CN111836065B - Intelligent method for automatically hiding live broadcast trademark - Google Patents
Intelligent method for automatically hiding live broadcast trademark Download PDFInfo
- Publication number
- CN111836065B CN111836065B CN202010677367.2A CN202010677367A CN111836065B CN 111836065 B CN111836065 B CN 111836065B CN 202010677367 A CN202010677367 A CN 202010677367A CN 111836065 B CN111836065 B CN 111836065B
- Authority
- CN
- China
- Prior art keywords
- trademark
- live
- live broadcast
- trademarks
- image
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000005516 engineering process Methods 0.000 claims abstract description 4
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000010409 ironing Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/40—Filling a planar surface by adding surface attributes, e.g. colour or texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- 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
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
-
- 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
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/47815—Electronic shopping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The invention relates to an intelligent method for automatically hiding live broadcast trademarks, which is characterized in that a live broadcast field image is shot by a camera and is transmitted to an analysis server of a live broadcast application program background by a live broadcast network, trademarks contained in the field image are identified based on a deep neural network target detection model, and the trademarks which are not expected to be displayed are hidden by adopting a mosaic technology according to the selection result of a main broadcast, so that the hiding and the displaying of different trademarks are realized.
Description
Technical Field
The invention relates to the technical field of network live broadcast, in particular to an intelligent method for automatically hiding a live broadcast trademark.
Background
The network live broadcast is a propagation form which is raised along with the development of internet technology in recent years, and gradually becomes a behavior of realizing multi-dimensional interaction in a virtual social space. Direct broadcasting gradually becomes an important connection way from person to person, from person to object, and from person to society in a revolutionary propagation form.
Content management and constraints for the live network process are gradually developing. For example, in the process of marketing a product by a live dealer (also called an electronic business anchor), there are many factors to be considered, and besides the marketing target product, for other products of different brands involved in the live dealer, the brand of the brand needs to be concealed in time to avoid unnecessary disputes. Taking a promotion garment steamer as an example, when a live salesperson promotes, the whole garment ironing process is inevitably shown, at the moment, if the brand of the garment is exposed, the salesperson hopes that the brand of the garment is hidden, otherwise, certain influence on the brand of the garment may be generated in the live broadcasting process.
The existing live broadcast usually hides the trademark of a non-promotion brand in a mode of shielding in advance, and cannot be operated in the live broadcast process, the method increases the manpower labor, and omission easily occurs, for example, the trademark on a cutter is usually directly sprayed or printed on the metal surface, and is difficult to shield. At present, no method specially for automatically hiding trademarks related to live broadcasting exists. Therefore, how to automatically and intelligently hide the trademark of the non-promotion brand in the live broadcast process is a technical problem to be solved urgently.
Disclosure of Invention
In view of this, the invention provides an intelligent method for automatically hiding live broadcast trademarks, and aims to realize automatic intelligent hiding of trademarks of non-promotion trademarks in a live broadcast process.
In order to achieve the above object, the present invention provides an intelligent method for automatically hiding a live broadcast trademark, which hides a trademark of a non-promotion brand related to a live broadcast salesman in a live broadcast process, and comprises:
1) live broadcast live shooting: shooting image information of a live broadcast site by using a camera;
2) live image transmission: uploading the shot live image information to a background analysis server of a live broadcast application program;
3) live broadcast trademark identification: identifying, on the analysis server, all trademarks appearing in the live image;
4) and (3) sending an identification result: the background analysis server sends a message to the anchor, and the content is all identified trademarks;
5) selecting a live trademark: according to the recognized trademark result, the anchor selects the trademark to be displayed and the trademark to be hidden, and if the part of the trademark to be displayed or hidden is not recognized, the trademark can be manually added;
6) and (3) selecting a result and sending: the anchor sends the selected result to a background analysis server of the live broadcast application program;
7) hiding a live broadcast trademark: according to the trademark result selected by the anchor, the analysis server hides the trademark needing to be hidden;
in the scheme of the invention, live broadcast scene shooting is realized by using a live broadcast camera to shoot information of a live broadcast scene, and shooting time can be before live broadcast starts, before live broadcast scene switching or during live broadcast;
specifically, live shooting may be local one-by-one shooting or whole shooting;
in the scheme of the invention, the field image transmission is to transmit the image shot by the camera to a background analysis server of a live broadcast application platform;
specifically, live images are transmitted using a live network;
further, the scene information transmission rate is the current live broadcast network rate;
the live broadcast trademark recognition in the scheme of the invention is to recognize all trademarks appearing in live broadcast field images on an analysis server by utilizing a deep neural network algorithm of image processing;
further, the trademark identification process is realized through a target detection model;
specifically, the working principle of the target detection model is as follows:
1) collecting all trademark images which may appear in a current live broadcast scene to make an image sample;
2) labeling a detection object in an image sample to manufacture a detection sample;
3) training a target detection model by using a detection sample to obtain a target detector;
4) the target detector is used for carrying out target detection on a trademark image contained in an image shot by the camera;
further, the method for collecting the trademark image includes but is not limited to:
1) shooting by using a camera;
2) searching through the Internet;
further, the target detection model detects the target in the image in a frame-by-frame or frame skipping manner;
further, the output result of the target detection model contains the identified trademark, the number of the trademarks and the positions of the trademarks in the image;
the identification result sending in the scheme of the invention is that all identified trademarks are sent to the anchor by the analysis server according to the trademark identification result;
preferably, the trademark sent to the anchor is displayed in the sending content in a mode of images, characters or image and character combination;
specifically, the identification result is sent by using a live broadcast network;
further, the sending rate of the identification result is the current live broadcast network rate;
the live broadcast trademark selection in the scheme of the invention is that the anchor actively selects the trademark to be displayed and the trademark to be hidden, and unidentified trademarks can be added manually;
preferably, the default is that the trademark with the largest number is detected as the trademark needing to be displayed, and the rest are trademarks needing to be hidden;
specifically, the manual addition of the unidentified partial trademark can be realized by uploading the trademark image or the text description form;
the selection result is sent in the scheme of the invention, the anchor sends the trademark result which is selectively displayed and hidden to the target detector of the analysis server again to complete the trademark selection interaction with the analysis server;
specifically, when the selection result of the anchor has unidentified trademarks, updating the target to be detected by the target detector, and repeating the steps from 'live trademark identification' to 'selection result sending' until all trademarks to be hidden are completely identified;
the live broadcast trademark hiding method is characterized in that an analysis server hides a trademark needing to be hidden according to a trademark result selected by a main broadcast;
specifically, according to the trademark result selected by the anchor, combining the trademark position detected by the target detector, and hiding the trademark at the position;
preferably, the trademark hiding processing is realized by adopting an image mosaic technology on the identified trademark position;
compared with the prior art, the invention has the following beneficial effects:
the invention utilizes the camera to shoot the live broadcast field information and transmits the live broadcast field information to the analysis server; identifying the trademark contained in the site by using a target detection model based on a deep neural network, and sending an identification result to the anchor; the anchor can manually select the trademark result to be hidden and displayed; and hiding the trademark to be hidden by the analysis server according to the trademark position detected by the target detection model. Compared with the prior art, the technical scheme provided by the invention has the advantages that the camera is utilized to collect live broadcast field images, the deep neural network algorithm is utilized to detect and identify trademarks contained in the field images, and hiding and displaying of different trademarks are realized according to the selection of the anchor.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a schematic diagram of steps of an intelligent method for automatically hiding a live broadcast trademark according to the present invention.
Fig. 2 is a schematic diagram of an identification result transmission page.
