CN110300316A - Method, apparatus, electronic equipment and the storage medium of pushed information are implanted into video - Google Patents
Method, apparatus, electronic equipment and the storage medium of pushed information are implanted into video Download PDFInfo
- Publication number
- CN110300316A CN110300316A CN201910704475.1A CN201910704475A CN110300316A CN 110300316 A CN110300316 A CN 110300316A CN 201910704475 A CN201910704475 A CN 201910704475A CN 110300316 A CN110300316 A CN 110300316A
- Authority
- CN
- China
- Prior art keywords
- image
- video
- implanted
- prospect
- entity
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 239000000203 mixture Substances 0.000 claims abstract description 11
- 230000015654 memory Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 13
- 239000012634 fragment Substances 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims 1
- 238000002513 implantation Methods 0.000 description 43
- 238000010586 diagram Methods 0.000 description 34
- 244000269722 Thea sinensis Species 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 241000531891 Alburnus alburnus Species 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 4
- 239000008267 milk Substances 0.000 description 4
- 210000004080 milk Anatomy 0.000 description 4
- 235000013336 milk Nutrition 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 2
- 210000000746 body region Anatomy 0.000 description 2
- 235000019219 chocolate Nutrition 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 239000003826 tablet Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000001755 vocal effect Effects 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]
- H04N21/20—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]
- H04N21/20—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
- H04N21/23424—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
- H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
-
- 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
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
- H04N21/4316—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations for displaying supplemental content in a region of the screen, e.g. an advertisement in a separate window
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides method, apparatus, electronic equipment and storage mediums that pushed information is implanted into a kind of video；Wherein, method includes: to carry out Entity recognition to the frame image of video to be implanted, determines the corresponding entity area of entity in frame image；Obtain the image to be implanted of the carrying pushed information in correspondent entity region；Using the entity area of frame image as background, using corresponding image to be implanted as prospect, be implanted into image to be implanted in the entity area of frame image, obtain target frame image；The image parameter for adjusting prospect in target frame image, so that the image parameter of prospect and the image parameter of background match；Video Composition is carried out based on target frame image adjusted, obtains target video.It so, it is possible the harmonious degree of pushed information and video content in promotion target video.
Description
Technical field
The present invention relates in field of artificial intelligence more particularly to a kind of video be implanted into pushed information method, apparatus,
Electronic equipment and storage medium.
Background technique
In video playing scene, other than playing the content of video itself, there is also the demands for showing pushed information, push away
Deliver letters breath one of exhibition method for pushed information is implanted into video, to show the push letter of implantation in video display process
Breath.
In the related technology, the implantation for pushed information in video, needs professional to manually complete, and to implantation
Pushed information is manually adjusted, visual prominent caused by being discord after being implanted into avoid pushed information with video content
Towering, implantation low efficiency, the human cost of right such implantation are high.
Summary of the invention
The embodiment of the present invention provides method, apparatus, electronic equipment and the storage medium that pushed information is implanted into a kind of video,
The harmony of pushed information and video content after pushed information implantation in video and pushed information implantation can be realized automatically
Change.
The embodiment of the present invention provides a kind of method that pushed information is implanted into video, comprising:
Entity recognition is carried out to the frame image of video to be implanted, determines the corresponding entity area of entity described in the frame image
Domain；
Obtain the image to be implanted of the carrying pushed information of the corresponding entity area；
Using the entity area of the frame image as background, using the corresponding image to be implanted as prospect, in the frame figure
The entity area of picture is implanted into the image to be implanted, obtains target frame image；
The image parameter of prospect described in the target frame image is adjusted, so that the image parameter of the prospect and the back
The image parameter of scape matches；
Video Composition is carried out based on target frame image adjusted, obtains target video.
The embodiment of the present invention also provides the device that pushed information is implanted into a kind of video, and described device includes:
Recognition unit carries out Entity recognition for the frame image to video to be implanted, determines real described in the frame image
The corresponding entity area of body；
Acquiring unit, the image to be implanted of the carrying pushed information for obtaining the corresponding entity area；
Be implanted into unit, for using the entity area of the frame image as background, be with the corresponding image to be implanted before
Scape is implanted into the image to be implanted in the entity area of the frame image, obtains target frame image；
Adjustment unit, for adjusting the image parameter of prospect described in the target frame image, so that the figure of the prospect
As the image parameter of parameter and the background matches；
Synthesis unit obtains target video for carrying out Video Composition based on target frame image adjusted.
The embodiment of the invention also provides a kind of electronic equipment, comprising:
Memory, for storing executable instruction；
Processor when for executing the executable instruction stored in the memory, is realized provided in an embodiment of the present invention
The method of pushed information is implanted into video.
The embodiment of the invention also provides a kind of storage mediums, are stored with executable instruction, for causing processor to execute
When, realize the method that pushed information is implanted into video provided in an embodiment of the present invention.
It is had the advantages that using the embodiment of the present invention
1), using the entity area of the frame image of video to be implanted as background, using corresponding image to be implanted as prospect, in frame
The entity area of image is implanted into image to be implanted, obtains target frame image, realizes pushed information in the automatic of video to be implanted
Implantation, improves the implantation efficiency of pushed information；
2), by adjusting the image parameter of prospect in target frame image, so that the image of the image parameter of prospect and background
Parameter matches, and after realizing implantation pushed information, prospect and the automatic harmonization of background are handled in video frame images, so that mesh
The harmonization for marking pushed information and video content in video, greatly promotes reception of the user when watching video to pushed information
Degree.
Detailed description of the invention
Fig. 1 is the configuration diagram that the system 100 of pushed information is implanted into video provided in an embodiment of the present invention；
Fig. 2 is the hardware structural diagram of server provided in an embodiment of the present invention；
Fig. 3 is the flow diagram that the method for pushed information is implanted into video provided in an embodiment of the present invention；
Fig. 4 is an optional data structure schematic diagram of video provided in an embodiment of the present invention；
Fig. 5 is the frame image schematic diagram of the video before implantation pushed information provided in an embodiment of the present invention；
Fig. 6 is the frame image schematic diagram of the video after implantation pushed information provided in an embodiment of the present invention；
Fig. 7 is the schematic diagram of the image to be implanted provided in an embodiment of the present invention for screening corresponding desktop area；
Fig. 8 is the signal of threedimensional model and poster that determining angle presentation provided in an embodiment of the present invention and desktop match
Figure；
Fig. 9 is the schematic diagram provided in an embodiment of the present invention that image to be implanted is implanted into phase frame region；
Figure 10 is the schematic diagram provided in an embodiment of the present invention that image to be implanted is implanted into television screen region；
Figure 11 is the schematic diagram that the image parameter provided in an embodiment of the present invention to prospect in interception image is adjusted；
Figure 12 is the schematic diagram of the target frame image after progress image parameter adjusting provided in an embodiment of the present invention；
Figure 13 is the method flow schematic diagram that pushed information is implanted into video provided in an embodiment of the present invention；
Figure 14 is the method flow schematic diagram that pushed information is implanted into video provided in an embodiment of the present invention；
Figure 15 is the advantage display diagram of product placement in video provided in an embodiment of the present invention；
Figure 16 is the year provisional profit schematic diagram of product placement in video provided in an embodiment of the present invention；
Figure 17 is the structural schematic diagram that the device of pushed information is implanted into video provided in an embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, described embodiment is not construed as limitation of the present invention, and those of ordinary skill in the art are not having
All other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
In the following description, it is related to " some embodiments ", which depict the subsets of all possible embodiments, but can
To understand, " some embodiments " can be the same subsets or different subsets of all possible embodiments, and can not conflict
In the case where be combined with each other.
