CN107124648A - The method that advertisement video is originated is recognized by intelligent terminal - Google Patents
The method that advertisement video is originated is recognized by intelligent terminal Download PDFInfo
- Publication number
- CN107124648A CN107124648A CN201710249938.0A CN201710249938A CN107124648A CN 107124648 A CN107124648 A CN 107124648A CN 201710249938 A CN201710249938 A CN 201710249938A CN 107124648 A CN107124648 A CN 107124648A
- Authority
- CN
- China
- Prior art keywords
- information
- video
- audio
- recognized
- intelligent terminal
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 241001269238 Data Species 0.000 claims description 3
- 206010047571 Visual impairment Diseases 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
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
- H04N21/43—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]
- H04N21/40—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
- H04N21/439—Processing of audio elementary streams
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of method that advertisement video source is recognized by intelligent terminal, and methods described includes step:S1, intelligent terminal collection obtain an images to be recognized, and the images to be recognized is pre-processed;S2, one real-time data base of offer, the pretreated images to be recognized is identified with the image information in the real-time data base and compared, and is obtained and the images to be recognized information identical described image information according to identification comparison result;S3, the corresponding audio-frequency information of acquisition described image information;S4, one video library of offer, the audio-frequency information is compared with the voice data in the video library, obtains the corresponding video source information of the audio-frequency information.For traditional image is compared or audio is compared, the above method can allow user by simplest operation, obtain high recognition rate and the result of high discrimination.
Description
Technical field
The present invention relates to audio frequency and video process field, more particularly to a kind of side that advertisement video source is recognized by intelligent terminal
Method.
Background technology
With the development of electronic product, various videos are flooded with our life, particularly TV and advertisement machine, daily
There is substantial amounts of advertisement to broadcast.But it is due to the characteristic of advertisement, the time of each advertisement is shorter, so user is for interested
Advertised product, its detailed content can not be recognized by the so short time.In order to solve this problem, often now
Mode is that user can be by shooting one section of advertisement audio of an advertising image or record, to be identified in video library
Processing, finally to obtain the video source information of the advertisement, i.e. name of product, detailed product introduction, contact method etc..But,
Due to there is substantial amounts of advertising data information in video library, if so only directly carried out by a two field picture in video library
Compare, recognition result is likely to occur deviation, and recognition time also can be very long.In order to consider recognition efficiency, user can directly adopt
Voice data in the audio & video storehouse is compared collection audio, but when gathering audio, user needs one section of collection
The audio of time, will also ensure that Input Process is not influenceed by noise, this is unfavorable for the operation of user.Therefore it provides one kind is just
Operated in user and the method for recognizing advertisement video source with high discrimination, as current urgent problem to be solved.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of method that advertisement video source is recognized by intelligent terminal,
To reach effect that simple to operate, discrimination is high.
The technical scheme is that:It is a kind of that the method that advertisement video is originated, methods described bag are recognized by intelligent terminal
Include step:
S1, intelligent terminal collection obtain an images to be recognized, and the images to be recognized is pre-processed;
S2, one real-time data base of offer, by the figure in the pretreated images to be recognized and the real-time data base
As comparison is identified in information, is obtained and believed with the images to be recognized information identical described image according to identification comparison result
Breath;
S3, the corresponding audio-frequency information of acquisition described image information;
S4, one video library of offer, the audio-frequency information is compared with the voice data in the video library, institute is obtained
State the corresponding video source information of audio-frequency information.
Preferably, the real-time data base includes some comes Source coding information and audio/video information correspondingly,
The audio-video signal include current point in time before predetermined amount of time in it is each it is described come the corresponding institute of Source coding information
State audio-frequency information and described image information.
Preferably, it is described come Source coding information include TV station's coding information and/or advertisement machine machine information.
Preferably, the video library includes some one-to-one video data, voice data and video source datas.
Preferably, the video source data includes one-to-one name of product and/or product introduction and/or advertiser's name
Claim and/or vendor name and/or contact method.
Preferably, providing a set top box, it is each that real-time data base write-in in real time is transmitted from the set top box
It is described come the corresponding audio/video information of Source coding information.
A frame is stored to the reality every some frames preferably, the described image information come will be transmitted from the set top box
When database in.
Above-mentioned technical proposal has the following advantages that or beneficial effect:In above-mentioned recognition methods, due to being deposited in real-time data base
What is stored up is the view data in real-time update and certain period of time, so image recognition processes are rapid.It is that video library is carried out
During comparison, or be compared using audio, the high efficiency and the performance of high-accuracy compared using audio, can quickly,
Accurately obtain final video source.For traditional image is compared or audio is compared, the above method can allow use
Family obtains high recognition rate and the result of high discrimination by simplest operation.
Brief description of the drawings
With reference to appended accompanying drawing, more fully to describe embodiments of the invention.However, appended accompanying drawing be merely to illustrate and
Illustrate, and be not meant to limit the scope of the invention.
Fig. 1 recognizes the schematic flow sheet for the method that advertisement video is originated for the present invention by intelligent terminal.
Embodiment
The method that advertisement video is originated, which is entered, to be recognized by intelligent terminal to the present invention with specific embodiment below in conjunction with the accompanying drawings
Row is described in detail.
As shown in figure 1, a kind of recognize the method that advertisement video is originated, including step by intelligent terminal:
S1, by intelligent terminal collection obtain an images to be recognized, the images to be recognized is pre-processed;
S2, one real-time data base of offer, by the image information in pretreated images to be recognized and the real-time data base
Comparison is identified, is obtained and the images to be recognized information identical image information according to identification comparison result;
S3, obtain the corresponding audio-frequency information of the image information;
S4, the voice data in the audio-frequency information and video library is compared, obtains the corresponding video of the audio-frequency information
Source data.
Specifically, in the method in advertisement video source is recognized above by intelligent terminal, one is gathered in intelligent terminal
After images to be recognized, first have to pre-process the image, the pretreatment can include denoising, filtering and image enhaucament etc.
Process.After image is pre-processed, pretreated images to be recognized is entered with the image information in real-time data base
Row is compared, until comparing out and the images to be recognized information identical image information.Now, the corresponding sound of the image information is obtained
Frequency information, and the audio-frequency information is compared with the voice data in video library, obtain the corresponding video source of the audio-frequency information
Data.
It is worthy of note that, real-time data base includes some and comes Source coding information and audio frequency and video letter correspondingly
Breath, wherein carrying out Source coding information includes TV station's coding information and/or advertisement machine machine information.A scheduled time is provided, the sound
Video information in the predetermined amount of time before the current time including each coming the corresponding audio-frequency information of Source coding information and figure
As information.In simple terms, in the real-time data base, be stored with each TV station or advertisement machine information are calculated with current time node
The audio/video information in predetermined amount of time risen, i.e., during the audio/video information is real-time update.It is worthy of note that, with height
The popularization of clear TV, even so in predetermined amount of time, the data volume of image information is still larger, and in advertisement video,
The data differences of adjacent a few frames are not too much big.So, it is not to store all advertisements in predetermined amount of time in actual applications
Video, but a frame image data is stored at interval of several frames, this way is greatly reduced the data storage of real-time data base
Amount, improves storage efficiency, and when carrying out image recognition, recognition result is not influenceed and recognition efficiency can be improved.
For further, the real-time data base is connected with set top box, to update audio-frequency information and image information in real time.
For further, by image recognition, contrast obtain images to be recognized that intelligent terminal photographs it is corresponding come
After Source coding information, transfer this and carry out the corresponding audio-frequency information of Source coding information, by the audio in the audio-frequency information and video library
Data are compared, to obtain the video source data of the audio-frequency information.It is worthy of note that, due to real-time data base middle pitch frequency
According to the real-time and synchronism with image information, so after the source of the images to be recognized is obtained by image recognition, should
Voice data in the corresponding audio frequency and video of images to be recognized is, under the time corresponding to the images to be recognized identical vision signal
It is stored into the audio of the real-time data base.It is worthy of note that, due to image recognition processes quickly, and after images to be recognized collection
Immediately be identified stored in processing, real-time data base be current point in time before predetermined amount of time in audio frequency and video, institute
With when transferring corresponding audio-frequency information, this in current real-time data storehouse is carried out into the corresponding audio-frequency information of Source coding information whole
Transfer.I.e. due to the instantaneity of image processing process, thus now this in real-time data base to carry out Source coding information corresponding
Audio-frequency information still comes from same video source with images to be recognized.
For further, video library includes some one-to-one video datas, voice data and video source number
According to wherein video source data includes one-to-one name of product and/or product introduction and/or advertiser's title and/or producer
Title and/or contact method etc..
Because audio identification is more much higher than the efficiency and success rate of image recognition, if so only straight by a two field picture
It is connected in video library and is compared, recognition result is likely to occur deviation, and recognition time also can be very long.But if user is direct
Voice data in the audio & video storehouse is compared collection audio, and user needs to gather the audio of long period, and also
Ensure that Input Process is not influenceed by noise.So there is provided a real-time data base, and by above-mentioned identification, shoot treating for acquisition
Identification image is sent to real-time data base and carries out image recognition in real time, with image recognition quick obtaining images to be recognized correspondence
Audio-frequency information, then be compared by the audio-frequency information with the voice data in video library, obtain final video source.Due to reality
When database in store is view data in real-time update and certain period of time, so image recognition processes are rapid.
It is compared when video library is compared, or using audio, the high efficiency and the property of high-accuracy compared using audio
Can, it can fast and accurately obtain final video source.It is above-mentioned for traditional image is compared or audio is compared
Method can allow user by simplest operation, obtain high recognition rate and the result of high discrimination.
For a person skilled in the art, read after described above, various changes and modifications undoubtedly will be evident.
Therefore, appended claims should regard whole variations and modifications of the true intention and scope that cover the present invention as.In power
Any and all scope and content of equal value, are all considered as still belonging to the intent and scope of the invention in the range of sharp claim.
Claims (7)
1. a kind of recognize the method that advertisement video is originated by intelligent terminal, it is characterised in that methods described includes step:
S1, intelligent terminal collection obtain an images to be recognized, and the images to be recognized is pre-processed;
S2, one real-time data base of offer, the image in the pretreated images to be recognized and the real-time data base is believed
Comparison is identified in breath, is obtained and the images to be recognized information identical described image information according to identification comparison result;
S3, the corresponding audio-frequency information of acquisition described image information;
S4, one video library of offer, the audio-frequency information is compared with the voice data in the video library, the sound is obtained
The corresponding video source information of frequency information.
2. according to claim 1 recognize the method that advertisement video is originated by intelligent terminal, it is characterised in that the reality
When database include some and come Source coding information and audio/video information correspondingly, the audio-video signal includes current
In predetermined amount of time before time point it is each it is described come the corresponding audio-frequency information of Source coding information and described image letter
Breath.
3. according to claim 2 recognize the method that advertisement video is originated by intelligent terminal, it is characterised in that described next
Source coding information includes TV station's coding information and/or advertisement machine machine information.
4. according to claim 1 recognize the method that advertisement video is originated by intelligent terminal, it is characterised in that described to regard
Frequency storehouse includes some one-to-one video data, voice data and video source datas.
5. according to claim 4 recognize the method that advertisement video is originated by intelligent terminal, it is characterised in that described to regard
Frequency source data include one-to-one name of product and/or product introduction and/or advertiser's title and/or vendor name and/or
Contact method.
6. according to claim 1 recognize the method that advertisement video is originated by intelligent terminal, it is characterised in that provides one
Set top box, the real-time data base in real time write-in transmitted from the set top box come it is each it is described come Source coding information it is corresponding
The audio/video information.
7. according to claim 6 recognize the method that advertisement video is originated by intelligent terminal, it is characterised in that will be from institute
State the described image information for transmitting to come in set top box and store a frame into the real-time data base every some frames.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710249938.0A CN107124648A (en) | 2017-04-17 | 2017-04-17 | The method that advertisement video is originated is recognized by intelligent terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710249938.0A CN107124648A (en) | 2017-04-17 | 2017-04-17 | The method that advertisement video is originated is recognized by intelligent terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107124648A true CN107124648A (en) | 2017-09-01 |
Family
ID=59725347
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710249938.0A Pending CN107124648A (en) | 2017-04-17 | 2017-04-17 | The method that advertisement video is originated is recognized by intelligent terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107124648A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110677718A (en) * | 2019-09-27 | 2020-01-10 | 腾讯科技(深圳)有限公司 | Video identification method and device |
CN112448868A (en) * | 2020-12-02 | 2021-03-05 | 新华三人工智能科技有限公司 | Network traffic data identification method, device and equipment |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289281A (en) * | 2011-06-07 | 2011-12-21 | 苏海洋 | Open stereometric information interactive system |
CN102650993A (en) * | 2011-02-25 | 2012-08-29 | 北大方正集团有限公司 | Index establishing and searching methods, devices and systems for audio-video file |
US20130006625A1 (en) * | 2011-06-28 | 2013-01-03 | Sony Corporation | Extended videolens media engine for audio recognition |
CN103021404A (en) * | 2012-11-23 | 2013-04-03 | 黄伟 | Advertisement identification method based on audio |
CN103024464A (en) * | 2011-12-31 | 2013-04-03 | 中国科学院计算技术研究所 | System and method for providing information related to video playing content |
CN103108229A (en) * | 2013-02-06 | 2013-05-15 | 上海云联广告有限公司 | Method for identifying video contents in cross-screen mode through audio frequency |
CN103514196A (en) * | 2012-06-25 | 2014-01-15 | 联想(北京)有限公司 | Information processing method and electronic device |
CN103747293A (en) * | 2014-01-10 | 2014-04-23 | 北京酷云互动科技有限公司 | Television program-associated product recommending method and recommending device |
CN104391924A (en) * | 2014-11-21 | 2015-03-04 | 南京讯思雅信息科技有限公司 | Mixed audio and video search method and system |
CN104599692A (en) * | 2014-12-16 | 2015-05-06 | 上海合合信息科技发展有限公司 | Recording method and device and recording content searching method and device |
CN104754377A (en) * | 2013-12-27 | 2015-07-01 | 阿里巴巴集团控股有限公司 | Smart television data processing method, smart television and smart television system |
CN104754413A (en) * | 2013-12-30 | 2015-07-01 | 北京三星通信技术研究有限公司 | Image search based television signal identification and information recommendation method and device |
CN104902345A (en) * | 2015-05-26 | 2015-09-09 | 多维新创(北京)技术有限公司 | Method and system for realizing interactive advertising and marketing of products |
CN105095316A (en) * | 2014-05-22 | 2015-11-25 | 扬智科技股份有限公司 | Video content marking and searching method |
CN105373938A (en) * | 2014-08-27 | 2016-03-02 | 阿里巴巴集团控股有限公司 | Method for identifying commodity in video image and displaying information, device and system |
CN106097040A (en) * | 2016-05-31 | 2016-11-09 | 北京小米移动软件有限公司 | Information-pushing method, device and terminal unit |
CN106462609A (en) * | 2014-04-18 | 2017-02-22 | 谷歌公司 | Methods, systems, and media for presenting music items relating to media content |
-
2017
- 2017-04-17 CN CN201710249938.0A patent/CN107124648A/en active Pending
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102650993A (en) * | 2011-02-25 | 2012-08-29 | 北大方正集团有限公司 | Index establishing and searching methods, devices and systems for audio-video file |
CN102289281A (en) * | 2011-06-07 | 2011-12-21 | 苏海洋 | Open stereometric information interactive system |
US20130006625A1 (en) * | 2011-06-28 | 2013-01-03 | Sony Corporation | Extended videolens media engine for audio recognition |
CN103024464A (en) * | 2011-12-31 | 2013-04-03 | 中国科学院计算技术研究所 | System and method for providing information related to video playing content |
CN103514196A (en) * | 2012-06-25 | 2014-01-15 | 联想(北京)有限公司 | Information processing method and electronic device |
CN103021404A (en) * | 2012-11-23 | 2013-04-03 | 黄伟 | Advertisement identification method based on audio |
CN103108229A (en) * | 2013-02-06 | 2013-05-15 | 上海云联广告有限公司 | Method for identifying video contents in cross-screen mode through audio frequency |
CN104754377A (en) * | 2013-12-27 | 2015-07-01 | 阿里巴巴集团控股有限公司 | Smart television data processing method, smart television and smart television system |
CN104754413A (en) * | 2013-12-30 | 2015-07-01 | 北京三星通信技术研究有限公司 | Image search based television signal identification and information recommendation method and device |
CN103747293A (en) * | 2014-01-10 | 2014-04-23 | 北京酷云互动科技有限公司 | Television program-associated product recommending method and recommending device |
CN106462609A (en) * | 2014-04-18 | 2017-02-22 | 谷歌公司 | Methods, systems, and media for presenting music items relating to media content |
CN105095316A (en) * | 2014-05-22 | 2015-11-25 | 扬智科技股份有限公司 | Video content marking and searching method |
CN105373938A (en) * | 2014-08-27 | 2016-03-02 | 阿里巴巴集团控股有限公司 | Method for identifying commodity in video image and displaying information, device and system |
CN104391924A (en) * | 2014-11-21 | 2015-03-04 | 南京讯思雅信息科技有限公司 | Mixed audio and video search method and system |
CN104599692A (en) * | 2014-12-16 | 2015-05-06 | 上海合合信息科技发展有限公司 | Recording method and device and recording content searching method and device |
CN104902345A (en) * | 2015-05-26 | 2015-09-09 | 多维新创(北京)技术有限公司 | Method and system for realizing interactive advertising and marketing of products |
CN106097040A (en) * | 2016-05-31 | 2016-11-09 | 北京小米移动软件有限公司 | Information-pushing method, device and terminal unit |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110677718A (en) * | 2019-09-27 | 2020-01-10 | 腾讯科技(深圳)有限公司 | Video identification method and device |
CN110677718B (en) * | 2019-09-27 | 2021-07-23 | 腾讯科技(深圳)有限公司 | Video identification method and device |
CN112448868A (en) * | 2020-12-02 | 2021-03-05 | 新华三人工智能科技有限公司 | Network traffic data identification method, device and equipment |
CN112448868B (en) * | 2020-12-02 | 2022-09-30 | 新华三人工智能科技有限公司 | Network traffic data identification method, device and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110826398B (en) | Intelligent image recognition big data acquisition and analysis system and application method | |
US11620678B2 (en) | Advertising method, device and system, and computer-readable storage medium | |
JP2020025322A (en) | Automatic content recognition fingerprint sequence matching | |
CN103514242A (en) | Intelligent interaction method and system for electronic advertising board | |
CN103581705A (en) | Method and system for recognizing video program | |
CN109429103B (en) | Method and device for recommending information, computer readable storage medium and terminal equipment | |
CN202998337U (en) | Video program identification system | |
WO2020259510A1 (en) | Method and apparatus for detecting information embedding region, electronic device, and storage medium | |
CN101489139A (en) | Video advertisement correlation method and system based on visual saliency | |
CN104837059A (en) | Video processing method, device and system | |
US20230368248A1 (en) | Method and system for analyzing live broadcast video content with a machine learning model implementing deep neural networks to quantify screen time of displayed brands to the viewer | |
CN103607635A (en) | Method, device and terminal for caption identification | |
CN105451029A (en) | Video image processing method and device | |
CN109906611A (en) | Characteristic spectrum for content characteristic map is laid out | |
WO2015169141A1 (en) | Channel classification method and device | |
CN104217718A (en) | Method and system for voice recognition based on environmental parameter and group trend data | |
CN103942275A (en) | Video identification method and device | |
CN103593356A (en) | Method and system for information searching on basis of multimedia information fingerprint technology and application | |
US20240062581A1 (en) | Obtaining artist imagery from video content using facial recognition | |
CN107124648A (en) | The method that advertisement video is originated is recognized by intelligent terminal | |
CN104796734B (en) | The smart television program combination commending system and method for real-time, interactive | |
CN111724199A (en) | Intelligent community advertisement accurate delivery method and device based on pedestrian active perception | |
CN110750719A (en) | IPTV-based information accurate pushing system and method | |
CN109947990A (en) | A kind of wonderful detection method and system | |
CN102695086A (en) | Content pushing methods and device for interactive network protocol television |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170901 |