Detailed Description
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
The embodiments of the present invention are intended to explain the concept of the present invention, the technical problems to be solved, the technical features constituting the technical solutions, and the technical effects to be brought about. The description of the embodiments is not intended to limit the present invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In the embodiment, sales promotion of kitchen supplies is taken as an example, a target product promoted by direct-broadcast salesman is taken as a frying pan, and in order to ensure the completeness of the sales promotion process, the whole preparation and cooking process needs to be displayed;
furthermore, trademarks are set on the surfaces of electric products such as an induction cooker, a range hood and the like, and the trademarks are inconsistent with the brand of a frying pan to be promoted;
further, setting a trademark on the surface of the cutter product, wherein the trademark is consistent with the brand of the frying pan to be promoted;
furthermore, the surfaces of other articles have no trademark;
as shown in fig. 1, an intelligent method for automatically hiding a live trademark includes the following steps:
6) and (3) selecting a result and sending: the anchor sends the selected result to a background analysis server of the live broadcast application program;
7) hiding a live broadcast trademark: according to the trademark result selected by the anchor, the analysis server hides the trademark needing to be hidden;
s1: live broadcast live shooting
In the embodiment, live broadcast scene shooting is to shoot information of a live broadcast scene by using a live broadcast camera;
specifically, the content shot in the live broadcast site includes a scene and an object in the live broadcast site;
specifically, live broadcast live shooting is performed before live broadcast is performed or before live broadcast is transferred;
in this embodiment, live scene shooting is the whole shooting of multi-angle, through the shooting angle of adjustment camera, guarantees that whole shooting covers all objects in the live scene.
S2: live image transmission
In this embodiment, live image information captured by a camera is uploaded to a background analysis server of a live application program;
in particular, live image transmission is realized through a live network;
specifically, the rate of live image transmission is the current live network rate.
S3: target detection model training
In this embodiment, a trademark recognition model needs to be trained in advance, specifically, an image recognition method based on a deep neural network is adopted;
specifically, a YOLO v3 (Joseph Redmon, Ali Farhadi, YOLOv3: An included Improvement) target detection algorithm is adopted;
further, training of the YOLO v3 target detection model is performed by importing detection samples of various trademarks in advance, and includes:
1) searching for PNG pictures of brand trademarks related to kitchen supplies through the Internet, downloading or saving files to manufacture detection samples;
preferably, for a single picture containing a plurality of trademarks, the picture can be cut to ensure that each file only contains one trademark;
preferably, for a brand with multiple trademarks, the brands can be distinguished by name or serial number;
2) the detection sample is used for training a YOLO v3 target detection model, and the trained target detection model is a target detector;
preferably, the trained target detector is capable of outputting the detected trademark and position information of the trademark;
3) the target detector can be used for detecting trademarks in live-broadcast live images shot by the camera in real time;
further, the object detector may detect on a frame-by-frame or frame-skipping basis.
S4: live broadcast trademark selection
In the present embodiment, a trademark image included in a live image is detected by an object detector;
preferably, the target detector outputs the detected trademarks, the number of detections of each trademark, and its position information in the image.
S5: recognition result sending
In this embodiment, the analysis server sends a message to the live salesman, where the content of the message is a page including a trademark identification result, and a schematic diagram of the sent page is shown in fig. 2;
preferably, the trademark identification result is displayed in a page in an image form, and the trademark identification results are arranged in descending order according to each trademark, namely, the trademark with the largest number is arranged at the forefront;
further, the live salesman can select a trademark to be displayed or hidden in the page;
further, if the page does not contain all trademarks that the live salesman wishes to display or hide, the addition may be made through the page.
S6: live broadcast trademark selection
In this embodiment, the live salesman selects a page to be displayed or hidden from the pages in S5;
preferably, if the selection of the live salesman is the trademark needing to be displayed, the rest trademarks are hidden, and vice versa;
preferably, the trademarks of the number in the default identification result are trademarks needing to be displayed, and the other trademarks needing to be hidden;
preferably, the live salesperson can invoke the default result without selecting a brand that needs to be displayed or hidden.