In the following description, related term " first second " be only be the similar object of difference, do not represent needle
To the particular sorted of object, it is possible to understand that specific sequence or successively can be interchanged in ground, " first second " in the case where permission
Order, so that the embodiment of the present invention described herein can be implemented with the sequence other than illustrating or describing herein.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term used herein is intended merely to the purpose of the description embodiment of the present invention,
It is not intended to limit the present invention.
Before the embodiment of the present invention is further elaborated, to noun involved in the embodiment of the present invention and term
It is illustrated, noun involved in the embodiment of the present invention and term are suitable for following explanation.
1) entity refers to herein for carrying the main body or material object of pushed information in video to be implanted, such as desktop, wall
Face, photo frame, screen of electronic equipment etc..
2) frame image refers to the minimum unit of video, is the image of width static state；For example, fixing when playing video information
Picture at any time, as a frame image.
3) camera lens, the basic unit of video data, during video capture, continuously uninterruptedly shoot one section of camera
Video is known as camera lens.
4) key frame images can be used to represent the image of camera lens content, after being syncopated as lens construction, key frame figure
As being used to represent the low-level image feature of each camera lens, to carry out further video structural；In a video lens, close
The number of key frame will be far smaller than the number for the frame image that camera lens is included.
5) in response to the condition or state relied on for indicating performed operation, when the relied on condition of satisfaction
Or when state, performed one or more operations be can be in real time, it is possible to have the delay of setting；Do not saying especially
In the case where bright, there is no the limitations for executing sequencing for performed multiple operations.
Fig. 1 is that an optional framework of the system 100 that pushed information is implanted into video provided in an embodiment of the present invention shows
It is intended to, referring to Fig. 1, supports an exemplary application to realize, terminal (including terminal 400-1 and terminal 400-2) passes through network
300 connection servers 200, network 300 can be wide area network or local area network, or is combination, using wireless or
Wire link realizes data transmission.
Terminal (such as terminal 400-1), the implantation for sending pushed information request to be implanted into request and take to server 200
Video identifier with video to be implanted can also carry image to be implanted in implantation request in some embodiments；
Server 200, for carrying out Entity recognition to the frame image of video to be implanted based on the implantation request received,
Determine the corresponding entity area of entity in frame image；Obtain the image to be implanted of the carrying pushed information in correspondent entity region；With
The entity area of frame image is background, using corresponding image to be implanted as prospect, to be implanted in the entity area implantation of frame image
Image obtains target frame image；The image parameter of prospect in target frame image is adjusted, so that the image parameter of prospect and background
Image parameter matches；Video Composition is carried out based on target frame image adjusted, obtains target video, and return to target video
To terminal；
Here, in practical applications, server 200 both can be a service of the support various businesses being separately configured
Device can also be configured to a server cluster.
Terminal (terminal 400-1 and/or terminal 400-2) is also used to play the target video for being implanted with pushed information.
In practical applications, terminal can be whole for various types of users such as smart phone, tablet computer, laptop
End can also be wearable computing devices, personal digital assistant (PDA), desktop computer, cellular phone, media player, lead
Any two or multiple in boat equipment, game machine, television set etc. or these data processing equipments or other data processing equipments
Combination.
The electronic equipment for the method for implementing to be implanted into pushed information in implementation video of the embodiment of the present invention is illustrated below.
In some embodiments, electronic equipment can be various types of terminals such as smart phone, tablet computer, laptop, also
It can be server.The embodiment of the present invention elaborates to the hardware configuration of server so that electronic equipment is server as an example.
Fig. 2 is the hardware structural diagram of server provided in an embodiment of the present invention, it will be understood that Fig. 2 illustrate only
The exemplary structure of server rather than entire infrastructure, can be implemented as needed Fig. 2 shows part-structure or entire infrastructure.Ginseng
See that Fig. 2, server provided in an embodiment of the present invention include: at least one processor 201, memory 202,203 and of user interface
At least one network interface 204.Various components in server are coupled by bus system 205.It is appreciated that bus
System 205 is for realizing the connection communication between these components.Bus system 205 further includes electricity in addition to including data/address bus
Source bus, control bus and status signal bus in addition.But for the sake of clear explanation, various buses are all designated as always in Fig. 2
Linear system system 205.
Wherein, user interface 203 may include display, keyboard, mouse, trace ball, click wheel, key, button, sense of touch
Plate or touch screen etc..
It is appreciated that memory 202 can be volatile memory or nonvolatile memory, may also comprise volatibility and
Both nonvolatile memories.
Memory 202 in the embodiment of the present invention is for storing various types of data to support the operation of server.This
The example of a little data includes: any executable instruction for operating on the server, and such as executable instruction realizes that the present invention is real
The program for applying the method for example may be embodied in executable instruction.
The method that pushed information is implanted into the video that the embodiment of the present invention discloses can be realized by processor 201.Processor
201 may be a kind of IC chip, the processing capacity with signal.During realization, pushed information is implanted into video
Each step of method can be completed by the instruction of the integrated logic circuit of the hardware in processor 201 or software form.
Above-mentioned processor 201 can be general processor, digital signal processor (DSP, Digital Signal Processor),
Either other programmable logic device, discrete gate or transistor logic, discrete hardware components etc..Processor 201 can be with
Realize or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor can be micro- place
Manage device or any conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly in
Hardware decoding processor executes completion, or in decoding processor hardware and software module combination execute completion.Software mould
Block can be located in storage medium, which is located at memory 202, and processor 201 reads the information in memory 202,
The step of method of pushed information is implanted into video provided in an embodiment of the present invention is completed in conjunction with its hardware.
Next the method that pushed information is implanted into video provided in an embodiment of the present invention is illustrated, Fig. 3 is this hair
The flow diagram that the method for pushed information is implanted into the video that bright embodiment provides is planted in the video in some embodiments
The method for entering pushed information can be implemented by server or terminal, or by server and terminal coordinated implementation, be with server implementation
Example, as implemented by the server 200 in Fig. 1, in conjunction with Fig. 1 and Fig. 3, implantation push letter in video provided in an embodiment of the present invention
The method of breath includes:
Step 301: server carries out Entity recognition to the frame image of video to be implanted, determines that entity is corresponding in frame image
Entity area.
In practical applications, video to be implanted both can be a complete video, such as a complete movie file, or
Person is a video clip, such as the segment selected parts of a film.
In practical applications, entity is for carrying the main body or things of pushed information in video to be implanted, such as desktop, wall
Face, photo frame, electronic equipment screen (such as television screen)；In actual implementation, can by the polygon frame detector of single (SSD,
Single Shot Multi-Box Detector) identification frame image in entity, example partitioning algorithm mask also can be used
RCNN identifies the entity in frame image, and the embodiment of the present invention is not construed as limiting.In practical applications, it can preset what needs identified
Entity, as only identified metope and photo frame in the desktop in frame image, or identification frame image.
In some embodiments, Entity recognition can be carried out by the frame image to video to be implanted in the following way, determined
The corresponding entity area of entity in frame image:
The key frame for extracting video to be implanted carries out Entity recognition to the key frame of video to be implanted, determines each key
The corresponding entity area of entity in frame.
In some embodiments, Entity recognition can also be carried out by the frame image to video to be implanted in the following way, really
The corresponding entity area of entity in framing image:
Cutting processing is carried out to video to be implanted, obtains multiple video slicings；Entity is carried out to multiple video slicings respectively
Identification, determines the corresponding entity area of entity in the frame image of each video slicing.
In practical applications, different Entity recognitions can be carried out for different video slicings, as video be split for
10 video slicings carry out desktop identification to the 1st to 3 video slicing, to the 4th to 6 progress photo frame identification, to the 7th to 10
A progress metope identification；Identical Entity recognition can also be carried out certainly for different video slicings, still with video be split for
For 10 video slicings, 10 video slicings are carried out with the Entity recognition of desktop and photo frame.
Here, the data structure of video is illustrated.Fig. 4 is that one of video provided in an embodiment of the present invention is optional
Data structure schematic diagram, referring to fig. 4, video data can be divided into four film, scene, camera lens and frame levels from structure, depending on
Continuous video is constantly shown by a series of static images to being formed on screen or display in feel, this is a series of static
Image is video frame；During video capture, one section of video that camera is continuously uninterruptedly shot is known as camera lens, and camera lens is
The basic unit of video data, camera lens similar in several contents form a scene, they describe same from different angles
A event, and film is then made of many scenes, describes a complete story.
Data structure based on video can carry out cutting to video to be implanted in the following way, obtain in actual implementation
To multiple video slicings: carrying out shot cut detection to the video frame of video to be implanted, it is corresponding multiple to obtain video to be implanted
Camera lens；Cutting is carried out to video to be implanted based on a plurality of lenses, obtains the corresponding video slicing of each camera lens.
Here, shot cut detection is illustrated.In practical applications, shot cut detection can be cut using camera lens
The characteristic shown when changing finds the position to switch, thus entire Video segmentation at independent camera lens one by one.For example,
The shot cut detection to video to be detected can be realized in the following way: using inter-pixel point match method, being calculated to be detected
The diversity factor of the pixel of same position in the adjacent video frames of video determines in two adjacent video frames that diversity factor is more than the
The quantity of the pixel of one discrepancy threshold when reaching preset amount threshold, determines and Shot change occurs between two frame video frames.
Data structure based on video can also carry out cutting to video to be implanted in the following way in actual implementation,
It obtains multiple video slicings: scene change detection being carried out to the video frame of video to be implanted, it is corresponding more to obtain video to be implanted
A scene；Cutting is carried out to video to be implanted based on multiple scenes, obtains the corresponding video slicing of each scene.
Here, in practical applications, can realize the scene change detection to video to be detected in the following way: calculate to
The histogram difference degree for detecting the adjacent video frames of video, determines that histogram difference degree reaches two frame videos of the second discrepancy threshold
Occurrence scene switches between frame.
Step 302: server obtains the image to be implanted of the carrying pushed information in correspondent entity region.
In practical applications, pushed information can be advertisement, specifically, can be product placement, also known as Video-In,
It is a kind of soft advertising form, refers to that entity area in the video frame, such as desktop, metope, photo frame, bar desk and billboard implantation push away
It delivers letters breath.Fig. 5 is the frame image schematic diagram of the video before implantation pushed information provided in an embodiment of the present invention, and Fig. 6 is the present invention
The frame image schematic diagram of video after the implantation pushed information that embodiment provides, in conjunction with Fig. 5 and Fig. 6 it is found that in the video frame
Desktop area implants the icy bleak tea as pushed information.
In some embodiments, pushed information may include at least one of: push entity, push text；Wherein, it pushes away
Sending entity is the entity that showing advertisement is carried out in a manner of tangible physical form, such as has the coffee cup of specific shape；Push
Text is the text that the showing advertisement of specific content is carried out in the form of text, such as uses verbal description specific electronic equipment set
Function.
In actual implementation, different entity areas can correspond to different pushed informations or different entity areas
Corresponding identical pushed information.For example, can be carried on desktop including three-dimensional for the case where entity area is desktop and photo frame
The pushed information of model and poster form can carry the pushed information including poster form in photo frame；Here, poster is vision
One of form of expression of reception and registration is completely combined using elements such as picture, text, color, spaces, is opened up in a specified pattern
Show advertisement information.
Using the entity of identification as desktop, corresponding entity area be desktop area for be illustrated.In some embodiments
In, the corresponding pushed information of desktop area includes push entity, and for same push entity, there can be different presentation angles
The image to be implanted of degree can choose the figure to be implanted to match with the angle presentation of desktop for the different angle presentations of desktop
Picture.
In some embodiments, server can obtain in the following way the carrying pushed information in correspondent entity region to
Implantation image: obtaining the corresponding video identifier of video to be implanted, determines corresponding video to be implanted based on the video identifier of acquisition
The push entity of desktop area obtains first angle presentation of the push entity in image to be implanted；Obtaining entity area is in
Second angle presentation of real body；The image to be implanted that the first angle presentation and the second angle presentation match is determined, for correspondence
The image to be implanted of entity area.
Here, for pushing entity and be icy bleak tea, corresponding desktop area, there are multiple comprising icy bleak tea entity wait plant
Enter image, the angle presentation of icy bleak tea is different in different images to be implanted, and referring to Fig. 7, Fig. 7 is sieve provided in an embodiment of the present invention
The schematic diagram for selecting the image to be implanted of corresponding desktop area, in actual implementation, respectively to being pushed in desktop and image to be implanted
Entity carries out edge detection, then carries out straight line fitting to the lower edge of desktop and push entity respectively, is obtained based on fitting
Straight line determines the first angle presentation and the second angle presentation respectively, chooses and pushes entity corresponding first in multiple images to be implanted
The smallest image to be implanted of the difference of angle presentation and the second angle presentation, as the image to be implanted in correspondent entity region.
When pushed information includes threedimensional model and poster, in the same way, the first angle presentation of threedimensional model is obtained, determined
The threedimensional model and poster to match with the second angle presentation, referring to Fig. 8, Fig. 8 is determining presentation provided in an embodiment of the present invention
The schematic diagram of threedimensional model and poster that angle and desktop match.
Using the entity of identification as photo frame, metope or electronic equipment screen, corresponding entity area is phase frame region, metope area
It is illustrated for domain or electronic equipment screen region.In some embodiments, server can obtain correspondence in the following way
The image to be implanted of the carrying pushed information of entity area: obtaining the corresponding video identifier of video to be implanted, is based on video identifier
The image to be implanted for determining corresponding video to be implanted is at least one of: the image to be implanted of corresponding phase frame region, corresponding wall
The image to be implanted in face region and the image to be implanted in corresponding electronic equipment screen region.
Step 303: server using the entity area of frame image as background, using corresponding image to be implanted as prospect, in frame
The entity area of image is implanted into image to be implanted, obtains target frame image.
In practical applications, when frame image is the key frame directly extracted from video, for each key frame,
Server using the entity area of key frame images as background, using corresponding image to be implanted as prospect, in the reality of key frame images
The center of body region is implanted into image to be implanted, obtains target frame image.
In practical applications, when frame image is the key frame of video slicing, for each video slicing, server
Using the entity area of key frame images in video slicing as background, using corresponding image to be implanted as prospect, in key frame images
The center of entity area be implanted into image to be implanted, obtain target frame image.
By taking entity area is phase frame region and television screen as an example, referring to Fig. 9, Fig. 9 is provided in an embodiment of the present invention
It is implanted into the schematic diagram of image to be implanted in phase frame region, in Fig. 9, number 91 is the phase frame region before image to be implanted implantation,
Number 92 is the phase frame region after image to be implanted implantation.Referring to Figure 10, Figure 10 is provided in an embodiment of the present invention in television set
Screen area is implanted into the schematic diagram of image to be implanted, and in Figure 10, number 11 is the phase frame region before image to be implanted implantation, compiles
Numbers 12 be the phase frame region after image to be implanted implantation.
Step 304: server adjusts the image parameter of prospect in target frame image, so that the image parameter and background of prospect
Image parameter match.
In some embodiments, server can be directly based upon the background in target frame image, to prospect in target frame image
Image parameter be adjusted so that the image parameter of prospect and the image parameter of background match；In some embodiments, it takes
Business device can carry out image interception to target frame image, obtain the interception image comprising prospect, be then based on the background of interception image
(local background of target frame image), is adjusted the image parameter of prospect in interception image, so that the image parameter of prospect
Match with the image parameter of background；Wherein, the area of interception image is the constant times of the area of prospect, for example, being with prospect
Center, twice of foreground area is the size of interception image, is intercepted to target frame image.
To carry out image interception to target frame image, for obtaining the interception image comprising prospect, the image of prospect is joined
Several adjustment are illustrated.
In practical applications, image parameter includes at least one of: brightness, saturation degree, fuzziness and shadow length.
In some embodiments, image parameter includes brightness, can adjust prospect in target frame image in the following way
Image parameter, so that the image parameter of prospect and the image parameter of background match:
Obtain the prospect of interception image and the luminance difference of background；It converts the prospect of interception image to for tone-saturation degree-
Lightness HSV image；Based on luminance difference, brightness adjustment is carried out to the pixel of V figure layer in HSV image.Such as: calculate separately interception
The prospect of image and the average brightness of background calculate the luminance difference diff of the average brightness of prospect and the average brightness of backgroundv, will
It converts the prospect of interception image to for HSV image, completion then is carried out to each pixel of V figure layer in HSV image
diffv* the brightness harmonization of prospect and background is completed in 0.8 operation.
In some embodiments, image parameter includes saturation degree, can adjust prospect in target frame image in the following way
Image parameter so that the image parameter of prospect and the image parameter of background match:
The saturation degree of the prospect and background that obtain interception image is poor；HSV image is converted by the prospect of interception image；It is based on
Saturation degree is poor, carries out saturation degree adjustment to the pixel of S figure layer in HSV image.Such as: calculate separately the prospect of interception image with
The average staturation of background calculates the luminance difference diff of the average staturation of prospect and the average staturation of backgrounds, will will intercept
The prospect of image is converted into as HSV image, then carries out completion diff to each pixel of S figure layer in HS V images*0.8
Operation, complete the saturation degree harmonization of prospect and background.
In some embodiments, image parameter includes fuzziness, can adjust prospect in target frame image in the following way
Image parameter so that the image parameter of prospect and the image parameter of background match:
Laplace transform is carried out to the prospect of interception image and background respectively, and determines standard deviation based on transformation results；
When standard deviation reaches standard deviation threshold method, Gaussian Blur processing is carried out to the prospect of interception image, so that the interception image
The fuzziness of prospect and background matches.In practical applications, standard deviation threshold method can be set according to actual needs, for example,
Established standards difference threshold value is 1.4, when the standard deviation being calculated is more than 1.4, shows the mould of prospect and background in interception image
Paste degree is there are dramatically different,, therefore, can be directly right caused by background blurring this is because when large aperture and focal length cooperation photography
Prospect carries out Gaussian Blur operation, and the fuzziness of prospect and background are evened up.
In some embodiments, image parameter includes shadow length, before can adjusting in the following way in target frame image
The image parameter of scape, so that the image parameter of prospect and the image parameter of background match:
Shadow Detection is carried out to the prospect of interception image and background respectively, determines the prospect of interception image and the shade of background
Length ratio；When shadow length ratio is not within the scope of preset ratio, the shadow length of the prospect of interception image is adjusted, is made
The shadow length ratio of the prospect and background that obtain interception image is within the scope of preset ratio.In practical applications, proportional region
Size can be set according to actual needs, such as preset ratio range be [0.2,0.8], when the prospect and back of interception image
The shadow length ratio of scape is 0.1, when being not in [0.2,0.8] range, adjusts the shadow length of the prospect of interception image, such as
The shadow length ratio of the prospect and background that adjust interception image according to default value is 0.5；When the prospect and background of interception image
Shadow length ratio be 0.6, shadow length ratio is not adjusted.
In some embodiments, when image parameter includes brightness, saturation degree, fuzziness and shadow length, interception is schemed
The brightness of prospect, saturation degree, the adjustment sequence of fuzziness and shadow length are not construed as limiting as in, and Figure 11 mentions for the embodiment of the present invention
The schematic diagram that the image parameter of prospect in interception image is adjusted supplied, referring to Figure 11, successively to before in interception image
Scape carries out the adjustment of brightness, saturation degree, fuzziness and shadow length.
In actual implementation, after being adjusted to the image parameter figure of prospect in interception image, need adjusted section
Image is taken to be returned to original position, the target frame image after being adjusted.Figure 12 is carry out image parameter provided in an embodiment of the present invention
The schematic diagram of target frame image after adjusting, referring to Figure 12, number 21 be user be implanted into manually carry pushed information be milk tea
The effect diagram of image to be implanted, number 22 are that the implantation of above scheme of the embodiment of the present invention is used to carry pushed information as milk tea
Image to be implanted effect diagram, can significantly find out, using above scheme of the embodiment of the present invention be implanted into prospect (milk
Tea image) with the harmonious Du Genggao of background (video frame images).
Step 305: server is based on target frame image adjusted and carries out Video Composition, obtains target video.
In some embodiments, in the case where carrying out cutting to video to be implanted, target frame image adjusted includes
The target frame image adjusted of corresponding each video slicing obtains mesh correspondingly, Video Composition can be carried out in the following way
Mark video: it is based respectively on target frame image progress Video coding adjusted in each video slicing, obtains corresponding to each video slicing
Target video fragment；The target video fragment of each video slicing of correspondence is merged, target video is obtained.
In some embodiments, the frame image for carrying out Entity recognition is the key frame images of video to be implanted, correspondingly, can
Video Composition is carried out in the following way, obtains target video: the non-pass of video to be implanted is positioned by way of target tracking
The entity area of key frame image；By way of affine transformation, in the entity area of non-key frame image, it is implanted into adjusted
Prospect in target frame image obtains target non-key frame image；To target frame image adjusted and target non-key frame figure
As carrying out Video coding, target video is obtained.
In some embodiments, target video is also sent to terminal after obtaining target video by server, so that terminal
Play the target video for being implanted with pushed information.
Continue to be illustrated the method for being implanted into pushed information in video provided in an embodiment of the present invention.Figure 13 is the present invention
The method flow schematic diagram of pushed information, referring to Figure 13, view provided in an embodiment of the present invention are implanted into the video that embodiment provides
The method of implantation pushed information includes: in frequency
Step 401: server inquires the video identifier of video to be implanted, and is obtained based on the video identifier of video to be implanted
Video to be implanted.
In practical applications, it is provided with video library to be implanted, for storing multiple views to be implanted of pushed information to be implanted
Frequently, server can inquire the video identifier of video to be implanted to be treated based on the sequencing that video library to be implanted is added,
The video identifier of video to be implanted can be the video ID of video to be implanted, and the video ID based on video to be implanted obtains to be implanted
Video obtains the video file of video to be implanted.
Step 402: cutting processing being carried out to video to be implanted, obtains multiple video slicings.
Here, in actual implementation, the cutting to video to be implanted can be realized in the following way:
Shot cut detection is carried out to the video frame of video to be implanted, obtains the corresponding a plurality of lenses of video to be implanted, base
In obtained a plurality of lenses, cutting is carried out to video to be implanted, obtains the corresponding video slicing of each camera lens.
Step 403: Entity recognition being carried out to each video slicing respectively, is determined real in the key frame images of each video slicing
The corresponding entity area of body.
Here, it by taking entity includes desktop, metope and photo frame as an example, detects a video slicing respectively by Entity recognition and is wrapped
Desktop, metope and the photo frame for including in the frame image included, and determine corresponding desktop area, wall section and phase frame region.?
It, can be real to be carried out to key frame images included by video slicing for the Entity recognition of each video slicing when actual implementation
Body identification.
Step 404: obtaining the image to be implanted of the carrying pushed information of corresponding each entity area respectively.
Here, in practical applications, there is the image library to be implanted of corresponding video to be implanted, different videos to be implanted can
With the different image library to be implanted of correspondence, multiple images to be implanted are stored in image library to be implanted, different entity areas can
With the different image to be implanted of correspondence.
Illustratively, corresponding image library to be implanted, the image library to be implanted are determined according to the video ID of video to be implanted
In be stored with carry pushed information be automobile image to be implanted, carry pushed information be milk tea image to be implanted, carry push away
Breath of delivering letters is the image to be implanted etc. of plain chocolate, determines that the corresponding image to be implanted of wall section is carrying in the video to be implanted
Pushed information be automobile image to be implanted, determine the corresponding image to be implanted of desktop area be carry pushed information be plain chocolate
Image to be implanted.
In some embodiments, the case where being desktop area for entity area, since the angle presentation of desktop is different, it is
The harmonious Du Genggao for making the push entity and desktop that are implanted into desktop area, needs to choose the presentation angle of push entity (automobile)
The image to be implanted that the angle presentation of degree and desktop matches.Specific mode of choosing is no longer superfluous herein referring to previous embodiment
It states.
Step 405: using the corresponding entity area of entity in key frame images as background, with the to be implanted of correspondent entity region
Image is prospect, is implanted into corresponding image to be implanted in the entity area of key frame images, obtains target frame image.
Step 406: image interception being carried out to the target frame image of each video slicing respectively, obtains the interception figure comprising prospect
Picture.
Here, in actual implementation, image interception can be carried out in the following way: with the minimum square comprising image to be implanted
Shape frame is boundary, and the area that equal proportion extends to rectangle frame is the constant times of image area to be implanted, obtains the square comprising prospect
Shape interception image.It is boundary with the minimum rectangle frame 02 comprising image 01 to be implanted, equal proportion extends to rectangle frame referring to Figure 11
Area be 2 times of image area to be implanted, obtain the rectangle interception image 03 comprising prospect (image 01 to be implanted).It needs
It is bright, the shape embodiment of the present invention of interception image is not construed as limiting, such as can also include the smallest circle of image to be implanted
Shape frame is boundary, and the area that equal proportion extends to circular frame is the constant times of image area to be implanted, obtains the circle comprising prospect
Shape interception image.
Step 407: brightness, saturation degree, fuzziness, shadow length are respectively successively carried out to the prospect in each interception image
Adjustment, so that the prospect of interception image matches with background.
Here, before to the brightness of prospect, saturation degree, fuzziness, the adjustment process of shadow length can be found in interception image
Record is stated, details are not described herein again.
Step 408: the interception image adjusted will be carried out and playbacked respectively to corresponding target frame image.
Here, by the target frame image co-registration after being implanted into frame by frame at video slicing, and the sound in upper original video fragment is merged
Frequency information completes the fusion of entire video slicing.
Step 409: Video coding being carried out based on the target frame image after the corresponding playback of each video slicing, is obtained pair
Answer the target video fragment of each video slicing.
Step 410: the target video fragment of each video slicing of correspondence being merged, target video is obtained.
Using the above embodiment of the present invention, using the entity area of the frame image of video to be implanted as background, with it is corresponding to
Implantation image is prospect, is implanted into image to be implanted in the entity area of frame image, obtains target frame image, realize pushed information
In the automatic implantation of video to be implanted, the implantation efficiency of pushed information is improved；By adjusting the figure of prospect in target frame image
As parameter, so that the image parameter of prospect and the image parameter of background match, after realizing implantation pushed information, video frame figure
Prospect and the automatic harmonization of background are handled as in so that in target video pushed information and video content harmonization, significantly
User is promoted when watching video to the receiving degree of pushed information.
Next the embodiment of the present invention is mentioned for advertisement, by taking product placement on the desktop in video as an example by pushed information
The method that pushed information is implanted into the video of confession is illustrated.Figure 14 is implantation push letter in video provided in an embodiment of the present invention
The method flow schematic diagram of breath, referring to Figure 14, in video provided in an embodiment of the present invention be implanted into pushed information method include with
Lower key step:
Step 1: the input of complete video material
Here, in actual implementation, the video ID of video to be implanted, and the view obtained according to inquiry can be inquired from server
Frequency ID requests corresponding video source file.
Step 2: monoscopic video fragment
Here, in actual implementation, shot cut detection is carried out to video to be implanted, and by the video source of video to be implanted
File declustering at each camera lens of correspondence video slicing.
Step 3: multi-modal video product placement position detection algorithm
Video can be regarded as a series of data flow of upper complementary picture frame composition of times.Typically, it is regarding
When frequency plot and content changes, it may appear that Shot change is transferred to another camera lens content from a camera lens content.Video
Implication has vision, the sense of hearing and caption information abundant, these low-level image features can be color, texture, shape, tone and text
Deng, using multimode analysis method, i.e., simultaneously handled using two kinds or two or more modal informations, to realize video
Data analysis.
In practical applications, in the first key frame images of video slicing, the region of given ad position, this region can
It is based on multi-modal video product placement position detection algorithm to be provided in such a way that, directly with the advertisement position frame to be selected of output
Trace regions as background；Alternatively, rule of thumb setting trace regions.
Step 4: Desktop-scene material object direction selection
Here, in actual implementation, using automatic direction selection technology in kind, from magnanimity prospect advertisement material object picture certainly
It is dynamic to filter out towards angle and the highest picture of background harmony degree, complete implantation；For example, by prospect material object and background table
Face carries out edge detection, and chooses and meet the prospect material object of preset condition as to be implanted with the edge line slope differences of background desktop
Object.
Step 5: prospect rendering
For the foreground picture (such as in kind, three-dimensional stage property or poster) of desktop area to be implanted into, saturation degree, brightness, mould
Paste degree etc. differs larger with background, using the local background of prospect implanted region as template, to the brightness of prospect, saturation degree, mould
Paste degree and the long depth of inverted image (i.e. shadow length) are adjusted, and realize the visual sense harmonization of front and back scape after the implantation.
It specifically, can be by operating the adjustment realized to image parameters such as the saturation degree of prospect, brightness, fuzzinesses as follows:
1), local background demarcates
In actual implementation, it will be implanted into prospect (advertising pictures, i.e., image to be implanted), be implanted into the key frame figure of video slicing
Desktop-centric region as in, to be implanted into the external surrounding frame of prospect as boundary, equal proportion extends to twice of implantation foreground area, with
Size after extension carries out image interception, and to determine local background, local background is as subsequent adaptive prospect parameter adjustment
Data parameters demarcate acquisition source.
2), adaption brightness adjusts
The average brightness of implantation prospect and local background is calculated, luminance difference diff is calculatedv, HSV is converted by foreground picture
Figure carries out completion diff to each pixel of the 3rd layer of V figure layerv* the brightness harmonization of front and back scape is completed in 0.8 operation.
3), adaptive saturation adjusts
The average staturation of implantation prospect and local background is calculated, saturation degree difference diff is calculateds, and foreground picture is converted
For HSV figure, completion diff is carried out to each pixel of the 2nd layer of S figure layers* 0.8 operation, complete front and back scape saturation degree and
Humorousization.
4), adaptive fuzzy degree adjusts
Laplacian is done to front and back scape respectively and converts and calculate standard deviation, if standard deviation differs by more than 1.4, before explanation
The fog-level of background is dramatically different, this is because when large aperture and focal length cooperation photography, caused by background blurring, therefore, directly
It connects and Gaussian Blur operation is carried out to prospect, the fuzziness of prospect and background are evened up.
5), the long depth adjustment of adaptive inverted image
It is detected using shade of the BDRAR algorithm to background, according to the shade ratio of preset prospect and background, to preceding
Scape increase the operation of shade.
Step 6: the tracking of tabletop advertisement position and implantation
Based on motion tracking technology, advertisement position is tracked, and by affine change technique, before previous step output
Scape is implanted into video.
Step 7: video slicing fusion
The video slicing fusion of advertisement implantation will be completed, forms new complete video.
Using the above embodiment of the present invention, realize automatic product placement in video and advertisement implantation after be used as before
The advertisement of scape with as background video content harmonization, save human cost spending, while relative to before manually into
The case where row prospect renders, operation duration were fallen to 30 seconds from 20 minutes, saved time cost.
Using the above embodiment of the present invention, for advertiser, had using the form of product placement in video
Advantage is as shown in figure 15, is shown according to advertisement marketing trend report in 2018, " 73% advertiser will increase and maintain implantation etc.
The spending of soft advertising ".Relative to conventional ads, it has, and touching is high up to rate, Cooperation Risk is small and saves the advantages such as budget.Especially exist
The growth in the period that member (video VIP) expands energetically, traditional preceding patch and middle bumper advertisements flow is restricted.It is this
Based on later period technology, the soft advertisement form by member touching up to limitation does not seem more significant.Meanwhile compared to traditional trick
The advertisement (just needing to bring to a conclusion advertisement implantation before variety and TV play shooting) of quotient's form, it is acute to have that advertiser gambles.Have
Product placement technology, advertiser can be according to the pouplarities of collection of drama and variety, and later period product placement, is reduced in video
The risk of advertising input.
Using the above embodiment of the present invention, for flow side, Figure 16 is to plant in video provided in an embodiment of the present invention
The year provisional profit schematic diagram for entering advertisement makes the plan of acute (variety and TV play) by oneself according to video platform referring to Figure 16, deduces
The ad traffic increased newly by Video-In (product placement) mode is gone out.Form is sold based on this flow and contract advertisement,
About 3,600,000,000 yuan of market scale can be deduced out.As it can be seen that the gradually receiving with market to Video-In advertisement form, this wide
Announcement form can become the important profit growth point of video platform.
Continue to the device row explanation for being implanted into pushed information in video provided in an embodiment of the present invention.Figure 17 is that the present invention is real
Apply the structural schematic diagram that the device of pushed information is provided in the video of example offer, referring to Figure 17, view provided in an embodiment of the present invention
The device 170 of implantation pushed information includes: in frequency
Recognition unit 171 carries out Entity recognition for the frame image to video to be implanted, determines described in the frame image
The corresponding entity area of entity；
Acquiring unit 172, the image to be implanted of the carrying pushed information for obtaining the corresponding entity area；
It is implanted into unit 173, for being as background, with the corresponding image to be implanted using the entity area of the frame image
Prospect is implanted into the image to be implanted in the entity area of the frame image, obtains target frame image；
Adjustment unit 174, for adjusting the image parameter of prospect described in the target frame image, so that the prospect
The image parameter of image parameter and the background matches；
Synthesis unit 175 obtains target video for carrying out Video Composition based on target frame image adjusted.
In some embodiments, the recognition unit is also used to carry out cutting processing to the video to be implanted, obtain more
A video slicing；
Entity recognition is carried out to the multiple video slicing respectively, is determined real described in the frame image of each video slicing
The corresponding entity area of body.
In some embodiments, the recognition unit is also used to carry out camera lens to the video frame of the video to be implanted to cut
Detection is changed, the corresponding a plurality of lenses of the video to be implanted are obtained；
Cutting is carried out to the video to be implanted based on the multiple camera lens, obtains the corresponding video point of each camera lens
Piece.
In some embodiments, the synthesis unit is also used to be based respectively on mesh adjusted in each video slicing
It marks frame image and carries out Video coding, obtain the target video fragment for corresponding to each video slicing；
The target video fragment of each video slicing of correspondence is merged, the target video is obtained.
In some embodiments, the acquiring unit is also used in response to, comprising push entity, obtaining in the pushed information
Take first angle presentation of the push entity in image to be implanted；
Obtain the second angle presentation of the presented entity of the entity area；
The image to be implanted that first angle presentation and second angle presentation match is determined, for the correspondence reality
The image to be implanted of body region.
In some embodiments, described device further include:
Interception unit, for obtaining the interception image comprising the prospect to target frame image progress image interception,
The area of the interception image is the constant times of the area of the prospect.
In some embodiments, the adjustment unit is also used to include brightness in response to described image parameter, described in acquisition
The prospect of interception image and the luminance difference of background；
It converts the prospect of the interception image to for tone-saturation degree-lightness HSV image；
Based on the luminance difference, brightness adjustment is carried out to the pixel of V figure layer in the HSV image.
In some embodiments, the adjustment unit is also used in response to described image parameter include saturation degree, obtains institute
The saturation degree of the prospect and background of stating interception image is poor；
HSV image is converted by the prospect of the interception image；
It is poor based on the saturation degree, saturation degree adjustment is carried out to the pixel of S figure layer in the HSV image.
In some embodiments, the adjustment unit is also used in response to described image parameter include fuzziness, right respectively
The prospect and background of the interception image carry out Laplace transform, and determine standard deviation based on transformation results；
When the standard deviation reaches standard deviation threshold method, Gaussian Blur processing is carried out to the prospect of the interception image, is made
The fuzziness of the prospect and background that obtain the interception image matches.
In some embodiments, the adjustment unit is also used in response to described image parameter include shadow length, respectively
Prospect and background to the interception image carry out shadow Detection, determine the prospect of the interception image and the shadow length of background
Ratio；
When the shadow length ratio is not within the scope of preset ratio, the shade of the prospect of the interception image is adjusted
Length, so that the shadow length ratio of the prospect of the interception image and background is within the scope of preset ratio.
In some embodiments, the synthesis unit is also used in response to the frame image be the video to be implanted
Key frame images position the entity area of the non-key frame image of the video to be implanted by way of target tracking；
By way of affine transformation, in the entity area of the non-key frame image, it is implanted into the mesh adjusted
The prospect in frame image is marked, target non-key frame image is obtained；
Video coding is carried out to the target frame image adjusted and the target non-key frame image, obtains the mesh
Mark video.
It need to be noted that: above is referred to the description of device, be with above method description it is similar, with having for method
Beneficial effect description, does not repeat them here, for undisclosed technical detail in described device of the embodiment of the present invention, please refers to present invention side
The description of method embodiment.
The embodiment of the invention also provides a kind of electronic equipment, the electronic equipment includes:
Memory, for storing executable program；
Processor when for executing the executable program stored in the memory, is realized provided in an embodiment of the present invention
The method of pushed information is implanted into above-mentioned video.
The embodiment of the present invention also provides a kind of storage medium for being stored with executable instruction, wherein being stored with executable finger
It enables, when executable instruction is executed by processor, processor will be caused to execute to be implanted into video provided in an embodiment of the present invention and push away
It delivers letters the method for breath.
This can be accomplished by hardware associated with program instructions for all or part of the steps of embodiment, and program above-mentioned can be with
It is stored in a computer readable storage medium, which when being executed, executes step including the steps of the foregoing method embodiments；And
Storage medium above-mentioned includes: movable storage device, random access memory (RAM, Random Access Memory), read-only
The various media that can store program code such as memory (ROM, Read-Only Memory), magnetic or disk.
If alternatively, the above-mentioned integrated unit of the present invention is realized in the form of software function module and as independent product
When selling or using, it also can store in a computer readable storage medium.Based on this understanding, the present invention is implemented
The technical solution of example substantially in other words can be embodied in the form of software products the part that the relevant technologies contribute,
The computer software product is stored in a storage medium, including some instructions are used so that computer equipment (can be with
It is personal computer, server or network equipment etc.) execute all or part of each embodiment the method for the present invention.
And storage medium above-mentioned includes: that movable storage device, RAM, ROM, magnetic or disk etc. are various can store program code
Medium.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (15)
1. being implanted into the method for pushed information in a kind of video, which is characterized in that the described method includes:
Entity recognition is carried out to the frame image of video to be implanted, determines the corresponding entity area of entity described in the frame image；
Obtain the image to be implanted of the carrying pushed information of the corresponding entity area；
Using the entity area of the frame image as background, using the corresponding image to be implanted as prospect, in the frame image
Entity area is implanted into the image to be implanted, obtains target frame image；
The image parameter of prospect described in the target frame image is adjusted, so that the image parameter of the prospect and the background
Image parameter matches；
Video Composition is carried out based on target frame image adjusted, obtains target video.
2. the method as described in claim 1, which is characterized in that the frame image to video to be implanted carries out Entity recognition,
Determine the corresponding entity area of entity described in the frame image, comprising:
Cutting processing is carried out to the video to be implanted, obtains multiple video slicings；
Entity recognition is carried out to the multiple video slicing respectively, determines entity pair described in the frame image of each video slicing
The entity area answered.
3. method according to claim 2, which is characterized in that it is described that cutting processing is carried out to the video to be implanted, it obtains
Multiple video slicings, comprising:
Shot cut detection is carried out to the video frame of the video to be implanted, obtains the corresponding multiple mirrors of the video to be implanted
Head；
Cutting is carried out to the video to be implanted based on the multiple camera lens, obtains the corresponding video slicing of each camera lens.
4. method according to claim 2, which is characterized in that described to carry out video conjunction based on target frame image adjusted
At obtaining target video, comprising:
It is based respectively on target frame image progress Video coding adjusted in each video slicing, obtains corresponding to each video
The target video fragment of fragment；
The target video fragment of each video slicing of correspondence is merged, the target video is obtained.
5. the method as described in claim 1, which is characterized in that the carrying pushed information for obtaining the corresponding entity area
Image to be implanted, comprising:
In response to, comprising push entity, obtaining first presentation of the push entity in image to be implanted in the pushed information
Angle；
Obtain the second angle presentation of the presented entity of the entity area；
The image to be implanted that first angle presentation and second angle presentation match is determined, for the correspondence entity area
The image to be implanted in domain.
6. the method as described in claim 1, which is characterized in that the method also includes:
Image interception is carried out to the target frame image, obtains the interception image comprising the prospect, the face of the interception image
Product is the constant times of the area of the prospect.
7. method as claimed in claim 6, which is characterized in that the image of prospect described in the adjustment target frame image
Parameter, so that the image parameter of the image parameter of the prospect and the background matches, comprising:
Include brightness in response to described image parameter, obtains the prospect of the interception image and the luminance difference of background；
It converts the prospect of the interception image to for tone-saturation degree-lightness HSV image；
Based on the luminance difference, brightness adjustment is carried out to the pixel of V figure layer in the HSV image.
8. method as claimed in claim 6, which is characterized in that the image of prospect described in the adjustment target frame image
Parameter, so that the image parameter of the image parameter of the prospect and the background matches, comprising:
It include saturation degree in response to described image parameter, the saturation degree of the prospect and background that obtain the interception image is poor；
HSV image is converted by the prospect of the interception image；
It is poor based on the saturation degree, saturation degree adjustment is carried out to the pixel of S figure layer in the HSV image.
9. method as claimed in claim 6, which is characterized in that the image of prospect described in the adjustment target frame image
Parameter, so that the image parameter of the image parameter of the prospect and the background matches, comprising:
Include fuzziness in response to described image parameter, Laplce's change is carried out to the prospect of the interception image and background respectively
It changes, and determines standard deviation based on transformation results；
When the standard deviation reaches standard deviation threshold method, Gaussian Blur processing is carried out to the prospect of the interception image, so that institute
The fuzziness of the prospect and background of stating interception image matches.
10. method as claimed in claim 6, which is characterized in that the figure of prospect described in the adjustment target frame image
As parameter, so that the image parameter of the image parameter of the prospect and the background matches, comprising:
Include shadow length in response to described image parameter, shade inspection is carried out to the prospect of the interception image and background respectively
It surveys, determines the prospect of the interception image and the shadow length ratio of background；
When the shadow length ratio is not within the scope of preset ratio, the shade for adjusting the prospect of the interception image is long
Degree, so that the shadow length ratio of the prospect of the interception image and background is within the scope of preset ratio.
11. the method as described in claim 1, which is characterized in that described to carry out video conjunction based on target frame image adjusted
At obtaining target video, comprising:
Be the key frame images of the video to be implanted in response to the frame image, positioned by way of target tracking it is described to
It is implanted into the entity area of the non-key frame image of video；
By way of affine transformation, in the entity area of the non-key frame image, it is implanted into the target frame adjusted
Prospect in image obtains target non-key frame image；
Video coding is carried out to the target frame image adjusted and the target non-key frame image, obtains the target view
Frequently.
12. being implanted into the device of pushed information in a kind of video, which is characterized in that described device includes:
Recognition unit carries out Entity recognition for the frame image to video to be implanted, determines entity pair described in the frame image
The entity area answered；
Acquiring unit, the image to be implanted of the carrying pushed information for obtaining the corresponding entity area；
Be implanted into unit, for using the entity area of the frame image as background, using the corresponding image to be implanted as prospect,
The entity area of the frame image is implanted into the image to be implanted, obtains target frame image；
Adjustment unit, for adjusting the image parameter of prospect described in the target frame image, so that the image of the prospect is joined
Several and the background image parameter matches；
Synthesis unit obtains target video for carrying out Video Composition based on target frame image adjusted.
13. device as claimed in claim 12, which is characterized in that
The recognition unit is also used to carry out cutting processing to the video to be implanted, obtains multiple video slicings；
Entity recognition is carried out to the multiple video slicing respectively, determines entity pair described in the frame image of each video slicing
The entity area answered.
14. a kind of electronic equipment, which is characterized in that the electronic equipment includes:
Memory, for storing executable instruction；
Processor when for executing the executable instruction stored in the memory, realizes any one of claims 1 to 11 institute
The method of pushed information is implanted into the video stated.
