CN101790049A - Newscast video segmentation method and system - Google Patents
Newscast video segmentation method and system Download PDFInfo
- Publication number
- CN101790049A CN101790049A CN201010123111A CN201010123111A CN101790049A CN 101790049 A CN101790049 A CN 101790049A CN 201010123111 A CN201010123111 A CN 201010123111A CN 201010123111 A CN201010123111 A CN 201010123111A CN 101790049 A CN101790049 A CN 101790049A
- Authority
- CN
- China
- Prior art keywords
- frame
- announcer
- video
- key frame
- segmentation
- 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
- Studio Circuits (AREA)
Abstract
The invention discloses a newscast video segmentation method and a system thereof. The newscast video segmentation method comprises the following steps: analyzing a video file and detecting key frames in the video file, wherein the key frames comprise frames in positions with scene changes in a video image; detecting announcer frames in the key frames, wherein the announcer frames comprises frames of a scene image related to an announcer in a studio; and segmenting the video file with the detected announcer frames as a segmentation basis. The invention utilizes the inherent features of newscasts, and can realize the automatic segmentation of the newscast video with specific video frames determined through the image identification technology as the basis for video segmentation, thereby effectively reducing the labor and time input for video segmentation and improving the processing efficiency.
Description
Technical field
The present invention relates to the multimedia processing technology field, particularly relate to a kind of Newscast video segmentation method and system.
Background technology
News program is the program category that often contacts in a kind of people's daily life, along with multimedia and development of internet technology, the user watches that the approach of news program not only has been confined to televise, but can watch news program by various ways such as download or program requests.
The other types video is the same with watching, and under a lot of situations, the user may not need to watch complete news program content at every turn, and only pays close attention to some news footages wherein.In order to satisfy above-mentioned application demand, a kind of implementation commonly used is that the user by operations such as " F.F. ", " rewind downs ", perhaps directly drags playing progress bar when displaying video, find the specific video play time.But generally in whole video where user and not knowing oneself wants the video segment watched should be, also accurate positioning playing time point just, and the user may need repeatedly adjustment operation just can find the location of content of oneself needs like this.
News program generally is to be combined by many news contents, exists comparatively significantly segmentation foundation.Based on this characteristics of news program, Newscast video can be divided into several paragraphs in advance, and in addition suitable index, play demand with the selection of satisfying the user.Existing news program segmentation is mainly to be based on manually-operated mode, promptly goes out waypoint by operating personnel's manual markings in video file, and this just requires operating personnel at first will browse whole news videos, and workload is big and loaded down with trivial details, and treatment effeciency is lower.
Summary of the invention
For solving the problems of the technologies described above, the invention provides a kind of Newscast video segmentation method and system, to realize the automatic segmentation to Newscast video, technical scheme is as follows:
A kind of Newscast video segmentation method comprises:
Video file is analyzed, detected the key frame in the video file, described key frame is: the frame of scene variation place in the video image;
Detect the announcer's frame in the described key frame, described announcer's frame is: have the frame of announcer at the broadcasting studio scene image;
As the segmentation foundation, video file is carried out segment processing with detected announcer's frame.
A kind of Newscast video segmentation system comprises:
The key frame detecting unit is used for video file is analyzed, and detects the key frame in the video file, and described key frame is: the frame of scene variation place in the video image;
Announcer's frame detecting unit is used for detecting announcer's frame of described key frame, and described announcer's frame is: have the frame of announcer at the broadcasting studio scene image;
Segmenting unit is used for detected announcer's frame as the segmentation foundation video file being carried out segment processing.
Technical scheme provided by the present invention, utilize the inherent characteristics of news program, the application image recognition technology is determined some specific video frame as the foundation that video is carried out segmentation, wherein, can be announcer's frame or heading frame as the particular video frequency frame of segmentation foundation.Use technical solution of the present invention, can realize automatic segmentation, thereby the manpower and the time that effectively reduce video segmentation work are dropped into the raising treatment effeciency Newscast video.
Description of drawings
In order to be illustrated more clearly in the present invention or technical scheme of the prior art, to do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below, apparently, the accompanying drawing that describes below only is some embodiment that put down in writing among the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is a news program arranged mode schematic diagram;
Fig. 2 is a Newscast video segmentation method flow chart of the present invention;
Fig. 3 is a key frame testing result schematic diagram of the present invention;
Fig. 4 (a) is a kind of announcer's position view in the news program;
Fig. 4 (b) is the another kind of announcer's position view in the news program;
Fig. 5 is announcer's frame testing result schematic diagram of the present invention;
Fig. 6 is the main title area schematic in the news program;
Fig. 7 is a heading frame testing result schematic diagram of the present invention;
Fig. 8 is the testing result schematic diagram of announcer's frame of the present invention and heading frame;
Fig. 9 sets up the schematic diagram of program segments for the present invention;
Figure 10 is the structural representation of Newscast video segmentation of the present invention system;
Figure 11 is the another kind of structural representation of Newscast video segmentation of the present invention system.
Embodiment
By research to prior art, the inventor finds: news program has following characteristics: a complete news program, generally be made up of several news footages, each news footage is being the instructor in broadcasting, is being the particular content and the picture of news then by the announcer of TV station at first; Be the particular content and the picture of the instructor in broadcasting of next news footage, next news footage then; ... repeat with this rule, as shown in Figure 1.As seen, although the duration difference of each news footage, its arranged mode is to have certain rules governed, and according to this rule, " announcer " is a very important clue when doing the news segmentation.Find the announcer, just can find a newsreel section boundary very soon.The present invention then is based on this rule, and technology such as combining image processing realize the automatic segmentation to Newscast video.
In order to make those skilled in the art person understand technical scheme among the present invention better, below in conjunction with the accompanying drawing among the present invention, technical scheme among the present invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills should belong to the scope of protection of the invention not making the every other embodiment that is obtained under the creative work prerequisite.
Referring to shown in Figure 2, the segmentation method of Newscast video provided by the present invention can may further comprise the steps:
S201 analyzes video file, detects the key frame in the video file;
At first select pending video file, can carry out rapid analysis to it after opening video file, at this moment the key frame that extracts in the video is cut apart in system by camera lens.Key frame described here is to obtain by shot transition or the violent small fragment of front and back image change in the analysis video, because the variation of two field picture is often very little before and after in the same scene, so it is more accurate by the method scene to be divided, reduce redundant simultaneously.Key frame images can be shown the Storyboard that forms program, as shown in Figure 3, make the streaming program become the image list that non-linearly to browse.
S202 detects the announcer's frame in the key frame;
According to the analysis of this specification front as can be known, " announcer " is an important clue doing the news segmentation, and the scene that the announcer occurs can be thought the beginning of a news footage.In S201, detected the key frame that relates to scene change in the whole video, so, have the frame of announcer at the broadcasting studio scene image by in these key frames, further finding out, just can be with its foundation as video segmentation.
To the detection of announcer's frame, can realize by modes such as images match and/or the detections of people's face.
With the news hookup is example, the environment of news broadcasting studio all is changeless in long period, therefore can choose the normal pictures of a broadcast environment in advance, the key frame picture is carried out matching operation respectively with it, wherein, matching operation can be carried out according to parameters such as gradation of image value, histograms.By mating, similarity can be defined as announcer's frame greater than the key frame of certain preset threshold value.
In like manner, in instructor in broadcasting's scene of news program, announcer's position is also fixed, and generally comprises two kinds of forms: in the human settlements or about two people occupy respectively, shown in Fig. 4 (a) and Fig. 4 (b).According to this rule, can carry out people's face to key frame images and detect, comprise people's face in the key frame if detect, and the above-mentioned two kinds of situations of the region conforms at people's face place, then key frame can be defined as announcer's frame.
Be understandable that, in actual applications, in order to obtain the detection effect of better announcer's frame, also above-mentioned dual mode can be carried out combination: at first pass through the contrast of the image of broadcast environmental standard picture and key frame, filter out and the high frame of broadcasting studio normal pictures similarity.Again The selection result is carried out people's face and detect, obtain the human face region position in the picture, find out the frame that human face region is in ad-hoc location at last.Like this, by repeatedly screening, can make testing result more accurate.On the other hand, people's face detects needs to consume a large amount of system resource, handles and the key frame after the screening is carried out the detection of people's face, can effectively reduce the data volume that people's face detects, thereby obtain detection speed faster.
The testing result of announcer's frame as shown in Figure 5, wherein, this frame of the number of people in image sign expression be announcer's frame, the numbering of the numeral frame below the image.
S203 as the segmentation foundation, carries out segment processing to video file with detected announcer's frame.
After detecting announcer's frame, just can carry out segment processing to video file with these announcer's frames as the segmentation foundation.For example, with the starting point of each announcer's frame, set up and play index as segmentation.Certainly, when practical operation, can carry out manual fine setting again to detected announcer's frame, the present invention does not limit this yet.
In news program, general corresponding every section news content, the capital shows the headline captions when this section content play, and the demonstration of main title generally also is after scene change, based on these characteristics, in another embodiment of the present invention, can also be further with frame with headline captions image also as the foundation of video segmentation.
Referring to shown in Figure 6, be example with the news hookup, headline drops on the white undercolor region, and title fixedly appears at the image bottom.Can judge whether special frames exists the white background zone to determine whether to exist Title area by direct.Because title may be delegation or multirow, so regional location is not to be fixed on certain height.Because it is very low to occur horizontal probability in the natural image, system is by with image transitions being gray level image SOBEL operator image, detect marginal water horizontal line position and come Primary Location Title area position, whether reaffirm Title area by background colour in the coupling Title area then.Certainly, according to the difference of concrete news program picture design, can select other heading frame detection mode for use, the present invention need not limit this yet.
The testing result of heading frame as shown in Figure 7, wherein, this frame of " T " in image sign expression is a heading frame, the numbering of the numeral frame of image below.
Because every section news all has its corresponding heading frame, therefore similar with announcer's frame, also can utilize heading frame to be used as foundation to Newscast video segmentation.Certainly, in actual conditions, also can realize segmentation in conjunction with these two kinds of special frame types to Newscast video.And, be understandable that some frame also may be announcer's frame, also be heading frame simultaneously, as shown in Figure 8.
After determining the original position of program segments, can further be additional other information of program segments according to special frames.As shown in Figure 9, be a kind of schematic diagram of setting up program segments.Listed some in the upper right side of figure and can be used as the preview picture of fragment placard, the user can select the suitable picture of opening and closing as the fragment placard voluntarily therein.The title of fragment can be imported voluntarily by the user, also can carry out literal identification by the caption area to the heading frame image, with the text message that the obtains title as video segmentation.Further, the user also can carry out the copy editor to the content of news footage, wherein, because newsreader's pronunciation is unusual standard all, therefore also can pass through speech recognition technology, the content of will broadcasting is automatically converted to text message, and the user can directly carry out appropriateness editor intercepting to the text that is generated, as the brief introduction of news footage.
Corresponding to top method embodiment, the present invention also provides a kind of Newscast video segmentation system, referring to shown in Figure 10, comprising:
Key frame detecting unit 1001 is used for video file is analyzed, and detects the key frame in the video file, and described key frame is: the frame of scene variation place in the video image;
Announcer's frame detecting unit 1002 is used for detecting announcer's frame of described key frame, and described announcer's frame is: have the frame of announcer at the broadcasting studio scene image;
Segmenting unit 1003 is used for detected announcer's frame as the segmentation foundation video file being carried out segment processing.
Wherein, described announcer's frame detecting unit can comprise the first coupling subelement or the second coupling subelement:
The first coupling subelement is used for key frame images and broadcast environmental standard image are mated, if similarity greater than the threshold value that presets, then is defined as announcer's frame with described key frame.
The second coupling subelement is used for that described key frame images is carried out people's face and detects, if detected human face region and the announcer's location matches that presets then are defined as announcer's frame with described key frame.
Referring to shown in Figure 11, said system can further include:
Heading frame detecting unit 1004 is used for detecting the heading frame of described key frame, and described heading frame is: the frame with headline captions image;
Described segmenting unit 1003 can also carry out segment processing to video file with the detected heading frame of heading frame detecting unit 1004 as the segmentation foundation.
Caption character recognition unit 1005, the caption area that is used for the heading frame image carries out literal identification, with the text message that the obtains title as video segmentation.
For the convenience of describing, be divided into various unit with function when describing above the device and describe respectively.Certainly, when enforcement is of the present invention, can in same or a plurality of softwares and/or hardware, realize the function of each unit.
As seen through the above description of the embodiments, those skilled in the art can be well understood to the present invention and can realize by the mode that software adds essential general hardware platform.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words can embody with the form of software product, this computer software product can be stored in the storage medium, as ROM/RAM, magnetic disc, CD etc., comprise that some instructions are with so that a computer equipment (can be a personal computer, server, the perhaps network equipment etc.) carry out the described method of some part of each embodiment of the present invention or embodiment.
Each embodiment in this specification all adopts the mode of going forward one by one to describe, and identical similar part is mutually referring to getting final product between each embodiment, and each embodiment stresses all is difference with other embodiment.Especially, for system embodiment, because it is substantially similar in appearance to method embodiment, so describe fairly simplely, relevant part gets final product referring to the part explanation of method embodiment.System embodiment described above only is schematic, wherein said unit as the separating component explanation can or can not be physically to separate also, the parts that show as the unit can be or can not be physical locations also, promptly can be positioned at a place, perhaps also can be distributed on a plurality of network element.Can select wherein some or all of module to realize the purpose of present embodiment scheme according to the actual needs.Those of ordinary skills promptly can understand and implement under the situation of not paying creative work.
The present invention can be used in numerous general or special purpose computingasystem environment or the configuration.For example: personal computer, server computer, handheld device or portable set, plate equipment, multicomputer system, the system based on microprocessor, set top box, programmable consumer-elcetronics devices, network PC, minicom, mainframe computer, comprise distributed computing environment (DCE) of above any system or equipment or the like.
The present invention can describe in the general context of the computer executable instructions of being carried out by computer, for example program module.Usually, program module comprises the routine carrying out particular task or realize particular abstract, program, object, assembly, data structure or the like.Also can in distributed computing environment (DCE), put into practice the present invention, in these distributed computing environment (DCE), by by communication network connected teleprocessing equipment execute the task.In distributed computing environment (DCE), program module can be arranged in the local and remote computer-readable storage medium that comprises memory device.
The above only is the specific embodiment of the present invention; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the principle of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (10)
1. a Newscast video segmentation method is characterized in that, comprising:
Video file is analyzed, detected the key frame in the video file, described key frame is: the frame of scene variation place in the video image;
Detect the announcer's frame in the described key frame, described announcer's frame is: have the frame of announcer at the broadcasting studio scene image;
As the segmentation foundation, video file is carried out segment processing with detected announcer's frame.
2. method according to claim 1 is characterized in that, the announcer's frame in the described detection key frame comprises:
Key frame images and broadcast environmental standard image are mated, if similarity greater than the threshold value that presets, then is defined as announcer's frame with described key frame.
3. method according to claim 1 is characterized in that, the announcer's frame in the described detection key frame comprises:
Described key frame images is carried out people's face detect, if detected human face region and the announcer's location matches that presets then are defined as announcer's frame with described key frame.
4. according to each described method of claim 1 to 3, it is characterized in that, further comprise:
Detect the heading frame in the described key frame, described heading frame is: the frame with headline captions image;
As the segmentation foundation, video file is carried out segment processing with detected heading frame.
5. method according to claim 4 is characterized in that, further comprises:
The caption area of heading frame image is carried out literal identification, with the text message that obtains title as video segmentation.
6. a Newscast video segmentation system is characterized in that, comprising:
The key frame detecting unit is used for video file is analyzed, and detects the key frame in the video file, and described key frame is: the frame of scene variation place in the video image;
Announcer's frame detecting unit is used for detecting announcer's frame of described key frame, and described announcer's frame is: have the frame of announcer at the broadcasting studio scene image;
Segmenting unit is used for detected announcer's frame as the segmentation foundation video file being carried out segment processing.
7. system according to claim 6 is characterized in that, described announcer's frame detecting unit comprises:
The first coupling subelement is used for key frame images and broadcast environmental standard image are mated, if similarity greater than the threshold value that presets, then is defined as announcer's frame with described key frame.
8. system according to claim 6 is characterized in that, described announcer's frame detecting unit comprises:
The second coupling subelement is used for that described key frame images is carried out people's face and detects, if detected human face region and the announcer's location matches that presets then are defined as announcer's frame with described key frame.
9. according to each described system of claim 6 to 8, it is characterized in that, further comprise:
The heading frame detecting unit is used for detecting the heading frame of described key frame, and described heading frame is: the frame with headline captions image;
Described segmenting unit also is used for detected heading frame as the segmentation foundation video file being carried out segment processing.
10. system according to claim 9 is characterized in that, further comprises:
The caption character recognition unit, the caption area that is used for the heading frame image carries out literal identification, with the text message that the obtains title as video segmentation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010123111A CN101790049A (en) | 2010-02-25 | 2010-02-25 | Newscast video segmentation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010123111A CN101790049A (en) | 2010-02-25 | 2010-02-25 | Newscast video segmentation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101790049A true CN101790049A (en) | 2010-07-28 |
Family
ID=42533079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010123111A Pending CN101790049A (en) | 2010-02-25 | 2010-02-25 | Newscast video segmentation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101790049A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102915755A (en) * | 2012-09-07 | 2013-02-06 | 博康智能网络科技股份有限公司 | Method for extracting moving objects on time axis based on video display |
| CN103313122A (en) * | 2012-03-09 | 2013-09-18 | 联想(北京)有限公司 | Data processing method and electronic device |
| CN103491381A (en) * | 2013-08-22 | 2014-01-01 | 合一网络技术(北京)有限公司 | Method for optimizing video coding keyframe positions through dynamic planning |
| CN103577063A (en) * | 2012-07-23 | 2014-02-12 | Lg电子株式会社 | Mobile tmerinal and control method thereof |
| WO2016066092A1 (en) * | 2014-10-29 | 2016-05-06 | 腾讯科技（深圳）有限公司 | Multimedia playing controlling method and device, and storage medium |
| CN105979267A (en) * | 2015-12-03 | 2016-09-28 | 乐视致新电子科技（天津）有限公司 | Video compression and play method and device |
| CN106162222A (en) * | 2015-04-22 | 2016-11-23 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device of video lens cutting |
| CN106470358A (en) * | 2015-08-21 | 2017-03-01 | 深圳市天易联科技有限公司 | The video memory image-recognizing method of intelligent TV set and device |
| CN107087211A (en) * | 2017-03-30 | 2017-08-22 | 北京奇艺世纪科技有限公司 | A kind of anchor shots detection method and device |
| WO2017162010A1 (en) * | 2016-03-21 | 2017-09-28 | 中兴通讯股份有限公司 | Method and apparatus for realizing caption processing |
| CN107277557A (en) * | 2017-06-16 | 2017-10-20 | 深圳市茁壮网络股份有限公司 | A kind of methods of video segmentation and system |
| CN107436921A (en) * | 2017-07-03 | 2017-12-05 | 李洪海 | Video data handling procedure, device, equipment and storage medium |
| CN107977645A (en) * | 2017-12-19 | 2018-05-01 | 北京奇艺世纪科技有限公司 | A kind of news-video poster map generalization method and device |
| CN108471543A (en) * | 2018-03-12 | 2018-08-31 | 北京搜狐新媒体信息技术有限公司 | A kind of advertisement information adding method and device |
| CN108495185A (en) * | 2018-03-14 | 2018-09-04 | 北京奇艺世纪科技有限公司 | A kind of video title generation method and device |
| CN108710860A (en) * | 2018-05-23 | 2018-10-26 | 北京奇艺世纪科技有限公司 | A kind of news-video dividing method and device |
| CN108804980A (en) * | 2017-04-28 | 2018-11-13 | 合信息技术（北京）有限公司 | Switching detection method of video scene and device |
| CN110337027A (en) * | 2019-07-11 | 2019-10-15 | 北京字节跳动网络技术有限公司 | Video generation method, device and electronic equipment |
| CN108566567B (en) * | 2018-04-25 | 2020-09-01 | 中影数字巨幕（北京）有限公司 | Movie editing method and device |
| CN114339299A (en) * | 2021-12-27 | 2022-04-12 | 司法鉴定科学研究院 | Video evidence obtaining method for automobile driving recorder |
-
2010
- 2010-02-25 CN CN201010123111A patent/CN101790049A/en active Pending
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103313122A (en) * | 2012-03-09 | 2013-09-18 | 联想(北京)有限公司 | Data processing method and electronic device |
| US9710136B2 (en) | 2012-07-23 | 2017-07-18 | Lg Electronics Inc. | Mobile terminal having video playback and method for controlling of the same |
| CN103577063A (en) * | 2012-07-23 | 2014-02-12 | Lg电子株式会社 | Mobile tmerinal and control method thereof |
| CN103577063B (en) * | 2012-07-23 | 2016-09-14 | Lg电子株式会社 | Mobile terminal and control method thereof |
| CN102915755A (en) * | 2012-09-07 | 2013-02-06 | 博康智能网络科技股份有限公司 | Method for extracting moving objects on time axis based on video display |
| CN103491381A (en) * | 2013-08-22 | 2014-01-01 | 合一网络技术(北京)有限公司 | Method for optimizing video coding keyframe positions through dynamic planning |
| CN103491381B (en) * | 2013-08-22 | 2016-03-02 | 合一网络技术(北京)有限公司 | Video coding key frame position method is optimized in a kind of Dynamic Programming |
| WO2016066092A1 (en) * | 2014-10-29 | 2016-05-06 | 腾讯科技（深圳）有限公司 | Multimedia playing controlling method and device, and storage medium |
| US9918138B2 (en) | 2014-10-29 | 2018-03-13 | Tencent Technology (Shenzhen) Company Limited | Method for controlling multimedia playing, apparatus thereof and storage medium |
| US10419823B2 (en) | 2014-10-29 | 2019-09-17 | Tencent Technology (Shenzhen) Company Limited | Method for controlling multimedia playing, apparatus thereof and storage medium |
| CN106162222A (en) * | 2015-04-22 | 2016-11-23 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device of video lens cutting |
| CN106162222B (en) * | 2015-04-22 | 2019-05-24 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device of video lens cutting |
| CN106470358B (en) * | 2015-08-21 | 2020-09-25 | 深圳市天易联科技有限公司 | Video memory image identification method and device of smart television |
| CN106470358A (en) * | 2015-08-21 | 2017-03-01 | 深圳市天易联科技有限公司 | The video memory image-recognizing method of intelligent TV set and device |
| WO2017092340A1 (en) * | 2015-12-03 | 2017-06-08 | 乐视控股（北京）有限公司 | Method and device for compressing and playing video |
| CN105979267A (en) * | 2015-12-03 | 2016-09-28 | 乐视致新电子科技（天津）有限公司 | Video compression and play method and device |
| WO2017162010A1 (en) * | 2016-03-21 | 2017-09-28 | 中兴通讯股份有限公司 | Method and apparatus for realizing caption processing |
| CN107087211A (en) * | 2017-03-30 | 2017-08-22 | 北京奇艺世纪科技有限公司 | A kind of anchor shots detection method and device |
| CN108804980A (en) * | 2017-04-28 | 2018-11-13 | 合信息技术（北京）有限公司 | Switching detection method of video scene and device |
| CN107277557B (en) * | 2017-06-16 | 2019-12-03 | 深圳市茁壮网络股份有限公司 | A kind of methods of video segmentation and system |
| CN107277557A (en) * | 2017-06-16 | 2017-10-20 | 深圳市茁壮网络股份有限公司 | A kind of methods of video segmentation and system |
| CN107436921A (en) * | 2017-07-03 | 2017-12-05 | 李洪海 | Video data handling procedure, device, equipment and storage medium |
| CN107977645A (en) * | 2017-12-19 | 2018-05-01 | 北京奇艺世纪科技有限公司 | A kind of news-video poster map generalization method and device |
| CN108471543A (en) * | 2018-03-12 | 2018-08-31 | 北京搜狐新媒体信息技术有限公司 | A kind of advertisement information adding method and device |
| CN108495185A (en) * | 2018-03-14 | 2018-09-04 | 北京奇艺世纪科技有限公司 | A kind of video title generation method and device |
| CN108566567B (en) * | 2018-04-25 | 2020-09-01 | 中影数字巨幕（北京）有限公司 | Movie editing method and device |
| CN108710860A (en) * | 2018-05-23 | 2018-10-26 | 北京奇艺世纪科技有限公司 | A kind of news-video dividing method and device |
| CN108710860B (en) * | 2018-05-23 | 2021-01-12 | 北京奇艺世纪科技有限公司 | Video news segmentation method and device |
| CN110337027A (en) * | 2019-07-11 | 2019-10-15 | 北京字节跳动网络技术有限公司 | Video generation method, device and electronic equipment |
| CN114339299A (en) * | 2021-12-27 | 2022-04-12 | 司法鉴定科学研究院 | Video evidence obtaining method for automobile driving recorder |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101790049A (en) | Newscast video segmentation method and system | |
| KR101435140B1 (en) | Display apparatus and method | |
| US10242265B2 (en) | Actor/person centric auto thumbnail | |
| US8750681B2 (en) | Electronic apparatus, content recommendation method, and program therefor | |
| KR102290419B1 (en) | Method and Appratus For Creating Photo Story based on Visual Context Analysis of Digital Contents | |
| US8861898B2 (en) | Content image search | |
| US8935169B2 (en) | Electronic apparatus and display process | |
| EP3044725B1 (en) | Generating alerts based upon detector outputs | |
| US8285114B2 (en) | Electronic apparatus and display method | |
| US8559683B2 (en) | Electronic apparatus and scene-type display method | |
| US8396332B2 (en) | Electronic apparatus and face image display method | |
| US6954900B2 (en) | Method for summarizing news video stream using synthetic key frame based upon video text | |
| WO2020006309A1 (en) | Video subtitle display method and apparatus | |
| CN111930994A (en) | Video editing processing method and device, electronic equipment and storage medium | |
| CN102342124A (en) | Method and apparatus for providing information related to broadcast programs | |
| CN101057247A (en) | Detection and modification of text in a image | |
| CN106028160A (en) | Image data processing method and device | |
| JP2005243035A (en) | Apparatus and method for determining anchor shot | |
| KR100374040B1 (en) | Method for detecting caption synthetic key frame in video stream | |
| CN110177295B (en) | Subtitle out-of-range processing method and device and electronic equipment | |
| US10897658B1 (en) | Techniques for annotating media content | |
| CN111625716A (en) | Media asset recommendation method, server and display device | |
| KR20140044663A (en) | Information retrieval method by using broadcast receiving apparatus with display device and the apparatus thereof | |
| CN113301382A (en) | Video processing method, device, medium, and program product | |
| CN116389849A (en) | Video generation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1144512 Country of ref document: HK |
|
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20100728 |
|
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: WD Ref document number: 1144512 Country of ref document: HK |