CN103780973B - Video tab adding method and device - Google Patents
Video tab adding method and device Download PDFInfo
- Publication number
- CN103780973B CN103780973B CN201210395412.0A CN201210395412A CN103780973B CN 103780973 B CN103780973 B CN 103780973B CN 201210395412 A CN201210395412 A CN 201210395412A CN 103780973 B CN103780973 B CN 103780973B
- Authority
- CN
- China
- Prior art keywords
- label
- interest
- video
- picture
- incidence relation
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The invention discloses video tab adding method and device.Method includes:When carrying out video capture, choose object of interest in real time in the picture of shooting, on this map office and/or network search with interested to as similar picture and associating word, a label as object of interest is selected, the loading position of image, label, label in picture, the incidence relation between video frame identification of object of interest is preserved;In subsequent video shooting process, continue to track the object of interest, if tracing into, current video frame identification is added in the incidence relation;Video capture terminates, and relevant the institute of preservation is saved in into video file leading portion;When recording or playing video file, the incidence relation is read from video file leading portion, according to the incidence relation, label is loaded into the video pictures recorded or played.The present invention is realized adds label in real time in video pictures.
Description
Technical field
The present invention relates to technical field of video processing, and in particular to video tab adding method and device.
Background technology
Existing video tab adding method is mainly handled after video capture terminates, and is regarded for user is interested
The fileinfo of frequency frame, special time point and video itself sets up label, and label substance is generally written form, the label of foundation
It is mainly used in video search and management.
Existing video tab adding method has as a drawback that:
First, handled in the video later stage, it is impossible to synchronization process.
2nd, the content of label is all text information, including the explanatory note of a certain frame of video, the temporal information of key frame with
And the fileinfo of video itself, wherein, the fileinfo of video itself includes video duration, style, resolution ratio and picture
Ratio etc..
3rd, existing video tab and video are in itself without interaction function, and label is used as static form, it is impossible in video mistake
Dynamic Display and loading in journey, it is impossible to a certain picture to video or a certain user's object of interest carry out intuitively explanation and
Tracking is highlighted.
The content of the invention
The present invention provides video tab adding method and device, and label is added in real time in video pictures to realize.
The technical proposal of the invention is realized in this way:
A kind of video tab adding method, this method includes:
When carrying out video capture, object of interest is chosen in real time in the picture of shooting, in this map office and/or network
Upper search, to as similar picture and associate word, in the picture searched and associates one conduct of selection in word with interested
The label of object of interest, preserves loading position, the video frame identification of the image, label, label of object of interest in picture
Between incidence relation;
In subsequent video shooting process, continue to track the object of interest, if tracing into, by current video frame identification
It is added in the incidence relation;
Video capture terminates, by the loading position of the image, label, label of all object of interest of preservation in picture
Put, the incidence relation between video frame identification is saved in video file leading portion;
When recording or playing video file, the incidence relation is read from video file leading portion, according to the incidence relation,
Label is loaded into the video pictures recorded or played.
It is described according to the incidence relation, label is loaded into the video pictures recorded or played to be included:
If present frame mark is appeared in the incidence relation, the image of the object of interest in the incidence relation,
Object of interest is identified on present frame, chooses and highlights the object of interest, label in the incidence relation,
Loading position of the label in picture, label is loaded into the frame picture.
It is described to continue to further comprise after tracking the object of interest:If tracing into, and label is changed in picture
Loading position, then preserve loading position of the label after the image of object of interest, label, renewal in picture, current
Incidence relation between video frame identification.
It is described to continue to further comprise after tracking the object of interest:To stop the addition label, then stop with
The track object of interest.
A kind of video tab adding set, the device includes:
Tag search module:When carrying out video capture, object of interest is chosen in real time in the picture of shooting, local
Search in the picture searched and associates word with interested to as similar picture and associating word on picture library and/or network
One label as object of interest of middle selection, by the loading position of the image, label, label of object of interest in picture
Put, the incidence relation between video frame identification is saved in label relating module;In subsequent video shooting process, continue to track the sense
Object of interest, if tracing into, in the incidence relation that current video frame identification is added to the preservation of label relating module;
Label relating module:Video capture terminates, and the image, label, label of all object of interest of preservation are being drawn
The incidence relation between loading position, video frame identification in face is saved in video file leading portion.
Described device further comprises:
Record or playing module:When recording or playing video file, the incidence relation is read from video file leading portion,
According to the incidence relation, label is loaded into the video pictures recorded or played.
The recording or playing module are further used for, after the incidence relation is read from video file leading portion, if
Appeared in it was found that present frame is identified in the incidence relation, then the image of the object of interest in the incidence relation, current
Object of interest is identified on frame, the object of interest is chosen, the adding in picture of the label, label in the incidence relation
Position is carried, label is loaded into the frame picture.
The tag search module is further used for, after continuing to track the object of interest, if tracing into and will be more
Change loading position of the label in picture, then the adding in picture by the label after the image, label, renewal of object of interest
The incidence relation carried between position, current video frame identification is saved in label relating module.
The tag search module is further used for, after continuing to track the object of interest, to stop addition institute
Label is stated, then stops tracking the object of interest.
Described device is located in mobile device.
Compared with prior art, the present invention can add label in real time during video capture, reduce label addition
It is time-consuming;Label also includes image in addition to word simultaneously, enriches label substance;Furthermore it is possible in video record or broadcasting
During Dynamic Display and loading label.
Brief description of the drawings
Fig. 1 is video tab adding method flow chart provided in an embodiment of the present invention;
Fig. 2 applies the schematic diagram of example one for the present invention;
Fig. 3 is the composition schematic diagram of video tab adding set provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawings and specific embodiment the present invention is further described in more detail.
Fig. 1 is video tab adding method flow chart provided in an embodiment of the present invention, as shown in figure 1, its specific steps is such as
Under:
Step 101:When carrying out video capture, object of interest is chosen in real time in the picture of shooting.
Specifically, when finding object of interest in the video pictures in shooting, the object of interest can be chosen immediately.Example
Such as:Object of interest can be chosen with shapes such as rectangles.Object of interest is such as:Personage, landscape, building either present frame it is whole
Picture etc..
If the screen of video capture equipment is touch-screen, user directly can choose object of interest with hand in picture.
Step 102:On this map office and network search with interested to as similar picture and associating word.
Here it is possible to use the image search method based on content.
In actual applications, when search with interested to as similar picture and when associating word, can also be local
In picture library or only search in a network, can also first search for, if not searching, then be searched on network in this map office,
It can also be searched for simultaneously on this map office and network.
If all not searched on this map office and network, user can also oneself editor's label.
Search result may also only search picture, or only search word.
Step 103:A label as object of interest is selected in the picture and association word searched.
Multiple pictures similar with object of interest and association word may be searched on this map office and network, this
When, one of them is selected as the label of object of interest.
Step 104:Preserve between the loading position in picture of image, label, label of object of interest, video frame identification
Incidence relation.
Video frame identification can be represented with the frame of video time residing in whole video file.
Step 105:In subsequent video shooting process, continue to track the object of interest, if tracing into, update step
Incidence relation in 104.
Specifically, when in subsequent video shooting process, when tracing into the object of interest, by current video frame identification
It is added in the incidence relation of step 104.
In subsequent video shooting process, user can also change loading position of the label in picture, now, only need to protect
Loading position of the label in picture after the image, label, renewal of object of interest, the association between video frame identification is deposited to close
System, user can also select to stop adding the label, now, stop tracking object of interest.
Step 106:Video capture terminates, by the image, label, label of all object of interest of preservation in picture
Incidence relation between loading position, video frame identification is saved in video file leading portion.
Step 107:When recording or playing video file, incidence relation is read from video file leading portion, according to the association
Relation, identifies and chooses object of interest, is then loaded into label in the video pictures where object of interest.
Specifically, if present frame mark is appeared in the incidence relation, according to the object of interest in the incidence relation
Image, object of interest is identified on present frame, chooses and highlights the object of interest, then according to the association close
The loading position of label, label in picture in system, label is loaded into the frame picture.
When the video frame identification in incidence relation is a period, it is interested right continuously to be tracked within the period
As, and load label.
In actual applications, when in label include word when, the word can as frame of video index, index video
When, can be using the word in the label as index, to find the video of needs.
The Scene case applied below to the present invention.
People tag addition example during scene one, video capture:
It is mostly that theme is used as using people when shooting video.As shown in Fig. 2 during video capture, at one
Video pictures center has selected personage A, by this map office and web search, have found A photo, and obtains A name,
A photo and name are then determined into position of the label in video pictures as the label of personage A in video pictures, preserved
Loading position of personage A image, A label, the A label in picture and the pass between current video frame identification in video pictures
Connection relation;In subsequent video shooting process, tracking person A, when occurring A in picture, updates the personage A preserved image, A
Label, A loading position of the label in picture and the incidence relation between current video frame identification;When video capture terminates
When, by between loading position and video frame identification of the label of all persons A of preservation image, A label, A in picture
Incidence relation is added to video file leading portion.
Scenery label addition example during scene two, video capture:
When shooting scenic spot, it is possible to use Internet resources search for being discussed in detail for scenic spot, then with tag-shaped
Formula and captured video are associated.For example:Video capture is carried out to pyramid, frame selects pyramid area in video pictures
Domain, searches for pyramid diagram picture and character introduction on network, and one is chosen in the pyramid diagram picture and character introduction searched
As label, and loading position of the label in video pictures is determined, preserve pyramid diagram picture, the pyramid in video pictures
The loading position of label, the label in video pictures and the incidence relation between current video frame identification;Clapped in subsequent video
During taking the photograph, track pyramid, when occurring pyramid in picture, update preserve pyramidal image, pyramidal label,
Loading position of the label in picture and the incidence relation between current video frame identification;At the end of video capture, it will preserve
Loading position and video frame identification in picture of all pyramidal images, pyramidal label, pyramidal label between
Incidence relation be added to video file leading portion.
It is not the sight spot at showplace for some, the word that can be searched in this map office in label, label can be added by user
Plus.
Fig. 3 is the composition schematic diagram of video tab adding set provided in an embodiment of the present invention, as shown in figure 3, its is main
Including:Tag search module 31 and label relating module 32, wherein:
Tag search module 31:When carrying out video capture, object of interest is chosen in real time in the picture of shooting, at this
Search in the picture searched and is associated literary with interested to as similar picture and associate word on map office and/or network
A label as object of interest is selected in word, by the loading position of the image, label, label of object of interest in picture
Put, the incidence relation between video frame identification is saved in label relating module 32;In subsequent video shooting process, continue to track and be somebody's turn to do
Object of interest, if tracing into, the corresponding incidence relation that label relating module 32 is preserved is added to by current video frame identification
In.
Tag search module can be further used for, after continuing to track the object of interest, if trace into and to change
Loading position of the label in picture, the then loading by the label after the image, label, renewal of object of interest in picture
Incidence relation between position, current video frame identification is saved in label relating module 32.
Tag search module can be further used for, after continuing to track the object of interest, to stop addition label,
Then stop tracking the object of interest.
Label relating module 32:Video capture terminates, and image, label, the label of all object of interest of preservation are existed
The incidence relation between loading position, video frame identification in picture is saved in video file leading portion.
In actual applications, video tab adding set can further comprise:Record or playing module, for when record or
During playing video file, the loading position of the image, label, label of object of interest in picture is read from video file leading portion
Put, the incidence relation between video frame identification, according to the incidence relation, label is loaded into the video pictures recorded or played.
Recording or playing module can be further used for, when from video file leading portion read the image of object of interest, label,
After loading position of the label in picture, the incidence relation between video frame identification, if finding, present frame mark appears in the pass
In connection relation, then the image of the object of interest in the incidence relation, identifies object of interest on present frame, chooses
Label is loaded into the frame and drawn by the object of interest, the loading position of label, label in picture in the incidence relation
In face.
Video tab adding set can be located in mobile device.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
God is with principle, and any modification, equivalent substitution and improvements done etc. should be included within the scope of protection of the invention.
Claims (10)
1. a kind of video tab adding method, it is characterised in that this method includes:
When carrying out video capture, choose object of interest in real time in the picture of shooting, searched on this map office and/or network
Rope is with interested to as similar picture and associating word, and selection one is as feeling emerging in the picture and association word searched
The label of interesting object, is preserved between the loading position in picture of image, label, label of object of interest, video frame identification
Incidence relation;
In subsequent video shooting process, continue to track the object of interest, if tracing into, current video frame identification is added
Into the incidence relation;
Video capture terminates, and by loading position in picture of the image, label, label of all object of interest of preservation, regards
Incidence relation between frequency frame identification is saved in video file leading portion;
When recording or playing video file, the incidence relation is read from video file leading portion, according to the incidence relation, will be marked
Label are loaded into the video pictures recorded or played.
2. label according to the method described in claim 1, it is characterised in that described according to the incidence relation, is loaded into recording
Or the video pictures played include:
If present frame mark is appeared in the incidence relation, the image of the object of interest in the incidence relation, working as
Object of interest is identified in previous frame, chooses and highlights the object of interest, label, label in the incidence relation
Loading position in picture, label is loaded into the frame picture.
3. according to the method described in claim 1, it is characterised in that described to continue further to wrap after tracking the object of interest
Include:If tracing into, and loading position of the label in picture is changed, then after the image, label, renewal that preserve object of interest
Loading position of the label in picture, the incidence relation between current video frame identification.
4. according to the method described in claim 1, it is characterised in that described to continue further to wrap after tracking the object of interest
Include:To stop the addition label, then stop tracking the object of interest.
5. a kind of video tab adding set, it is characterised in that the device includes:
Tag search module:When carrying out video capture, object of interest is chosen in real time in the picture of shooting, in this map office
And/or on network search with interested to as similar picture and associate word, in the picture searched and associate choosing in word
A label as object of interest is selected, by loading position in picture of the image, label, label of object of interest, is regarded
Incidence relation between frequency frame identification is saved in label relating module;In subsequent video shooting process, continuing tracking, this is interested
Object, if tracing into, in the incidence relation that current video frame identification is added to the preservation of label relating module;
Label relating module:Video capture terminates, by the image, label, label of all object of interest of preservation in picture
Loading position, the incidence relation between video frame identification be saved in video file leading portion.
6. device according to claim 5, it is characterised in that described device further comprises:
Record or playing module:When recording or playing video file, the incidence relation is read from video file leading portion, according to
The incidence relation, label is loaded into the video pictures recorded or played.
7. device according to claim 6, it is characterised in that the recording or playing module are further used for, when from regarding
Frequency file leading portion is read after the incidence relation, if finding, present frame mark is appeared in the incidence relation, according to the pass
The image of object of interest in connection relation, identifies object of interest on present frame, the object of interest is chosen, according to this
The loading position of label, label in picture in incidence relation, label is loaded into the frame picture.
8. device according to claim 5, it is characterised in that the tag search module is further used for, when continue with
After the track object of interest, if trace into and to change loading position of the label in picture, by the figure of object of interest
Loading position of the label in picture, the incidence relation between current video frame identification after picture, label, renewal are saved in label
Relating module.
9. device according to claim 5, it is characterised in that the tag search module is further used for, when continue with
After the track object of interest, to stop the addition label, then stop tracking the object of interest.
10. according to any described device of claim 5 to 9, it is characterised in that described device is located in mobile device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210395412.0A CN103780973B (en) | 2012-10-17 | 2012-10-17 | Video tab adding method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210395412.0A CN103780973B (en) | 2012-10-17 | 2012-10-17 | Video tab adding method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103780973A CN103780973A (en) | 2014-05-07 |
CN103780973B true CN103780973B (en) | 2017-08-04 |
Family
ID=50572723
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210395412.0A Active CN103780973B (en) | 2012-10-17 | 2012-10-17 | Video tab adding method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103780973B (en) |
Families Citing this family (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103970906B (en) * | 2014-05-27 | 2017-07-04 | 百度在线网络技术(北京)有限公司 | The method for building up and device of video tab, the display methods of video content and device |
CN104184923B (en) * | 2014-08-27 | 2018-01-09 | 天津三星电子有限公司 | System and method for retrieving people information in video |
KR102252072B1 (en) * | 2014-10-14 | 2021-05-14 | 삼성전자주식회사 | Method and Apparatus for Managing Images using Voice Tag |
CN106358092B (en) * | 2015-07-13 | 2019-11-26 | 阿里巴巴集团控股有限公司 | Information processing method and device |
CN105847948A (en) * | 2016-03-28 | 2016-08-10 | 乐视控股(北京)有限公司 | Data processing method and device |
CN105898560A (en) * | 2016-03-31 | 2016-08-24 | 广州华多网络科技有限公司 | Video editing method and device |
US10629166B2 (en) * | 2016-04-01 | 2020-04-21 | Intel Corporation | Video with selectable tag overlay auxiliary pictures |
CN107515871A (en) * | 2016-06-15 | 2017-12-26 | 北京陌上花科技有限公司 | Searching method and device |
CN107770614A (en) * | 2016-08-18 | 2018-03-06 | 中国电信股份有限公司 | The label producing method and device of content of multimedia |
CN106303726B (en) * | 2016-08-30 | 2021-04-16 | 北京奇艺世纪科技有限公司 | Video tag adding method and device |
CN108337471B (en) * | 2017-02-24 | 2020-08-04 | 腾讯科技(深圳)有限公司 | Video picture processing method and device |
CN107529029A (en) * | 2017-07-31 | 2017-12-29 | 深圳回收宝科技有限公司 | One kind adds tagged method, equipment and storage medium in file is detected |
CN107577489A (en) * | 2017-08-03 | 2018-01-12 | 捷开通讯(深圳)有限公司 | Method, mobile terminal and the storage device of remote assistance |
CN109429065A (en) * | 2017-09-05 | 2019-03-05 | 联咏科技股份有限公司 | Video coding apparatus and method for video coding |
CN108200390A (en) * | 2017-12-28 | 2018-06-22 | 北京陌上花科技有限公司 | Video structure analyzing method and device |
CN108260009B (en) * | 2018-01-25 | 2021-11-02 | 努比亚技术有限公司 | Video processing method, mobile terminal and computer readable storage medium |
US10796157B2 (en) * | 2018-03-13 | 2020-10-06 | Mediatek Inc. | Hierarchical object detection and selection |
CN108460151A (en) * | 2018-03-26 | 2018-08-28 | 武汉南博网络科技有限公司 | The generation method and device of a kind of expert's video interior joint label in recording |
CN108616772B (en) * | 2018-05-04 | 2020-10-30 | 维沃移动通信有限公司 | Bullet screen display method, terminal and server |
CN108769781B (en) * | 2018-06-14 | 2019-02-26 | 视云融聚(广州)科技有限公司 | A kind of video tab localization method |
JP2020035086A (en) * | 2018-08-28 | 2020-03-05 | 富士ゼロックス株式会社 | Information processing system, information processing apparatus and program |
CN109446456A (en) * | 2018-09-22 | 2019-03-08 | 北京微播视界科技有限公司 | The dissemination method of point of interest and device, terminal, storage medium in media information |
CN110297943B (en) * | 2019-07-05 | 2022-07-26 | 联想(北京)有限公司 | Label adding method and device, electronic equipment and storage medium |
CN110427508A (en) * | 2019-08-01 | 2019-11-08 | 湖南航天天麓新材料检测有限责任公司 | A kind of generation method and system of position variable electronic label |
CN110557565B (en) * | 2019-08-30 | 2022-06-17 | 维沃移动通信有限公司 | Video processing method and mobile terminal |
CN110855921B (en) * | 2019-11-12 | 2021-12-03 | 维沃移动通信有限公司 | Video recording control method and electronic equipment |
CN111491206B (en) * | 2020-04-17 | 2023-03-24 | 维沃移动通信有限公司 | Video processing method, video processing device and electronic equipment |
CN111625737B (en) * | 2020-05-27 | 2023-04-07 | 腾讯科技(深圳)有限公司 | Label display method, device, equipment and storage medium |
CN114896455A (en) * | 2022-05-11 | 2022-08-12 | 北京达佳互联信息技术有限公司 | Video tag generation method and device, electronic equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100471255C (en) * | 2006-10-25 | 2009-03-18 | 浙江大学 | Method for making and playing interactive video frequency with heat spot zone |
CN101753941A (en) * | 2008-12-19 | 2010-06-23 | 康佳集团股份有限公司 | Method for realizing markup information in imaging device and imaging device |
CN101833978A (en) * | 2009-03-12 | 2010-09-15 | 新奥特硅谷视频技术有限责任公司 | Character signal-triggered court trial video real-time indexing method |
CN101930779B (en) * | 2010-07-29 | 2012-02-29 | 华为终端有限公司 | Video commenting method and video player |
-
2012
- 2012-10-17 CN CN201210395412.0A patent/CN103780973B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN103780973A (en) | 2014-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103780973B (en) | Video tab adding method and device | |
US10419715B2 (en) | Automatic selection of video from active cameras | |
CN101930779B (en) | Video commenting method and video player | |
US11244488B2 (en) | Video processing device, video processing system, and video processing method | |
CN111093026B (en) | Video processing method, electronic device and computer-readable storage medium | |
CN104205209B (en) | Playback controlling apparatus, playback controls method | |
US9524282B2 (en) | Data augmentation with real-time annotations | |
US9154856B2 (en) | Video segmenting | |
CN103346955B (en) | A kind of image processing method, device and terminal | |
CN106254941A (en) | Method for processing video frequency and device | |
JP2009093478A (en) | Virtual space broadcasting apparatus | |
US20170256283A1 (en) | Information processing device and information processing method | |
US9378768B2 (en) | Methods and systems for media file management | |
CN106293052A (en) | Reinforced augmented reality multimedia system | |
JP2017169140A (en) | Generation device, generation method, and generation program | |
US8677240B2 (en) | Video processing system providing association between displayed video and media content and related methods | |
KR20140078171A (en) | A method for play a contents of augmented reality and a system for excuting the method | |
CN113873100B (en) | Video recording method, device, electronic equipment and storage medium | |
JP2000099524A (en) | Multimedia information viewing device | |
EP2711853B1 (en) | Methods and systems for media file management | |
CN104021215B (en) | Picture sorting method and device | |
CN106936830B (en) | Multimedia data playing method and device | |
KR101403317B1 (en) | Information providing system using video with tag information | |
CN103218157B (en) | A kind of mobile terminal and the management method of explainative information | |
Watanabe et al. | WillCam: a digital camera visualizing users. interest |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP02 | Change in the address of a patent holder |
Address after: 5-12 / F, building 6, 57 Andemen street, Yuhuatai District, Nanjing City, Jiangsu Province Patentee after: Samsung Electronics (China) R&D Center Patentee after: SAMSUNG ELECTRONICS Co.,Ltd. Address before: 17 / F, Xindi center, 188 Lushan Road, Jianye District, Nanjing, Jiangsu 210019 Patentee before: Samsung Electronics (China) R&D Center Patentee before: SAMSUNG ELECTRONICS Co.,Ltd. |
|
CP02 | Change in the address of a patent holder |