15. a kind of storage medium, which is characterized in that the storage medium is stored with executable instruction, for causing processor to be held
When row, the method that pushed information is implanted into video described in any one of claims 1 to 11 is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910704475.1A CN110300316B (en) | 2019-07-31 | 2019-07-31 | Method and device for implanting push information into video, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910704475.1A CN110300316B (en) | 2019-07-31 | 2019-07-31 | Method and device for implanting push information into video, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110300316A true CN110300316A (en) | 2019-10-01 |
| CN110300316B CN110300316B (en) | 2022-02-11 |
Family
ID=68032437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910704475.1A Active CN110300316B (en) | 2019-07-31 | 2019-07-31 | Method and device for implanting push information into video, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110300316B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111182335A (en) * | 2019-10-18 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Streaming media processing method and device |
| CN111246315A (en) * | 2020-01-21 | 2020-06-05 | 咪咕视讯科技有限公司 | Video interaction method, system, edge node, client and storage medium |
| CN111988657A (en) * | 2020-08-05 | 2020-11-24 | 网宿科技股份有限公司 | Advertisement insertion method and device |
| CN112860944A (en) * | 2021-02-05 | 2021-05-28 | 北京百度网讯科技有限公司 | Video rendering method, device, equipment, storage medium and computer program product |
| CN113225587A (en) * | 2020-02-06 | 2021-08-06 | 阿里巴巴集团控股有限公司 | Video processing method, video processing device and electronic equipment |
| CN113489919A (en) * | 2021-06-21 | 2021-10-08 | 北京德风新征程科技有限公司 | Digital video production system based on internet big data |
| US20210352343A1 (en) * | 2019-06-27 | 2021-11-11 | Tencent Technology (Shenzhen) Company Limited | Information insertion method, apparatus, and device, and computer storage medium |
| CN114760517A (en) * | 2022-04-15 | 2022-07-15 | 广州华多网络科技有限公司 | Image activity embedding method and device, equipment, medium and product thereof |
| WO2023065961A1 (en) * | 2021-10-21 | 2023-04-27 | 星河视效科技(北京)有限公司 | Video implantation method and apparatus, device, and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130188833A1 (en) * | 2007-09-04 | 2013-07-25 | Objectvideo, Inc. | Stationary target detection by exploiting changes in background model |
| CN103607554A (en) * | 2013-10-21 | 2014-02-26 | 无锡易视腾科技有限公司 | Fully-automatic face seamless synthesis-based video synthesis method |
| CN104170392A (en) * | 2013-11-21 | 2014-11-26 | 华为技术有限公司 | Method, device, system and terminal of inplanting advertisements in files |
| CN104700354A (en) * | 2015-03-31 | 2015-06-10 | 北京奇艺世纪科技有限公司 | Information embedding method and device |
| CN104766229A (en) * | 2015-04-22 | 2015-07-08 | 合一信息技术（北京）有限公司 | Implantable advertisement putting method |
| CN106991641A (en) * | 2017-03-10 | 2017-07-28 | 北京小米移动软件有限公司 | It is implanted into the method and device of picture |
-
2019
- 2019-07-31 CN CN201910704475.1A patent/CN110300316B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130188833A1 (en) * | 2007-09-04 | 2013-07-25 | Objectvideo, Inc. | Stationary target detection by exploiting changes in background model |
| CN103607554A (en) * | 2013-10-21 | 2014-02-26 | 无锡易视腾科技有限公司 | Fully-automatic face seamless synthesis-based video synthesis method |
| CN104170392A (en) * | 2013-11-21 | 2014-11-26 | 华为技术有限公司 | Method, device, system and terminal of inplanting advertisements in files |
| CN104700354A (en) * | 2015-03-31 | 2015-06-10 | 北京奇艺世纪科技有限公司 | Information embedding method and device |
| CN104766229A (en) * | 2015-04-22 | 2015-07-08 | 合一信息技术（北京）有限公司 | Implantable advertisement putting method |
| CN106991641A (en) * | 2017-03-10 | 2017-07-28 | 北京小米移动软件有限公司 | It is implanted into the method and device of picture |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210352343A1 (en) * | 2019-06-27 | 2021-11-11 | Tencent Technology (Shenzhen) Company Limited | Information insertion method, apparatus, and device, and computer storage medium |
| US11854238B2 (en) * | 2019-06-27 | 2023-12-26 | Tencent Technology (Shenzhen) Company Limited | Information insertion method, apparatus, and device, and computer storage medium |
| CN111182335B (en) * | 2019-10-18 | 2021-08-20 | 腾讯科技（深圳）有限公司 | Streaming media processing method, device, equipment and computer readable storage medium |
| CN111182335A (en) * | 2019-10-18 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Streaming media processing method and device |
| CN111246315A (en) * | 2020-01-21 | 2020-06-05 | 咪咕视讯科技有限公司 | Video interaction method, system, edge node, client and storage medium |
| CN111246315B (en) * | 2020-01-21 | 2022-06-03 | 咪咕视讯科技有限公司 | Video interaction method, system, edge node, client and storage medium |
| CN113225587A (en) * | 2020-02-06 | 2021-08-06 | 阿里巴巴集团控股有限公司 | Video processing method, video processing device and electronic equipment |
| CN111988657A (en) * | 2020-08-05 | 2020-11-24 | 网宿科技股份有限公司 | Advertisement insertion method and device |
| CN112860944B (en) * | 2021-02-05 | 2023-07-25 | 北京百度网讯科技有限公司 | Video rendering method, apparatus, device, storage medium, and computer program product |
| CN112860944A (en) * | 2021-02-05 | 2021-05-28 | 北京百度网讯科技有限公司 | Video rendering method, device, equipment, storage medium and computer program product |
| CN113489919A (en) * | 2021-06-21 | 2021-10-08 | 北京德风新征程科技有限公司 | Digital video production system based on internet big data |
| WO2023065961A1 (en) * | 2021-10-21 | 2023-04-27 | 星河视效科技(北京)有限公司 | Video implantation method and apparatus, device, and computer readable storage medium |
| CN114760517A (en) * | 2022-04-15 | 2022-07-15 | 广州华多网络科技有限公司 | Image activity embedding method and device, equipment, medium and product thereof |
| CN114760517B (en) * | 2022-04-15 | 2024-02-02 | 广州华多网络科技有限公司 | Image moving embedding method and device, equipment, medium and product thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110300316B (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110300316A (en) | Method, apparatus, electronic equipment and the storage medium of pushed information are implanted into video | |
| US11019283B2 (en) | Augmenting detected regions in image or video data | |
| US9038100B2 (en) | Dynamic insertion of cinematic stage props in program content | |
| US8549554B2 (en) | Dynamic replacement of cinematic stage props in program content | |
| CN105472434B (en) | It is implanted into method and system of the content into video display | |
| US11334779B1 (en) | Dynamic embedding of machine-readable codes within video and digital media | |
| WO2021012837A1 (en) | Method and apparatus for determining recommendation information implantation position, device and storage medium | |
| US20160050465A1 (en) | Dynamically targeted ad augmentation in video | |
| RU2460233C2 (en) | System of inserting video online | |
| US7689062B2 (en) | System and method for virtual content placement | |
| EP2523192B1 (en) | Dynamic replacement of cinematic stage props in program content | |
| CN104066003B (en) | Method and device for playing advertisement in video | |
| JP6672305B2 (en) | Method and apparatus for generating extrapolated images based on object detection | |
| CN111556336B (en) | Multimedia file processing method, device, terminal equipment and medium | |
| KR20190075177A (en) | Context-based augmented ad | |
| CN108605119B (en) | 2D to 3D video frame conversion | |
| CN110458820A (en) | A kind of multimedia messages method for implantation, device, equipment and storage medium | |
| CN109982141B (en) | Method for analyzing video image area and implanting advertisement by using AI technology | |
| CN110213629B (en) | Information implantation method, device, server and storage medium | |
| CN110663044A (en) | Method and apparatus for providing product placement | |
| JP2004304791A (en) | Method and apparatus for modifying digital cinema frame content | |
| CN112312195A (en) | Method and device for implanting multimedia information into video, computer equipment and storage medium | |
| CN116308530A (en) | Advertisement implantation method, advertisement implantation device, advertisement implantation equipment and readable storage medium | |
| CN112840377A (en) | System and method for enhancing a live audience experience on an electronic device | |
| CN116761037B (en) | Method, device, equipment and medium for video implantation of multimedia information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |