CN103970906B - The method for building up and device of video tab, the display methods of video content and device - Google Patents
The method for building up and device of video tab, the display methods of video content and device Download PDFInfo
- Publication number
- CN103970906B CN103970906B CN201410228398.4A CN201410228398A CN103970906B CN 103970906 B CN103970906 B CN 103970906B CN 201410228398 A CN201410228398 A CN 201410228398A CN 103970906 B CN103970906 B CN 103970906B
- Authority
- CN
- China
- Prior art keywords
- video
- matched
- matching
- frame
- information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Method for building up and device, the display methods of video content and device the invention discloses a kind of video tab.Methods described includes：Searching in video includes at least one matching picture frame of object to be matched, and obtains match information corresponding with matching picture frame, wherein, match information at least includes：Matching picture frame timing node in video；According to match information, in video for object to be matched sets up video labeling label.The present invention is by being in video object to be matched sets up video labeling label and is shown in video display process markup information corresponding with video labeling label being added into video image technological means, optimize existing Web Video Service, improve the validity that product manufacturer promotes product in video, ensure that video user can be timely, accurate and effective obtains product interested in video, enormously simplify process of purchase of the video user to product of interest.
Description
Technical field
The present embodiments relate to video image processing technology, more particularly to a kind of video tab method for building up and dress
Put, the display methods of video content and device.
Background technology
With continuing to develop for Internet technology, in the network bandwidth ever-increasing today, Internet video with it easily
Access experience, diversified film source and renewal speed has attracted vast user in real time so that Internet video turns into
Indispensable important component in user network life.Accordingly, be implanted into for the product of oneself by increasing manufacturer
To in Internet video, it is desirable to carry out benign popularization to Related product by the temperature and popularity of video.
So-called Internet video refers to being provided by Web Video Service business (for example, Baidu's iqiyi.com), with Streaming Media to broadcast
Put form, can live or program request audio video interleaved online.Internet video generally requires independent player, file format master
If taking the less FLV of client resource (Flash Video, stream based on P2P (Peer to Peer, peer-to-peer network) technology
Media) form.
But, with continuing to develop for terminal technology and video website designing technique so that people are for Internet video
Requirement become higher, traditional Web Video Service business cannot meet people watch Internet video during, increasingly
The enhanced personalized, demand of facilitation.
The content of the invention
In view of this, the embodiment of the present invention provides method for building up and device, the display of video content of a kind of video tab
Method and apparatus, to enrich the information content in video, improve the personalization and facilitation of Video service.
In a first aspect, the embodiment of the invention provides a kind of method for building up of video tab, including：
Searching in video includes at least one matching picture frame of object to be matched, and acquisition matches picture frame with described
Corresponding match information, wherein, the match information at least includes：When segmentum intercalaris of the matching picture frame in the video
Point；
It is that the object to be matched sets up video labeling label in the video according to the match information.
In second aspect, a kind of display methods of video content is the embodiment of the invention provides, including：
Play video；
According to the match information of video labeling label in the video, will mark letter corresponding with the video labeling label
Breath is shown in video image.
In the third aspect, a kind of device of setting up of video tab is the embodiment of the invention provides, including：
Match information acquiring unit, for searching at least one matching picture frame including object to be matched in video,
And match information corresponding with the matching picture frame is obtained, wherein, the match information at least includes：The matching picture frame
Timing node in the video；
Mark label sets up unit, for being that the object to be matched is built in the video according to the match information
Vertical video labeling label.
In fourth aspect, a kind of display device of video content is the embodiment of the invention provides, including：
Video playback unit, for playing video；
Markup information display unit, for the match information according to video labeling label in the video, will regard with described
The corresponding markup information of frequency marking note label is shown in video image.
The present invention is by video for object to be matched sets up video labeling label and the general in video display process
Markup information corresponding with video labeling label is added to the technological means shown in video image, optimizes existing net
Network Video service, enriches the information content in video, improves the validity that product manufacturer promotes product in video, it is ensured that
Product interested, enormously simplify video user to interested in the acquisition video that video user can be timely, accurate and effective
The process of purchase of product, improves the personalization and facilitation of Video service.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the method for building up of video tab of first embodiment of the invention；
Fig. 2 is a kind of signal of determination object to be matched particular location in picture frame is matched of first embodiment of the invention
Figure；
Fig. 3 is a kind of flow chart of the method for building up of video tab of second embodiment of the invention；
Fig. 4 is a kind of flow chart of the method for building up of video tab of third embodiment of the invention；
Fig. 5 is whether a kind of of third embodiment of the invention judges include the method stream of object to be matched in associated images frame
Cheng Tu；
Fig. 6 is a kind of schematic diagram that candidate region is determined in associated region of third embodiment of the invention；
Fig. 7 is a kind of flow chart of the display methods of video content of fourth embodiment of the invention；
Fig. 8 is a kind of schematic diagram that markup information is shown in video pause of fourth embodiment of the invention；
Fig. 9 is a kind of schematic diagram that markup information is shown in video display process of fourth embodiment of the invention；
Figure 10 is a kind of application scenarios schematic diagram of the embodiment of the present invention；
Figure 11 is a kind of structure chart for setting up device of video tab of fifth embodiment of the invention；
Figure 12 is a kind of structure chart of the display device of video content of sixth embodiment of the invention.
Specific embodiment
In order that the object, technical solutions and advantages of the present invention are clearer, below in conjunction with the accompanying drawings to specific reality of the invention
Example is applied to be described in further detail.It is understood that specific embodiment described herein is used only for explaining the present invention,
Rather than limitation of the invention.It also should be noted that, for the ease of description, be illustrate only in accompanying drawing related to the present invention
Part rather than full content.
The realization approach of various embodiments of the present invention is summarized as follows first：By the method for various embodiments of the present invention, product
The product and corresponding product introduction that production firm or third-party product dealer will can occur in video are supplied to
Web Video Service business or third-party video processing business, the product of introduction can be that any user may be interested, or uncommon
The content of user is recommended in prestige, for example, the building occurred in the dress ornament of video personage, video personage automobile, the video opened or
Sight spot occurred in person's video etc.；It is to be matched that Web Video Service business or third-party video processing business search this in video
The position that product occurs, and add corresponding video labeling label；When regarding that video user logging in network Video service business provides
During frequency website viewing video, if occurring in that the product in video, Web Video Service business can be by the detailed letter of product
Breath pushes to video user.
First embodiment
Fig. 1 is a kind of flow chart of the method for building up of video tab of first embodiment of the invention, the method for the present embodiment
Can set up device to perform by video tab, the device can be realized by way of hardware and/or software, typically can be integrated
In in server, such as Web Video Service business or third-party video process the clothes that can provide Video service of business's control
Business device.The method of the present embodiment specifically includes following operation：
110th, searching in video includes at least one matching picture frame of object to be matched, and acquisition matches figure with described
As the corresponding match information of frame, wherein, the match information at least includes：Time of the matching picture frame in the video
Node.
In the present embodiment, server searches at least one matching picture frame including object to be matched in video, and
Obtain match information corresponding with the matching picture frame.
In the present embodiment, object to be matched is specifically as follows personage, animal, dress ornament, automobile, the electricity for occurring in video
The entity objects such as sub- product, furniture or sight spot.Certainly, object to be matched can also be other entities pair of appearance in video
As, this is not limited, usually need the entity object to user's recommendation information.
The video, is formed by the way that a series of static picture (frame of video) is continuously played.In this implementation
In example, matching picture frame is specifically referred in a video, includes the frame of video of above-mentioned object to be matched.
It is understood that including object to be matched at least one can in video be searched by way of artificial matching
Individual matching picture frame, but this lookup mode wastes time and energy, and object particularly to be matched is more or during video time more long,
Search efficiency extreme difference, and easily under-enumeration is looked for.
In the present embodiment, the mode of server matches is taken to search including object to be matched at least one in video
Matching picture frame.Wherein, server can obtain the characteristic information of object to be matched (for example, gray feature information or image
Characteristic information etc.), the characteristic information is carried out into images match with each frame of video of the video respectively, by regarding for fitting through
Frequency frame obtains timing node of the matching picture frame in the video as match information as matching picture frame.
Wherein, timing node of the matching picture frame in the video refers to that matching picture frame is specifically played in video
Position：Wherein it is possible to obtain the frame number of matching picture frame or match picture frame markers in video as matching image
Timing node of the frame in the video.
For example, object to be matched is the automobile of a certain model, and the automobile is appeared in video A, and server passes through will
The characteristic information of the automobile is matched with each frame of video in video A, if the video that video A was played at the 3rd point and 40 seconds
Frame (or numbering be 10004 frame of video) include the characteristic information of the automobile, then by 3 points of 40 seconds this time stamp value (or
10004 this frame number value) as matching timing node of the picture frame in the video.
Certainly, it will be appreciated by persons skilled in the art that match information is except including matching picture frame in the video
In timing node outside, can also include object to be matched it is described matching picture frame in positional information or to be matched right
As with match frame of video and carry out the information such as the matching factor that matching operation is obtained, this is not limited.Wherein, matching factor is specific
Refer to that object to be matched carries out the degree of correlation weights that degree of correlation computing is obtained with frame of video is matched, wherein, matching factor is bigger, generation
The probability that table object to be matched is appeared in matching frame of video is bigger.In actual applications, when multiple successive video frames are
During with frame of video, corresponding video labeling label is inserted in the matching frame of video that may be selected in matching factor maximum.
Wherein, positional information of the object to be matched in the matching picture frame specifically refers to object to be matched in matching figure
As the position coordinates in frame.A kind of schematic diagram of object to be matched position coordinates in picture frame is matched is shown in Fig. 2.As schemed
Shown in 2, matching frame of video 200 is the picture of 1024 × 768 forms, object to be matched and the region 21 matched in frame of video 200
Match, then can obtain four extreme coordinates (256,256), (384,256), (256,736) and (384,736) in region 21
As position coordinates of the object to be matched in picture frame is matched.
120th, it is that the object to be matched sets up video labeling label in the video according to the match information.
In the present embodiment, server, according to the match information, is that the object to be matched is set up in the video
Video labeling label.
Wherein it is possible to by the corresponding relation between the markup information of timing node and object to be matched, as video labeling
Label；Can also be by the corresponding relation between the markup information of timing node, positional information and object to be matched, as video mark
Note label.Wherein, a kind of structural table of video labeling label is shown in table 1.
Wherein, the markup information of object to be matched can be specially the description information to object to be matched, for example：When treating
During with object for dress ornament, markup information can be the information such as the brand name of dress ornament, style name, price and purchase link；When treating
When matching object is sight spot, markup information can be the information such as the link of sight name, sight spot site and sight spot description.
Wherein, in the present embodiment, can be by the storage corresponding with video of video labeling label.
Table 1
The technical scheme of the embodiment of the present invention, it is not necessary to which user obtains the detailed letter of content recommendation by carrying out manual search
Breath, the manual search ability to user is not also required, therefore is adapted to any user group.Meanwhile, it is capable to make user in viewing
Know the information of content recommendation during video immediately, thus user desire to purchase or consumption plan will not be with product
The delay of information acquisition times and it is weakened, be conducive to product manufacturer and video user, not only improve product manufacturer promote produce
Product are also beneficial to the information of timely, the accurate and effective acquisition product of interest of video user.Existing network video is optimized to be taken in small doses at short intervals
Business, enriches the information content in video, improves the validity that product manufacturer promotes product in video, it is ensured that video user
Product interested, enormously simplify purchase of the video user to product of interest in acquisition video that can be timely, accurate and effective
Flow is bought, the personalization and facilitation of Video service is improved.
It is understood that when carrying out video retrieval to different objects to be matched, matching accuracy rate and matching efficiency are all
It is not quite similar.For example, face recognition technology is highly developed at present, also there are many emerging algorithms to be all based on face at present
Identification, its matching speed and matching accuracy are all at a relatively high.And the identification technology of the class object of such as dress ornament then compares unexpected winner,
Conventional image recognition technology can only be taken, its matching speed and matching accuracy are all well below recognition of face.
Regarding to the issue above, the embodiment of the present invention is not easy to carry out the to be matched right of image recognition in video for some
As before being searched, searching the association matching object being associated with the object to be matched in video first, including association
The object to be matched is searched in the associated images frame for matching object.Wherein, the selection principle of association matching object is：To association
Video retrieval relatively easy (identification technology relative maturity or identification process relatively easy etc.) and association are carried out with object
The probability come across with object and object to be matched in same frame of video is more than predetermined threshold value.
For example, if object to be matched is dress ornament, can search in video first including dressing the dress ornament
Video personage face associated images frame set, further search for dress ornament in associated images frame set afterwards；Or, such as
When object really to be matched is automobile, the associated images frame set including road can be in video searched first, afterwards in association
Automobile is further searched in set of frames.
Second embodiment
Fig. 3 is a kind of method for building up flow chart of video tab of second embodiment of the invention, and the present embodiment is with above-mentioned reality
Apply and optimize based on example, in the present embodiment, preferably will operation according to the association matching object, search in video
At least one matching picture frame including object to be matched simultaneously obtains corresponding match information and is optimized for：Obtain described to be matched right
The association matching object of elephant；Being searched in the video includes the associated images frame set of the association matching object；Described
Being searched in associated images frame set includes at least one matching picture frame of the object to be matched, and obtains corresponding matching letter
Breath.
Correspondingly, the method for the present embodiment specifically includes following operation：
310th, the association matching object of object to be matched is obtained.
In an exemplary, object to be matched is dress ornament, and the association matching object of acquisition is face, wherein, it is described
Face is corresponding with the video personage that the dress ornament is dressed in the video.
320th, being searched in the video includes the associated images frame set of the association matching object.
330th, being searched in the associated images frame set includes at least one matching picture frame of the object to be matched,
And obtain corresponding match information.
340th, it is that the object to be matched sets up video labeling label in the video according to the match information.
The embodiment of the present invention includes the associated images frame set of association matching object by searching in video first, afterwards
Being searched in associated images frame set includes at least one matching picture frame of the object to be matched, and obtains corresponding matching
The technological means of information, for not being direct in the bad object to be matched of field of image recognition matching effect (such as dress ornament)
Matched in each frame of video in video, but it is first that be associated with object to be matched, matching effect is preferable
Association matching object (such as face) is matched in video, and obtains corresponding associated video frame set, is now only needed to
Object to be matched is searched in associated video frame set, which greatly simplifies the lookup difficulty of matching frame of video,
Substantially increase the matching speed and matching accuracy to object to be matched.
On the basis of the various embodiments described above, before being searched in the video, also include：
The key frame set in the video is obtained, as video to be found, wherein, it is each in the key frame set
Key frame is arranged according to the time sequencing in the video.
Wherein, the key frame set obtained in the video is specifically included：
According to predetermined sampling frequency, sequential sampling is carried out to the video, the collection cooperation of the frame of video that order is obtained
It is the key frame set.
For example, 100000 frame of video are included in a video, video frame rate is 16HZ, that is to say, that per second
Continuously display 16 frame of video, it is contemplated that in practical application, the scene changes speed in video content will not be very violent,
Picture material in many continuous frame of video is very approximate, in addition, the main purpose of the embodiment of the present invention is to viewing video
User push the markup information corresponding with object to be matched, in theory, as long as ensure that under each scene
Matched and searched can be carried out to object to be matched, it becomes possible to meet actual demand.Therefore there is no need all to enter the image of each frame
Row is searched, it is preferred that (such as 2s) frame of video can be extracted from video as key frame at regular intervals, and will closed
Used as video to be found, the benefit for so setting is for the set of key frame, on the basis of final lookup result is not appreciably affected,
The search efficiency of matching frame of video is further increased, it is accurate to the matching speed of object to be matched and matching to further increase
Degree.
3rd embodiment
Fig. 4 is a kind of flow chart of the method for building up of video tab of third embodiment of the invention, and the present embodiment is with above-mentioned
Optimized based on embodiment, in the present embodiment, operation is preferably matched into object according to the association, looked into video
Look for including object to be matched at least one to match picture frame and obtain corresponding match information to be optimized for：Obtain described to be matched
The association matching object of object；Sequential search includes the associated images frame of the association matching object in the video；If
Determine that the associated images frame includes the object to be matched, using the associated images frame as the matching picture frame, and
Obtain corresponding match information；Using video tracking algorithm, since the video location where the associated images frame, described
Being searched in video includes at least one matching picture frame of the object to be matched, and obtains corresponding match information.
Correspondingly, the method for the present embodiment specifically includes following operation：
410th, the association matching object of the object to be matched is obtained.
420th, sequential search one includes the associated images frame of the association matching object in the video.
430th, judge whether include the object to be matched in the associated images frame：If so, performing operation 440；Otherwise,
Return to operation 420.
In the present embodiment, directly can be matched in all images region of associated images frame, to determine association
Whether include the object to be matched in picture frame, it is also possible to according to position letter of the association matching object in the associated images frame
Breath, selectes one or more candidate image area, is matched in candidate image area, to determine to be in associated images frame
It is no including the object to be matched, this is not limited.It will be apparent that by selecting the side that candidate image area is matched
Formula can further improve the matching speed to object to be matched, improve matching efficiency.
For example, object to be matched is dress ornament, and association matching image is face, and server can be in associated images frame
Positional information where obtaining face, as associated region, a candidate region is determined in the lower section of associated region, determines the time
Whether include the dress ornament in favored area；Object to be matched is automobile, and association matching image is road, and server can be in associated diagram
Positional information as where obtaining road in frame, as associated region, determines a candidate region, really in the top of associated region
Whether include the automobile in the fixed candidate region.
Judge whether include the method flow diagram of object to be matched, such as Fig. 5 in associated images frame figure 5 illustrates a kind of
Shown, the method specifically includes following operation：
4301st, the associated region of match objects is matched in the acquisition associated images frame with the association.
4302nd, according to the associated region, it is determined that at least one candidate region corresponding with the object to be matched.
In a specific example, object to be matched is clothes, association matching object is the video personage for wearing the clothes
Head portrait.Figure 6 illustrates a kind of schematic diagram that candidate region is determined in associated region.As shown in fig. 6, server is first
Obtain the associated region 61 that matches with head portrait in frame of video 600, it is contemplated that dress ornament is can be located at head portrait institute under very big probability
Associated region 61 under, it is possible to the position where candidate region 62 is determined according to associated region 61, and in candidate
Matching object to be matched in region 62.
Certainly, in order to avoid under-enumeration to look for as far as possible, it is also possible to which selected multiple candidate region is matched, and this is not limited
It is fixed.
4303rd, the characteristics of objects information of the object to be matched is carried out into the degree of correlation with the characteristic information of the candidate region
Matching primitives simultaneously obtain corresponding relevance threshold.
In a specific example, server using characteristic matching method by the characteristics of objects information of the object to be matched with
The characteristic information of the candidate region carries out degree of correlation matching primitives, specially：Object to be matched and candidate region are extracted respectively
Set of characteristic points, carry out degree of correlation matching primitives using two set of characteristic points extracted, and obtain the corresponding degree of correlation
Threshold value.
Certainly, server can also use other method by the characteristics of objects information of object to be matched and the candidate region
Characteristic information carry out degree of correlation matching primitives, for example, category of model method etc., does not limit this.
4304th, judge the relevance threshold whether more than predetermined threshold value：If so, performing operation 4305；Otherwise, perform
Operation 4306.
4305th, determine that the associated images frame includes the object to be matched.
4306th, determine not include the object to be matched in the associated images frame.
440th, using the associated images frame as the matching picture frame, and corresponding match information is obtained.
450th, using video tracking algorithm, since the video location where the associated images frame, in the video
Lookup includes at least one matching picture frame of the object to be matched, and obtains corresponding match information.
In view of in practical application, the scene changes speed in video content will not be very acutely front and rear in video
The correlation of two frames is generally large, it is possible to rationally estimate when some matching video includes object to be matched, at it
The object to be matched can equally be included in one or more frame of video afterwards.So can be with video tracking algorithm, to be matched
The region that object is likely to occur in next frame of video is pre-estimated, and it is to be matched to search this in the position being likely to occur
Object.
460th, judge current lookup to last matching picture frame whether be the video last frame of video：
If so, performing operation 460；Otherwise, operation 420 is returned.
470th, it is that the object to be matched sets up video labeling label in the video according to the match information.
The embodiment of the present invention is by the matching video where an object to be matched is found according to association matching object
After frame, using video tracking algorithm, start in the video location where the matching frame of video, continue to search for the skill of object to be matched
Art means, further increase the search efficiency of matching frame of video, further increase the matching speed to object to be matched.
Fourth embodiment
Figure 7 illustrates a kind of flow chart of the display methods of video content of fourth embodiment of the invention.This implementation
The method of example can be performed by the display device of video content, and the device can be realized by way of hardware and/or software, and one
As can be integrated in terminal device.The method of the present embodiment specifically includes following operation：
710th, video is played.
In the present embodiment, terminal device is obtained and played and regarded by the video website that logging in network Video service business provides
Frequently.
720th, according to the match information of video labeling label in the video, will mark corresponding with the video labeling label
Note information is shown in video image.
In the present embodiment, terminal device, will be with the video mark according to the match information of video labeling label in video
The corresponding markup information of note label is shown in video image.
Wherein, the match information of video labeling label includes：The matching picture frame of object to be matched is included described
Timing node in video, can also include positional information or to be matched right of the object to be matched in the matching picture frame
As with match frame of video and carry out the information such as the matching factor that matching operation is obtained, this is not limited.
The corresponding markup information of video labeling label is specially the description information to object to be matched, for example：When to be matched
When object is dress ornament, markup information can be the information such as the brand name of dress ornament, style name, price and purchase link；When treating
During with object for sight spot, markup information can be the letters such as web site url of sight name, sight spot site and description sight spot
Breath.
In the present embodiment, server, will be with the video according to the match information of video labeling label in the video
The corresponding markup information of mark label is shown can specifically include following four kinds of modes in video image：
If there is corresponding video labeling label in mode 1, the current time node of the video played, will be with the video
The corresponding markup information of mark label is shown in being added to the video image adapted to match information middle position confidence manner of breathing.
If mode 2, when video pause is played, pause play time is located at the corresponding time zone of the timing node
Between within, by the markup information of the video labeling label be added to match information middle position confidence manner of breathing adapt to video image
In shown.Wherein, figure 8 illustrates the schematic diagram that occupation mode 2 shows markup information in video pause.
If there is corresponding video labeling label in mode 3, the current time node of the video played, will be with the video
The boundary position that the corresponding markup information of mark label is added to currently playing video image is shown.
If mode 4, when video pause is played, pause play time is located at the corresponding time zone of the timing node
Between outside, the boundary position that the markup information of the video labeling label is added to currently playing video image is shown
Show.Wherein, the boundary position includes the top area and/or bottom section of video image.Wherein, figure 9 illustrates making
The schematic diagram of markup information is shown in video display process with mode 4.
The technical scheme of the embodiment of the present invention, it is not necessary to which user obtains the detailed letter of content recommendation by carrying out manual search
Breath, the manual search ability to user is not also required, therefore is adapted to any user group.Meanwhile, it is capable to make user in viewing
Know the information of content recommendation during video immediately, thus user desire to purchase or consumption plan will not be with product
The delay of information acquisition times and it is weakened, be conducive to product manufacturer and video user, not only improve product manufacturer promote produce
Product are also beneficial to the information of timely, the accurate and effective acquisition product of interest of video user.Existing network video is optimized to be taken in small doses at short intervals
Business, enriches the information content in video, improves the validity that product manufacturer promotes product in video, it is ensured that video user
Product interested, enormously simplify purchase of the video user to product of interest in acquisition video that can be timely, accurate and effective
Flow is bought, the personalization and facilitation of Video service is improved.
A kind of application scenarios schematic diagram of the embodiment of the present invention is shown in Figure 10.As shown in Figure 10, this application scene bag
Include：Product manufacturer or third party dealer terminal 101, network video server or third-party server 102 and user
Terminal 103.Assuming that product manufacturer or third party dealer terminal 101 are wanted to promote hot broadcast play《You from star》06th collection
Middle virtuous the passed through wardrobes (being assumed to be 6) of actor Jin Xiu, can be by the picture of 6 clothes to be promoted and corresponding
6 markup informations (brand, model, purchase link etc.) send to network video server or third-party server 102, with
Realize in Internet video《You from star》06th concentrates the corresponding video labeling label of addition.
Network video server or third-party server 102 are receiving product manufacturer or third party's dealer's terminal
After clothes are promoted, picture that can be first according to this 6 clothes sets up 6 different dress forms to 101 6 for sending, with
And one be not belonging to this 6 dress form intersection a mismatching model, Ran Hou《You from star》06th collection regard
Frequently the face that Jin Xiuxian is carried out in is searched, and after an association matching frame of video including gold show person of virtue's face is found, is made respectively
Matching frame of video is associated with this with 7 models set up before to be matched, is that matching degree highest model correspondence clothes are built
Found corresponding video labeling label.After the completion of to the video matching, each video labeling label and the video pair that will be set up
Should be stored in network video server.
When user terminal 103 is obtained by the video website that network video server is provided and plays the video, network
Video server is shown markup information corresponding with the video labeling label in video image.
5th embodiment
A kind of video tab figure 11 illustrates fifth embodiment of the invention sets up structure drawing of device.Such as Figure 11 institutes
Show, described device includes：
Match information acquiring unit 111, for searching at least one matching image including object to be matched in video
Frame, and match information corresponding with the matching picture frame is obtained, wherein, the match information at least includes：The matching figure
As timing node of the frame in the video.
Mark label sets up unit 112, for being the object to be matched in the video according to the match information
Set up video labeling label.
The technical scheme of the embodiment of the present invention, it is not necessary to which user obtains the detailed letter of content recommendation by carrying out manual search
Breath, the manual search ability to user is not also required, therefore is adapted to any user group.Meanwhile, it is capable to make user in viewing
Know the information of content recommendation during video immediately, thus user desire to purchase or consumption plan will not be with product
The delay of information acquisition times and it is weakened, be conducive to product manufacturer and video user, not only improve product manufacturer promote produce
Product are also beneficial to the information of timely, the accurate and effective acquisition product of interest of video user.Existing network video is optimized to be taken in small doses at short intervals
Business, enriches the information content in video, improves the validity that product manufacturer promotes product in video, it is ensured that video user
Product interested, enormously simplify purchase of the video user to product of interest in acquisition video that can be timely, accurate and effective
Flow is bought, the personalization and facilitation of Video service is improved.
On the basis of the various embodiments described above, the match information acquiring unit can be also used for, and obtain described to be matched
Positional information of the object in the matching picture frame is used as match information corresponding with the matching picture frame.
On the basis of the various embodiments described above, the match information acquiring unit specifically can be used for：
Obtain the association matching object of the object to be matched；
Being searched in the video includes the associated images frame set of the association matching object；
Being searched in the associated images frame set includes at least one matching picture frame of the object to be matched, and obtains
Take corresponding match information.
On the basis of the various embodiments described above, the match information acquiring unit can specifically include：
Association matching object acquisition subelement, the association for obtaining the object to be matched matches object；
Associated images frame obtains subelement, and the pass of the association matching object is included for the sequential search in the video
Connection picture frame；
Coupling subelement, for if it is determined that the associated images frame includes the object to be matched, by the association
Picture frame obtains corresponding match information as the matching picture frame；
Match information obtains subelement, for using video tracking algorithm, the video position from where the associated images frame
Beginning is put, being searched in the video includes at least one matching picture frame of the object to be matched, and obtains corresponding
With information.
On the basis of the various embodiments described above, the object to be matched can be dress ornament, and association matching object can be with
It is face, wherein, the face is corresponding with the video personage that the dress ornament is dressed in the video.
On the basis of the various embodiments described above, the coupling subelement specifically can be used for：
Obtain in the associated images frame with the associated region for associating and matching match objects；
According to the associated region, it is determined that at least one candidate region corresponding with the object to be matched；
The characteristics of objects information of the object to be matched is carried out into the degree of correlation with the characteristic information of the candidate region to match
Calculate and obtain corresponding relevance threshold；
If the relevance threshold is more than predetermined threshold value, determine that the associated images frame includes described to be matched right
As.
The device of setting up of the video tab that the embodiment of the present invention is provided can be used to perform any embodiment offer of the present invention
Video tab method for building up, possess corresponding functional module, realize identical beneficial effect.
Sixth embodiment
Figure 12 illustrates a kind of display device structure figure of video content of sixth embodiment of the invention.Such as Figure 12 institutes
Show, described device includes：
Video playback unit 121, for playing video.
Markup information display unit 122, for the match information according to video labeling label in the video, will with it is described
The corresponding markup information of video labeling label is shown in video image.
The technical scheme of the embodiment of the present invention, it is not necessary to which user obtains the detailed letter of content recommendation by carrying out manual search
Breath, the manual search ability to user is not also required, therefore is adapted to any user group.Meanwhile, it is capable to make user in viewing
Know the information of content recommendation during video immediately, thus user desire to purchase or consumption plan will not be with product
The delay of information acquisition times and it is weakened, be conducive to product manufacturer and video user, not only improve product manufacturer promote produce
Product are also beneficial to the information of timely, the accurate and effective acquisition product of interest of video user.Existing network video is optimized to be taken in small doses at short intervals
Business, enriches the information content in video, improves the validity that product manufacturer promotes product in video, it is ensured that video user
Product interested, enormously simplify purchase of the video user to product of interest in acquisition video that can be timely, accurate and effective
Flow is bought, the personalization and facilitation of Video service is improved.
On the basis of the various embodiments described above, the markup information display unit can be specifically for：
If there is corresponding video labeling label in the current time node of the video played, will be with the video labeling mark
Sign during corresponding markup information is added to the video image adapted to match information middle position confidence manner of breathing and shown；
If when video pause is played, pause play time be located at the corresponding time interval of the timing node it
It is interior, the markup information of the video labeling label is added in the video image adapted to match information middle position confidence manner of breathing
Row display；
If there is corresponding video labeling label in the current time node of the video played, will be with the video labeling mark
Sign corresponding markup information and be added to the boundary position of currently playing video image and shown；
If when video pause is played, pause play time be located at the corresponding time interval of the timing node it
Outward, the boundary position that the markup information of the video labeling label is added to currently playing video image is shown；
Wherein, the boundary position includes the top area and/or bottom section of video image.
The display device of the video content that the embodiment of the present invention is provided can be used to perform any embodiment offer of the present invention
Video content display methods, possess corresponding functional module, realize identical beneficial effect.
Obviously, it will be understood by those skilled in the art that above-mentioned of the invention each module or each step can be by as above
Described server implementation.Alternatively, the program that the embodiment of the present invention can be can perform with computer installation be realized, so that can
To be stored in being performed by processor in storage device, described program can be stored in a kind of computer-readable storage
In medium, storage medium mentioned above can be read-only storage, disk or CD etc.；Or be fabricated to them respectively each
Individual integrated circuit modules, or the multiple modules or step in them are fabricated to single integrated circuit module to realize.So,
The present invention is not restricted to the combination of any specific hardware and software.
The preferred embodiments of the present invention are the foregoing is only, is not intended to limit the invention, for those skilled in the art
For, the present invention can have various changes and change.It is all any modifications made within spirit and principles of the present invention, equivalent
Replace, improve etc., should be included within the scope of the present invention.
Claims (12)
1. a kind of method for building up of video tab, it is characterised in that including：
Searching in video includes at least one matching picture frame of object to be matched, and obtains corresponding with the matching picture frame
Match information, wherein, the match information at least includes：Timing node of the matching picture frame in the video；
It is that the object to be matched sets up video labeling label in the video according to the match information；
Described lookup in video includes at least one matching picture frame of object to be matched and obtains corresponding match information have
Body includes：
Obtain the association matching object of the object to be matched；
Being searched in the video includes the associated images frame set of the association matching object；
Being searched in the associated images frame set includes at least one matching picture frame of the object to be matched, and obtains phase
The match information answered；
Or,
Obtain the association matching object of the object to be matched；
Sequential search includes the associated images frame of the association matching object in the video；
If it is determined that the associated images frame includes the object to be matched, using the associated images frame as the matching figure
As frame, and obtain corresponding match information；
Using video tracking algorithm, since the video location where the associated images frame, being searched in the video includes
At least one matching picture frame of the object to be matched, and obtain corresponding match information.
2. method according to claim 1, it is characterised in that：The match information also includes the object to be matched in institute
State the positional information in matching picture frame.
3. method according to claim 1, it is characterised in that the object to be matched is dress ornament, the association matching is right
As being face, wherein, the face is corresponding with the video personage that the dress ornament is dressed in the video.
4. method according to claim 1, it is characterised in that before being searched in the video, also include：
The key frame set in the video is obtained, as video to be found, wherein, each key in the key frame set
Frame is arranged according to the time sequencing in the video；
Wherein, the key frame set obtained in the video is specifically included：
According to predetermined sampling frequency, sequential sampling is carried out to the video, using the set of the frame of video of order acquisition as institute
State key frame set.
5. method according to claim 1, it is characterised in that it is described if it is determined that the associated images frame include it is described
Object to be matched, using the associated images frame is as the matching picture frame and obtains corresponding match information and specifically includes：
Obtain in the associated images frame with the associated region for associating and matching match objects；
According to the associated region, it is determined that at least one candidate region corresponding with the object to be matched；
The characteristics of objects information of the object to be matched is carried out into degree of correlation matching primitives with the characteristic information of the candidate region
And obtain corresponding relevance threshold；
If the relevance threshold is more than predetermined threshold value, determine that the associated images frame includes the object to be matched.
6. a kind of display methods of video content, it is characterised in that including：
Play video；
According to the match information of video labeling label in the video, markup information corresponding with the video labeling label is existed
Shown in video image, wherein, the video labeling label is set up by the method described in claim any one of 1-5.
7. method according to claim 6, it is characterised in that according to the matching letter of video labeling label in the video
Breath, markup information corresponding with the video labeling label is carried out display in video image and includes：
If there is corresponding video labeling label in the current time node of the video played, will be with the video labeling label pair
The markup information answered be added to match information middle position confidence manner of breathing adapt to video image in shown, or will with it is described
The boundary position that the corresponding markup information of video labeling label is added to currently playing video image is shown；
If when video pause is played, pause play time is located within the corresponding time interval of the timing node, will
The markup information of the video labeling label is shown in being added to the video image adapted to match information middle position confidence manner of breathing
Show；
If when video pause is played, pause play time is located at outside the corresponding time interval of the timing node, will
The boundary position that the markup information of the video labeling label is added to currently playing video image is shown；
Wherein, the boundary position includes the top area and/or bottom section of video image.
8. a kind of video tab sets up device, it is characterised in that including：
Match information acquiring unit, for searching at least one matching picture frame including object to be matched in video, and obtains
Match information corresponding with the matching picture frame is taken, wherein, the match information at least includes：The matching picture frame is in institute
State the timing node in video；
Mark label sets up unit, for being that the object foundation to be matched is regarded in the video according to the match information
Frequency marking notes label；
The match information acquiring unit specifically for：
Obtain the association matching object of the object to be matched；
Being searched in the video includes the associated images frame set of the association matching object；
Being searched in the associated images frame set includes at least one matching picture frame of the object to be matched, and obtains phase
The match information answered,
Or, the match information acquiring unit is specifically included：
Association matching object acquisition subelement, the association for obtaining the object to be matched matches object；
Associated images frame obtains subelement, and the associated diagram of the association matching object is included for the sequential search in the video
As frame；
Coupling subelement, for if it is determined that the associated images frame includes the object to be matched, by the associated images
Frame obtains corresponding match information as the matching picture frame；
Match information obtains subelement, for using video tracking algorithm, the video location from where the associated images frame to open
Begin, being searched in the video includes at least one matching picture frame of the object to be matched, and obtains corresponding matching letter
Breath.
9. device according to claim 8, it is characterised in that：The match information acquiring unit is additionally operable to, and obtains described
Positional information of the object to be matched in the matching picture frame is used as match information corresponding with the matching picture frame.
10. device according to claim 8, it is characterised in that the object to be matched is dress ornament, the association matching is right
As being face, wherein, the face is corresponding with the video personage that the dress ornament is dressed in the video.
11. devices according to claim 8, it is characterised in that the coupling subelement specifically for：
Obtain in the associated images frame with the associated region for associating and matching match objects；
According to the associated region, it is determined that at least one candidate region corresponding with the object to be matched；
The characteristics of objects information of the object to be matched is carried out into degree of correlation matching primitives with the characteristic information of the candidate region
And obtain corresponding relevance threshold；
If the relevance threshold is more than predetermined threshold value, determine that the associated images frame includes the object to be matched.
A kind of 12. display devices of video content, it is characterised in that including：
Video playback unit, for playing video；
Markup information display unit, for the match information according to video labeling label in the video, will be with the video mark
The corresponding markup information of label is noted to be shown in video image, wherein, the video labeling label passes through claim 8-
Device described in 11 any one is set up.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410228398.4A CN103970906B (en) | 2014-05-27 | 2014-05-27 | The method for building up and device of video tab, the display methods of video content and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410228398.4A CN103970906B (en) | 2014-05-27 | 2014-05-27 | The method for building up and device of video tab, the display methods of video content and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103970906A CN103970906A (en) | 2014-08-06 |
| CN103970906B true CN103970906B (en) | 2017-07-04 |
Family
ID=51240404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410228398.4A Active CN103970906B (en) | 2014-05-27 | 2014-05-27 | The method for building up and device of video tab, the display methods of video content and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103970906B (en) |
Families Citing this family (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104391960B (en) * | 2014-11-28 | 2019-01-25 | 北京奇艺世纪科技有限公司 | A kind of video labeling method and system |
| CN104602128A (en) * | 2014-12-31 | 2015-05-06 | 北京百度网讯科技有限公司 | Video processing method and device |
| US10629166B2 (en) * | 2016-04-01 | 2020-04-21 | Intel Corporation | Video with selectable tag overlay auxiliary pictures |
| WO2018023677A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Data acquisition method for time-based interest recognition technology and recognition system |
| WO2018023680A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Data acquisition method for time-based content recommendation technology and recommendation system |
| WO2018023678A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Information pushing method during interest recognition and recognition system |
| WO2018023679A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Method for recognizing user's interests on basis of time and recognition system |
| 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 |
| TWI647637B (en) * | 2017-04-12 | 2019-01-11 | 緯創資通股份有限公司 | Methods for supplying, ordering, and transacting items based on motion images |
| CN107147959B (en) * | 2017-05-05 | 2020-06-19 | 中广热点云科技有限公司 | Broadcast video clip acquisition method and system |
| TWI655867B (en) * | 2017-09-14 | 2019-04-01 | 財團法人工業技術研究院 | System and method for combining optical code and film |
| CN110121108B (en) * | 2018-02-06 | 2022-01-04 | 阿里巴巴（中国）有限公司 | Video value evaluation method and device |
| CN110121083A (en) * | 2018-02-06 | 2019-08-13 | 上海全土豆文化传播有限公司 | The generation method and device of barrage |
| CN108446390B (en) * | 2018-03-22 | 2022-01-04 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information |
| CN108833964B (en) * | 2018-06-11 | 2022-01-25 | 阿依瓦（北京）技术有限公司 | Real-time continuous frame information implantation identification system |
| CN110866936B (en) * | 2018-08-07 | 2023-05-23 | 创新先进技术有限公司 | Video labeling method, tracking device, computer equipment and storage medium |
| CN108989851A (en) * | 2018-08-27 | 2018-12-11 | 努比亚技术有限公司 | A kind of video broadcasting method, terminal and computer readable storage medium |
| KR20200040097A (en) * | 2018-10-08 | 2020-04-17 | 삼성전자주식회사 | Electronic apparatus and method for controlling the electronicy apparatus |
| CN109274999A (en) * | 2018-10-08 | 2019-01-25 | 腾讯科技（深圳）有限公司 | A kind of video playing control method, device, equipment and medium |
| CN109495780A (en) * | 2018-10-16 | 2019-03-19 | 深圳壹账通智能科技有限公司 | A kind of Products Show method, terminal device and computer readable storage medium |
| CN109547861A (en) * | 2018-11-14 | 2019-03-29 | 深圳康佳电子科技有限公司 | Shopping recommendation process method, apparatus and storage medium based on video playing |
| CN109753975B (en) * | 2019-02-02 | 2021-03-09 | 杭州睿琪软件有限公司 | Training sample obtaining method and device, electronic equipment and storage medium |
| CN110120087B (en) * | 2019-04-15 | 2023-06-09 | 深圳市思为软件技术有限公司 | Label marking method and device for three-dimensional virtual sand table and terminal equipment |
| 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 |
| CN110837580A (en) * | 2019-10-30 | 2020-02-25 | 平安科技（深圳）有限公司 | Pedestrian picture marking method and device, storage medium and intelligent device |
| CN110991260B (en) * | 2019-11-12 | 2024-01-19 | 苏州智加科技有限公司 | Scene marking method, device, equipment and storage medium |
| CN110798736B (en) * | 2019-11-28 | 2021-04-20 | 百度在线网络技术（北京）有限公司 | Video playing method, device, equipment and medium |
| CN113392675B (en) * | 2020-03-12 | 2023-04-07 | 平湖莱顿光学仪器制造有限公司 | Method and equipment for presenting microscopic video information |
| CN111586492A (en) * | 2020-05-27 | 2020-08-25 | 上海极链网络科技有限公司 | Video playing method and device, client device and storage medium |
| CN111615007A (en) * | 2020-05-27 | 2020-09-01 | 北京达佳互联信息技术有限公司 | Video display method, device and system |
| CN112783986B (en) * | 2020-09-23 | 2022-12-13 | 上海芯翌智能科技有限公司 | Object grouping compiling method and device based on label, storage medium and terminal |
| CN116896654B (en) * | 2023-09-11 | 2024-01-30 | 腾讯科技（深圳）有限公司 | Video processing method and related device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103024576A (en) * | 2012-12-20 | 2013-04-03 | 广东欧珀移动通信有限公司 | Method for positioning video playing time point |
| CN103400393A (en) * | 2013-08-21 | 2013-11-20 | 中科创达软件股份有限公司 | Image matching method and system |
| CN103703789A (en) * | 2013-06-28 | 2014-04-02 | 华为技术有限公司 | Method, terminal and system of data presentation |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100355382B1 (en) * | 2001-01-20 | 2002-10-12 | 삼성전자 주식회사 | Apparatus and method for generating object label images in video sequence |
| US8209223B2 (en) * | 2007-11-30 | 2012-06-26 | Google Inc. | Video object tag creation and processing |
| US8370396B2 (en) * | 2008-06-11 | 2013-02-05 | Comcast Cable Holdings, Llc. | System and process for connecting media content |
| CN101753913B (en) * | 2008-12-17 | 2012-04-25 | 华为技术有限公司 | Method and device for inserting hyperlinks in video, and processor |
| CN103780973B (en) * | 2012-10-17 | 2017-08-04 | 三星电子（中国）研发中心 | Video tab adding method and device |
-
2014
- 2014-05-27 CN CN201410228398.4A patent/CN103970906B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103024576A (en) * | 2012-12-20 | 2013-04-03 | 广东欧珀移动通信有限公司 | Method for positioning video playing time point |
| CN103703789A (en) * | 2013-06-28 | 2014-04-02 | 华为技术有限公司 | Method, terminal and system of data presentation |
| CN103400393A (en) * | 2013-08-21 | 2013-11-20 | 中科创达软件股份有限公司 | Image matching method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103970906A (en) | 2014-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103970906B (en) | The method for building up and device of video tab, the display methods of video content and device | |
| CN108769823B (en) | Direct broadcasting room display methods, device, equipment | |
| Zhang et al. | Object-level video advertising: an optimization framework | |
| CN103760968B (en) | Method and device for selecting display contents of digital signage | |
| CN104035982B (en) | Multimedia resource recommends method and device | |
| CN103426003A (en) | Implementation method and system for enhancing real interaction | |
| JP6369909B2 (en) | Facial expression scoring device, dance scoring device, karaoke device, and game device | |
| WO2018017836A1 (en) | Live video streaming services with machine-learning based highlight replays | |
| US20220269723A1 (en) | Song similarity determination | |
| CN110209843A (en) | Multimedia resource playback method, device, equipment and storage medium | |
| CN103365936A (en) | Video recommendation system and method thereof | |
| CN110019961A (en) | Method for processing video frequency and device, for the device of video processing | |
| CN101807393B (en) | KTV system, implement method thereof and TV set | |
| CN105975472A (en) | Method and device for recommendation | |
| CN102930454A (en) | Intelligent 3D (Three Dimensional) advertisement recommendation method based on multiple perception technologies | |
| CN105488135B (en) | Live content classification method and device | |
| Khiun | K-pop dance trackers and cover dancers: Global cosmopolitanization and local spatialization | |
| CN101517550A (en) | Social and interactive applications for mass media | |
| KR20100107036A (en) | Laugh detector and system and method for tracking an emotional response to a media presentation | |
| CN108920585A (en) | The method and device of music recommendation, computer readable storage medium | |
| CN109947510A (en) | A kind of interface recommended method and device, computer equipment | |
| CN111311315A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN109618229A (en) | Association playback method, device, server and the storage medium of audio-video | |
| CN109429077A (en) | Method for processing video frequency and device, for the device of video processing | |
| US20130247085A1 (en) | Method for generating video markup data on the basis of video fingerprint information, and method and system for providing information using same |
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 |