CN105812942A - Data interaction method and device - Google Patents
Data interaction method and device Download PDFInfo
- Publication number
- CN105812942A CN105812942A CN201610201987.2A CN201610201987A CN105812942A CN 105812942 A CN105812942 A CN 105812942A CN 201610201987 A CN201610201987 A CN 201610201987A CN 105812942 A CN105812942 A CN 105812942A
- Authority
- CN
- China
- Prior art keywords
- field picture
- destination object
- region
- identified
- 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.)
- Pending
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000008569 process Effects 0.000 claims abstract description 17
- 230000002452 interceptive effect Effects 0.000 claims description 27
- 230000001143 conditioned effect Effects 0.000 claims description 26
- 238000001514 detection method Methods 0.000 claims description 18
- 238000002372 labelling Methods 0.000 claims description 17
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 33
- 239000000284 extract Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47205—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention discloses a data interaction method and device. The method comprises following steps of identifying each frame image contained in a target video; determining the region of a target object in a currently identified frame image according to preset characteristic data; determining the determined regions in the frame images which contain the target object and satisfy a preset condition in a preset frame time period as an interaction region; detecting whether the region clicked by a user is the interaction region or not in a process of playing the target video; and executing interaction operations related to the target object if the region clicked by the user is the interaction region. Through application of the embodiment of the method and device, the problem that interaction with the object of the video frame image in the video frame images of the played video cannot be carried out is solved.
Description
Technical field
The present invention relates to technical field of image processing, particularly to a kind of data interactive method and device.
Background technology
Along with the development of Internet technology, mutual form is had higher requirement by user, so-called mutual, i.e. exchange and interdynamic, is that internet platform pursues the functional status made.By certain, there is the internet platform of interactive function, user can be allowed to obtain relevent information, information or service on platform, can also mutually exchange with interactive between user with user or between user with platform, thus colliding out more intention, thought and demand etc., such as, at mobile terminal device when playing video, user wishes the discussion that can participate in video image content in the process of viewing video, evaluation etc..
At present, typically by the mode adding button outside the video frame images playing video, the object that the user enable passes through to click in the video frame images of button and the play video added interacts, although also being able to the object realized with the video frame images of play video interact, but the object being only capable of in the outer video frame images with play video of video frame images of play video interacts, it is impossible to enough interact with the object in video frame images in the video frame images of play video.
Summary of the invention
The purpose of the embodiment of the present invention is in that to provide a kind of data interactive method and device, it is possible to the problem solving to interact with the object in video frame images in the video frame images of play video.
In order to achieve the above object, embodiments providing a kind of data interactive method, be applied to server, gather in advance and store the characteristic for destination object, described method includes:
Each two field picture that target video is comprised is identified；
According to described characteristic, it is judged that whether the current two field picture identified exists described destination object；
If it does, determine described destination object region in the current two field picture identified；
Described destination object will be comprised in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；
In the process that described target video is play, whether the region that detection user clicks is described interaction area；
If it is, perform the interactive operation relevant to described destination object.
Optionally, described destination object is target face；
Described each two field picture that target video is comprised is identified, including:
Utilizing face recognition technology, each two field picture that described target video is comprised is identified.
Optionally, described pre-conditioned include:
Presetting in frame period, the region correspondence of determined adjacent two two field pictures presets the changes in coordinates amount of labelling point less than or equal to predetermined threshold value, and described default labelling point is the pixel in the region of determined two field picture.
Optionally, described determine described destination object region in the current two field picture identified after, also include:
Record is preset in frame period and is comprised described destination object and meet the frame time of pre-conditioned two field picture；
When described target video is play to the frame time of the two field picture of described record, push information, so that client shows that described information, described information are used for pointing out user to pass through to click described interaction area and interact with described destination object.
Optionally, described data interactive method also includes:
Push the display position of described information, so that described client is in information described in described display position display.
In order to achieve the above object, embodiments providing a kind of data interaction device, be applied to server, described device includes:
Memory module, for storing the characteristic for destination object collected in advance；
Identification module, is identified for each two field picture that target video is comprised；
Judge module, for according to described characteristic, it is judged that whether there is described destination object in the current two field picture identified；
First determines module, for when described judge module judged result is for being, it is determined that described destination object region in the current two field picture identified；
Second determines module, for will comprise described destination object in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；
Detection module, in the process that described target video is play, whether the region that detection user clicks is described interaction area；
Perform module, for when described detection module testing result is for being, performing the interactive operation relevant to described destination object.
Optionally, described destination object is target face；
Described identification module, specifically for:
Utilizing face recognition technology, each two field picture that target video is comprised is identified.
Optionally, described pre-conditioned include:
Presetting in frame period, the region correspondence of determined adjacent two two field pictures presets the changes in coordinates amount of labelling point less than or equal to predetermined threshold value, and described default labelling point is the pixel in the region of determined two field picture.
Optionally, data interaction device also includes:
Logging modle, comprises described destination object for recording and meets the frame time of pre-conditioned two field picture in default frame period；
First pushing module, for when described target video is play to the frame time of the two field picture of described record, push information, so that client shows that described information, described information are used for pointing out user to pass through to click described interaction area and interact with described destination object.
Optionally, data interaction device also includes:
Second pushing module, for pushing the display position of described information, so that described client is in information described in described display position display.
A kind of data interactive method of embodiment of the present invention offer and device, it is identified by each two field picture that target video is comprised, further according to default characteristic, determine destination object region in the current two field picture identified, and destination object will be comprised in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；In the process that target video is play, whether the region that detection user clicks is interaction area, if it is, perform the interactive operation relevant to destination object.The application embodiment of the present invention, solves the problem that can not interact in the video frame images of play video with the destination object in video frame images.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The schematic flow sheet of a kind of data interactive method that Fig. 1 provides for the embodiment of the present invention；
The schematic flow sheet of the another kind of data interactive method that Fig. 2 provides for the embodiment of the present invention；
The schematic flow sheet of the another kind of data interactive method that Fig. 3 provides for the embodiment of the present invention；
The structural representation of a kind of data interaction device that Fig. 4 provides for the embodiment of the present invention；
The structural representation of the another kind of data interaction device that Fig. 5 provides for the embodiment of the present invention；
The structural representation of the another kind of data interaction device that Fig. 6 provides for the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
A kind of data interactive method of embodiment of the present invention offer and device, it is identified by each two field picture that target video is comprised, further according to default characteristic, determine destination object region in the current two field picture identified, and destination object will be comprised in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；In the process that target video is play, whether the region that detection user clicks is interaction area, if it is, perform the interactive operation relevant to destination object.The application embodiment of the present invention, solves the problem that can not interact in the video frame images of play video with the object in video frame images.
Below by specific embodiment, the present invention will be described in detail.The schematic flow sheet of a kind of data interactive method that Fig. 1 provides for the embodiment of the present invention, method can include step:
S101: each two field picture that target video is comprised is identified；
It will be appreciated by persons skilled in the art that it is made up of substantial amounts of two field picture for a video, it is to be understood that each two field picture comprised at video file all includes substantial amounts of information；Before video playback, server can carry out image recognition for each two field picture comprised in video in advance, concrete, and the object in the server each two field picture to comprising in video is identified, it is possible to understand that, object can be face, automobile, basketball etc.；Two field picture being identified, it is simply that the object comprised in two field picture is caught, extract the characteristic of the object comprised in corresponding two field picture, characteristic can comprise the shape of object, size and each principal character.Such as: the two field picture that video comprises has star Li Chen face, current two field picture is identified by server, face in current frame image is caught, the feature of the shape of face, size and each organ is extracted, obtain this face characteristic of correspondence data；If the object more than one in current frame image, having 3 faces in current frame image, now, these three face is caught by server respectively, extracts this 3 face characteristic of correspondence data；Each two field picture that video is comprised by server is identified, and will obtain the face characteristic data corresponding with each two field picture.
Further, the step S101 provided based on above-described embodiment may include that and utilizes face recognition technology, and each two field picture that described target video is comprised is identified；Wherein, destination object is target face.
In prior art, face recognition technology is quite ripe, and face recognition technology is based on the face feature of people, first determines whether whether there is face in two field picture, if there is face, then further provide the positional information of the position of each face, size and each major facial organ.And according to these information, extract the identity characteristic contained in each face further, and it is contrasted with presetting the face characteristic data set up, thus identifying the identity of each face.The actual a series of correlation techniques including building face identification system of the recognition of face of broad sense, including man face image acquiring, Face detection, recognition of face pretreatment, identity validation and identity finder etc.；And the technology being carried out identity validation or identity finder by face is refered in particular in the recognition of face of narrow sense, each two field picture that current video is comprised by embodiment of the present invention application face recognition technology is identified, and obtains and object characteristic of correspondence data in each two field picture.
S102: according to described characteristic, it is judged that whether there is described destination object in the current two field picture identified, if it is, perform S103；
Each two field picture characteristic of correspondence data after identifying are compareed with the characteristic of the destination object pre-building and being saved in server memory block, when similarity meets certain requirement, it is determined that current frame image comprises destination object.Illustrate, if pre-building and be saved in destination object in server memory block for star Li Chen face, then, as long as meet face characteristic data corresponding in the current frame image identified in S101 with the star's Li Chen face feature data similarity pre-build more than or equal to 90% time, the star's Li Chen face feature data thinking these face characteristic data and pre-build are mated, say, that there is destination object in current frame image.But the concrete form of destination object can be indefinite, can being such as star Li Chen, star's Fan Bing ice etc., here, the concrete form of destination object not be done further restriction by the present embodiment.Certainly, the method carrying out mating with the characteristic pre-build here can have multiple, and further, the value of similarity also may be set to other values, and the method for coupling and the value of similarity are not also done and clearly limited by the application.
What deserves to be explained is, when pre-building the characteristic of destination object, can pass through to add up in the video comprising destination object or image library, when such as face, automobile etc. being set up characteristic, can pass through substantial amounts of photo album of stars, photos etc. carry out facial feature extraction, it is thus achieved that characteristic of correspondence data, set up a facial feature data for this star.It is same, it is also possible to automobile to be carried out the foundation of characteristic, it is possible to use the trade mark of automobile and vehicle color, vehicle etc. set up characteristic of correspondence data, for instance, set up and obtain automobile, the characteristic of popular, white, SUV.
Being saved in a specific memory area by the one or more characteristics pre-build, the RAM (random access memory) card of such as server, hard disk etc., further restriction is not done in the preservation region of characteristic by the application here；Further, the concrete form of object is not done yet and clearly limits by the present invention, object origin when setting up characteristics of objects data is not done further restriction yet.
S103: determine described destination object region in the current two field picture identified；
If it is determined that current frame image comprises destination object, server will transfer the characteristic of current frame image correspondence destination object, the information such as the position comprised in characteristic and shape size are extracted, again the information such as the position extracted and shape size are calculated, it is determined that go out the region that the destination object comprised in current frame image is residing in current frame image.
S104: described destination object will be comprised in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；
It is understood that owing to human eye has the characteristic of persistence of vision, a large amount of two field pictures comprised when video, in time in extremely rapid succession refreshing, just define the illusion of motion at human eye.Known, the two field picture number of times refreshed in 1 seconds is called frame per second by us, represents typically by FPS (FramesPerSecond).In order to better reality play video frame images continuity, content between generally adjacent two width two field pictures is close, in order to destination object occurring in longer frame period, the embodiment of the present invention is by being identified the two field picture in default frame period, the frame period that all two field pictures in default frame period all comprise destination object is found out, further, the destination object in two field picture in default frame period position in corresponding two field picture is compared, the region of the destination object in the location variation of correspondence destination object two field picture in default threshold value in adjacent two field picture is defined as interaction area, this interaction area is the region that user interacts with video, for receiving the access of user, and obtain the access data of user.
For example, current video includes 259200 width two field pictures, if the frame per second FPS (FramesPerSecond) that current video is play is 48, namely within every 1 second, 48 width two field pictures will be play, so it is not difficult to be obtained by calculating, current video is all play to be needed to use the 259200/48=5400 second, and namely total duration of current video is 5400 seconds；nullThe time span taking default frame period in the embodiment of the present invention is 3 seconds，To whether institute in any 3 seconds frame period in the total duration of current video 5400 seconds comprises destination object in 144 width two field pictures judge playing，If comprising destination object，Meet pre-conditioned two field picture simultaneously，The determined region of destination object in two field picture is defined as interaction area，Here pre-conditioned can be: presets the destination object location variable quantity in the consecutive frame image in frame period less than 10 pixels，Or think that this two width two field picture is that fine motion is motionless，Now the region of destination object corresponding for this two width two field picture is defined as interaction area，As，144 width two field pictures all include star Li Chen face in presetting in 3 seconds true time periods the 1001-1144 width two field picture comprised，And this 144 width two field picture meets the destination object present position variable quantity in consecutive frame image less than 10 pixels，So，Server will be corresponding to the characteristic comprising star Li Chen in this 144 width image region，Ji Li face in morning is defined as interaction area.What deserves to be explained is, here in the frame period of default 3 seconds, allow to have in a small amount of two field picture and do not comprise destination object, or the destination object comprised is adjacent the target object position variable quantity in two field picture more than 10 pixels, now, such two field picture is thought bad image by the embodiment of the present invention, such as, 1049th width two field picture does not comprise star Li Chen face, or be in the 1049th width two field picture the location variation of comprised star Li Chen face and the star Li Chen in the 1048th width and 1050 width two field pictures more than 10 pixels, now server thinks that the 1049th width two field picture is bad image, it is not processed when determining interaction area.It should be understood that the length of above-mentioned default frame period is adjustable in, e.g., being set to 2 seconds, 4 seconds, therefore, default frame period is not defined by the embodiment of the present invention.Same, the change value of predeterminated position is also adjustable in, for instance be set to 15 pixels, 20 pixels, needs exist for the total pixel size according to actual video frame images and sets, and the application is not to do further restriction to it.
Understandable, above-mentioned pre-conditioned can be: preset in frame period, the region correspondence of determined adjacent two two field pictures presets the changes in coordinates amount of labelling point less than or equal to predetermined threshold value, and described default labelling point is the pixel in the region of determined two field picture.
In reality, for two field picture, each pixel in two field picture is all to there being coordinate, when judging the regional location variable quantity of adjacent two two field pictures, in order to reduce the calculating pressure of server, the present embodiment is by having determined that the region comprising destination object carries out feature point extraction, such as, the face of star Li Chen in two field picture is carried out feature extraction, obtain pixel corresponding to nose as labelling point, like this when calculating the regional location variable quantity of adjacent two width two field picture correspondence destination objects, the changes in coordinates amount having only to calculate correspondence markings point is just passable, again to the changes in coordinates amount calculated whether less than or equal to predetermined threshold value；Such as, in the 1047th width two field picture, labelling point coordinates corresponding for star Li Chen is (10,5)；Labelling point coordinates corresponding for star Li Chen in 1048th width two field picture is (12,8), it is not difficult to calculate labelling point coordinates variable quantity corresponding for star Li Chen in this two width two field picture and is: Δ x=2, Δ y=3, predetermined threshold value takes Δ x=10, Δ y=10, is not difficult here to obtain, the 1047th width labelling point coordinates variable quantity corresponding for star Li Chen with the 1048th width two field picture is less than predetermined threshold value, or namely thinks that this two width two field picture is that fine motion is motionless.For above-mentioned predetermined threshold value, specifically can setting according to the amount of pixels comprised in actual frame image, its concrete numerical value is not done clear stipulaties by the application.
S105: in the process that described target video is play, whether the region that detection user clicks is described interaction area, if it is, perform S106；
In the process that current video is play, user is mutual by what click that the destination object in play two field picture realizes with destination object；In playing process, two field picture can be clicked by user when the two field picture comprising interaction area arbitrarily is play, access instruction in the interaction area play in video frame images will be acquired by server, if the position accessed in user's current frame image is in interaction area, so now user accesses effectively, and namely server will collect the access instruction for current frame image.For not having the interaction area of destination object in the two field picture that current video comprises, at this moment no matter user is either with or without click, the access instruction that server is corresponding by not accepting this two field picture.
S106: perform the interactive operation relevant to described destination object.
If collection of server to user's access instruction be in interaction area, now server is by corresponding with destination object for the access instruction collected, the interactive operation that current target object is correlated with, such as, the access instruction of the user interaction area that to be in current frame image corresponding for star Li Chen, time in region residing for Ji Li face in morning, star Li Chen in current frame image is carried out a little praising operation by server, to improve the popularity value of star Li Chen, it is achieved user is mutual with destination object Li Chen's.
Apply embodiment of the method provided by the invention, it is identified by each two field picture that target video is comprised, further according to default characteristic, determine destination object region in the current two field picture identified, and destination object will be comprised in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；In the process that target video is play, whether the region that detection user clicks is interaction area, if it is, perform the interactive operation relevant to destination object；Solve the problem that can not interact in the video frame images of play video with the destination object in video frame images.
Further, based on Fig. 1 embodiment provided, a kind of data interactive method that the embodiment of the present invention provides can also comprise the steps: as in figure 2 it is shown, after step S104 shown in Fig. 1, also include step S107 and step S108, particularly as follows:
S107: record is preset in frame period and comprised described destination object and meet the frame time of pre-conditioned two field picture；
It should be noted that, in step S104 is by default frame period, comprises described destination object and meets determined region in pre-conditioned two field picture, after being defined as interaction area, have been determined as two field picture corresponding to the destination object of interaction area in current video, have unique corresponding frame time, under server record, have been determined as the frame time that two field picture corresponding to the destination object of interaction area is corresponding.
S108: when described target video is play to the frame time of the two field picture of described record, push information, so that client shows that described information, described information are used for pointing out user to pass through to click described interaction area and interact with described destination object.
In the present embodiment institute offer scheme, interact with the destination object in two field picture to better realize user, also for client push for pointing out user by clicking the information that interaction area and destination object interact.nullWhen current video is play to the frame time that the two field picture that the step S107 destination object having been determined as interaction area recorded is corresponding is corresponding，Server push information，Such as: the 259200 width two field pictures comprised for current video，The all corresponding frame time of each width two field picture，Assume the condition that the 4800th width two field picture meets in S104，Have determined that the interaction area in the 4800th width two field picture，It will be appreciated that，The frame time that 4800th width two field picture is corresponding is the 4800/48=100 second，So，When current video is play to corresponding the 100th second of the 4800th width two field picture，Server will push information in the 4800th width two field picture，So that the information content that client display pushes，Further prompting user can be interacted with described destination object by the described interaction area of click.
Based on Fig. 2 embodiment provided, a kind of data interactive method that the embodiment of the present invention provides as it is shown on figure 3, after step S108 shown in Fig. 2, also include step S109, particularly as follows:
S109: push the display position of described information, so that described client is in information described in described display position display.
In practical application, server is after propelling movement information is to client, also by pushing position data corresponding to information to client, so that client is in the position display reminding information pushed；There are certain corresponding relation in the position of the information that client shows and star face, and such as, the position of information is all the time in lower right 50 pixel of star face.Certainly, the position of this information is corresponding with star face is only the concrete example of the present invention, in addition the information edge at client terminal playing window can also be set, such as, the lower left corner of client terminal playing window, the lower right corner, left side, right side etc., therefore, the particular location of information is not done and clearly limits by the application.
It is understandable that, in the above embodiments, comprise destination object in default frame period by recording and meet the frame time of pre-conditioned two field picture, when video playback to corresponding frame time, server push information, ensure that information and the current frame image one_to_one corresponding play, further, server also pushes the display position of information, so that client shows position display in correspondence, for pointing out user can be interacted with destination object by click interaction area, improve the accuracy that user interacts.
Corresponding to embodiment of the method shown in Fig. 1, the embodiment of the present invention additionally provides a kind of data interaction device, and as shown in Figure 4, device may include that
Memory module 201, identification module 202, it is judged that module 203, first determines module 204, and second determines module 205, detection module 206, performs module 207, wherein:
Memory module 201, for storing the characteristic for destination object collected in advance；
Identification module 202, is identified for each two field picture that target video is comprised；
In practical application, destination object can be face, described identification module 202, and specifically for utilizing face recognition technology, each two field picture that target video is comprised is identified.
Judge module 203, for according to described characteristic, it is judged that whether there is described destination object in the current two field picture identified；
First determines module 204, for when judge module 203 judged result is for being, it is determined that described destination object region in the current two field picture identified；
Second determines module 205, for will comprise described destination object in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；
In practical application, the condition preset can be: presets in frame period, the region correspondence of determined adjacent two two field pictures presets the changes in coordinates amount of labelling point less than or equal to predetermined threshold value, and described default labelling point is the pixel in the region of determined two field picture.
Detection module 206, in the process that described target video is play, whether the region that detection user clicks is described interaction area；
Perform module 207, for when detection module 206 testing result is for being, performing the interactive operation relevant to described destination object.
Apply device embodiment provided by the invention, it is identified by each two field picture that target video is comprised, further according to default characteristic, determine destination object region in the current two field picture identified, and destination object will be comprised in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；In the process that target video is play, whether the region that detection user clicks is interaction area, if it is, perform the interactive operation relevant to destination object；Solve the problem that can not interact in the video frame images of play video with the destination object in video frame images.
Corresponding to embodiment of the method shown in Fig. 2, the embodiment of the present invention additionally provides a kind of data interaction device as it is shown in figure 5, embodiment illustrated in fig. 5 of the present invention is on the basis of embodiment illustrated in fig. 4, it is also possible to include logging modle 208 and the first pushing module 209；
Wherein, logging modle 208, comprise described destination object in default frame period for recording and meet the frame time of pre-conditioned two field picture；
First pushing module 209, for when described target video is play to the frame time of the two field picture of described record, push information, so that client shows that described information, described information are used for pointing out user to pass through to click described interaction area and interact with described destination object.
Corresponding to embodiment of the method shown in Fig. 3, the embodiment of the present invention additionally provides a kind of data interaction device as shown in Figure 6, and embodiment illustrated in fig. 6 of the present invention is on the basis of embodiment illustrated in fig. 5, it is also possible to include, the second pushing module 210；
Second pushing module 210, for pushing the display position of described information, so that described client is in information described in described display position display.
It is understandable that, in the above embodiments, comprise destination object in default frame period by recording and meet the frame time of pre-conditioned two field picture, when video playback to corresponding frame time, server push information, ensure that information and the current frame image one_to_one corresponding play, further, also by the display position pushing information, so that client shows position display in correspondence, for pointing out user can be interacted with destination object by click interaction area, improve the accuracy that user interacts.
It should be noted that, in this article, the relational terms of such as first and second or the like is used merely to separate an entity or operation with another entity or operating space, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, so that include the process of a series of key element, method, article or equipment not only include those key elements, but also include other key elements being not expressly set out, or also include the key element intrinsic for this process, method, article or equipment.When there is no more restriction, statement " including ... " key element limited, it is not excluded that there is also other identical element in including the process of described key element, method, article or equipment.
Each embodiment in this specification all adopts relevant mode to describe, between each embodiment identical similar part mutually referring to, what each embodiment stressed is the difference with other embodiments.Especially for device embodiment, owing to it is substantially similar to embodiment of the method, so what describe is fairly simple, relevant part illustrates referring to the part of embodiment of the method.
One of ordinary skill in the art will appreciate that all or part of step realizing in said method embodiment can be by the hardware that program carrys out instruction relevant and completes, described program can be stored in computer read/write memory medium, the storage medium obtained designated herein, as: ROM/RAM, magnetic disc, CD etc..
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit protection scope of the present invention.All make within the spirit and principles in the present invention any amendment, equivalent replacement, improvement etc., be all contained in protection scope of the present invention.
Claims (10)
1. a data interactive method, is applied to server, it is characterised in that gathering in advance and store the characteristic for destination object, described method includes:
Each two field picture that target video is comprised is identified；
According to described characteristic, it is judged that whether the current two field picture identified exists described destination object；
If it does, determine described destination object region in the current two field picture identified；
Described destination object will be comprised in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；
In the process that described target video is play, whether the region that detection user clicks is described interaction area；
If it is, perform the interactive operation relevant to described destination object.
2. method according to claim 1, it is characterised in that described destination object is target face；
Described each two field picture that target video is comprised is identified, including:
Utilizing face recognition technology, each two field picture that described target video is comprised is identified.
3. method according to claim 1, it is characterised in that described pre-conditioned include:
Presetting in frame period, the region correspondence of determined adjacent two two field pictures presets the changes in coordinates amount of labelling point less than or equal to predetermined threshold value, and described default labelling point is the pixel in the region of determined two field picture.
4. method according to claim 1, it is characterised in that described determine described destination object region in the current two field picture identified after, also include:
Record is preset in frame period and is comprised described destination object and meet the frame time of pre-conditioned two field picture；
When described target video is play to the frame time of the two field picture of described record, push information, so that client shows that described information, described information are used for pointing out user to pass through to click described interaction area and interact with described destination object.
5. method according to claim 4, it is characterised in that also include:
Push the display position of described information, so that described client is in information described in described display position display.
6. a data interaction device, is applied to server, it is characterised in that described device includes:
Memory module, for storing the characteristic for destination object collected in advance；
Identification module, is identified for each two field picture that target video is comprised；
Judge module, for according to described characteristic, it is judged that whether there is described destination object in the current two field picture identified；
First determines module, for when described judge module judged result is for being, it is determined that described destination object region in the current two field picture identified；
Second determines module, for will comprise described destination object in default frame period and meet determined region in pre-conditioned two field picture, it is determined that for interaction area；
Detection module, in the process that described target video is play, whether the region that detection user clicks is described interaction area；
Perform module, for when described detection module testing result is for being, performing the interactive operation relevant to described destination object.
7. device according to claim 6, it is characterised in that described destination object is target face；
Described identification module, specifically for:
Utilizing face recognition technology, each two field picture that target video is comprised is identified.
8. device according to claim 6, it is characterised in that described pre-conditioned include:
Presetting in frame period, the region correspondence of determined adjacent two two field pictures presets the changes in coordinates amount of labelling point less than or equal to predetermined threshold value, and described default labelling point is the pixel in the region of determined two field picture.
9. device according to claim 6, it is characterised in that also include:
Logging modle, comprises described destination object for recording and meets the frame time of pre-conditioned two field picture in default frame period；
First pushing module, for when described target video is play to the frame time of the two field picture of described record, push information, so that client shows that described information, described information are used for pointing out user to pass through to click described interaction area and interact with described destination object.
10. device according to claim 9, it is characterised in that also include:
Second pushing module, for pushing the display position of described information, so that described client is in information described in described display position display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610201987.2A CN105812942A (en) | 2016-03-31 | 2016-03-31 | Data interaction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610201987.2A CN105812942A (en) | 2016-03-31 | 2016-03-31 | Data interaction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105812942A true CN105812942A (en) | 2016-07-27 |
Family
ID=56460140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610201987.2A Pending CN105812942A (en) | 2016-03-31 | 2016-03-31 | Data interaction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105812942A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909369A (en) * | 2017-01-11 | 2017-06-30 | 广州视源电子科技股份有限公司 | User interface display method and system |
| CN108650555A (en) * | 2018-05-15 | 2018-10-12 | 优酷网络技术（北京）有限公司 | The displaying of video clip, the generation method of interactive information, player and server |
| CN108900629A (en) * | 2018-07-25 | 2018-11-27 | 西安艾润物联网技术服务有限责任公司 | A kind of service push method and device |
| WO2019119643A1 (en) * | 2017-12-21 | 2019-06-27 | 平安科技（深圳）有限公司 | Interaction terminal and method for mobile live broadcast, and computer-readable storage medium |
| CN111225266A (en) * | 2020-02-25 | 2020-06-02 | 上海哔哩哔哩科技有限公司 | User interface interaction method and system |
| CN111523467A (en) * | 2020-04-23 | 2020-08-11 | 北京百度网讯科技有限公司 | Face tracking method and device |
| CN111753574A (en) * | 2019-03-26 | 2020-10-09 | 顺丰科技有限公司 | Throwing area positioning method, device, equipment and storage medium |
| CN114415870A (en) * | 2021-12-29 | 2022-04-29 | 中国电信股份有限公司 | Method and device for pushing article information in video data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102591553A (en) * | 2011-01-13 | 2012-07-18 | 京宏科技股份有限公司 | Video interaction method system and device, and video-related tag generation device and method |
| US20150189384A1 (en) * | 2013-12-27 | 2015-07-02 | Alibaba Group Holding Limited | Presenting information based on a video |
| CN104967908A (en) * | 2014-09-05 | 2015-10-07 | 腾讯科技（深圳）有限公司 | Video hot spot marking method and apparatus |
| CN105141986A (en) * | 2015-08-06 | 2015-12-09 | 小米科技有限责任公司 | Method and device for video processing and method and device for image recognition |
-
2016
- 2016-03-31 CN CN201610201987.2A patent/CN105812942A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102591553A (en) * | 2011-01-13 | 2012-07-18 | 京宏科技股份有限公司 | Video interaction method system and device, and video-related tag generation device and method |
| US20150189384A1 (en) * | 2013-12-27 | 2015-07-02 | Alibaba Group Holding Limited | Presenting information based on a video |
| CN104967908A (en) * | 2014-09-05 | 2015-10-07 | 腾讯科技（深圳）有限公司 | Video hot spot marking method and apparatus |
| CN105141986A (en) * | 2015-08-06 | 2015-12-09 | 小米科技有限责任公司 | Method and device for video processing and method and device for image recognition |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909369B (en) * | 2017-01-11 | 2020-07-24 | 广州视源电子科技股份有限公司 | User interface display method and system |
| CN106909369A (en) * | 2017-01-11 | 2017-06-30 | 广州视源电子科技股份有限公司 | User interface display method and system |
| WO2019119643A1 (en) * | 2017-12-21 | 2019-06-27 | 平安科技（深圳）有限公司 | Interaction terminal and method for mobile live broadcast, and computer-readable storage medium |
| CN108650555A (en) * | 2018-05-15 | 2018-10-12 | 优酷网络技术（北京）有限公司 | The displaying of video clip, the generation method of interactive information, player and server |
| CN108650555B (en) * | 2018-05-15 | 2022-11-22 | 北京优酷科技有限公司 | Video interface display method, interactive information generation method, player and server |
| CN108900629A (en) * | 2018-07-25 | 2018-11-27 | 西安艾润物联网技术服务有限责任公司 | A kind of service push method and device |
| CN108900629B (en) * | 2018-07-25 | 2021-11-30 | 西安艾润物联网技术服务有限责任公司 | Service pushing method and device |
| CN111753574A (en) * | 2019-03-26 | 2020-10-09 | 顺丰科技有限公司 | Throwing area positioning method, device, equipment and storage medium |
| US11442606B2 (en) | 2020-02-25 | 2022-09-13 | Shanghai Bilibili Technology Co., Ltd. | User interface interaction method and system |
| CN111225266A (en) * | 2020-02-25 | 2020-06-02 | 上海哔哩哔哩科技有限公司 | User interface interaction method and system |
| CN111523467A (en) * | 2020-04-23 | 2020-08-11 | 北京百度网讯科技有限公司 | Face tracking method and device |
| CN111523467B (en) * | 2020-04-23 | 2023-08-08 | 北京百度网讯科技有限公司 | Face tracking method and device |
| CN114415870A (en) * | 2021-12-29 | 2022-04-29 | 中国电信股份有限公司 | Method and device for pushing article information in video data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105812942A (en) | Data interaction method and device | |
| Zhang et al. | Wide-area crowd counting via ground-plane density maps and multi-view fusion cnns | |
| US20250086809A1 (en) | Determining multiple camera positions from multiple videos | |
| US20240273737A1 (en) | System and method for transforming video data into directional object count | |
| US8983184B2 (en) | Vision image information storage system and method thereof, and recording medium having recorded program for implementing method | |
| Han et al. | Employing a RGB-D sensor for real-time tracking of humans across multiple re-entries in a smart environment | |
| Chen et al. | Ball tracking and 3D trajectory approximation with applications to tactics analysis from single-camera volleyball sequences | |
| US10210423B2 (en) | Image match for featureless objects | |
| CN110189378A (en) | A kind of method for processing video frequency, device and electronic equipment | |
| EP2034426A1 (en) | Moving image analyzing, method and system | |
| CN109190508A (en) | A kind of multi-cam data fusion method based on space coordinates | |
| Dubuisson et al. | A survey of datasets for visual tracking | |
| CN111160243A (en) | Passenger flow volume statistical method and related product | |
| Sun et al. | Salient montages from unconstrained videos | |
| CN108109010A (en) | A kind of intelligence AR advertisement machines | |
| CN106446002A (en) | Moving target-based video retrieval method for track in map | |
| Bettadapura et al. | Egocentric field-of-view localization using first-person point-of-view devices | |
| KR101189609B1 (en) | System and method for providing video related service based on image | |
| CN105678802A (en) | Method for generating three-dimensional information by identifying two-dimensional image | |
| Xiong et al. | Snap angle prediction for 360 panoramas | |
| Joshi | A low cost and computationally efficient approach for occlusion handling in video surveillance systems | |
| CN113468914B (en) | A method, device and equipment for determining the purity of commodities | |
| US20220122341A1 (en) | Target detection method and apparatus, electronic device, and computer storage medium | |
| Nakabayashi et al. | Event-based high-speed ball detection in sports video | |
| CN104254019A (en) | Information push result detecting method and information push result detecting system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160727 |