CN106412720A - Method and device of removing video watermarks - Google Patents
Method and device of removing video watermarks Download PDFInfo
- Publication number
- CN106412720A CN106412720A CN201510447572.9A CN201510447572A CN106412720A CN 106412720 A CN106412720 A CN 106412720A CN 201510447572 A CN201510447572 A CN 201510447572A CN 106412720 A CN106412720 A CN 106412720A
- Authority
- CN
- China
- Prior art keywords
- pixel
- watermark
- current spatial
- piecemeal
- video
- 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 28
- 230000001143 conditioned effect Effects 0.000 claims description 8
- 230000000903 blocking effect Effects 0.000 claims description 2
- 238000005192 partition Methods 0.000 abstract 1
- 238000000638 solvent extraction Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 8
- 238000000205 computational method Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009885 systemic 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]
- H04N21/80—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
- H04N21/835—Generation of protective data, e.g. certificates
- H04N21/8358—Generation of protective data, e.g. certificates involving watermark
-
- 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The present invention relates to a method of removing video watermarks. The method comprises the steps of when a video is played, obtaining a watermark range area in the video; adjusting the watermark range area to enable the watermark range area to satisfy a preset condition; obtaining the video frames of the video, and according to the pixel values of the pixel points at the same positions of the video frames, identifying to obtain the watermark removing areas; partitioning the adjusted watermark range area in the YUV spaces separately according to the preset pixel lengths and widths, and carrying out the in-frame prediction on the watermark removing area in each partition in the YUV spaces separately to obtain the prediction pixel values; replacing the original pixel values of the watermark removing areas in the YUV spaces as the corresponding prediction pixel values, thereby being able to remove the watermarks when the video is played. In addition, the present invention also provides a device of removing video watermarks.
Description
Technical field
The present invention relates to field of computer technology, the method and apparatus that more particularly to a kind of video watermark removes.
Background technology
With the development of digital media technology and computer technology, various Digital Medias such as video, by interconnection
Net is propagated, and people can be downloaded viewing and online viewing.In order to protect the copyright of video, often
Embed watermark in video production, play video watermark in video playback simultaneously.
In video playback, because video watermark and video original image content are compressed together, watermark itself
It is exactly image, watermark can be shown while playing original video, prior art is often to static image
Carry out watermark removal it is impossible to watermark removal is carried out to the video play.
Content of the invention
Based on this it is necessary to be directed to the problems referred to above, provide the method and apparatus that a kind of video watermark removes, energy
Watermark removal is carried out to the video play.
A kind of method that video watermark removes, methods described includes:
In video playback, obtain the watermark range areas in video;
Adjust described watermark range areas, so that described watermark range areas is met pre-conditioned;
Obtain the frame of video of described video, the pixel value according to the pixel of same position in described frame of video is known
Do not obtain watermark and remove region;
Watermark range areas after described adjustment are entered according to presetted pixel length and width in yuv space respectively
Row piecemeal, the watermark removal region in each piecemeal described is carried out infra-frame prediction in yuv space respectively and obtains
Predicted pixel values;
The original pixel value that described watermark is removed region yuv space replaces with described corresponding prediction pixel
Value.
The device that a kind of video watermark removes, described device includes:
Region chosen module, in video playback, obtaining the watermark range areas in video;
Adjusting module, for adjusting described watermark range areas, makes described watermark range areas meet default bar
Part;
Identification module, for obtaining the frame of video of described video, according to the picture of same position in described frame of video
The pixel value identification of vegetarian refreshments obtains watermark and removes region;
Prediction module, for by described adjustment after watermark range areas respectively in yuv space according to default picture
Plain length and width carries out piecemeal, the watermark in each piecemeal described is removed region and enters in yuv space respectively
Row infra-frame prediction obtains predicted pixel values;
Watermark removes module, and the original pixel value for described watermark removes region yuv space replaces with institute
State corresponding predicted pixel values.
The method and apparatus that above-mentioned video watermark removes, in video playback, obtains the watermark scope in video
Region, adjusts watermark range areas, so that watermark range areas is met pre-conditioned, obtains the frame of video of video,
Watermark is obtained according to the pixel value identification of the pixel of same position in frame of video and removes region, can automatic identification
Watermark removes region, by the watermark range areas after adjustment respectively yuv space according to presetted pixel length and
Width carries out piecemeal, the watermark removal region in each piecemeal is carried out infra-frame prediction in yuv space respectively and obtains
To predicted pixel values, it is predicted obtaining predicted pixel values using the pixel value of the film strip area of surrounding, by water
The original pixel value that print removes region yuv space replaces with corresponding predicted pixel values, in video playback,
Watermark can be automatically removed in real time.
Brief description
Fig. 1 is the cut-away view of terminal in an embodiment;
Fig. 2 is the flow chart of the method that video watermark removes in an embodiment;
Fig. 3 is the schematic diagram of video watermark in an embodiment;
Fig. 4 is film viewing area, watermark region and watermark range areas schematic diagram in an embodiment;
Fig. 5 is to obtain the flow chart that watermark removes region in an embodiment;
Fig. 6 is the flow chart adjusting watermark range areas in an embodiment;
Fig. 7 is the flow chart obtaining predicted pixel values in an embodiment;
Fig. 8 be piecemeal in an embodiment after the completion of watermark range areas schematic diagram;
Fig. 9 is that in an embodiment, current wa removes piecemeal neighborhood pixels schematic diagram;
Figure 10 is the coordinate schematic diagram of part pixel in an embodiment;
Figure 11 is the flow chart of the current spatial predicted pixel values calculating target pixel points in an embodiment;
Figure 12 is the flow chart of the current spatial predicted pixel values calculating target pixel points in another embodiment;
Figure 13 is the structured flowchart of the device that video watermark removes in an embodiment;
Figure 14 is the structured flowchart of identification module in an embodiment;
Figure 15 is the structured flowchart of adjusting module in an embodiment;
Figure 16 is the structured flowchart of prediction module in an embodiment.
Specific embodiment
The method that in one embodiment, video watermark removes is applied in terminal, and terminal can be smart mobile phone, shifting
Dynamic panel computer etc., but be not limited thereto.The internal structure of terminal is as shown in figure 1, this terminal includes leading to
Cross system bus connection processor, GPU, storage medium, internal memory, network interface, display
Screen and input equipment and output equipment.Wherein, the storage medium of terminal is stored with operating system, also includes
The device that a kind of video watermark removes, the device that this video watermark removes is used for realizing a kind of video watermark removal
Method.This processor is used for providing calculating and control ability, supports the operation of whole terminal.In terminal
GPU is used for providing at the drawing ability of display web interface, inside saves as regarding in storage medium
The operation of the device that frequency watermark removes provides environment, and network interface is used for carrying out network service with miscellaneous equipment.
Display screen is used for showing video and web interface etc., such as plays multimedia video etc..Input equipment is used for connecing
Receive the data of user input, such as the watermark range areas of receiving user's input.Output equipment is used for output data,
As exported the voice data of video playback.For the terminal with touch-screen, display screen and input equipment can be
Touch-screen.
In one embodiment, as shown in Figure 2, there is provided a kind of method that video watermark removes, to apply
To illustrate in above-mentioned terminal, including:
Step S110, in video playback, obtains the watermark range areas in video.
Specifically, the watermark range areas that watermark range areas can be selected for user, or the watermark of systemic presupposition
Range areas.Video watermark identifies source video sequence, often occurs in video in the form of icon or word a certain
Individual ad-hoc location, usually upper right Angle Position, as shown in figure 3, the schematic diagram for a watermark.In video
During broadcasting, the behavior to video for the monitoring users, obtain the watermark range areas that user selectes, such as obtain and pass through
The region that mouse delimited or finger touch the region delimited.As shown in figure 4, region A is film viewing area,
Region C is watermark region, the watermark range areas that region B selectes for user.
Step S120, adjusts watermark range areas, so that watermark range areas is met pre-conditioned.
Specifically, select if watermark range areas are users, the watermark range areas selected due to user
May be irregular, need watermark range areas are adjusted, so that watermark range areas is met pre-conditioned,
It is square or rectangular, the length of adjustment watermark range areas and width as adjusted watermark range areas, make
It is integral multiple of default value etc., can customize the rule of adjustment.If it is pre- that watermark range areas are systems
If, also dependent on the resolution ratio of currently playing video, whether full frame etc. condition is adaptive is sized.
Step S130, obtains the frame of video of video, according in frame of video in watermark range areas after the adjustment
The pixel value identification of the pixel of same position obtains watermark and removes region.
Specifically, frame of video can be obtained forward or backward according to the time point of present frame, such as can obtain default
The frame of video of number, concrete numerical value can be self-defined as needed, such as 20 frames, and the number of the frame of video of acquisition can
Self-adaptative adjustment.The pixel value of watermark region is indeclinable during video playback, so contrast obtains
In the frame of video taking, the pixel value of the pixel of each frame same position, if each frame is all identical, identifies
Remove region for watermark.The pixel value of the directly relatively pixel of each frame same position during identification, can be passed through,
By the method for mathematical operation, can also such as calculate the variance yields of each pixel and remove region identifying watermark.
Step S140, by adjustment after watermark range areas respectively in yuv space according to presetted pixel length
Carry out piecemeal with width, the watermark in each piecemeal is removed region and carries out infra-frame prediction in yuv space respectively
Obtain predicted pixel values.
Specifically, YUV is a kind of colour coding method being adopted by eurovision system, luminance signal Y
It is detached with carrier chrominance signal U, V.Yuv space refers to YUV corresponding data respectively, Y space pair
Answer is brightness data, and U space is corresponding to be U chroma data, V space is corresponding is V chroma data.
By the watermark range areas after adjustment respectively Y space, U space, V space according to presetted pixel length and
Width carries out piecemeal, due to the difference of sample mode, Y space, U space, the size of data possibility in V space
Difference, such as sample mode are 4:2:0 view data, Y space, U space, V space size of data it
Than for 4:1:1, such as Y space is 16 × 16 pixels, then U space and V space are respectively 8 × 8 pixels.
Presetted pixel length and width can be self-defined as needed, and different spaces can be using different default pictures
Plain length and width.After piecemeal success, carry out infra-frame prediction respectively in each space and obtain in each piecemeal
Watermark removes the predicted pixel values in region.Infra-frame prediction refers to the spatial coherence using adjacent piecemeal, permissible
The pixel value of the piecemeal according to surrounding is predicting the pixel value of current piecemeal.As divided using left side piecemeal and top
The pixel value of block carries out being calculated the predicted value of current piecemeal pixel according to prediction algorithm.Infra-frame prediction can be adopted
With Forecasting Methodology h.264 or h.265, prediction algorithm or self-defined prediction algorithm can be selected as needed.?
It is only necessary to calculate the predicted pixel values that watermark removes area pixel, film area in current piecemeal when being predicted
The predicted pixel values in domain are without calculating.
Step S150, the original pixel value that watermark is removed region yuv space replaces with corresponding prediction picture
Element value.
Specifically, after each space of YUV calculates the predicted pixel values of watermark removal area pixel in piecemeal,
The original pixel value that watermark is removed region replaces with corresponding predicted pixel values, because watermark removes region is
It is predicted obtaining using the pixel value of the film strip area of surrounding, therefore can remove watermark.
In the present embodiment, in video playback, obtain the watermark range areas in video, adjust watermark scope
Region, makes watermark range areas meet pre-conditioned, obtains the frame of video of video, according to identical in frame of video
The pixel value identification of the pixel of position obtains watermark and removes region, automatic identification watermark can remove region, will
Watermark range areas after adjustment carry out piecemeal in yuv space according to presetted pixel length and width respectively, will
Watermark removal region in each piecemeal carries out infra-frame prediction in yuv space respectively and obtains predicted pixel values, profit
It is predicted obtaining predicted pixel values with the pixel value of the film strip area of surrounding, watermark is removed region YUV empty
Between original pixel value replace with corresponding predicted pixel values, in video playback, can automatically remove in real time
Watermark.
In one embodiment, as shown in figure 5, step S130 includes:
Step S131, calculates the pixel of same position in frame of video respectively in watermark range areas after the adjustment
The average pixel value of point.
Specifically, obtain the pixel value of the pixel of same position in frame of video, use Pn(i, j) represents, wherein
1≤n≤N, N represent the number of frame of video, and i, j represent abscissa and the ordinate of pixel position respectively,
0≤i≤W-1,0≤j≤H-1, wherein W represent the length of the watermark range areas after adjustment, and H represents adjustment
The width of watermark range areas afterwards.By formulaBeing calculated each frame coordinate position is
The average pixel value of the pixel of i, j.
Step S132, calculates average pixel value and the original pixel value of pixel of same position in frame of video
Variance.
Specifically, by formulaBeing calculated coordinate position is i, j's
The variance of pixel, variance denotation coordination position is i, the change in each frame of the pixel value of the pixel of j.
Step S133, the region recognition that the pixel that variance is 0 is located removes region for watermark.
Specifically, variance is 0 then it represents that coordinate position is i, the pixel value of the pixel of j in each frame all
It is not changed in, and this pixel being not changed in is often watermark region, be identified as watermark and remove region.
In one embodiment, as shown in fig. 6, step S120 includes:
Step S121, the length in pixels of watermark range areas is extended for the integral multiple of presetted pixel length, will
The pixel wide of watermark range areas is extended for the integral multiple of presetted pixel width.
When specifically, in order to avoid subsequently carrying out piecemeal, piecemeal situation not of uniform size, by watermark scope area
The length in pixels in domain is extended for the integral multiple of presetted pixel length, and the pixel wide of watermark range areas is expanded
Integral multiple for presetted pixel width is it is possible to be divided into integer size the same watermark range areas
Length is presetted pixel length, and width is the piecemeal of presetted pixel width.
Step S122, the watermark range areas after expanding is expanded presetted pixel width pixel upwards, will expand
Watermark range areas after filling expand presetted pixel length pixel to the left.
When specifically, in order to ensure that the predicted pixel values subsequently carrying out each pixel of watermark removal region calculate
The pixel using is the pixel of film strip area, by the watermark range areas expanded through step S121 upwards
Expand presetted pixel width pixel, the watermark range areas after expanding are expanded presetted pixel length picture to the left
Vegetarian refreshments.Wherein refer to the top in the direction of the normal viewing of video upwards, refer to the side of the normal viewing of video to the left
To left.Watermark region as user selectes is less, in the case of not comprising whole watermark region, warp
Cross and expand the effect that can improve watermark removal.
In one embodiment, as shown in fig. 7, step S140 includes:Respectively Y space, U space and
V space executes following steps:
Step S141, by the watermark range areas after adjustment in current spatial according to corresponding with current spatial pre-
If length in pixels and width carry out piecemeal, current spatial is one of Y space, U space, V space.
Specifically, due to the difference of sample rate, the size of data of different spaces is different, can be using different pre-
If length in pixels and width carry out piecemeal, such as Y space carries out piecemeal, U space and V using 16 × 16 sizes
Space carries out piecemeal, wherein 16 × 16 a length of 16 pixels of expression, a width of 16 pixels using 8 × 8 sizes.
Step S142, each piecemeal is carried out watermark removal according to order from left to right, from top to bottom, will
First piecemeal removes piecemeal as current wa.
Specifically, be illustrated in figure 8 the watermark range areas schematic diagram after the completion of piecemeal, according in figure each
The ascending order of piecemeal sequence number is processed.
Step S143, the current spatial of acquisition current wa removal piecemeal left side a line and top a line is adjacent to picture
Element value.
Specifically, the left side refers to the left side in the direction of the normal viewing of video, and top refers to the normal viewing of video
The top in direction.As shown in figure 9, as current wa remove piecemeal be serial number 0 piecemeal, its length and
Wide respectively 16 pixels, then obtain piecemeal left side a line 210 of serial number 0 and the neighbouring of top a line 220
Pixel value.As taken the pixel value of 17 pixels and 16 pictures of top a line 220 of left side a line 210
The pixel value of vegetarian refreshments, can adjust the number of the vicinity points needing to obtain as needed.
Step S144, obtains current wa according to order from left to right, from top to bottom and removes piecemeal in watermark
Removing the pixel in region is target pixel points.
Specifically, remove in current wa in each pixel of piecemeal, only remove in region in watermark
Pixel is target pixel points, and other points do not need to process.
Step S145, obtains the coordinate in current spatial for the target pixel points.
Specifically, target pixel points are coordinate in current piecemeal for the target pixel points in the coordinate of current spatial,
If current piecemeal is 16 × 16 piecemeals, the coordinate (x, y) of each picture element is from left to right distinguished from top to bottom
For (0,0), (1,0), (2,0) ... (15,15), wherein x is abscissa, and y is ordinate.As
Shown in Figure 10, it is the coordinate schematic diagram of partial pixel point.
Step S146, the coordinate according to current spatial neighborhood pixels value and current spatial calculates target pixel points
Current spatial predicted pixel values.
Specifically, can be according to intraframe prediction algorithm according to the coordinate of current spatial neighborhood pixels value and current spatial
Calculate the current spatial predicted pixel values of target pixel points, can be according to the current spatial chosen adjacent to picture during calculating
The number of element value selects different intraframe prediction algorithms, such as h.264 the vertical prediction of standard, horizontal forecast,
DC prediction, planar prediction etc..
Repeat step S144 to S146 is until current wa removes all target pixel points in piecemeal and corresponded to
Current spatial predicted pixel values.
Specifically, obtain corresponding current spatial up to all target pixel points in current wa removal piecemeal pre-
Survey pixel value just enters next piecemeal and is predicted.
In one embodiment, as shown in figure 11, step S146 includes:
Step S146a, calculates predictive coefficient according to current spatial neighborhood pixels value.
Specifically, the difference according to intraframe prediction algorithm, has different algorithms to calculate predictive coefficient, and different
Space, computational methods are different, and taking planar prediction as a example, if current spatial is Y space, piecemeal size is
16 × 16 by formulaIt is calculated predictive coefficient a, b and c, wherein
P [- 1,15] denotation coordination position is the pixel value of the pixel of (- 1,15), and p [15, -1] denotation coordination position is (15, -1)
Pixel pixel value, can find coordinate position in Fig. 10 is the pixel of (- 1,15) and coordinate position
Pixel for (15, -1).Wherein H, V are calculated by following formula:
Wherein x ' and y ' is coordinated indexing.
If current spatial is U space or V space, by formulaIt is calculated pre-
Survey coefficient a ', b ' and c '.Wherein H ' and V ' is calculated by following formula:
Wherein x ' and y ' is coordinated indexing.
Step S146b, is calculated current spatial initial predicted picture according to the coordinate of predictive coefficient and current spatial
Element value.
Specifically, the difference according to intraframe prediction algorithm, has different algorithms to calculate current spatial initial predicted
Pixel value, and different spaces, computational methods are different, taking planar prediction as a example, if current spatial is Y
Space, then according to formula pred_pre [x, y]=((a+b × (x-7)+c × (y-7)+16) > > 5 is calculated current sky
Between initial predicted pixel value, wherein 0≤x≤15,0≤y≤15.If current spatial is U space, basis
Formula pred_pre [x, y]=((a+b × (x-3)+c × (y-3)+16) > > 5 is calculated current spatial initial predicted picture
Element value.
Step S146c, current spatial initial predicted pixel value is entered line range and is defined so as to working as of target pixel points
Front space predicted pixel values.
Specifically, current spatial initial predicted pixel value substitution formula is made m=pred_pre [x, y], be calculated
Clip (m)=Clip3 (0, (1 < < 8) -1, m), whereinClip (pred_pre [x, y]) is scope
Current spatial predicted pixel values after restriction.
In one embodiment, as shown in figure 12, step S146 includes:
Step S146d, obtains current spatial corresponding presetted pixel length or width.
Specifically, current spatial corresponding presetted pixel length or width can be equal, such as presetted pixel length
It is respectively 4X4,8X8,16X16,32X32 with width, if current spatial is brightness space, preset
Length in pixels and width can also be 64X64, and different spaces corresponding presetted pixel length and width is permissible
Different.
Step S146e, according to current spatial corresponding presetted pixel length or width, current spatial neighborhood pixels
The coordinate of value and current spatial calculates the current spatial predicted pixel values of target pixel points.
Specifically, the difference according to the intraframe prediction algorithm adopting, can obtain current sky according to different algorithms
Between predicted pixel values, taking planar prediction as a example, the intraframe prediction algorithm that can be provided using h265, due to currently empty
Between corresponding presetted pixel length or variable-width, this algorithm is more more flexible than h264, and the current spatial obtaining is pre-
Survey pixel value more accurate.As by formula:
It is calculated and work as
Front space predicted pixel values pred [x] [y], wherein Tbs is current spatial corresponding presetted pixel length or width,
X is the abscissa of current spatial prediction pixel, and y is the ordinate of current spatial prediction pixel.
In one embodiment, as shown in figure 13, there is provided the device that a kind of video watermark removes, including:
Region chosen module 310, in video playback, obtaining the watermark range areas in video.
Adjusting module 320, for adjusting watermark range areas, makes watermark range areas meet pre-conditioned.
Identification module 330, for obtaining the frame of video of video, according to the pixel of same position in frame of video
Pixel value identification obtains watermark and removes region.
Prediction module 340, for by adjustment after watermark range areas respectively in yuv space according to default picture
Plain length and width carries out piecemeal, the watermark in each piecemeal is removed region and carries out frame in yuv space respectively
Interior prediction obtains predicted pixel values.
Watermark removes module 350, and it is right that the original pixel value for watermark removes region yuv space replaces with
The predicted pixel values answered.
In one embodiment, as shown in figure 14, identification module 330 includes:
Average pixel value computing unit 331, for calculating the average of the pixel of same position in frame of video respectively
Pixel value.
Recognition unit 332, for calculating the original image of average pixel value and the pixel of same position in frame of video
The variance of element value, the region recognition that the pixel that variance is 0 is located removes region for watermark.
In one embodiment, as shown in figure 15, adjusting module 320 includes:
First adjustment unit 321, for being extended for presetted pixel length by the length in pixels of watermark range areas
Integral multiple, the pixel wide of watermark range areas is extended for the integral multiple of presetted pixel width.
Second adjustment unit 322, for expanding presetted pixel width picture upwards by the watermark range areas after expanding
Vegetarian refreshments, the watermark range areas after expanding are expanded presetted pixel length pixel to the left.
In one embodiment, as shown in figure 16, prediction module 340 is respectively in Y space, U space and V
Space includes:
Blocking unit 341, for by adjustment after watermark range areas current spatial according to current spatial pair
The presetted pixel length and width answered carries out piecemeal, current spatial is Y space, U space, in V space
One.
Current wa remove piecemeal determining unit 342, for by each piecemeal described according to from left to right, from
To under order carry out watermark removal, using first piecemeal as current wa remove piecemeal;
Neighborhood pixels value acquiring unit 343, removes piecemeal left side a line and top a line for obtaining current wa
Current spatial neighborhood pixels value.
Target pixel points determining unit 344, for obtaining current water according to order from left to right, from top to bottom
It is target pixel points that print removes pixel in watermark removal region for the piecemeal.
Coordinate acquiring unit 345, for obtaining the coordinate in current spatial for the target pixel points.
Predicted pixel values computing unit 346, for the coordinate according to current spatial neighborhood pixels value and current spatial
Calculating the current spatial predicted pixel values of target pixel points, entering target pixel points determining unit 344 until working as
Front watermark removes all target pixel points in piecemeal and obtains corresponding current spatial predicted pixel values.
Current wa removes piecemeal determining unit 342 and is additionally operable to remove next piecemeal as current wa and divides
Block, to the last a piecemeal completes to predict to enter neighborhood pixels value acquiring unit.
In one embodiment, predicted pixel values computing unit 346 is additionally operable to according to current spatial neighborhood pixels
The calculating predictive coefficient of value, is calculated current spatial according to the coordinate of predictive coefficient and current spatial initially pre-
Survey pixel value, current spatial initial predicted pixel value is entered the current sky that line range is defined so as to target pixel points
Between predicted pixel values.
In one embodiment, predicted pixel values computing unit 346 be additionally operable to obtain current spatial corresponding pre-
If length in pixels or width, according to described current spatial corresponding presetted pixel length or width, current spatial
The coordinate of neighborhood pixels value and current spatial calculates the current spatial predicted pixel values of described target pixel points.
One of ordinary skill in the art will appreciate that realizing all or part of flow process in above-described embodiment method,
Can be by computer program to complete come the hardware to instruct correlation, described program can be stored in a computer
In read/write memory medium, such as in the embodiment of the present invention, the storage that this program can be stored in computer system is situated between
In matter, and by least one of this computer system computing device, to realize including as above-mentioned each method
Embodiment flow process.Wherein, described storage medium can be magnetic disc, CD, read-only memory
(Read-Only Memory, ROM) or random access memory (Random Access Memory, RAM)
Deng.
Each technical characteristic of embodiment described above can arbitrarily be combined, for making description succinct, not right
The all possible combination of each technical characteristic in above-described embodiment is all described, as long as however, these skills
There is not contradiction in the combination of art feature, be all considered to be the scope of this specification record.
Embodiment described above only have expressed the several embodiments of the present invention, and its description is more concrete and detailed,
But can not therefore be construed as limiting the scope of the patent.It should be pointed out that for this area
For those of ordinary skill, without departing from the inventive concept of the premise, can also make and some deform and change
Enter, these broadly fall into protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be with appended power
Profit requires to be defined.
Claims (12)
1. a kind of method that video watermark removes, methods described includes:
In video playback, obtain the watermark range areas in video;
Adjust described watermark range areas, so that described watermark range areas is met pre-conditioned;
Obtain the frame of video of described video, the pixel value according to the pixel of same position in described frame of video is known
Do not obtain watermark and remove region;
Watermark range areas after described adjustment are entered according to presetted pixel length and width in yuv space respectively
Row piecemeal, the watermark removal region in each piecemeal described is carried out infra-frame prediction in yuv space respectively and obtains
Predicted pixel values;
The original pixel value that described watermark is removed region yuv space replaces with described corresponding prediction pixel
Value.
2. method according to claim 1 it is characterised in that described according to identical in described frame of video
The step that the pixel value identification of the pixel of position obtains watermark removal region includes:
Calculate the average pixel value of the pixel of same position in described frame of video respectively;
Calculate the side of described average pixel value and the original pixel value of pixel of same position in described frame of video
Difference;
The region recognition that the pixel that described variance is 0 is located removes region for watermark.
3. method according to claim 1 is it is characterised in that described adjustment described watermark range areas,
Make described watermark range areas meet pre-conditioned step to include:
The length in pixels of described watermark range areas is extended for the integral multiple of presetted pixel length;
The pixel wide of described watermark range areas is extended for the integral multiple of presetted pixel width;
Watermark range areas after described expansion are expanded presetted pixel width pixel upwards;
Watermark range areas after described expansion are expanded presetted pixel length pixel to the left.
4. method according to claim 1 it is characterised in that described by described adjustment after watermark model
Enclose region and carry out piecemeal in yuv space according to presetted pixel length and width respectively, by each piecemeal described
Watermark remove region and carry out infra-frame prediction and obtain the step of predicted pixel values including in yuv space respectively:
Execute following steps in Y space, U space and V space respectively:
By the watermark range areas after described adjustment in current spatial according to presetted pixel corresponding with current spatial
Length and width carries out piecemeal, and described current spatial is one of Y space, U space, V space;
Each piecemeal described is carried out watermark removal according to order from left to right, from top to bottom, by first
Piecemeal removes piecemeal as current wa;
Step A, obtains described current wa removal piecemeal left side a line and the current spatial of top a line is neighbouring
Pixel value;
Step B, obtains described current wa according to order from left to right, from top to bottom and removes piecemeal in watermark
Removing the pixel in region is target pixel points;
Step C, obtains the coordinate in current spatial for the described target pixel points;
Step D, the coordinate according to described current spatial neighborhood pixels value and current spatial calculates described target picture
The current spatial predicted pixel values of vegetarian refreshments;
Repeat step B to D obtains corresponding up to all target pixel points in described current wa removal piecemeal
Current spatial predicted pixel values;
Next piecemeal is removed piecemeal as current wa, enters a described step A to the last piecemeal
Complete to predict.
5. method according to claim 4 is it is characterised in that described neighbouring according to described current spatial
The coordinate of pixel value and current spatial calculates the step bag of the current spatial predicted pixel values of described target pixel points
Include:
Predictive coefficient is calculated according to described current spatial neighborhood pixels value;
Current spatial initial predicted pixel value is calculated according to the coordinate of described predictive coefficient and current spatial;
Described current spatial initial predicted pixel value is entered line range and is defined so as to the current of described target pixel points
Spatial prediction pixel value.
6. method according to claim 4 is it is characterised in that described neighbouring according to described current spatial
The coordinate of pixel value and current spatial calculates the step bag of the current spatial predicted pixel values of described target pixel points
Include:
Obtain current spatial corresponding presetted pixel length or width;
According to described current spatial corresponding presetted pixel length or width, current spatial neighborhood pixels value with work as
The coordinate of front space calculates the current spatial predicted pixel values of described target pixel points.
7. the device that a kind of video watermark removes is it is characterised in that described device includes:
Region chosen module, in video playback, obtaining the watermark range areas in video;
Adjusting module, for adjusting described watermark range areas, makes described watermark range areas meet default bar
Part;
Identification module, for obtaining the frame of video of described video, according to the picture of same position in described frame of video
The pixel value identification of vegetarian refreshments obtains watermark and removes region;
Prediction module, for by described adjustment after watermark range areas respectively in yuv space according to default picture
Plain length and width carries out piecemeal, the watermark in each piecemeal described is removed region and enters in yuv space respectively
Row infra-frame prediction obtains predicted pixel values;
Watermark removes module, and the original pixel value for described watermark removes region yuv space replaces with institute
State corresponding predicted pixel values.
8. device according to claim 7 is it is characterised in that described identification module includes:
Average pixel value computing unit, for calculating the flat of the pixel of same position in described frame of video respectively
All pixel values;
Recognition unit, for calculating described average pixel value and the pixel of same position in described frame of video
The variance of original pixel value, the region recognition that the pixel that described variance is 0 is located removes region for watermark.
9. device according to claim 7 is it is characterised in that described adjusting module includes:
First adjustment unit, for being extended for presetted pixel length by the length in pixels of described watermark range areas
Integral multiple, the pixel wide of described watermark range areas is extended for the integral multiple of presetted pixel width;
Second adjustment unit, for expanding presetted pixel width upwards by the watermark range areas after described expansion
Pixel, the watermark range areas after described expansion are expanded presetted pixel length pixel to the left.
10. device according to claim 7 is it is characterised in that described prediction module is empty in Y respectively
Between, U space and V space include:
Blocking unit, for by described adjustment after watermark range areas current spatial according to current spatial
Corresponding presetted pixel length and width carries out piecemeal, and described current spatial is Y space, U space, V are empty
One of between;
Current wa remove piecemeal determining unit, for by each piecemeal described according to from left to right, to
Under order carry out watermark removal, using first piecemeal as current wa remove piecemeal;
Neighborhood pixels value acquiring unit, removes piecemeal left side a line and top one for obtaining described current wa
The current spatial neighborhood pixels value of row;
Target pixel points determining unit, described current for obtaining according to order from left to right, from top to bottom
It is target pixel points that watermark removes pixel in watermark removal region for the piecemeal;
Coordinate acquiring unit, for obtaining the coordinate in current spatial for the described target pixel points;
Predicted pixel values computing unit, for the seat according to described current spatial neighborhood pixels value and current spatial
Mark calculate described target pixel points current spatial predicted pixel values, enter target pixel points determining unit until
Described current wa removes all target pixel points in piecemeal and obtains corresponding current spatial predicted pixel values;
Described current wa removes piecemeal determining unit and is additionally operable to remove next piecemeal as current wa and divides
Block, to the last a piecemeal completes to predict to enter neighborhood pixels value acquiring unit.
11. devices according to claim 10 are it is characterised in that described predicted pixel values computing unit
Be additionally operable to the calculating predictive coefficient according to described current spatial neighborhood pixels value, according to described predictive coefficient and work as
The coordinate of front space is calculated current spatial initial predicted pixel value, by described current spatial initial predicted picture
Element value enters the current spatial predicted pixel values that line range is defined so as to described target pixel points.
12. devices according to claim 10 are it is characterised in that described predicted pixel values computing unit
It is additionally operable to obtain current spatial corresponding presetted pixel length or width, corresponding pre- according to described current spatial
If the coordinate of length in pixels or width, current spatial neighborhood pixels value and current spatial calculates described object pixel
The current spatial predicted pixel values of point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510447572.9A CN106412720B (en) | 2015-07-27 | 2015-07-27 | Method and device for removing video watermark |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510447572.9A CN106412720B (en) | 2015-07-27 | 2015-07-27 | Method and device for removing video watermark |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106412720A true CN106412720A (en) | 2017-02-15 |
CN106412720B CN106412720B (en) | 2020-06-16 |
Family
ID=58008530
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510447572.9A Active CN106412720B (en) | 2015-07-27 | 2015-07-27 | Method and device for removing video watermark |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106412720B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106934780A (en) * | 2017-03-15 | 2017-07-07 | 中山大学 | A kind of automatic watermark minimizing technology based on image repair |
CN108550099A (en) * | 2018-04-13 | 2018-09-18 | 北京焦点新干线信息技术有限公司 | The method and apparatus of watermark in a kind of removal image |
CN108810619A (en) * | 2018-06-29 | 2018-11-13 | 北京奇虎科技有限公司 | Identify the method, apparatus and electronic equipment of watermark in video |
CN108810618A (en) * | 2018-06-29 | 2018-11-13 | 北京奇虎科技有限公司 | Identify the method, apparatus and electronic equipment of watermark in video |
CN110198492A (en) * | 2019-04-28 | 2019-09-03 | 腾讯科技(深圳)有限公司 | A kind of watermark adding method of video, device, equipment and storage medium |
CN110278439A (en) * | 2019-06-28 | 2019-09-24 | 北京云摄美网络科技有限公司 | De-watermarked algorithm based on inter-prediction |
CN110619597A (en) * | 2018-11-06 | 2019-12-27 | 北京时光荏苒科技有限公司 | Semitransparent watermark removing method and device, electronic equipment and storage medium |
CN110798750A (en) * | 2019-11-29 | 2020-02-14 | 广州市百果园信息技术有限公司 | Video watermark removing method, video data publishing method and related device |
CN111263242A (en) * | 2020-02-12 | 2020-06-09 | 山东三宏信息科技有限公司 | Frame sequence processing method, system and storage medium |
CN111277914A (en) * | 2020-03-05 | 2020-06-12 | 山东三宏信息科技有限公司 | Frame sequence processing method, system and storage medium |
CN111510767A (en) * | 2020-04-21 | 2020-08-07 | 新华智云科技有限公司 | Video watermark identification method and identification device thereof |
CN111954086A (en) * | 2020-08-19 | 2020-11-17 | 浙江无极互联科技有限公司 | Invisible video copyright watermarking algorithm |
US11455757B2 (en) | 2017-12-19 | 2022-09-27 | Samsung Electronics Co., Ltd. | Method and apparatus for reconstruction of original images from modified images |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1679050A (en) * | 2002-08-28 | 2005-10-05 | 皇家飞利浦电子股份有限公司 | Method and arrangement for watermark detection |
WO2010089383A3 (en) * | 2009-02-06 | 2010-10-07 | Thomson Licensing | Method for fingerprint-based video registration |
EP2835783A1 (en) * | 2013-07-05 | 2015-02-11 | Thomson Licensing | Method and device for assessing the presence of a watermark in a video |
CN106296593A (en) * | 2015-05-29 | 2017-01-04 | 腾讯科技(深圳)有限公司 | Image recovery method and device |
-
2015
- 2015-07-27 CN CN201510447572.9A patent/CN106412720B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1679050A (en) * | 2002-08-28 | 2005-10-05 | 皇家飞利浦电子股份有限公司 | Method and arrangement for watermark detection |
WO2010089383A3 (en) * | 2009-02-06 | 2010-10-07 | Thomson Licensing | Method for fingerprint-based video registration |
EP2835783A1 (en) * | 2013-07-05 | 2015-02-11 | Thomson Licensing | Method and device for assessing the presence of a watermark in a video |
CN106296593A (en) * | 2015-05-29 | 2017-01-04 | 腾讯科技(深圳)有限公司 | Image recovery method and device |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106934780B (en) * | 2017-03-15 | 2019-11-01 | 北京思创科泰科技有限公司 | A kind of automatic watermark minimizing technology based on image repair |
CN106934780A (en) * | 2017-03-15 | 2017-07-07 | 中山大学 | A kind of automatic watermark minimizing technology based on image repair |
US11455757B2 (en) | 2017-12-19 | 2022-09-27 | Samsung Electronics Co., Ltd. | Method and apparatus for reconstruction of original images from modified images |
CN108550099A (en) * | 2018-04-13 | 2018-09-18 | 北京焦点新干线信息技术有限公司 | The method and apparatus of watermark in a kind of removal image |
CN108810618B (en) * | 2018-06-29 | 2021-02-05 | 北京奇虎科技有限公司 | Method and device for identifying watermark in video and electronic equipment |
CN108810619A (en) * | 2018-06-29 | 2018-11-13 | 北京奇虎科技有限公司 | Identify the method, apparatus and electronic equipment of watermark in video |
CN108810618A (en) * | 2018-06-29 | 2018-11-13 | 北京奇虎科技有限公司 | Identify the method, apparatus and electronic equipment of watermark in video |
CN110619597A (en) * | 2018-11-06 | 2019-12-27 | 北京时光荏苒科技有限公司 | Semitransparent watermark removing method and device, electronic equipment and storage medium |
CN110198492A (en) * | 2019-04-28 | 2019-09-03 | 腾讯科技(深圳)有限公司 | A kind of watermark adding method of video, device, equipment and storage medium |
CN110278439A (en) * | 2019-06-28 | 2019-09-24 | 北京云摄美网络科技有限公司 | De-watermarked algorithm based on inter-prediction |
CN110798750A (en) * | 2019-11-29 | 2020-02-14 | 广州市百果园信息技术有限公司 | Video watermark removing method, video data publishing method and related device |
WO2021103643A1 (en) * | 2019-11-29 | 2021-06-03 | 百果园技术(新加坡)有限公司 | Video watermark removing method and apparatus, video data publishing method and apparatus, device and storage medium |
CN111263242B (en) * | 2020-02-12 | 2021-03-19 | 山东三宏信息科技有限公司 | Frame sequence processing method, system and storage medium |
CN111263242A (en) * | 2020-02-12 | 2020-06-09 | 山东三宏信息科技有限公司 | Frame sequence processing method, system and storage medium |
CN111277914A (en) * | 2020-03-05 | 2020-06-12 | 山东三宏信息科技有限公司 | Frame sequence processing method, system and storage medium |
CN111277914B (en) * | 2020-03-05 | 2021-03-19 | 山东三宏信息科技有限公司 | Frame sequence processing method, system and storage medium |
CN111510767A (en) * | 2020-04-21 | 2020-08-07 | 新华智云科技有限公司 | Video watermark identification method and identification device thereof |
CN111954086A (en) * | 2020-08-19 | 2020-11-17 | 浙江无极互联科技有限公司 | Invisible video copyright watermarking algorithm |
CN111954086B (en) * | 2020-08-19 | 2022-10-14 | 浙江无极互联科技有限公司 | Invisible video copyright watermarking method |
Also Published As
Publication number | Publication date |
---|---|
CN106412720B (en) | 2020-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106412720A (en) | Method and device of removing video watermarks | |
US6163621A (en) | Histogram equalization method and device in contrast enhancement apparatus for image processing system | |
US7418131B2 (en) | Image-capturing device and method for removing strangers from an image | |
CN102763117B (en) | Data generating device, data creation method, data generator and recording medium | |
JP7175197B2 (en) | Image processing method and device, storage medium, computer device | |
US8681880B2 (en) | Adaptive dithering during image processing | |
US20130162629A1 (en) | Method for generating depth maps from monocular images and systems using the same | |
KR20010039885A (en) | Image processing apparatus | |
US20090310882A1 (en) | Method, apparatus and integrated circuit capable of reducing image ringing noise | |
JP2007504709A (en) | Method and apparatus for modeling film grain patterns in the frequency domain | |
JP2007520822A (en) | Depth map generation | |
US11645734B2 (en) | Circuitry for image demosaicing and contrast enhancement and image-processing method | |
CN110162986B (en) | Reversible information hiding method based on adjacent pixel prediction model | |
CN110852334A (en) | System and method for adaptive pixel filtering | |
EP2178289B1 (en) | Method and unit for motion detection based on a difference histogram | |
CN104756151A (en) | System and method to enhance and process a digital image | |
JP2007512750A (en) | Detection of local image space-temporal details in video signals | |
CN112073718B (en) | Television screen splash detection method and device, computer equipment and storage medium | |
CN111654747B (en) | Bullet screen display method and device | |
US8031945B2 (en) | Image-processing device, image-processing method, program of image-processing method, and recording medium recording program of image-processing method | |
CN103139583A (en) | Method and device for compressing depth map of three-dimensional video | |
JP2008287329A (en) | Image evaluation device and image evaluation program | |
US9215474B2 (en) | Block-based motion estimation method | |
JPH10155139A (en) | Image processor and image processing method | |
CN105992072A (en) | Watermark processing method, watermark extracting method and corresponding devices |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20221116 Address after: 1402, Floor 14, Block A, Haina Baichuan Headquarters Building, No. 6, Baoxing Road, Haibin Community, Xin'an Street, Bao'an District, Shenzhen, Guangdong 518100 Patentee after: Shenzhen Yayue Technology Co.,Ltd. Address before: 2, 518000, East 403 room, SEG science and Technology Park, Zhenxing Road, Shenzhen, Guangdong, Futian District Patentee before: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. |
|
TR01 | Transfer of patent right |