S7: hand-operated adding trade mark
In this embodiment, if the page in S5 does not include all trademarks that the live salesman wishes to display or hide, the live salesman may manually add trademarks through the page;
preferably, the live salesman can add trademarks that need to be displayed and/or hidden;
preferably, the modes of adding the trademark comprise instant shooting, calling from an album and searching through the Internet;
further, if the page in S5 includes all trademarks that the live salesman wishes to display or hide, S7 is skipped.
S8: selection result transmission
In this embodiment, after the page operation of the live salesman in S5 is completed, click on the page to 'complete', and then the selection result may be directly sent to the background analysis server of the live application program;
preferably, after the result is sent, the page is not automatically closed;
preferably, if the live salesman needs to correct the selection result, the operation can be performed again on the page, based on the result sent last time.
S9: trademark re-identification
In the present embodiment, when the live salesperson manually adds a trademark in S7, the trademark is input to the object detector, and the trademark contained in the live image is re-recognized by the object detector;
further, S4 to S9 are repeated until all trademarks desired to be hidden are recognized;
further, if the live salesperson does not manually add a trademark, S9 is skipped.
S10: live broadcast trademark hiding
In the embodiment, a mosaic image is generated at the position of the trademark needing to be hidden according to the output result of the target detector, so as to hide the trademark;
further, in the live broadcasting process, the target detector can detect live broadcasting field images in real time, if the trademark type detected by the target detector is not changed, S4 to S9 are not repeated, and the analysis server only hides the trademark needing to be hidden;
further, when a transition occurs in the live broadcast or a new type of trademark is introduced, the target detector detects the new type of trademark, and S4 to S9 are repeated, and trademark hiding is performed again according to the recognition result detected by the target detector.
In summary, the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. An intelligent method for automatically hiding a live trademark is characterized by comprising the following steps:
live broadcast live shooting: shooting image information of a live broadcast site by using a camera;
live image transmission: uploading the shot live image information to a background analysis server of a live broadcast application program;
live broadcast trademark identification: identifying, on the analysis server, all trademarks appearing in the live image;
and (3) sending an identification result: the background analysis server sends a message to the anchor, and the content is all identified trademarks;
selecting a live trademark: according to the recognized trademark result, the anchor selects the trademark to be displayed and the trademark to be hidden, and if the trademark to be displayed or hidden is not recognized, the trademark can be manually added;
and (3) selecting a result and sending: the anchor sends the selected result to a background analysis server of the live broadcast application program;
hiding a live broadcast trademark: according to the trademark result selected by the anchor, the analysis server hides the trademark needing to be hidden;
the live broadcast trademark identification is to identify all trademarks appearing in live broadcast live images on an analysis server by utilizing a target detection model;
the working principle of the target detection model is as follows:
1) collecting all trademark images which may appear in a current live broadcast scene to make an image sample;
2) labeling a detection object in an image sample to manufacture a detection sample;
3) training a target detection model by using a detection sample to obtain a target detector;
4) the target detector is used for carrying out target detection on a trademark image contained in an image shot by the camera;
the target detection model detects the target in the image in a frame-by-frame or frame skipping mode;
the output result of the target detection model comprises the identified trademark, the number of the trademarks and the positions of the trademarks in the image.
2. The intelligent method for automatically hiding the live broadcast trademark as claimed in claim 1, wherein the live broadcast scene shooting is to shoot the information of the live broadcast scene by using a live broadcast camera, the shooting time can be before the live broadcast starts, before the live broadcast scene is switched or during the live broadcast, and the shooting mode can be local one-by-one shooting or integral shooting.
3. The intelligent method for automatically hiding the live trademark according to claim 1, wherein the live image transmission is to transmit the image shot by the camera to a background analysis server of a live application platform by using a live network.
4. An intelligent method for automatically hiding a live trademark according to claim 1, wherein the method for collecting trademark images comprises but is not limited to:
1) shooting by using a camera;
2) searching through the internet.
5. The intelligent method for automatically hiding the live trademark according to claim 1, wherein the identification result is sent by an analysis server to a host by using a live network according to the trademark identification result of a target detection model;
and the trademark in the identification result is displayed in a mode of images, characters or image and character combination.
6. The intelligent method for automatically hiding the live trademark according to claim 1, wherein the live trademark is selected by a broadcaster to select the trademark to be displayed and the trademark to be hidden, and unidentified trademarks can be added manually;
the default of the trademark needing to be displayed is the trademark with the largest detected quantity, and the rest are the trademarks needing to be hidden;
the manual addition of unidentified trademarks can be realized by uploading images or text description forms of the trademarks.
7. The intelligent method for automatically hiding the live trademark according to claim 1, wherein the selection result is sent by the anchor to resend the selection display and hidden trademark result to the analysis server;
and if the trademark to be displayed or hidden is not recognized, updating the target to be detected by the target detector through manual addition after the manual addition of the unidentified trademark is completed, and repeating the steps from the 'live trademark recognition' to the 'selection result sending' until all the trademarks to be hidden are recognized.
8. An intelligent method for automatically hiding a live trademark according to claim 1, wherein the live trademark hiding is trademark hiding processing on the position according to a trademark result selected by a main broadcaster and a trademark position detected by an object detector;
the trademark hiding processing is realized by adopting an image mosaic technology at the identified trademark position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010677367.2A CN111836065B (en) | 2020-07-14 | 2020-07-14 | Intelligent method for automatically hiding live broadcast trademark |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010677367.2A CN111836065B (en) | 2020-07-14 | 2020-07-14 | Intelligent method for automatically hiding live broadcast trademark |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111836065A CN111836065A (en) | 2020-10-27 |
| CN111836065B true CN111836065B (en) | 2022-04-29 |
Family
ID=72923174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010677367.2A Active CN111836065B (en) | 2020-07-14 | 2020-07-14 | Intelligent method for automatically hiding live broadcast trademark |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111836065B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2005203083A1 (en) * | 2004-07-21 | 2006-02-09 | Igt | Gaming method and system with a hidden image game piece |
| EP2632152A2 (en) * | 2005-03-02 | 2013-08-28 | United Video Properties, Inc. | Playlists and bookmarks in an interactive media guidance application system |
| WO2014059439A1 (en) * | 2012-10-12 | 2014-04-17 | Document Security Systems, Inc. | System and method for analysis and authentication using a smart device |
| EP2793478A1 (en) * | 2013-04-15 | 2014-10-22 | Nagravision S.A. | Method for managing multimedia devices within a local environment and system for implementing this method |
| CN105405092A (en) * | 2015-11-26 | 2016-03-16 | 熊桂荣 | Secure digital image propagation method based on reversible watermark and mosaic technology |
| CN107274373A (en) * | 2017-06-30 | 2017-10-20 | 武汉斗鱼网络科技有限公司 | Live middle code printing method and device |
| KR101859433B1 (en) * | 2017-02-14 | 2018-05-21 | 에스케이텔레콤 주식회사 | Method for processing of mosaic image and apparatus thereof |
| WO2019171128A1 (en) * | 2018-03-06 | 2019-09-12 | Yogesh Chunilal Rathod | In-media and with controls advertisement, ephemeral, actionable and multi page photo filters on photo, automated integration of external contents, automated feed scrolling, template based advertisement post and actions and reaction controls on recognized objects in photo or video |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7668791B2 (en) * | 2006-07-31 | 2010-02-23 | Microsoft Corporation | Distinguishing facts from opinions using a multi-stage approach |
| CA2973079C (en) * | 2015-01-07 | 2019-11-05 | Arris Enterprises Llc | Detecting and processing multiplexed closed caption data |
-
2020
- 2020-07-14 CN CN202010677367.2A patent/CN111836065B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2005203083A1 (en) * | 2004-07-21 | 2006-02-09 | Igt | Gaming method and system with a hidden image game piece |
| EP2632152A2 (en) * | 2005-03-02 | 2013-08-28 | United Video Properties, Inc. | Playlists and bookmarks in an interactive media guidance application system |
| WO2014059439A1 (en) * | 2012-10-12 | 2014-04-17 | Document Security Systems, Inc. | System and method for analysis and authentication using a smart device |
| EP2793478A1 (en) * | 2013-04-15 | 2014-10-22 | Nagravision S.A. | Method for managing multimedia devices within a local environment and system for implementing this method |
| CN105405092A (en) * | 2015-11-26 | 2016-03-16 | 熊桂荣 | Secure digital image propagation method based on reversible watermark and mosaic technology |
| KR101859433B1 (en) * | 2017-02-14 | 2018-05-21 | 에스케이텔레콤 주식회사 | Method for processing of mosaic image and apparatus thereof |
| CN107274373A (en) * | 2017-06-30 | 2017-10-20 | 武汉斗鱼网络科技有限公司 | Live middle code printing method and device |
| WO2019171128A1 (en) * | 2018-03-06 | 2019-09-12 | Yogesh Chunilal Rathod | In-media and with controls advertisement, ephemeral, actionable and multi page photo filters on photo, automated integration of external contents, automated feed scrolling, template based advertisement post and actions and reaction controls on recognized objects in photo or video |
Non-Patent Citations (1)
| Title |
|---|
| ""直播带货"要"带标"更要"带法"";李英锋;《当代广西》;20200616;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111836065A (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI615776B (en) | Method and system for creating virtual message onto a moving object and searching the same | |
| WO2013114638A1 (en) | Image processing system, image processing device, image processing method, program, and information storage medium | |
| JP6070705B2 (en) | Information processing apparatus, data processing method thereof, and program | |
| CN108230262A (en) | Image processing method, image processing apparatus and storage medium | |
| CN108124184A (en) | A kind of method and device of living broadcast interactive | |
| US20150049900A1 (en) | Information provision system | |
| CN103488528A (en) | QR code processing method and device based on mobile terminals | |
| WO2014168177A1 (en) | Image processing device | |
| US8593557B2 (en) | Shooting assist method, program product, recording medium, shooting device, and shooting system | |
| CN108197621A (en) | Company information acquisition methods and system and information processing method and system | |
| JP2010086194A (en) | Share image browsing method and device | |
| CN106599285A (en) | News searching-based searching result providing method and apparatus | |
| JP2017033293A (en) | Image processing device, image processing method, program, and recording medium | |
| CN108984576A (en) | A kind of patent document acquisition methods and system based on convolutional neural networks | |
| CN106980612A (en) | Information recommendation system and method | |
| CN111836065B (en) | Intelligent method for automatically hiding live broadcast trademark | |
| WO2015107424A1 (en) | System and method for product placement | |
| Shao et al. | Towards the creation of a nutrition and food group based image database | |
| CN106250541A (en) | The method for pushing of a kind of information and device | |
| Kawano et al. | [Demo paper] mirurecipe: A mobile cooking recipe recommendation system with food ingredient recognition | |
| CN110762943B (en) | Article display method and device and household appliance | |
| JP7395889B2 (en) | Image processing device and image search method | |
| CN112183914B (en) | Evaluation method and device for dish items | |
| JP2014010716A (en) | Electronic menu program and electronic menu server | |
| US20200111244A1 (en) | System and method for associating images and text |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220411 Address after: Room 101, bungalow, building 3 [8-8], courtyard 4, Sanjianfang Nanli, Chaoyang District, Beijing 100024 Applicant after: Beijing scene entertainment media Technology Co.,Ltd. Address before: Room f101-12, No.1 incubation and production building, guanshao shuangchuang (equipment) center, Huake City, 42 Baiwang Avenue, Wujiang District, Shaoguan City, Guangdong Province, 512026 Applicant before: Shaoguan Qizhi Information Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |