CN102685574A - System for automatically extracting images from digital television program and application thereof - Google Patents
System for automatically extracting images from digital television program and application thereof Download PDFInfo
- Publication number
- CN102685574A CN102685574A CN2011100555321A CN201110055532A CN102685574A CN 102685574 A CN102685574 A CN 102685574A CN 2011100555321 A CN2011100555321 A CN 2011100555321A CN 201110055532 A CN201110055532 A CN 201110055532A CN 102685574 A CN102685574 A CN 102685574A
- Authority
- CN
- China
- Prior art keywords
- module
- video
- voice
- detection
- captions
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a system for automatically extracting images from a digital television program and applications of the system for automatically extracting the images from the digital television program. The system provided by the invention comprises an image distinguishing module, a subtitle distinguishing module, a voice distinguishing module and a key video frame and voice extracting module, wherein the image distinguishing module analyzes video data through scene change detection, face detection, movement detection and character object detection; the subtitle distinguishing module confirms whether subtitle exists at present; the voice distinguishing module judges whether currently received voice frequency data is voice; and the key video frame and voice extracting module receives analysis and detection results for the video data, distinguishing results for the subtitle and the distinguishing results for the voice and extracts key video frames and relevant voices according to the arrangement of a user and the analysis and detection results for the video data, distinguishing results for the subtitle and the distinguishing results for the voice. The system provided by the invention can automatically extract the 'key frames' representing the understanding of the content from video signals of a digital television. Besides, the system provided by the invention can be applied to electronic books and cartoon and can be used for manufacturing a video document which has low resolution and can display images at fixed period.
Description
Technical field
The present invention relates to the digital television techniques field, particularly relate to a kind of system and application thereof of Automatic Extraction image from digital television program.
Background technology
Video is appreciated that and is continuous images sequence in time, finds with test by inquiry, and when the video content of DTV is understood, be not that all images all play a part no less important.The real image that the understanding of digital TV video frequency is played an important role has following several types:
● the frame of corresponding captions is arranged;
● the frame that occurrence scene switches;
● the frame that has people's face to occur;
● the frame that has who object to occur;
● the frame of certain movement amplitude is arranged;
● the frame that has corresponding voice to occur.
Above-mentioned image can be used as and judges whether to be the play an important role condition of image of the understanding to digital TV video frequency; Can make up according to user's demand; Finally define " key frame ", should " key frame " meet one of them conditioned disjunction full terms at least.
Therefore, how Automatic Extraction goes out the understanding of content significant " key frame " from the vision signal of DTV, just the problem paid close attention to of the present invention and insider.
Summary of the invention
The technical problem that the present invention will solve provide a kind of from digital television program the system of Automatic Extraction image, can from the vision signal of DTV, Automatic Extraction go out " key frame " that the understanding of content is had the meaning represented, simple in structure, realize easily.
For solving the problems of the technologies described above; Of the present invention from digital television program the system of Automatic Extraction image; Comprise receiving terminal for digital television, this receiving terminal for digital television comprises demultiplexing module, video decode module, subtitle resolving module, audio decoder module, video display module and audio frequency display module; Wherein, also comprise:
The image discriminating module is connected with said video decode module, is used for the output frame of receiver, video decoder module; Analyze video data through scene change detection, the detection of people's face, motion detection and who object detection algorithm;
The captions discrimination module is connected with said subtitle resolving module, receives the analysis result of subtitle resolving module, confirms whether exist at the current time captions;
The voice discrimination module is connected with said audio decoder module, receives the voice data of audio decoder module output, judges whether the current voice data of receiving is speech;
Key video sequence frame and speech extraction module are connected with said image discriminating module, captions discrimination module, voice discrimination module, video decode module and audio decoder module; The result of receiving video data analyzing and testing, captions discrimination result and speech discrimination result; And Voice & Video data; Judge whether the current video that receives has captions; Whether the current video that receives has corresponding speech, extracts key video sequence frame and associated voice according to user's the setting and result, captions discrimination result and the speech discrimination result of video data analyzing and testing.
Adopt of the present invention from digital television program the system of Automatic Extraction image; Can from the vision signal of DTV, Automatic Extraction go out " key frame " that the understanding of content is had the meaning represented; Can reduce resolution and carry out special effect treatment these key frames, like effects such as " oil painting ", " cartoons "; Be equipped with captions and voice again, under the understandable prerequisite of the substance of DTV, greatly reduce data volume and increase interest, final purposes comprises:
● cooperate captions and voice to be made into e-book;
● cooperate captions to print and be made into cartoon;
● cooperate captions and be made into little resolution with voice after multiplexing, the video file of regular display image is play on mobile device.
Description of drawings
Below in conjunction with accompanying drawing and embodiment the present invention is done further detailed explanation:
Fig. 1 is a structural principle block diagram of the present invention;
Fig. 2-Fig. 7 adopts the present invention to carry out the effect contrast figure of image processing front and back.
Embodiment
Referring to shown in Figure 1, of the present invention from digital television program the system of Automatic Extraction image comprise receiving terminal for digital television and image discriminating module, captions discrimination module, voice discrimination module and key video sequence frame and speech extraction module.
Said receiving terminal for digital television is the prior standard framework, does not wherein comprise channel tuner, rectification part.Said receiving terminal for digital television comprises demultiplexing module, video decode module, subtitle resolving module, audio decoder module, video display module and audio frequency display module.
Said demultiplexing module is used for resolution system layer such as TS stream (MPEG2 System Layer), isolates audio frequency stream, video-frequency basic flow and caption information basically, is input to audio decoder, Video Decoder and subtitle resolving module respectively.
Said video decode module is connected with demultiplexing module, is used for video compression stream decoding back output is used for the video data of reprocessing or broadcast.
Said subtitle resolving module is connected with demultiplexing module, is used for converting caption information to can show form.
Said audio decoder module is connected with demultiplexing module, is used for audio compression stream decoding back output is used for the voice data of reprocessing or broadcast.
Said video display module is connected with subtitle resolving module with the video decode module, is used for video information and caption information are shown to the user.
Said audio frequency display module is connected with the audio decoder module, is used for the broadcast of audio-frequency information.
Said image discriminating module is connected with said video decode module, is used for the output frame of receiver, video decoder module.Detect scheduling algorithm through scene change detection, the detection of people's face, motion detection and who object and analyze video data, and the result of analyzing and testing is delivered to " key video sequence frame and speech extraction module ".Said image discriminating module can be carried out combination in any (promptly realizing one or more algorithms wherein) to scene change detection, the detection of people's face, motion detection and who object detection algorithm; And realize wherein a kind of algorithm at least but and do not require and realize whole algorithms that concrete combination should be confirmed according to actual needs.
Said captions discrimination module is connected with said subtitle resolving module, receives the analysis result of subtitle resolving module, confirms whether exist at the current time captions, and the result is delivered to " key video sequence and speech extraction module ".
Said voice discrimination module is connected with said audio decoder module, receives the voice data of audio decoder module output, judges whether the current voice data of receiving is speech, and the result is delivered to " key video sequence and speech extraction module ".
Key video sequence frame and speech extraction module are connected with said image discriminating module, captions discrimination module, voice discrimination module, video decode module and audio decoder module; The result of receiving video data analyzing and testing, captions discrimination result and speech discrimination result; And Voice & Video data; Judge whether the current video that receives has captions; Whether the current video that receives has corresponding speech, extracts key video sequence frame and associated voice according to user's the setting and result, captions discrimination result and the speech discrimination result of video data analyzing and testing.
Image cartoon processing module is connected with the speech extraction module with said key video sequence frame, receives " key frame " that extract, and " key frame " form with image is appeared.Adopt the Boundary Extraction like image, image special effect Processing Algorithm commonly used such as oil paint effect processing is carried out special effect processing to " key frame ".Under the prerequisite that keeps " key frame " substance, increase the interest of image.Thereby for e-book is made and the cartoon print module provides material.
The e-book manufacturing module is connected with said image cartoon processing module, and " key frame " after image cartoon processing module is handled is made into e-book.
The cartoon print module is connected with said image cartoon processing module, and " key frame " after image cartoon processing module is handled is printed as cartoon.
Graphics/audio code multiplexing module is connected with the speech extraction module with said image cartoon processing module and key video sequence frame, and " key frame " after image cartoon processing module is handled is made into little resolution, regularly the video file of display image.
Adopt system of the present invention, after extracting " key frame " and carrying out special effect treatment, can reach effects such as " oil painting ", " cartoon ".Fig. 2-Fig. 7 adopts the final effect comparison instance of realizing of the present invention.Fig. 2 (a)-Fig. 7 is original video image a), and Fig. 2 (b)-Fig. 4 (b) carries out the oil paint effect image with boundary corresponding after the special effect treatment; Fig. 5 (b) carries out the image that colored thick border corresponding after the special effect treatment proposes; Fig. 6 (b) carries out the image that colored thin border corresponding after the special effect treatment proposes; Fig. 7 (b) carries out sketch effect image corresponding after the special effect treatment.
More than through embodiment and embodiment the present invention has been carried out detailed explanation, but these are not to be construed as limiting the invention.Under the situation that does not break away from the principle of the invention, those skilled in the art also can make many distortion and improvement, and these also should be regarded as protection scope of the present invention.
Claims (5)
1. the system of an Automatic Extraction image from digital television program; Comprise; Receiving terminal for digital television, this receiving terminal for digital television comprise demultiplexing module, video decode module, subtitle resolving module, audio decoder module, video display module and audio frequency display module; It is characterized in that, also comprise:
The image discriminating module is connected with said video decode module, is used for the output frame of receiver, video decoder module; Analyze video data through scene change detection, the detection of people's face, motion detection and who object detection algorithm;
The captions discrimination module is connected with said subtitle resolving module, receives the analysis result of subtitle resolving module, confirms whether exist at the current time captions;
The voice discrimination module is connected with said audio decoder module, receives the voice data of audio decoder module output, judges whether the current voice data of receiving is speech;
Key video sequence frame and speech extraction module are connected with said image discriminating module, captions discrimination module, voice discrimination module, video decode module and audio decoder module; The result of receiving video data analyzing and testing, captions discrimination result and speech discrimination result; And Voice & Video data; Judge whether the current video that receives has captions; Whether the current video that receives has corresponding speech, extracts key video sequence frame and associated voice according to user's the setting and result, captions discrimination result and the speech discrimination result of video data analyzing and testing.
2. the system of claim 1, it is characterized in that: said image discriminating module can be carried out combination in any to scene change detection, the detection of people's face, motion detection and who object detection algorithm, and realizes wherein a kind of algorithm at least.
3. the application of the described system of claim 1 in e-book.
4. the application of the described system of claim 1 in cartoon.
5. the described system of claim 1 is cooperating captions and is being made into little resolution, the application that the video file of regular display image is play with voice after multiplexing on mobile device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100555321A CN102685574A (en) | 2011-03-09 | 2011-03-09 | System for automatically extracting images from digital television program and application thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100555321A CN102685574A (en) | 2011-03-09 | 2011-03-09 | System for automatically extracting images from digital television program and application thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102685574A true CN102685574A (en) | 2012-09-19 |
Family
ID=46816837
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011100555321A Pending CN102685574A (en) | 2011-03-09 | 2011-03-09 | System for automatically extracting images from digital television program and application thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102685574A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103634605A (en) * | 2013-12-04 | 2014-03-12 | 百度在线网络技术(北京)有限公司 | Processing method and device for video images |
CN105100892A (en) * | 2015-07-28 | 2015-11-25 | 努比亚技术有限公司 | Video playing device and method |
CN105224925A (en) * | 2015-09-30 | 2016-01-06 | 努比亚技术有限公司 | Video process apparatus, method and mobile terminal |
CN105323634A (en) * | 2014-06-27 | 2016-02-10 | Tcl集团股份有限公司 | Method and system for generating thumbnail of video |
CN105847622A (en) * | 2015-01-29 | 2016-08-10 | 京瓷办公信息***株式会社 | Image Processing Apparatus |
CN108040282A (en) * | 2017-12-21 | 2018-05-15 | 山东亿海兰特通信科技有限公司 | A kind of video broadcasting method and device |
EP3499900A3 (en) * | 2018-05-31 | 2019-10-02 | Beijing Baidu Netcom Science and Technology Co., Ltd. | Video processing method, apparatus and device |
CN111540387A (en) * | 2014-08-14 | 2020-08-14 | 高通股份有限公司 | Detection of motion frames of a video stream |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101021857A (en) * | 2006-10-20 | 2007-08-22 | 鲍东山 | Video searching system based on content analysis |
CN101783873A (en) * | 2009-01-19 | 2010-07-21 | 北京视典无限传媒技术有限公司 | Digital multimedia information transmission platform |
-
2011
- 2011-03-09 CN CN2011100555321A patent/CN102685574A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101021857A (en) * | 2006-10-20 | 2007-08-22 | 鲍东山 | Video searching system based on content analysis |
CN101783873A (en) * | 2009-01-19 | 2010-07-21 | 北京视典无限传媒技术有限公司 | Digital multimedia information transmission platform |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103634605A (en) * | 2013-12-04 | 2014-03-12 | 百度在线网络技术(北京)有限公司 | Processing method and device for video images |
WO2015081776A1 (en) * | 2013-12-04 | 2015-06-11 | 百度在线网络技术(北京)有限公司 | Method and apparatus for processing video images |
US9973793B2 (en) | 2013-12-04 | 2018-05-15 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for processing video image |
CN103634605B (en) * | 2013-12-04 | 2017-02-15 | 百度在线网络技术(北京)有限公司 | Processing method and device for video images |
CN105323634A (en) * | 2014-06-27 | 2016-02-10 | Tcl集团股份有限公司 | Method and system for generating thumbnail of video |
CN105323634B (en) * | 2014-06-27 | 2019-01-04 | Tcl集团股份有限公司 | A kind of reduced graph generating method and system of video |
CN111540387A (en) * | 2014-08-14 | 2020-08-14 | 高通股份有限公司 | Detection of motion frames of a video stream |
CN111540387B (en) * | 2014-08-14 | 2022-03-22 | 高通股份有限公司 | Detection of motion frames of a video stream |
CN105847622A (en) * | 2015-01-29 | 2016-08-10 | 京瓷办公信息***株式会社 | Image Processing Apparatus |
CN105847622B (en) * | 2015-01-29 | 2019-01-01 | 京瓷办公信息***株式会社 | Image processing apparatus |
CN105100892A (en) * | 2015-07-28 | 2015-11-25 | 努比亚技术有限公司 | Video playing device and method |
CN105100892B (en) * | 2015-07-28 | 2018-05-15 | 努比亚技术有限公司 | Video play device and method |
CN105224925A (en) * | 2015-09-30 | 2016-01-06 | 努比亚技术有限公司 | Video process apparatus, method and mobile terminal |
CN108040282A (en) * | 2017-12-21 | 2018-05-15 | 山东亿海兰特通信科技有限公司 | A kind of video broadcasting method and device |
EP3499900A3 (en) * | 2018-05-31 | 2019-10-02 | Beijing Baidu Netcom Science and Technology Co., Ltd. | Video processing method, apparatus and device |
US10929683B2 (en) * | 2018-05-31 | 2021-02-23 | Beijing Baidu Netcom Science Technology Co., Ltd. | Video processing method, apparatus and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102685574A (en) | System for automatically extracting images from digital television program and application thereof | |
US9277183B2 (en) | System and method for distributing auxiliary data embedded in video data | |
CN201319640Y (en) | Digital television receiving terminal capable of synchronously translating in real time | |
US8645983B2 (en) | System and method for audible channel announce | |
KR20170128223A (en) | A system for distributing metadata embedded in video | |
KR102484216B1 (en) | Processing and provision of multiple symbol-encoded images | |
CN102630043B (en) | Object-based video transcoding method and device | |
CN102088631B (en) | Live and demand broadcast method of digital television (TV) programs as well as related device and system | |
CN100477799C (en) | Method for improving television terminal device digital caption data processing efficiency | |
CN101855897A (en) | A method of determining a starting point of a semantic unit in an audiovisual signal | |
KR20040078765A (en) | Method for detection of closed caption data format automatically and displaying the caption data and apparatus thereof | |
JP2007325282A (en) | Content distribution system, distribution server and display terminal for content distribution system, and content distribution program | |
Chattopadhyay et al. | Mash up of breaking news and contextual web information: a novel service for connected television | |
KR20100026361A (en) | Apparatus and method for receiving broadcasting signal in dmb system | |
CN112055253A (en) | Method and device for adding and multiplexing independent subtitle stream | |
CN114640882A (en) | Video processing method and device, electronic equipment and computer readable storage medium | |
KR100789911B1 (en) | Text Display Apparatus and Method in DMB Terminals | |
CN104639980B (en) | The image transmission device of digital television broadcasting | |
US20150179228A1 (en) | Synchronized movie summary | |
US20170094373A1 (en) | Audio/video state detector | |
CN109479112B (en) | Decoder, encoder, computer-readable storage medium, and method | |
KR101208612B1 (en) | The identifying system for filtering program except formality program in real time on television broadcasting and the method thereof | |
US20210029306A1 (en) | Magnification enhancement of video for visually impaired viewers | |
Yildirim et al. | Design and implementation of a software presenting information in DVB subtitles in various forms | |
KR100799537B1 (en) | Multimedia contents conversion apparatus which can convert data to sound and its method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120919 |