher 40.
- FIG. 4 is a diagram for describing a process of determining an advertisement segment in a test section 22.
- FIG. 5 is a diagram illustrating an example of segment information stored in the advertisement database 80.
- FIG. 6 is a diagram for describing an example of a method of changing a reference section in the section updater 70.
- FIG. 7 is a diagram for explaining a process of forming a new advertisement segment by dividing the advertisement segment into a small advertisement segment in the advertisement database manager 60.
- FIG. 10 is a view showing an embodiment of an advertisement detection method according to the present invention.
- FIG. 1 is a view showing the overall configuration of the advertisement detection system 100 based on the fingerprint according to an embodiment of the present invention.
- the fingerprint detection system 100 (hereinafter, referred to as the advertisement detection system 100) based on the fingerprint of the present embodiment may include a content stream storage unit 10, a section selection unit 20, and a fingerprint extraction unit. 30, a fingerprint matching unit 40, an advertisement section determiner 50, an advertisement database manager 60, an interval updater 70, and an advertisement database 80.
- the content stream storage unit 10 performs a function of storing broadcast content in real time.
- the broadcast content may be, for example, content provided through TV terrestrial or cable broadcasting.
- the content stream storage unit 10 stores such broadcast content in real time and continuously.
- the section selector 20 performs a function of selecting a reference section and a test section from the broadcast content stored by the content stream storage 10.
- the test section is a section for identifying whether an advertisement is included
- the reference section is a section to be compared to be able to identify whether an advertisement is included in the test section.
- the section selector 20 selects a predetermined time section as a test section from the most recently stored time point among the broadcast contents stored by the content stream storage unit 10, and selects a predetermined time section as a reference section from the end point of the test section. Can be.
- FIG. 2 is a view for explaining an example of a method for selecting a reference section and a test section in the section selector 20.
- a predetermined time length (N) from the right end point i.e., the last time point (t 0) is stored in
- the section up to the time point t 1 may be selected as the test section 22.
- a section from the end point t 1 of the test section 22 to a time point t 2 which becomes a predetermined time length L, may be selected as the reference section 21.
- the test interval 22 may have a shorter time length than the reference interval 21, that is, the length of the reference interval 21 may be longer than that of the test interval 21.
- the included advertising detection is because the longer the reference interval 21, the higher the discriminating power.
- the test section 22 may be selected as a 10 hour long section, and the reference section 21 may be selected as a 3 day long section.
- the fingerprint extractor 30 performs a function of extracting a fingerprint in at least one or more manners for the reference section and the test section selected by the section selector 20, and the fingerprint matcher 40 compares the fingerprint for the test section extracted from the fingerprint extractor 30 with the fingerprint for the reference section and performs matching.
- the advertisement section determiner 50 performs a function of determining an advertisement segment from the test section based on the matching result performed by the fingerprint matching unit 40.
- the fingerprint extractor 30 divides the reference section and the test section into unit sections each having a preset time length, and extracts the fingerprint by any one of fingerprint extraction methods for each unit section.
- the fingerprint matching unit 40 performs a process of comparing the extracted fingerprint for each unit section of the test section with the extracted fingerprint for all unit sections of the reference section for all unit sections of the test section. Perform a match.
- the advertisement section determiner 50 determines the advertisement segment from the test section based on the matching result.
- 3 is a diagram for describing operations of the fingerprint extractor 30 and the fingerprint matcher 40.
- a unit section corresponding to a preset time length is generated from the time point t 1 in the test section 22.
- the reference section 21 generates a unit section corresponding to the time length of the unit section in the test section 22 from the time point t 2 , and the fingerprint extractor 30 extracts the fingerprint for these two unit sections.
- the fingerprint matching unit 40 performs matching on the extracted fingerprint.
- the fingerprint matching unit 40 temporarily stores a matching result, for example, a matching score, generates a next unit section of the reference section 21, and performs fingerprint matching again.
- a matching result for example, a matching score
- the start point of the next unit section has an interval equal to the start point of the previously generated unit section and the moving length S shorter than the time length of the unit section on the time axis. That is, each unit section is preferably to have a section overlapping each other on the time axis.
- the next unit section of the test section 22 is generated and the above process is repeated.
- the starting point of the next unit section of the test section 22 also has a time length smaller than the starting point of the previous unit section and the time length of the unit section.
- the interval between the start points of the unit sections of the test section 22 and the interval between the start points of the unit sections of the reference section 21 may be the same or different.
- a fingerprint matching result for the reference section 21 may be obtained for each unit section of the test section 22.
- the advertisement section determiner 50 determines whether to match based on the fingerprint matching result for each unit section, that is, the fingerprint matching score, and determines the continuous section for the matching unit sections, thereby advertizing the consecutive unit sections. Decide on
- FIG. 4 is a diagram for describing a process of determining an advertisement segment in a test section 22.
- a section marked in blue in the test section 22 on the right side of FIG. 4 represents a continuous section in which the reference section 21 and the fingerprint match, and two consecutive sections (t a to t b , t c to t d). ) Is determined to be an ad segment.
- fingerprint refers to feature data representing characteristics of data such as audio data, image data, or video data, and is also referred to as fingerprint data, DNA data, or genetic data.
- DRM copyright management
- a fingerprint is generated using various characteristic data (eg, frequency, amplitude, etc.) representing the characteristics of the audio data, and in the case of image or video data, various feature data of the image or video data (eg, The fingerprint may be generated using motion vector information, color information, etc. of the frame.
- characteristic data e.g, frequency, amplitude, etc.
- feature data of the image or video data e.g. The fingerprint may be generated using motion vector information, color information, etc. of the frame.
- the present invention is not intended to extract (generate) such fingerprint data itself, and any form of fingerprint generation / extraction method according to the prior art may be used as it is, and thus the detailed description thereof will be omitted.
- Patent Application No. 10-2007-0044251 filed by the present applicant (A method and apparatus for generating audio fingerprint data and a method and device for comparing audio data using the same), No. 10-2007-0054601 (determination of the identity of the video data and the same Interval Detection Method and Apparatus), No. 10-2007-0060978 (Method and System for Clustering Video Datas with Identical Video Data), No.
- the fingerprint extraction method may be used in various ways. As described above, when the advertisement segment is determined by the advertisement section determination unit 50, the fingerprint may be extracted using another fingerprint extraction method for the advertisement segment. It may be configured to perform secondary matching by extracting and comparing it with a reference interval.
- the fingerprint extractor 30 divides the section corresponding to the advertisement segment among the advertisement segment and the reference section into the unit section corresponding to the preset time length, with respect to the advertisement segment determined by the advertisement section determiner 50.
- the fingerprint may be extracted by at least one method other than the method in which the fingerprint is extracted for the reference interval and the test interval for each unit interval.
- the fingerprint matching unit 40 compares the extracted fingerprint for each unit section of the advertisement segment with the extracted fingerprint for all unit sections corresponding to the advertisement segment among the reference section. Matching may be performed by performing all unit sections.
- the advertisement section determiner 50 may continue the unit of the advertisement segment that matches the unit sections corresponding to the advertisement segment in the reference section by the matching result of the fingerprint matching unit 40.
- the sections may be finally determined as an advertising segment.
- the advertisement section determiner 50 compares the fingerprint of the section determined as the advertisement segment with the fingerprints of the advertisement segments already registered in the advertisement database 80 and finally matches the advertisement segment as the advertisement segment. It can also be configured to determine.
- the fingerprint may be a fingerprint by at least one or more methods other than the method in which the fingerprint is extracted for the reference section and the test section in the above process.
- the advertisement database manager 60 stores the segment information on the advertisement segments determined by the advertisement section determiner in the advertisement database 80 and manages the advertisement database 80.
- FIG. 5 is a diagram illustrating an example of segment information stored in the advertisement database 80.
- the segment information includes a segment identifier, section start point time information, section length, and a fingerprint.
- the segment identifier refers to an identifier uniquely assigned to identify each advertisement segment, and the segment start point time information is, for example, May 20, 2013 11:59:35 (2013-05). -20/11: 59: 35).
- the section length may be stored as, for example, 30 seconds, 20 seconds, etc. as the total length of the section of the advertisement segment.
- the fingerprint is a fingerprint extracted from the fingerprint extractor 30 as described above.
- the fingerprint stored in the segment information may also be a fingerprint by multiple methods extracted for each method used.
- the section updater 70 performs a function of changing the reference section and the test section selected by the section selector 20.
- the section updater 70 may change the reference section so that the ad segment determined from the test section by the ad section determiner 50 is included in the reference section, that is, include the end point of the ad segment determined from the test section as the reference section. have.
- the time interval (t a ⁇ t b) of the section that is, t 1 ⁇ t b t b to the end point of the advertisement segment can change the reference period to be included in the reference region.
- the reference section may be changed so that up to the end point of the last ad segment (t d in FIG. 4) is included in the reference section.
- the total length of the reference section may be constant by changing the position of the start point of the reference section by the length newly included in the reference section. For example, as shown in FIG. 4, since the reference interval has a length as long as the length of time L, when the interval of t 1 to t d is newly included as the reference interval, t 1 to t d is moved from t 2 to the right direction. It may be possible to keep the total length of time at L by removing it.
- the start point of the test section is shortened by that much, and thus, the end point of the test section may be extended by the length of which the position of the start point of the reference section is changed.
- test section and the reference section are changed by the section updater 70 in this manner, the test is repeated by the fingerprint extractor 30, the fingerprint matching unit 40, and the advertisement section determiner 50 as described above.
- the process of determining the advertisement section by repeating the fingerprint of the section and the reference section may be repeated.
- section updater 70 may change the reference section by the method illustrated in FIG. 6.
- 6 is a diagram for describing an example of a method of changing a reference section in the section updater 70.
- the interval updater 70 determines the time information of the start point of the reference section corresponding to the advertisement segment determined by the advertisement section determiner 50 each time the advertisement segment is determined in the advertisement segment history 71. Stored sequentially from the top, and at the bottom of every predetermined time, that is, the minimum value is determined from the time information stored in the search section of the ad segment history of the preset length (W) from the last stored time information. It may be configured to remove the section corresponding to the reference section. This is to remove them from the reference section because the section corresponding to the point before the minimum value corresponds to the reference sections with little frequency of advertisement occurrence for a certain period of time.
- the advertisement database manager 60 stores each of the stored advertisement segments in smaller units. Can be divided into ad segments. This is because even the advertisement of the same product may be edited and configured with different time information.
- FIG. 7 is a diagram for explaining a process of forming a new advertisement segment by dividing the advertisement segment into a small advertisement segment in the advertisement database manager 60.
- ad segment 1 consists of [A] [B] [Z]
- ad segment 2 consists of [A] [B] [C]
- K consists of [B] [C] [A] [R].
- the same letter indicates the same section.
- any two ad segments are selected from each of the ad segments, and the fingerprints of the selected ad segments are compared to detect the same section, and then the new ad segment is divided by dividing the same section and the remaining section of the selected ad segment. Can be formed.
- Ad Segment 1 composed of [A] [B] [Z] and Ad Segment 2 composed of [A] [B] [C]
- [A] [B] can be detected.
- These sections and the remaining sections [Z] and [C] may be divided to form new advertisement segments. Repeating this process by selecting two of the respective ad segments may form a new ad segment as shown in FIG. 7 as the first new ad segment. Next, if the same process is repeated for these, the final new advertisement segments can be formed as shown in FIG. 7.
- FIG. 8 illustrates a process of detecting the same section by comparing the ad segments 1 and 2 of FIG. 7, and as shown in FIG. 8, the same section is [A] [B], as described above with reference to FIGS. 1 to 6.
- the fingerprint may be detected through a process of extracting and comparing the fingerprint.
- ad segments before the split ie ad segments 1 and 2 are removed from the ad database while forming a new ad segment.
- FIG. 9 is a view illustrating a process of detecting the same section by comparing an ad segment consisting of [C] among the newly created new ad segments in FIG. 8 and the ad segment K of FIG. 7. Referring to FIG. If [C] and the same section [C] are separated, it can be seen that two new advertising segments consisting of [A] [R] on the right side and [B] on the left side can be formed. Thereafter, the existing advertisement segment K is removed from the advertisement database 80.
- the final new advertisement segment can be obtained as shown in FIG.
- this new advertising segment forming process may be repeated for a predetermined number (N) for any two advertising segments.
- time length may be performed only for two segments having a predetermined time length K or more.
- the process of forming a new advertisement segment may be repeatedly performed until there is no longer an advertising segment having the same section among all the advertising segments included in the advertisement database.
- the advertising database manager 70 receives the segment information, that is, the fingerprint and time information (see FIG. 5), for the new advertising segments. Update to correspond.
- FIG. 10 is a diagram illustrating an embodiment of an advertisement detection method performed by the advertisement detection system 100 described with reference to FIGS. 1 to 9.
- the content stream storage unit 10 stores broadcast content in real time (S100), and the section selection unit 20 selects a reference section and a test section from the broadcast content stored by the content stream storage unit 10 ( S110).
- the fingerprint extractor 30 extracts the fingerprint in at least one or more manners with respect to the reference section and the test section selected by the section selector 20 (S120), and the fingerprint matching unit 40 is the fingerprint extractor.
- the fingerprint for the test interval extracted in operation 30 and the fingerprint for the reference interval are compared to perform matching (S130).
- the advertisement section determiner 50 determines an advertisement segment from the test section based on the matching result performed by the fingerprint matching unit 40 (S140), and the advertisement database manager 60 sends the advertisement section determiner 50 to the advertisement section determiner 50. Segment information about the advertising segments determined by the advertisement database 80 is stored (S150).
- the section updater 70 changes the reference section and the test section selected by the section selector 20 at every predetermined period or when a predetermined condition occurs (S160).
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Collating Specific Patterns (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Description
Claims (24)
- 핑거프린트에 기반한 광고 검출 시스템에 있어서,방송 콘텐츠를 실시간으로 저장하는 콘텐츠 스트림 저장부;상기 콘텐츠 스트림 저장부에 의해 저장된 방송 콘텐츠 중에서 레퍼런스 구간과 테스트 구간을 선택하는 구간 선택부;상기 구간 선택부에 의해 선택된 레퍼런스 구간과 테스트 구간에 대해 적어도 하나 이상의 방식으로 핑거프린트를 추출하는 핑거프린트 추출부;상기 핑거프린트 추출부에서 추출된 테스트 구간에 대한 핑거프린트와 레퍼런스 구간에 대한 핑거프린트를 비교하여 매칭을 수행하는 핑거프린트 매칭부;상기 핑거프린트 매칭부에서 수행된 매칭 결과에 기초하여 테스트 구간으로부터 광고 세그먼트를 결정하는 광고 구간 결정부;상기 광고 구간 결정부에 의해 결정된 광고 세그먼트들에 대한 세그먼트 정보를 광고 데이터베이스에 저장하고 광고 데이터베이스를 관리하는 광고 데이터베이스 관리부; 및상기 구간 선택부에서 선택된 레퍼런스 구간과 테스트 구간을 변경하는 구간 갱신부를 포함하는 핑거프린트에 기반한 광고 검출 시스템.
- 제1항에 있어서,상기 구간 분할부는, 상기 콘텐츠 스트림 저장부에 의해 저장된 방송 콘텐츠 중에서 가장 최근에 저장된 시점으로부터 소정 시간 구간을 테스트 구간으로 선택하고, 상기 테스트 구간의 종점으로부터 소정 시간 구간을 레퍼런스 구간으로 선택하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제2항에 있어서,상기 테스트 구간은 상기 레퍼런스 구간보다 시간 길이가 짧은 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제1항에 있어서,상기 핑거프린트 추출부는,상기 레퍼런스 구간과 테스트 구간을 각각 미리 설정된 시간 길이만큼의 단위 구간으로 분할하여 각 단위 구간에 대해 핑거프린트 추출 방식 중 어느 하나의 방식에 의해 핑거프린트를 추출하고,상기 핑거프린트 매칭부는,상기 테스트 구간의 각각의 단위 구간에 대해 추출된 핑거프린트와 레퍼런스 구간의 모든 단위 구간에 대해 추출된 핑거프린트를 비교하는 과정을 테스트 구간의 모든 단위 구간에 대해 수행함으로써 매칭을 수행하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제4항에 있어서,상기 단위 구간의 시작점은 시간 길이(S)만큼 간격을 갖는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제5항에 있어서,상기 단위 구간의 시작점 사이의 시간 길이(S)는 상기 단위 구간의 시간 길이보다 짧은 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제4항에 있어서,상기 광고 구간 결정부는,상기 핑거프린트 매칭부의 매칭 수행 결과에 의해 레퍼런스 구간의 단위 구간들과 매칭되는 테스트 구간의 연속하는 단위 구간들을 광고 세그먼트로 결정하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제7항에 있어서,상기 핑거프린트 추출부는,상기 광고 세그먼트와 레퍼런스 구간 중 상기 광고 세그먼트에 상응하는 구간을 각각 미리 설정된 시간 길이만큼의 단위 구간으로 분할하여 각 단위 구간에 대해 상기 레퍼런스 구간과 테스트 구간에 대해 핑거프린트를 추출한 방식 이외의 적어도 하나 이상의 다른 방식에 의하여 핑거프린트를 추출하고,상기 핑거프린트 매칭부는,상기 광고 세그먼트의 각각의 단위 구간에 대해 추출된 핑거프린트와 상기 레퍼런스 구간 중 상기 광고 세그먼트에 상응하는 모든 단위 구간에 대해 추출된 핑거프린트를 비교하는 과정을 광고 세그먼트의 모든 단위 구간에 대해 수행함으로써 매칭을 수행하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제8항에 있어서,상기 광고 구간 결정부는,상기 핑거프린트 매칭부의 매칭 수행 결과에 의해 상기 레퍼런스 구간 중 상기 광고 세그먼트에 상응하는 단위 구간들과 매칭되는 광고 세그먼트의 연속하는 단위 구간들을 광고 세그먼트로 최종 결정하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제7항에 있어서,상기 광고 구간 결정부는,상기 광고 세그먼트와 광고 데이터베이스에 이미 등록되어 있는 광고 세그먼트들의 핑거프린트를 비교하여 광고 세그먼트로 최종 결정하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제10항에 있어서,상기 핑거프린트는, 상기 레퍼런스 구간과 테스트 구간에 대해 핑거프린트를 추출한 방식 이외의 적어도 하나 이상의 다른 방식에 의한 핑거프린트인 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제1항에 있어서,상기 광고 데이터베이스 관리부는,상기 광고 구간 결정부에 의해 결정된 광고 세그먼트들에 대한 적어도 하나 이상의 핑거프린트와 광고 세그먼트의 시간 정보를 세그먼트 정보로서 광고 데이터베이스에 저장하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제1항에 있어서,상기 구간 갱신부는,상기 테스트 구간으로부터 결정된 광고 세그먼트의 종료점까지를 레퍼런스 구간으로 포함시켜서 레퍼런스 구간을 변경하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제13항에 있어서,상기 광고 세그먼트가 복수개인 경우 마지막 광고 세그먼트의 종료점까지를 레퍼런스 구간으로 포함시켜서 레퍼런스 구간을 변경하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제13항 또는 제14항에 있어서,상기 레퍼런스 구간에 신규로 포함되는 길이만큼 레퍼런스 구간의 시작점의 위치를 변경하여 레퍼런스 구간의 전체 길이가 일정하게 되도록 하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제15항에 있어서,상기 구간 갱신부는,레퍼런스 구간의 시작점의 위치가 변경된 길이만큼 테스트 구간의 길이를 연장시키는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제1항에 있어서,상기 구간 갱신부는,상기 광고 구간 결정부에서 결정된 광고 세그먼트에 상응하는 레퍼런스 구간의 시작점의 시간 정보를 광고 세그먼트 히스토리에 저장하고, 일정 시간 경과시마다 미리 설정된 광고 세그먼트 히스토리의 탐색 구간을 확인하여 상기 탐색 구간에 포함된 시간 정보 중 최소값 이전의 시점에 해당하는 구간을 레퍼런스 구간으로부터 제거하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제1항에 있어서,상기 광고 데이터베이스 관리부는,광고 데이터베이스에 저장되는 광고 세그먼트들 중 2개의 광고 세그먼트를 선택하고, 선택된 광고 세그먼트들의 핑거프린트를 비교하여 동일 구간을 검출한 후, 상기 선택된 광고 세그먼트의 동일 구간과 나머지 구간을 분할함으로써 신규 광고 세그먼트 형성 과정을 수행하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제18항에 있어서,상기 분할 이전의 광고 세그먼트들은 광고 데이터베이스에서 제거되는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제18항에 있어서,상기 신규 광고 세그먼트 형성 과정은, 임의의 2개의 광고 세그먼트에 대해 미리 설정된 횟수(N)만큼 반복하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제18항에 있어서,상기 신규 광고 세그먼트 형성 과정은, 시간 길이가 일정 시간 길이(K) 이상인 2개의 세그먼트에 대해서 수행되는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제18항에 있어서,상기 신규 광고 세그먼트 형성 과정은, 광고 데이터베이스에 포함된 모든 광고 세그먼트 중 서로 동일 구간을 갖는 광고 세그먼트가 존재하지 않을 때까지 반복 수행되는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 제18항에 있어서,상기 광고 데이터베이스 관리부는, 상기 형성된 신규 광고 세그먼트들에 대한 핑거프린트와 시간 정보를 갱신하는 것을 특징으로 하는 핑거프린트에 기반한 광고 검출 시스템.
- 핑거프린트에 기반한 광고 검출 방법에 있어서,방송 콘텐츠를 실시간으로 저장하는 제1 단계;상기 저장된 방송 콘텐츠 중에서 레퍼런스 구간과 테스트 구간을 선택하는 제2 단계;상기 선택된 레퍼런스 구간과 테스트 구간에 대해 적어도 하나 이상의 방식으로 핑거프린트를 추출하는 제3 단계;상기 추출된 테스트 구간에 대한 핑거프린트와 레퍼런스 구간에 대한 핑거프린트를 비교하여 매칭을 수행하는 제4 단계;상기 매칭 수행 결과에 기초하여 테스트 구간으로부터 광고 세그먼트를 결정하는 제5 단계;상기 결정된 광고 세그먼트들에 대한 세그먼트 정보를 광고 데이터베이스에 저장하는 제6 단계; 및상기 레퍼런스 구간과 테스트 구간을 변경하는 제7 단계를 포함하는 핑거프린트에 기반한 광고 검출 방법.
Priority Applications (11)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP13886824.5A EP3010235B1 (en) | 2013-06-14 | 2013-07-01 | System and method for detecting advertisements on the basis of fingerprints |
| EP19189421.1A EP3579563B1 (en) | 2013-06-14 | 2013-07-01 | System and method for detecting advertisements on the basis of fingerprints |
| JP2016519422A JP6216045B2 (ja) | 2013-06-14 | 2013-07-01 | フィンガープリントに基づく広告検出方法、広告検出システム及びプログラム |
| EP21167734.9A EP3905698B1 (en) | 2013-06-14 | 2013-07-01 | System and method for detecting advertisements on the basis of fingerprints |
| HK16106801.8A HK1219010B (en) | 2013-06-14 | 2013-07-01 | System and method for detecting advertisements on the basis of fingerprints |
| EP18180226.5A EP3410727B1 (en) | 2013-06-14 | 2013-07-01 | System and method for detecting advertisements on the basis of fingerprints |
| US14/122,674 US9495598B2 (en) | 2013-06-14 | 2013-07-01 | Advertisement detection system and method based on fingerprints |
| US15/228,243 US10104446B2 (en) | 2013-06-14 | 2016-08-04 | Advertisement detection system and method based on fingerprints |
| US16/133,240 US10284922B2 (en) | 2013-06-14 | 2018-09-17 | Advertisement detection system and method based on fingerprints |
| US16/360,453 US10623826B2 (en) | 2013-06-14 | 2019-03-21 | Advertisement detection system and method based on fingerprints |
| US16/812,896 US11197073B2 (en) | 2013-06-14 | 2020-03-09 | Advertisement detection system and method based on fingerprints |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR10-2013-0068305 | 2013-06-14 | ||
| KR1020130068305A KR101456926B1 (ko) | 2013-06-14 | 2013-06-14 | 핑거프린트에 기반한 광고 검출 시스템 및 방법 |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US14/122,674 A-371-Of-International US9495598B2 (en) | 2013-06-14 | 2013-07-01 | Advertisement detection system and method based on fingerprints |
| US15/228,243 Continuation US10104446B2 (en) | 2013-06-14 | 2016-08-04 | Advertisement detection system and method based on fingerprints |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2014200137A1 true WO2014200137A1 (ko) | 2014-12-18 |
Family
ID=51747994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2013/005805 Ceased WO2014200137A1 (ko) | 2013-06-14 | 2013-07-01 | 핑거프린트에 기반한 광고 검출 시스템 및 방법 |
Country Status (5)
| Country | Link |
|---|---|
| US (5) | US9495598B2 (ko) |
| EP (4) | EP3410727B1 (ko) |
| JP (1) | JP6216045B2 (ko) |
| KR (1) | KR101456926B1 (ko) |
| WO (1) | WO2014200137A1 (ko) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101456926B1 (ko) * | 2013-06-14 | 2014-10-31 | (주)엔써즈 | 핑거프린트에 기반한 광고 검출 시스템 및 방법 |
| US9602891B2 (en) * | 2014-12-18 | 2017-03-21 | Verance Corporation | Service signaling recovery for multimedia content using embedded watermarks |
| US10149022B2 (en) * | 2016-03-09 | 2018-12-04 | Silveredge Technologies Pvt. Ltd. | Method and system of auto-tagging brands of television advertisements |
| US20170264930A1 (en) * | 2016-03-09 | 2017-09-14 | Silveredge Technologies Pvt. Ltd. | Method and system of standardizing media content for channel agnostic detection of television advertisements |
| US10117000B2 (en) * | 2016-03-10 | 2018-10-30 | Silveredge Technologies Pvt. Ltd. | Method and system for hardware agnostic detection of television advertisements |
| WO2017216394A1 (es) * | 2016-06-14 | 2017-12-21 | Tagsonomy, S.L. | Metodo y sistema de sincronización entre un contenido audiovisual de referencia y una versión alterada del mismo emitida por televisión |
| KR101950328B1 (ko) * | 2016-09-13 | 2019-02-20 | 한국과학기술연구원 | 실내 위치 측정을 위한 데이터베이스 갱신 방법 및 서버 |
| US10390089B2 (en) * | 2016-12-09 | 2019-08-20 | Google Llc | Integral program content distribution |
| CN108810615A (zh) | 2017-04-28 | 2018-11-13 | 阿里巴巴集团控股有限公司 | 确定音视频中插播时段的方法和装置 |
| US11418858B2 (en) | 2017-09-01 | 2022-08-16 | Roku, Inc. | Interactive content when the secondary content is server stitched |
| US11234060B2 (en) | 2017-09-01 | 2022-01-25 | Roku, Inc. | Weave streaming content into a linear viewing experience |
| US10306333B2 (en) * | 2017-09-13 | 2019-05-28 | The Nielsen Company (Us), Llc | Flagging advertisement frames for automatic content recognition |
| US11341540B2 (en) | 2018-03-30 | 2022-05-24 | At&T Intellectual Property I, L.P. | Methods, systems and devices for selecting advertisements based on media profiles and advertisement profiles |
| KR102076275B1 (ko) * | 2018-08-22 | 2020-02-11 | 강운식 | 디지털 미디어 콘텐츠 재생 제어 방법 및 그 장치 |
| CN113169805B (zh) | 2018-11-27 | 2024-11-15 | 尼尔森(美国)有限公司 | 灵活商业广告监测 |
| TWI802797B (zh) | 2019-05-10 | 2023-05-21 | 美商六科股份有限公司 | 用於檢測和回應於在先前檢測到的指紋匹配之後檢測到的指紋不匹配的方法、非暫時性電腦可讀儲存介質及計算系統 |
| TWI795642B (zh) | 2019-05-10 | 2023-03-11 | 美商六科股份有限公司 | 用於與包括內容分發系統和內容呈現設備的內容修改系統結合使用的方法、非暫時性電腦可讀儲存介質及計算系統 |
| US10796159B1 (en) | 2019-05-10 | 2020-10-06 | The Nielsen Company (Us), Llc | Content-modification system with use of multiple fingerprint data types feature |
| WO2020231927A1 (en) | 2019-05-10 | 2020-11-19 | The Nielsen Company (Us), Llc | Content-modification system with responsive transmission of reference fingerprint data feature |
| KR102753350B1 (ko) | 2023-04-26 | 2025-01-14 | 주식회사 애드원 | 광고 노출 기반 실시간 서베이 시스템 |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR970071589A (ko) * | 1996-04-26 | 1997-11-07 | 김광호 | 시엠(cm) 스킵기능을 갖는 비데오 플레이어 |
| KR20070044251A (ko) | 2005-10-24 | 2007-04-27 | 삼성전자주식회사 | 금형장치와 금형용 히터 카트리지 |
| KR20070054601A (ko) | 2004-06-07 | 2007-05-29 | 캠브리지 엔터프라이즈 리미티드 | 홀로그래픽 센서를 이용한 분석물을 탐지하기 위한 방법 |
| KR20070060978A (ko) | 2005-12-09 | 2007-06-13 | 한국전자통신연구원 | 지상파 dmb 비디오, 오디오, 부가 데이터의 제한수신부호화 장치 및 그 방법과 그를 이용한 제한수신 시스템 |
| KR20070071633A (ko) | 2005-12-30 | 2007-07-04 | 엠텍비젼 주식회사 | 컬러 필터 어레이 및 영상 보간 방법 |
| KR20070091587A (ko) | 2006-03-06 | 2007-09-11 | 삼성전자주식회사 | 스테레오 신호 생성 방법 및 장치 |
| KR20080021369A (ko) * | 2006-09-04 | 2008-03-07 | 엘지전자 주식회사 | 방송 프로그램의 광고 스킵 녹화방법 |
| KR20080051688A (ko) | 2006-12-06 | 2008-06-11 | 주식회사 에이디피엔지니어링 | 기판 테이블 및 이를 가진 기판 합착장치 |
| KR20100037582A (ko) * | 2010-03-19 | 2010-04-09 | 유미특허법인 | 타겟 영상 검출 장치 및 그 방법 |
| KR20110129325A (ko) | 2010-05-25 | 2011-12-01 | 한국전자통신연구원 | 광고 영상 검출 방법 및 장치 |
| KR101143115B1 (ko) * | 2004-11-02 | 2012-05-08 | 마이크로소프트 코포레이션 | 다중 동기화된 데이터 스트림들에 대한 데이터베이스 검색속도를 증진하기 위한 시스템 및 방법 |
| KR101206179B1 (ko) * | 2005-11-28 | 2012-11-29 | 엘지전자 주식회사 | 광고 방송 스킵 처리 방법 |
Family Cites Families (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2285645A1 (en) * | 1997-01-06 | 1998-07-16 | Bellsouth Intellectual Property Corporation | Method and system for tracking network use |
| US7461392B2 (en) * | 2002-07-01 | 2008-12-02 | Microsoft Corporation | System and method for identifying and segmenting repeating media objects embedded in a stream |
| WO2004004351A1 (en) | 2002-07-01 | 2004-01-08 | Microsoft Corporation | A system and method for providing user control over repeating objects embedded in a stream |
| US7110338B2 (en) * | 2002-08-06 | 2006-09-19 | Matsushita Electric Industrial Co., Ltd. | Apparatus and method for fingerprinting digital media |
| WO2004036384A2 (en) * | 2002-10-18 | 2004-04-29 | Intellocity Usa, Inc. | Ichoose video advertising |
| US20040260682A1 (en) * | 2003-06-19 | 2004-12-23 | Microsoft Corporation | System and method for identifying content and managing information corresponding to objects in a signal |
| NZ560223A (en) * | 2003-06-23 | 2008-12-24 | Sony Pictures Entertainment | Fingerprinting of data |
| US10032192B2 (en) * | 2003-12-23 | 2018-07-24 | Roku, Inc. | Automatic localization of advertisements |
| US7336841B2 (en) * | 2004-03-25 | 2008-02-26 | Intel Corporation | Fingerprinting digital video for rights management in networks |
| US7516074B2 (en) * | 2005-09-01 | 2009-04-07 | Auditude, Inc. | Extraction and matching of characteristic fingerprints from audio signals |
| US8009861B2 (en) * | 2006-04-28 | 2011-08-30 | Vobile, Inc. | Method and system for fingerprinting digital video object based on multiresolution, multirate spatial and temporal signatures |
| US8238669B2 (en) * | 2007-08-22 | 2012-08-07 | Google Inc. | Detection and classification of matches between time-based media |
| US9177209B2 (en) * | 2007-12-17 | 2015-11-03 | Sinoeast Concept Limited | Temporal segment based extraction and robust matching of video fingerprints |
| GB2460844B (en) * | 2008-06-10 | 2012-06-06 | Half Minute Media Ltd | Automatic detection of repeating video sequences |
| US20090327334A1 (en) * | 2008-06-30 | 2009-12-31 | Rodriguez Arturo A | Generating Measures of Video Sequences to Detect Unauthorized Use |
| US8180891B1 (en) * | 2008-11-26 | 2012-05-15 | Free Stream Media Corp. | Discovery, access control, and communication with networked services from within a security sandbox |
| WO2010119996A1 (ko) * | 2009-04-13 | 2010-10-21 | (주)엔써즈 | 동영상 관련 광고를 제공하는 방법 및 그 장치 |
| US8713068B2 (en) * | 2009-06-11 | 2014-04-29 | Yahoo! Inc. | Media identification system with fingerprint database balanced according to search loads |
| US8594392B2 (en) * | 2009-11-18 | 2013-11-26 | Yahoo! Inc. | Media identification system for efficient matching of media items having common content |
| US9538209B1 (en) * | 2010-03-26 | 2017-01-03 | Amazon Technologies, Inc. | Identifying items in a content stream |
| US8694533B2 (en) * | 2010-05-19 | 2014-04-08 | Google Inc. | Presenting mobile content based on programming context |
| KR101181732B1 (ko) * | 2010-11-22 | 2012-09-19 | (주)엔써즈 | 동영상 핑거프린트 정보에 기반한 동영상 마크업 데이터 생성 방법 및 이를 이용한 정보 제공 방법 및 시스템 |
| WO2012091938A1 (en) * | 2010-12-30 | 2012-07-05 | Dolby Laboratories Licensing Corporation | Ranking representative segments in media data |
| US20110296452A1 (en) * | 2011-08-08 | 2011-12-01 | Lei Yu | System and method for providing content-aware persistent advertisements |
| US8793274B2 (en) * | 2011-08-08 | 2014-07-29 | Lei Yu | System and method for auto content recognition |
| GB2485694B (en) * | 2012-01-27 | 2013-02-20 | Half Minute Media Ltd | Automatic detection and replacement of commercial spots |
| US8918804B2 (en) * | 2012-02-07 | 2014-12-23 | Turner Broadcasting System, Inc. | Method and system for a reward program based on automatic content recognition |
| US8997164B2 (en) * | 2013-01-07 | 2015-03-31 | Gracenote, Inc. | Authorizing devices based on identifying content distributor |
| KR101456926B1 (ko) * | 2013-06-14 | 2014-10-31 | (주)엔써즈 | 핑거프린트에 기반한 광고 검출 시스템 및 방법 |
| US9459958B2 (en) * | 2013-12-02 | 2016-10-04 | Annapurna Labs Ltd. | Flexible redundant array of independent disks (RAID) computation device |
-
2013
- 2013-06-14 KR KR1020130068305A patent/KR101456926B1/ko active Active
- 2013-07-01 EP EP18180226.5A patent/EP3410727B1/en active Active
- 2013-07-01 WO PCT/KR2013/005805 patent/WO2014200137A1/ko not_active Ceased
- 2013-07-01 EP EP19189421.1A patent/EP3579563B1/en active Active
- 2013-07-01 JP JP2016519422A patent/JP6216045B2/ja active Active
- 2013-07-01 EP EP13886824.5A patent/EP3010235B1/en active Active
- 2013-07-01 US US14/122,674 patent/US9495598B2/en active Active
- 2013-07-01 EP EP21167734.9A patent/EP3905698B1/en active Active
-
2016
- 2016-08-04 US US15/228,243 patent/US10104446B2/en active Active
-
2018
- 2018-09-17 US US16/133,240 patent/US10284922B2/en active Active
-
2019
- 2019-03-21 US US16/360,453 patent/US10623826B2/en active Active
-
2020
- 2020-03-09 US US16/812,896 patent/US11197073B2/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR970071589A (ko) * | 1996-04-26 | 1997-11-07 | 김광호 | 시엠(cm) 스킵기능을 갖는 비데오 플레이어 |
| KR20070054601A (ko) | 2004-06-07 | 2007-05-29 | 캠브리지 엔터프라이즈 리미티드 | 홀로그래픽 센서를 이용한 분석물을 탐지하기 위한 방법 |
| KR101143115B1 (ko) * | 2004-11-02 | 2012-05-08 | 마이크로소프트 코포레이션 | 다중 동기화된 데이터 스트림들에 대한 데이터베이스 검색속도를 증진하기 위한 시스템 및 방법 |
| KR20070044251A (ko) | 2005-10-24 | 2007-04-27 | 삼성전자주식회사 | 금형장치와 금형용 히터 카트리지 |
| KR101206179B1 (ko) * | 2005-11-28 | 2012-11-29 | 엘지전자 주식회사 | 광고 방송 스킵 처리 방법 |
| KR20070060978A (ko) | 2005-12-09 | 2007-06-13 | 한국전자통신연구원 | 지상파 dmb 비디오, 오디오, 부가 데이터의 제한수신부호화 장치 및 그 방법과 그를 이용한 제한수신 시스템 |
| KR20070071633A (ko) | 2005-12-30 | 2007-07-04 | 엠텍비젼 주식회사 | 컬러 필터 어레이 및 영상 보간 방법 |
| KR20070091587A (ko) | 2006-03-06 | 2007-09-11 | 삼성전자주식회사 | 스테레오 신호 생성 방법 및 장치 |
| KR20080021369A (ko) * | 2006-09-04 | 2008-03-07 | 엘지전자 주식회사 | 방송 프로그램의 광고 스킵 녹화방법 |
| KR20080051688A (ko) | 2006-12-06 | 2008-06-11 | 주식회사 에이디피엔지니어링 | 기판 테이블 및 이를 가진 기판 합착장치 |
| KR20100037582A (ko) * | 2010-03-19 | 2010-04-09 | 유미특허법인 | 타겟 영상 검출 장치 및 그 방법 |
| KR20110129325A (ko) | 2010-05-25 | 2011-12-01 | 한국전자통신연구원 | 광고 영상 검출 방법 및 장치 |
Non-Patent Citations (2)
| Title |
|---|
| D. A. SADLIER ET AL.: "Automatic TV advertisement detection from mpeg bitstream", JOURNAL OF THE PATT. REC. SOCIETY, vol. 35, no. 12, December 2002 (2002-12-01), pages 215, XP004379642, DOI: doi:10.1016/S0031-3203(01)00251-5 |
| See also references of EP3010235A4 |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20140103802A (ko) | 2014-08-27 |
| EP3410727B1 (en) | 2019-09-04 |
| EP3010235B1 (en) | 2018-09-05 |
| EP3410727A1 (en) | 2018-12-05 |
| JP6216045B2 (ja) | 2017-10-18 |
| EP3905698B1 (en) | 2025-08-27 |
| US20190020932A1 (en) | 2019-01-17 |
| US10104446B2 (en) | 2018-10-16 |
| HK1219010A1 (en) | 2017-03-17 |
| US10284922B2 (en) | 2019-05-07 |
| EP3905698C0 (en) | 2025-08-27 |
| US20160381432A1 (en) | 2016-12-29 |
| EP3905698A1 (en) | 2021-11-03 |
| US20200213677A1 (en) | 2020-07-02 |
| US11197073B2 (en) | 2021-12-07 |
| EP3579563B1 (en) | 2021-04-21 |
| KR101456926B1 (ko) | 2014-10-31 |
| US10623826B2 (en) | 2020-04-14 |
| EP3010235A4 (en) | 2017-01-11 |
| US9495598B2 (en) | 2016-11-15 |
| EP3579563A1 (en) | 2019-12-11 |
| EP3010235A1 (en) | 2016-04-20 |
| US20190222907A1 (en) | 2019-07-18 |
| US20150003739A1 (en) | 2015-01-01 |
| JP2016524875A (ja) | 2016-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2014200137A1 (ko) | 핑거프린트에 기반한 광고 검출 시스템 및 방법 | |
| WO2013048068A2 (ko) | 수신기에서의 개인화 광고 제공 방법 | |
| WO2013176329A1 (ko) | 오디오 신호를 이용한 콘텐츠 인식 장치 및 방법 | |
| WO2013165083A1 (ko) | 이미지에 기반하여 동영상 서비스를 제공하는 시스템 및 방법 | |
| WO2008150109A1 (en) | Method of processing moving picture and apparatus thereof | |
| WO2015111826A1 (ko) | 참조 영역 분할을 이용한 인페인팅 장치 및 방법 | |
| WO2015129983A1 (ko) | 분산 퍼지 연관 규칙 마이닝에 기반한 영화 추천 장치 및 방법 | |
| WO2015020256A1 (ko) | 직접 반응 광고 검출 및 분류 시스템 및 방법 | |
| WO2021162237A1 (ko) | 비디오로부터의 색상 스키마 추출 방법 및 장치 | |
| WO2018056488A1 (ko) | 디지털 동영상 특징값 추출 시스템 및 방법, 및 상기 특징값을 이용한 디지털 동영상 유사도 판단 시스템 및 방법 | |
| WO2016080695A1 (ko) | 음향 정보에 기초한 사용자 다수 행위 인식 방법 | |
| WO2010095796A1 (ko) | 세그먼트 특징을 이용한 내용 기반 동영상 검출 방법 | |
| WO2019124632A1 (ko) | 압축영상에 대한 신택스 기반의 객체 배회 감지 방법 | |
| HK40011065B (en) | System and method for detecting advertisements on the basis of fingerprints | |
| HK40011065A (en) | System and method for detecting advertisements on the basis of fingerprints | |
| WO2017200165A1 (ko) | 도로 특이 정보의 자동 추출 장치 및 그 방법 | |
| HK1258830A1 (en) | System and method for detecting advertisements on the basis of fingerprints | |
| HK1258830B (en) | System and method for detecting advertisements on the basis of fingerprints | |
| WO2023136440A1 (ko) | 객체 검출 누락을 최소화한 객체 검출기의 학습 방법 및 이를 수행하기 위한 장치 | |
| WO2018030555A1 (ko) | 영상의 인기구간 검색 장치 | |
| HK1219010B (en) | System and method for detecting advertisements on the basis of fingerprints | |
| WO2019209027A1 (ko) | 동영상 복제 검출 및 추적을 위한 방법 및 시스템 | |
| WO2016137225A2 (ko) | 방송 연관 검색어를 제공하는 서버 및 이를 사용하는 단말 장치 | |
| WO2016024734A1 (ko) | 방송 콘텐츠의 음원 검색을 위한 오디오 신호 처리 시스템 및 방법 | |
| WO2019078387A1 (ko) | 컨텐츠 기반의 광고 추천 장치 및 방법 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WWE | Wipo information: entry into national phase |
Ref document number: 14122674 Country of ref document: US |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13886824 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2016519422 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2013886824 Country of ref document: EP |