CN107644423A

CN107644423A - Video data real-time processing method, device and computing device based on scene cut

Info

Publication number: CN107644423A
Application number: CN201710908422.2A
Authority: CN
Inventors: 张蕊; 颜水成; 唐胜
Original assignee: Beijing Qihoo Technology Co Ltd
Current assignee: Beijing Qihoo Technology Co Ltd
Priority date: 2017-09-29
Filing date: 2017-09-29
Publication date: 2018-01-30
Anticipated expiration: 2037-09-29
Also published as: CN107644423B

Abstract

The invention discloses a kind of video data real-time processing method, device, computing device and computer-readable storage medium based on scene cut, wherein, this method includes：Real-time image acquisition collecting device is captured and/or the video recorded in include special object current frame image；Or the current frame image that special object is included in currently played video is obtained in real time；Current frame image is inputted into scene cut network, obtains scene cut result corresponding with current frame image；According to scene cut result, the profile information of special object is determined；According to the profile information of special object, personalized special efficacy is added, obtains frame processing image；Video data after frame processing image covering current frame image is handled；Video data after display processing.The technical scheme can in real time, accurately obtain scene cut result corresponding to two field picture, personalized special efficacy more accurately can be added to two field picture based on scene cut result.

Description

Video data real-time processing method, device and computing device based on scene cut

Technical field

The present invention relates to technical field of image processing, and in particular to a kind of video data based on scene cut is handled in real time Method, apparatus, computing device and computer-readable storage medium.

Background technology

In the prior art, image scene segmentation processing method is mainly based upon the full convolutional Neural net in deep learning Network, these processing methods utilize the thought of transfer learning, the network that will be obtained on extensive categorized data set by pre-training Move to and be trained on image partitioned data set, so as to obtain the segmentation network for scene cut, then utilize the segmentation Network carries out scene cut to image.

The network architecture used in the segmentation network obtained in the prior art directly make use of image classification network, its convolution The size of convolution block is changeless in layer, is changeless so as to the size of receptive field, wherein, receptive field refers to export The region of input picture corresponding to the response of some node of characteristic pattern, fixed-size receptive field be adapted only to catch fixed size and The target of yardstick.But for image scene segmentation, different size of target is often included in scene, is consolidated using with size The segmentation network of fixed receptive field usually causes problems when handling excessive and too small target, for example, for less mesh Mark, receptive field can catch the background around excessive target, so as to which target and background be obscured, cause target to be omitted and misjudged For background；For larger target, receptive field is only capable of catching a part for target so that and target classification judges existing deviation, Cause discontinuous segmentation result.Therefore, there is image scene segmentation for image scene segmentation processing mode of the prior art Accuracy rate it is low the problem of, then utilize resulting segmentation result also can not well, accurately to the frame figure in video As adding personalized special efficacy, the display effect of the video data after resulting processing is poor.

The content of the invention

In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on State video data real-time processing method, device, computing device and the computer-readable storage medium based on scene cut of problem.

According to an aspect of the invention, there is provided a kind of video data real-time processing method based on scene cut, should Method is based on trained scene cut network and performed, and this method includes：

Real-time image acquisition collecting device is captured and/or the video recorded in include special object present frame figure Picture；Or the current frame image that special object is included in currently played video is obtained in real time；

Current frame image is inputted into scene cut network, wherein, at least one layer of convolutional layer in scene cut network, The scale coefficient exported using scale regression layer zooms in and out processing to the first convolution block of the convolutional layer, obtains the second convolution Block, the convolution algorithm of the convolutional layer is then carried out using the second convolution block, obtain the output result of the convolutional layer；Scale regression layer For the middle convolutional layer of scene cut network；

Obtain scene cut result corresponding with current frame image；

According to scene cut result corresponding with current frame image, the profile information of special object is determined；

According to the profile information of special object, personalized special efficacy is added, obtains frame processing image；

Video data after frame processing image covering current frame image is handled；

Video data after display processing.

Further, the convolution algorithm of the convolutional layer is carried out using the second convolution block, obtains the output result of the convolutional layer Further comprise：

Using linear interpolation method, sampled from the second convolution block and obtain characteristic vector, form the 3rd convolution block；

Convolution kernel according to the 3rd convolution block and the convolutional layer carries out convolution algorithm, obtains the output result of the convolutional layer.

Further, the sample used in scene cut network training includes：Multiple sample images of sample library storage and Mark scene cut result corresponding with sample image.

Further, the training process of scene cut network is completed by successive ignition；During an iteration, from sample Sample image and mark scene cut result corresponding with sample image are extracted in this storehouse, utilizes sample image and mark scene Segmentation result realizes the training of scene cut network.

Further, the training process of scene cut network is completed by successive ignition；Wherein an iteration process includes：

Sample image is inputted to scene cut network, obtains sample scene cut result corresponding with sample image；

Lost according to the segmentation between sample scene cut result and mark scene cut result, obtain scene cut network Loss function, the training of scene cut network is realized using scene cut network losses function.

Further, the training step of scene cut network includes：

Sample image and mark scene cut result corresponding with sample image are extracted from Sample Storehouse；

Sample image is inputted into scene cut network and is trained, wherein, it is at least one layer of in scene cut network Convolutional layer, using the scale coefficient or initial gauges coefficient of last iterative process scale regression layer output to the convolutional layer First convolution block zooms in and out processing, obtains the second convolution block, and the convolution that the convolutional layer is then carried out using the second convolution block is transported Calculate, obtain the output result of the convolutional layer；

Obtain sample scene cut result corresponding with sample image；

Lost according to the segmentation between sample scene cut result and mark scene cut result, obtain scene cut network Loss function, the weight parameter of scene cut network is updated according to scene cut network losses function；

Iteration performs the training step of scene cut network, until meeting predetermined convergence condition.

Further, predetermined convergence condition includes：Iterations reaches default iterations；And/or scene cut network The output valve of loss function is less than predetermined threshold value.

Further, scale coefficient is the characteristic vector in the scale coefficient characteristic pattern of scale regression layer output.

Further, this method also includes：When scene cut network training starts, to the weight parameter of scale regression layer Carry out initialization process.

Further, the video data after display processing further comprises：By the video data real-time display after processing；

This method also includes：Video data after processing is uploaded to Cloud Server.

Further, the video data after processing is uploaded into Cloud Server to further comprise：

Video data after processing is uploaded to cloud video platform server, so that cloud video platform server is in cloud video Platform is shown video data.

Video data after processing is uploaded to cloud direct broadcast server, so that cloud direct broadcast server pushes away video data in real time Give viewing subscription client.

Video data after processing is uploaded to cloud public number server, so that cloud public number server pushes away video data Give public number concern client.

According to another aspect of the present invention, there is provided a kind of video data real-time processing device based on scene cut, should Device is based on trained scene cut network and run, and the device includes：

Acquisition module, suitable for captured by real-time image acquisition collecting device and/or in the video recorded comprising specific right The current frame image of elephant；Or the current frame image that special object is included in currently played video is obtained in real time；

Split module, suitable for current frame image is inputted into scene cut network, wherein, in scene cut network extremely Few one layer of convolutional layer, the scale coefficient exported using scale regression layer zoom in and out processing to the first convolution block of the convolutional layer, The second convolution block is obtained, the convolution algorithm of the convolutional layer is then carried out using the second convolution block, obtains the output knot of the convolutional layer Fruit；Scale regression layer is the middle convolutional layer of scene cut network；

Generation module, suitable for obtaining scene cut result corresponding with current frame image；

Determining module, suitable for according to scene cut result corresponding with current frame image, determining that the profile of special object is believed Breath；

Processing module, suitable for the profile information according to special object, personalized special efficacy is added, obtain frame processing image；

Overlay module, suitable for the video data after frame processing image covering current frame image is handled；

Display module, suitable for the video data after display processing.

Further, segmentation module is further adapted for：

Further, the device also includes：Scene cut network training module；The training process of scene cut network passes through Successive ignition is completed；

Scene cut network training module is suitable to：During an iteration, from Sample Storehouse extract sample image and Mark scene cut result corresponding with sample image, utilize sample image and the existing scene cut net of mark scene cut fructufy The training of network.

Scene cut network training module is suitable to：During an iteration, sample image is inputted to scene cut net Network, obtain sample scene cut result corresponding with sample image；

Further, the device also includes：Scene cut network training module；

Scene cut network training module includes：

Extraction unit, suitable for extracting sample image and mark scene cut knot corresponding with sample image from Sample Storehouse Fruit；

Training unit, it is trained suitable for sample image is inputted into scene cut network, wherein, in scene cut net At least one layer of convolutional layer in network, the scale coefficient or initial gauges coefficient exported using last iterative process scale regression layer Processing is zoomed in and out to the first convolution block of the convolutional layer, the second convolution block is obtained, then carries out the volume using the second convolution block The convolution algorithm of lamination, obtain the output result of the convolutional layer；

Acquiring unit, suitable for obtaining sample scene cut result corresponding with sample image；

Updating block, suitable for being lost according to the segmentation between sample scene cut result and mark scene cut result, obtain To scene cut network losses function, according to the weight parameter of scene cut network losses function renewal scene cut network；

Scene cut network training module iteration is run, until meeting predetermined convergence condition.

Further, scene cut network training module is further adapted for：When scene cut network training starts, to chi The weight parameter that degree returns layer carries out initialization process.

Further, display module is further adapted for：By the video data real-time display after processing；

The device also includes：

Uploading module, suitable for the video data after processing is uploaded into Cloud Server.

Further, uploading module is further adapted for：

According to another aspect of the invention, there is provided a kind of computing device, including：Processor, memory, communication interface and Communication bus, processor, memory and communication interface complete mutual communication by communication bus；

Memory is used to deposit an at least executable instruction, and executable instruction makes computing device is above-mentioned to be based on scene cut Video data real-time processing method corresponding to operate.

In accordance with a further aspect of the present invention, there is provided a kind of computer-readable storage medium, be stored with least one in storage medium Executable instruction, executable instruction makes computing device, and the video data real-time processing method based on scene cut is corresponding as described above Operation.

According to technical scheme provided by the invention, real-time image acquisition collecting device is captured and/or the video recorded In include the current frame image of special object；Or obtain in real time current comprising special object in currently played video Two field picture, current frame image is inputted into scene cut network, wherein, at least one layer of convolutional layer in scene cut network, The scale coefficient exported using scale regression layer zooms in and out processing to the first convolution block of the convolutional layer, obtains the second convolution Block, the convolution algorithm of the convolutional layer is then carried out using the second convolution block, obtains the output result of the convolutional layer, then obtain with Scene cut result corresponding to current frame image, according to scene cut result corresponding with current frame image, determine special object Profile information, according to special object profile information, add personalized special efficacy, obtain frame processing image, frame is handled into image Covering current frame image handled after video data, the video data after display processing.Technical scheme provided by the invention Convolution block is zoomed in and out according to scale coefficient, realizes the self adaptive pantographic to receptive field, utilizes trained scene point Cut network can in real time, accurately obtain scene cut result corresponding to two field picture in video, be effectively improved image scene The accuracy rate and treatment effeciency of segmentation, more accurately two field picture can be added based on resulting scene cut result individual Property special efficacy, has beautified video data display effect.

Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention, And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can Become apparent, below especially exemplified by the embodiment of the present invention.

Brief description of the drawings

By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings：

Fig. 1 shows the stream of the video data real-time processing method according to an embodiment of the invention based on scene cut Journey schematic diagram；

Fig. 2 shows the schematic flow sheet of scene cut network training method according to an embodiment of the invention；

Fig. 3 shows the video data real-time processing method in accordance with another embodiment of the present invention based on scene cut Schematic flow sheet；

Fig. 4 shows the knot of the video data real-time processing device according to an embodiment of the invention based on scene cut Structure block diagram；

Fig. 5 shows the video data real-time processing device in accordance with another embodiment of the present invention based on scene cut Structured flowchart；

Fig. 6 shows a kind of structural representation of computing device according to embodiments of the present invention.

Embodiment

The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure Completely it is communicated to those skilled in the art.

Fig. 1 shows the stream of the video data real-time processing method according to an embodiment of the invention based on scene cut Journey schematic diagram, this method is based on trained scene cut network and performed, as shown in figure 1, this method comprises the following steps：

Step S100, real-time image acquisition collecting device is captured and/or the video recorded in comprising special object Current frame image；Or the current frame image that special object is included in currently played video is obtained in real time.

Image capture device illustrates by taking mobile terminal as an example in the present embodiment.Get mobile terminal camera in real time Current frame image when current frame image in recorded video or shooting video.Due to the present invention to special object at Reason, therefore only obtain the current frame image comprising special object during acquisition current frame image.Except real-time image acquisition collecting device Outside the captured and/or video recorded, it can also obtain in real time current comprising special object in currently played video Two field picture.

Step S101, current frame image is inputted into scene cut network.

Special object, such as human body are contained in current frame image.In order to accurately add individual character for current frame image Change special efficacy, it is necessary to carry out scene cut to current frame image using scene cut network.Wherein, scene cut network is by instruction Experienced, trained scene cut network can utilize the network mesoscale with returning the scale coefficient that layer exports to convolutional layer Convolution block zoom in and out, so as to more precisely carry out scene cut to the current frame image that is inputted.Specifically, field Sample used in scape segmentation network training includes：Multiple sample images of sample library storage and mark corresponding with sample image Scene cut result.Wherein, it is that each scene in sample image is split and mark gained through artificial to mark scene cut result The segmentation result arrived.

Wherein, the training process of scene cut network is completed by successive ignition.Alternatively, during an iteration, Sample image and mark scene cut result corresponding with sample image are extracted from Sample Storehouse, utilizes sample image and mark The training of the existing scene cut network of scene cut fructufy.

Alternatively, an iteration process includes：Sample image is inputted to scene cut network, obtained and sample image pair The sample scene cut result answered；Lost, obtained according to the segmentation between sample scene cut result and mark scene cut result To scene cut network losses function, the training of scene cut network is realized using scene cut network losses function.

Step S102, at least one layer of convolutional layer in scene cut network, the scale coefficient exported using scale regression layer Processing is zoomed in and out to the first convolution block of the convolutional layer, obtains the second convolution block.

Those skilled in the art can be carried out according to selection is actually needed to the convolution block of which layer or the convolutional layer of which layer Scaling processing, is not limited herein.For the ease of distinguishing, the convolution block for treating scaling processing is referred to as the first convolution in the present invention Block, the convolution block after scaled processing is referred to as the second convolution block.Assuming that to a certain layer convolutional layer in scene cut network First convolution block zooms in and out processing, then in the convolutional layer, the scale coefficient exported using scale regression layer is to the convolutional layer The first convolution block zoom in and out processing, obtain the second convolution block.

Wherein, scale regression layer is the middle convolutional layer of scene cut network, and middle convolutional layer refers to scene cut network In one or more layers convolutional layer, those skilled in the art can select suitable one according to being actually needed in scene cut network Layer or multilayer convolutional layer do not limit herein as scale regression layer.In the present invention, characteristic pattern scale regression layer exported Referred to as scale coefficient characteristic pattern, scale coefficient are the characteristic vector in the scale coefficient characteristic pattern of scale regression layer output.This hair It is bright that convolution block is zoomed in and out according to scale coefficient, it is achieved thereby that to the self adaptive pantographic of receptive field, can be more precisely Scene cut is carried out to the current frame image inputted, is effectively improved the accuracy rate of image scene segmentation.

Step S103, the convolution algorithm of the convolutional layer is carried out using the second convolution block, obtain the output result of the convolutional layer.

After the second convolution block has been obtained, so that it may the convolution algorithm of the convolutional layer is carried out using the second convolution block, is obtained The output result of the convolutional layer.

Step S104, obtain scene cut result corresponding with current frame image.

After step S103 obtains the output result of the convolutional layer, if in scene cut network after the convolutional layer Other convolutional layers also be present, then carry out follow-up convolution using the output result of the convolutional layer as the input of latter convolutional layer Computing.After the convolution algorithm by convolutional layer all in scene cut network, field corresponding with current frame image is obtained Scape segmentation result.

Step S105, according to scene cut result corresponding with current frame image, determine the profile information of special object.

After scene cut result corresponding with current frame image has been obtained, so that it may according to corresponding with current frame image Scene cut result, determine the profile information of special object.Assuming that special object is human body, then can be according to scene cut As a result, the profile information of human body is determined, is human body so as to distinguish which region in current frame image, which region is not people Body.

Step S106, according to the profile information of special object, personalized special efficacy is added, obtain frame processing image.

After the profile information of special object is determined, so that it may personalized according to the profile information of special object, addition Special efficacy, obtain frame processing image.Those skilled in the art can set personalized special efficacy according to being actually needed, and not limit herein. For example, can be according to the profile information of special object, in the edge additive effect textures of special object, effect textures can be quiet The effect textures of state, or dynamic effect textures, specifically, when special object is human body, effect textures can be Such as flame, the note of bounce, the spray and other effects textures；When special object is human body head, effect textures can be as tuinga, Ear rocked and other effects textures, are configured with specific reference to performance, do not limit herein.

Step S107, the video data after frame processing image covering current frame image is handled.

Original current frame image is directly override using frame processing image, the video counts after directly can be processed According to.Meanwhile the user of recording can also be immediately seen frame processing image.

When obtaining frame processing image, frame can be handled image and directly cover original current frame image.Speed during covering Degree is very fast, is typically completed within 1/24 second.For a user, because the time of covering treatment is relatively short, human eye is not bright Aobvious discovers, i.e., human eye does not perceive the process that the former current frame image in video data is capped.So subsequently showing During video data after processing, shoot and/or record equivalent to one side and/or during playing video data, one side real-time display For the video data after processing, user does not feel as the display effect that two field picture in video data covers.

Step S108, the video data after display processing.

After video data after being handled, it can be shown in real time, after user can directly be seen that processing Video data display effect.

The video data real-time processing method based on scene cut provided according to the present embodiment, real-time image acquisition collection Equipment is captured and/or the video recorded in include special object current frame image；Or obtain in real time currently played Video in include the current frame image of special object, current frame image is inputted into scene cut network, wherein, in scene Split at least one layer of convolutional layer in network, the scale coefficient exported using scale regression layer is entered to the first convolution block of the convolutional layer The processing of row scaling, is obtained the second convolution block, the convolution algorithm of the convolutional layer is then carried out using the second convolution block, obtains the convolution The output result of layer, then obtains scene cut result corresponding with current frame image, according to field corresponding with current frame image Scape segmentation result, the profile information of special object is determined, according to the profile information of special object, add personalized special efficacy, obtain Frame handles image, the video data after frame processing image covering current frame image is handled, the video counts after display processing According to.Technical scheme provided by the invention zooms in and out according to scale coefficient to convolution block, realizes the adaptive contracting to receptive field Put, using trained scene cut network can in real time, accurately obtain scene cut knot corresponding to two field picture in video Fruit, the accuracy rate and treatment effeciency of image scene segmentation are effectively improved, can based on resulting scene cut result Personalized special efficacy accurately more is added to two field picture, has beautified video data display effect.

Fig. 2 shows the schematic flow sheet of scene cut network training method according to an embodiment of the invention, such as Fig. 2 Shown, the training step of scene cut network comprises the following steps：

Step S200, sample image and mark scene cut result corresponding with sample image are extracted from Sample Storehouse.

Sample image is not only stored in Sample Storehouse, also stored for mark scene cut result corresponding with sample image. The quantity that those skilled in the art can set the sample image stored in Sample Storehouse according to being actually needed, is not limited herein. In step s 200, sample image is extracted from Sample Storehouse, and extracts mark scene cut result corresponding with the sample image.

Step S201, sample image is inputted into scene cut network and is trained.

After sample image is extracted, sample image is inputted into scene cut network and is trained.

Step S202, at least one layer of convolutional layer in scene cut network, utilize last iterative process scale regression layer The scale coefficient or initial gauges coefficient of output zoom in and out processing to the first convolution block of the convolutional layer, obtain the second convolution Block.

Those skilled in the art can be carried out according to selection is actually needed to the convolution block of which layer or the convolutional layer of which layer Scaling processing, is not limited herein.Assuming that the first convolution block of a certain layer convolutional layer in scene cut network is zoomed in and out Processing, then in the convolutional layer, scale coefficient or initial gauges system using the output of last iterative process scale regression layer Several the first convolution blocks to the convolutional layer zoom in and out processing, obtain the second convolution block.

Specifically,, can be to chi when scene cut network training starts in order to be effectively trained to scene cut network The weight parameter that degree returns layer carries out initialization process.Those skilled in the art can set specific initialization according to being actually needed Weight parameter, do not limit herein.Initial gauges coefficient is the yardstick of the scale regression layer output after initialized processing Characteristic vector in coefficient characteristics figure.

Step S203, the convolution algorithm of the convolutional layer is carried out using the second convolution block, obtain the output result of the convolutional layer.

After the second convolution block has been obtained, so that it may the convolution algorithm of the convolutional layer is carried out using the second convolution block, is obtained The output result of the convolutional layer.Because the second convolution block is obtained by being zoomed in and out to the first convolution block after processing, then the Coordinate corresponding to characteristic vector in two convolution blocks may not be integer, therefore, these be obtained using default computational methods Characteristic vector corresponding to non-integer coordinates.Those skilled in the art can set default computational methods according to being actually needed, herein not Limit.For example, default computational methods can be linear interpolation method, specifically, using linear interpolation method, from the second convolution block Middle sampling obtains characteristic vector, forms the 3rd convolution block, and then the convolution kernel according to the 3rd convolution block and the convolutional layer is rolled up Product computing, obtain the output result of the convolutional layer.

After the output result of the convolutional layer is obtained, if it also be present after the convolutional layer in scene cut network His convolutional layer, then carry out follow-up convolution algorithm using the output result of the convolutional layer as the input of latter convolutional layer. After convolution algorithm by convolutional layer all in scene cut network, scene cut knot corresponding with sample image is obtained Fruit.

Step S204, obtain sample scene cut result corresponding with sample image.

Obtain the sample scene cut result corresponding with sample image that scene cut network obtains.

Step S205, lost, must shown up according to the segmentation between sample scene cut result and mark scene cut result Scape splits network losses function, and the weight parameter of scene cut network is updated according to scene cut network losses function.

Wherein, those skilled in the art can according to be actually needed scene set segmentation network losses function particular content, Do not limit herein.According to scene cut network losses function, backpropagation (back propagation) computing is carried out, is passed through Operation result updates the weight parameter of scene cut network.

Step S206, iteration perform the training step of scene cut network, until meeting predetermined convergence condition.

Wherein, those skilled in the art can set predetermined convergence condition according to being actually needed, and not limit herein.For example, Predetermined convergence condition may include：Iterations reaches default iterations；And/or the output of scene cut network losses function Value is less than predetermined threshold value.Specifically, can be by judging whether iterations reaches default iterations to judge whether to meet Predetermined convergence condition, whether predetermined threshold value can also be less than to judge whether according to the output valve of scene cut network losses function Meet predetermined convergence condition.In step S206, iteration performs the training step of scene cut network, until meeting predetermined convergence Condition, so as to obtain trained scene cut network.

In a specific training process, such as need the first volume to a certain layer convolutional layer in scene cut network Product block zooms in and out processing, it is assumed that the convolutional layer is referred to as into convolutional layer J, convolutional layer J input feature vector figure is Wherein, H_AFor the height parameter of the input feature vector figure, W_AFor the width parameter of the input feature vector figure, C_AFor the input feature vector figure Port number；Convolutional layer J output characteristic figure isWherein, H_BFor the height parameter of the output characteristic figure, W_BFor this The width parameter of output characteristic figure, C_BFor the port number of the output characteristic figure；The scale coefficient characteristic pattern of scale regression layer output ForWherein, H_SFor the height parameter of the scale coefficient characteristic pattern, W_SJoin for the width of the scale coefficient characteristic pattern Number, the port number of the scale coefficient characteristic pattern is 1, specifically, H_S=H_B, and W_S=W_B。

In scene cut network, 3 × 3 common convolutional layer may be selected as scale regression layer, scale regression Port number corresponding to layer is that 1 output characteristic figure is scale coefficient characteristic pattern.In order to effectively be instructed to scene cut network Practice, prevent scene cut network from collapsing in the training process, it is necessary to when scene cut network training starts, to scale regression layer Weight parameter carry out initialization process.Wherein, the weight parameter of the initialization of scale regression layer is

Wherein, w₀For scale regression layer initialize after convolution kernel, a be convolution kernel in optional position, b₀For initialization Bias term.In the initialization process to the weight parameter of scale regression layer, convolution kernel be arranged to meet Gaussian Profile with Machine factor sigma, and its value very little, close to 0, and bias term is arranged to 1, therefore, the scale regression layer of initialized processing By all output, close to 1 value, i.e., initial gauges coefficient is close to 1, then initial gauges coefficient is applied into convolutional layer J Afterwards, the convolution results difference of resulting output result and standard is little, so as to provide relatively stable training process, effectively Scene cut network is prevented to collapse in the training process.

For convolutional layer J, it is assumed that convolutional layer J convolution kernel isIt is biased toConvolution Layer J input feature vector figure beConvolutional layer J output characteristic figure isThe convolutional layer J first volume Product block is X^t, to the first convolution block X^tThe second convolution block obtained by zooming in and out after handling is Y^t, wherein, generally, k =1.Optional position t in output characteristic figure B, corresponding characteristic vector areCharacteristic vector B^tFor from this feature to The second convolution block Y that amount corresponds in input feature vector figure A^tObtained with convolution kernel K inner products, wherein, position

First convolution block X^tIt it is one with (p in input feature vector figure A^t,q^t) centered on square area, its length of side fixes For 2kd+1, wherein,It is the coefficient of expansion of convolution,WithIt is input feature vector figure A In coordinate.First convolution block X^tIn will uniformly choose the individual characteristic vectors of (2k+1) × (2k+1) and be multiplied with convolution kernel K, have Body, the coordinate of these characteristic vectors is

Wherein,

Assuming that s^tIt is the characteristic vector B for corresponding to position t in output characteristic figure B in scale coefficient characteristic pattern^tYardstick system Number, s^tPosition in scale coefficient characteristic pattern is also t, with characteristic vector B^tPosition in output characteristic figure B is identical.

Utilize scale coefficient s^tTo convolutional layer J the first convolution block X^tProcessing is zoomed in and out, obtains the second convolution block Y^t, the Two convolution block Y^tIt it is one with (p in input feature vector figure A^t,q^t) centered on square area, its length of side can be according to scale coefficient s^tChange turns toSecond convolution block Y^tIn will uniformly choose the individual characteristic vectors of (2k+1) × (2k+1) and convolution kernel K It is multiplied, specifically, the coordinate of these characteristic vectors is

Wherein, scale coefficient s^tIt is real number value, then the coordinate x' of characteristic vector_ijAnd y'_ijIt may not be integer.At this In invention, characteristic vector corresponding to these non-integer coordinates is obtained using linear interpolation method.Using linear interpolation method, from Two convolution block Y^tMiddle sampling obtains characteristic vector, forms the 3rd convolution block Z^t, then for the 3rd convolution block Z^tIn each feature VectorSpecific calculation formula be：

Wherein, If (x'_ij,y'_ij) beyond input feature vector figure A scope, then corresponding characteristic vector will be set to 0 as filling up.Assuming thatConvolution kernel K with it is corresponding Characteristic vector be multiplied and output channel be c convolution vector, wherein,Institute is so corresponded in convolution algorithm Have passage by element multiplication process can withMatrix multiple expression is carried out, then propagated forward (forward propagation) process is

In back-propagation process, it is assumed that from B^tGradient g (the B transmitted^t), gradient is

G (b)=g (B^t)

Wherein, g () represents gradient function, ()^TRepresenting matrix transposition.It is worth noting that, calculating the mistake of gradient Cheng Zhong, convolution kernel K and biasing b final gradient are the sums of the gradient that all positions obtain from output characteristic figure B.For linear Interpolation Process, the local derviation of its character pair vector are

The local derviation of respective coordinates is

It is correspondingLocal derviation with it is above-mentionedFormula it is similar, here is omitted.

Because coordinate is by scale coefficient s^tIt is calculated, then coordinate pair answers the local derviation of scale coefficient to be

Based on above-mentioned local derviation, scale coefficient characteristic pattern S and input feature vector figure A gradient can be obtained by following formula：

As can be seen here, above-mentioned convolution process forms the calculating process that an entirety can be led, therefore, in scene cut network The weight parameter of each convolutional layer and the weight parameter of scale regression layer can be trained by end-to-end form.In addition, The gradient calculation that the gradient of scale coefficient can be transmitted by its later layer obtains, and therefore, scale coefficient is automatic and implicit Obtain.During concrete implementation, propagated forward process and back-propagation process can be in graphics processors (GPU) Concurrent operation, there is higher computational efficiency.

The scene cut network training method provided according to the present embodiment, it can train to obtain according to scale coefficient to convolution The scene cut network that block zooms in and out, the self adaptive pantographic to receptive field is realized, and can using scene cut network Scene cut result corresponding to being quickly obtained, it is effectively improved the accuracy rate and treatment effeciency of image scene segmentation.

Fig. 3 shows the video data real-time processing method in accordance with another embodiment of the present invention based on scene cut Schematic flow sheet, this method is based on trained scene cut network and performed, and as shown in Fig. 3, this method includes following step Suddenly：

Step S300, real-time image acquisition collecting device is captured and/or the video recorded in comprising special object Current frame image；Or the current frame image that special object is included in currently played video is obtained in real time.

Step S301, current frame image is inputted into scene cut network.

Wherein, scene cut network is trained that trained scene cut network can be utilized in the network The convolution block of convolutional layer is zoomed in and out, more precisely the present frame to being inputted the scale coefficient of scale regression layer output Image carries out scene cut.

Step S302, at least one layer of convolutional layer in scene cut network, the scale coefficient exported using scale regression layer Processing is zoomed in and out to the first convolution block of the convolutional layer, obtains the second convolution block.

Those skilled in the art can be carried out according to selection is actually needed to the convolution block of which layer or the convolutional layer of which layer Scaling processing, is not limited herein.Scale coefficient is the characteristic vector in the scale coefficient characteristic pattern of scale regression layer output, In step S302, processing is zoomed in and out to the first convolution block of the convolutional layer using scale coefficient, obtains the second convolution block.

Step S303, using linear interpolation method, sampled from the second convolution block and obtain characteristic vector, form the 3rd convolution Block.

Due to the second convolution block be to the first convolution block zoom in and out processing after obtained by, then in the second convolution block Coordinate corresponding to characteristic vector may not be integer, therefore using linear interpolation method, obtain these non-integer coordinates pair The characteristic vector answered.Using linear interpolation method, sampled from the second convolution block and obtain characteristic vector, then obtained according to sampling Characteristic vector form the 3rd convolution block.Assuming that the second convolution block is Y^t, the 3rd convolution block is Z^t, then for the 3rd convolution block Z^tIn each characteristic vectorSpecific calculation formula be：

Wherein, D is the coefficient of expansion of convolution, s^tIt is yardstick system Number, generally, k=1.

Step S304, the convolution kernel according to the 3rd convolution block and the convolutional layer carry out convolution algorithm, obtain the convolutional layer Output result.

After the 3rd convolution block has been obtained, the convolution kernel according to the 3rd convolution block and the convolutional layer carries out convolution algorithm, Obtain the output result of the convolutional layer.

Step S305, obtain scene cut result corresponding with current frame image.

After step S304 obtains the output result of the convolutional layer, if in scene cut network after the convolutional layer Other convolutional layers also be present, then carry out follow-up convolution using the output result of the convolutional layer as the input of latter convolutional layer Computing.After the convolution algorithm by convolutional layer all in scene cut network, field corresponding with current frame image is obtained Scape segmentation result.

Step S306, according to scene cut result corresponding with current frame image, determine the profile information of special object.

After step S305 has obtained scene cut result corresponding with current frame image, so that it may according to present frame figure The scene cut result as corresponding to, determine the profile information of special object.Assuming that special object is human body, then can basis Scene cut result, the profile information of human body is determined, be human body so as to distinguish which region in current frame image, which area Domain is not human body.

Step S307, according to the profile information of special object, personalized special efficacy is added, obtain frame processing image.

After the profile information of special object is determined, so that it may personalized according to the profile information of special object, addition Special efficacy, obtain frame processing image.Those skilled in the art can set personalized special efficacy according to being actually needed, and not limit herein.

For example, can be according to the profile information of special object, in the edge additive effect textures of special object, effect textures Can be static effect textures, or dynamic effect textures, specifically, and when special object is human body, effect patch Figure can be such as flame, the note of bounce, the spray and other effects textures；When special object is human body head, effect textures can be with For such as tuinga, the ear rocked and other effects textures, it is configured with specific reference to performance, does not limit herein.And for example, can be according to According to the profile information of special object, specific object region and nonspecific subject area are determined, nonspecific subject area can be claimed For background area, the image of background area is then replaced with into other background images, other background images can be two-dimensional scene Background image, can also three-dimensional scenic background image, specifically, can be by the image of background area when special object is human body Replace with such as three-dimensional seabed scene background image, three-dimensional volcano scene background image three-dimensional scenic background image.

Step S308, the video data after frame processing image covering current frame image is handled.

Step S309, the video data after display processing.

Step S310, the video data after processing is uploaded to Cloud Server.

Video data after processing can be directly uploaded to Cloud Server, specifically, can be by the video counts after processing According to be uploaded to one or more cloud video platform server, such as iqiyi.com, youku.com, fast video cloud video platform server, So that cloud video platform server is shown video data in cloud video platform.Or can also be by the video data after processing Cloud direct broadcast server is uploaded to, can be straight by cloud when the user for having live viewing end is watched into cloud direct broadcast server Broadcast server and give video data real time propelling movement to viewing subscription client.Or the video data after processing can also be uploaded to Cloud public number server, when there is user to pay close attention to the public number, video data is pushed to public number by cloud public number server Pay close attention to client；Further, cloud public number server can also be accustomed to according to the viewing of the user of concern public number, and push meets The video data of user's custom pays close attention to client to public number.

The video data real-time processing method based on scene cut provided according to the present embodiment, not only in accordance with scale coefficient Convolution block is zoomed in and out, realizes the self adaptive pantographic to receptive field, but also using linear interpolation method to scaling processing Convolution block is further processed afterwards, and it is the choosing of the characteristic vector of non-integer to solve for coordinate in convolution block after scaling processing Take problem；And using trained scene cut network can in real time, accurately obtain field corresponding to two field picture in video Scape segmentation result, the accuracy rate and treatment effeciency of image scene segmentation are effectively improved, based on resulting scene cut As a result personalized special efficacy accurately more can be added to two field picture, has beautified video data display effect, optimized video counts According to processing mode.

Fig. 4 shows the knot of the video data real-time processing device according to an embodiment of the invention based on scene cut Structure block diagram, the device is based on trained scene cut network and run, as shown in figure 4, the device includes：Acquisition module 410th, module 420, generation module 430, determining module 440, processing module 450, overlay module 460 and display module 470 are split.

Acquisition module 410 is suitable to：Real-time image acquisition collecting device is captured and/or the video recorded in comprising specific The current frame image of object；Or the current frame image that special object is included in currently played video is obtained in real time.

Segmentation module 420 is suitable to：Current frame image is inputted into scene cut network, wherein, in scene cut network Middle at least one layer of convolutional layer, the scale coefficient exported using scale regression layer zoom in and out place to the first convolution block of the convolutional layer Reason, is obtained the second convolution block, the convolution algorithm of the convolutional layer is then carried out using the second convolution block, obtains the output of the convolutional layer As a result.

Wherein, scene cut network is trained that specifically, the sample used in scene cut network training includes： Multiple sample images of sample library storage and mark scene cut result corresponding with sample image.Scale regression layer is scene Split the middle convolutional layer of network.Those skilled in the art can select suitable one according to being actually needed in scene cut network Layer or multilayer convolutional layer do not limit herein as scale regression layer.Scale coefficient is the scale coefficient of scale regression layer output Characteristic vector in characteristic pattern.

Generation module 430 is suitable to：Obtain scene cut result corresponding with current frame image.

Determining module 440 is suitable to：According to scene cut result corresponding with current frame image, the profile of special object is determined Information.

Processing module 450 is suitable to：According to the profile information of special object, personalized special efficacy is added, obtains frame processing image.

Overlay module 460 is suitable to：Video data after frame processing image covering current frame image is handled.

Overlay module 460 directly overrides former current frame image using frame processing image, after directly can be processed Video data.Meanwhile the user of recording can also be immediately seen frame processing image.

Display module 470 is suitable to：Video data after display processing.

Display module 470 handled after video data after, it can be shown in real time, user can be direct See the display effect of the video data after processing.

The video data real-time processing device based on scene cut provided according to the present embodiment, can be according to scale coefficient Convolution block is zoomed in and out, realizes the self adaptive pantographic to receptive field, can be real using trained scene cut network When, accurately obtain scene cut result corresponding to two field picture in video, be effectively improved the accuracy rate of image scene segmentation And treatment effeciency, personalized special efficacy more accurately can be added to two field picture based on resulting scene cut result, it is beautiful Video data display effect is changed.

Fig. 5 shows the video data real-time processing device in accordance with another embodiment of the present invention based on scene cut Structured flowchart, the device is based on trained scene cut network and run, as shown in figure 5, the device includes：Acquisition module 510th, scene cut network training module 520, segmentation module 530, generation module 540, determining module 550, processing module 560, Overlay module 570, display module 580 and uploading module 590.

Acquisition module 510 is suitable to：Real-time image acquisition collecting device is captured and/or the video recorded in comprising specific The current frame image of object；Or the current frame image that special object is included in currently played video is obtained in real time.

Wherein, the training process of scene cut network is completed by successive ignition.Scene cut network training module 520 is suitable In：During an iteration, sample image and mark scene cut knot corresponding with sample image are extracted from Sample Storehouse Fruit, utilize the training of sample image and the existing scene cut network of mark scene cut fructufy.

Alternatively, scene cut network training module 520 is suitable to：During an iteration, by sample image input to Scene cut network, obtain sample scene cut result corresponding with sample image；According to sample scene cut result and mark Segmentation loss between scene cut result, obtains scene cut network losses function, utilizes scene cut network losses function Realize the training of scene cut network.

In a specific embodiment, scene cut network training module 520 may include：Extraction unit 521, training unit 522nd, acquiring unit 523 and updating block 524.

Specifically, extraction unit 521 is suitable to：Sample image and mark corresponding with sample image are extracted from Sample Storehouse Scene cut result.

Training unit 522 is suitable to：Sample image is inputted into scene cut network and is trained, wherein, in scene point At least one layer of convolutional layer in network is cut, utilizes the scale coefficient or initial gauges of the output of last iterative process scale regression layer Coefficient zooms in and out processing to the first convolution block of the convolutional layer, obtains the second convolution block, is then carried out using the second convolution block The convolution algorithm of the convolutional layer, obtain the output result of the convolutional layer.

Wherein, scale regression layer is the middle convolutional layer of scene cut network, and scale coefficient is the output of scale regression layer Characteristic vector in scale coefficient characteristic pattern.

Alternatively, training unit 522 is further adapted for：Using linear interpolation method, sample and obtain from the second convolution block Characteristic vector, form the 3rd convolution block；Convolution kernel according to the 3rd convolution block and the convolutional layer carries out convolution algorithm, obtains the volume The output result of lamination.

Acquiring unit 523 is suitable to：Obtain sample scene cut result corresponding with sample image.

Updating block 524 is suitable to：Lost according to the segmentation between sample scene cut result and mark scene cut result, Scene cut network losses function is obtained, the weight parameter of scene cut network is updated according to scene cut network losses function.

The iteration of scene cut network training module 520 is run, until meeting predetermined convergence condition.

Wherein, those skilled in the art can set predetermined convergence condition according to being actually needed, and not limit herein.For example, Predetermined convergence condition may include：Iterations reaches default iterations；And/or the output of scene cut network losses function Value is less than predetermined threshold value.Specifically, can be by judging whether iterations reaches default iterations to judge whether to meet Predetermined convergence condition, whether predetermined threshold value can also be less than to judge whether according to the output valve of scene cut network losses function Meet predetermined convergence condition.

Alternatively, scene cut network training module 520 is further adapted for：It is right when scene cut network training starts The weight parameter of scale regression layer carries out initialization process.

Segmentation module 530 is suitable to：Current frame image is inputted into scene cut network, wherein, in scene cut network Middle at least one layer of convolutional layer, the scale coefficient exported using scale regression layer zoom in and out place to the first convolution block of the convolutional layer Reason, obtains the second convolution block, then using linear interpolation method, from the second convolution block sampling obtain characteristic vector, composition the Three convolution blocks；Convolution kernel according to the 3rd convolution block and the convolutional layer carries out convolution algorithm, obtains the output result of the convolutional layer.

Generation module 540 is suitable to：Obtain scene cut result corresponding with current frame image.

Determining module 550 is suitable to：According to scene cut result corresponding with current frame image, the profile of special object is determined Information.

Processing module 560 is suitable to：According to the profile information of special object, personalized special efficacy is added, obtains frame processing image.

Overlay module 570 is suitable to：Video data after frame processing image covering current frame image is handled.

Display module 580 is suitable to：Video data after display processing.

Display module 580 handled after video data after, it can be shown in real time, user can be direct See the display effect of the video data after processing.

Uploading module 590, suitable for the video data after processing is uploaded into Cloud Server.

Video data after processing can be directly uploaded to Cloud Server by uploading module 590, specifically, uploading module 590 can be uploaded to the video data after processing the cloud video platform server of one or more, such as iqiyi.com, youku.com, fast The cloud video platform server such as video, so that cloud video platform server is shown video data in cloud video platform.Or Video data after processing can also be uploaded to cloud direct broadcast server by uploading module 590, when the user for having live viewing end enters When entering cloud direct broadcast server and being watched, can by cloud direct broadcast server by video data real time propelling movement to viewing user client End.Or the video data after processing can also be uploaded to cloud public number server by uploading module 590, it is somebody's turn to do when there is user's concern During public number, video data is pushed to public number concern client by cloud public number server；Further, cloud public number service Device can also be accustomed to according to the viewing of the user of concern public number, and the video data that push meets user's custom is paid close attention to public number Client.

The video data real-time processing device based on scene cut provided according to the present embodiment, not only in accordance with scale coefficient Convolution block is zoomed in and out, realizes the self adaptive pantographic to receptive field, but also using linear interpolation method to scaling processing Convolution block is further processed afterwards, and it is the choosing of the characteristic vector of non-integer to solve for coordinate in convolution block after scaling processing Take problem；And using trained scene cut network can in real time, accurately obtain field corresponding to two field picture in video Scape segmentation result, the accuracy rate and treatment effeciency of image scene segmentation are effectively improved, based on resulting scene cut As a result personalized special efficacy accurately more can be added to two field picture, has beautified video data display effect, optimized video counts According to processing mode.

Present invention also offers a kind of nonvolatile computer storage media, computer-readable storage medium is stored with least one can Execute instruction, the video data based on scene cut that executable instruction can perform in above-mentioned any means embodiment are handled in real time Method.

Fig. 6 shows a kind of structural representation of computing device according to embodiments of the present invention, the specific embodiment of the invention The specific implementation to computing device does not limit.

As shown in fig. 6, the computing device can include：Processor (processor) 602, communication interface (Communications Interface) 604, memory (memory) 606 and communication bus 608.

Wherein：

Processor 602, communication interface 604 and memory 606 complete mutual communication by communication bus 608.

Communication interface 604, for being communicated with the network element of miscellaneous equipment such as client or other servers etc..

Processor 602, for configuration processor 610, it is real-time can specifically to perform the above-mentioned video data based on scene cut Correlation step in processing method embodiment.

Specifically, program 610 can include program code, and the program code includes computer-managed instruction.

Processor 602 is probably central processor CPU, or specific integrated circuit ASIC (Application Specific Integrated Circuit), or it is arranged to implement the integrated electricity of one or more of the embodiment of the present invention Road.The one or more processors that computing device includes, can be same type of processor, such as one or more CPU；Also may be used To be different types of processor, such as one or more CPU and one or more ASIC.

Memory 606, for depositing program 610.Memory 606 may include high-speed RAM memory, it is also possible to also include Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.

Program 610 specifically can be used for so that processor 602 performs dividing based on scene in above-mentioned any means embodiment The video data real-time processing method cut.The specific implementation of each step may refer to above-mentioned based on scene cut in program 610 Corresponding description in corresponding steps and unit in the real-time Processing Example of video data, will not be described here.The skill of art Art personnel can be understood that, for convenience and simplicity of description, the equipment of foregoing description and the specific work process of module, The corresponding process description in preceding method embodiment is may be referred to, will not be repeated here.

Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein. Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair Bright preferred forms.

In the specification that this place provides, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail And technology, so as not to obscure the understanding of this description.

Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect, Above in the description to the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore, Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself Separate embodiments all as the present invention.

Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so to appoint Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power Profit requires, summary and accompanying drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation Replace.

In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed One of meaning mode can use in any combination.

The all parts embodiment of the present invention can be realized with hardware, or to be run on one or more processor Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice Microprocessor or digital signal processor (DSP) are come one of some or all parts in realizing according to embodiments of the present invention A little or repertoire.The present invention is also implemented as setting for performing some or all of method as described herein Standby or program of device (for example, computer program and computer program product).Such program for realizing the present invention can deposit Storage on a computer-readable medium, or can have the form of one or more signal.Such signal can be from because of spy Download and obtain on net website, either provide on carrier signal or provided in the form of any other.

It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims, Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such Element.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer real It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame Claim.

Claims

1. a kind of video data real-time processing method based on scene cut, methods described is based on trained scene cut net Network and perform, methods described includes：

Real-time image acquisition collecting device is captured and/or the video recorded in include special object current frame image；Or Person, the current frame image that special object is included in currently played video is obtained in real time；

The current frame image is inputted into the scene cut network, wherein, at least one layer of volume in scene cut network Lamination, the scale coefficient exported using scale regression layer are zoomed in and out processing to the first convolution block of the convolutional layer, obtain second Convolution block, the convolution algorithm of the convolutional layer is then carried out using the second convolution block, obtain the output result of the convolutional layer；Institute State the middle convolutional layer that scale regression layer is the scene cut network；

Obtain scene cut result corresponding with current frame image；

According to scene cut result corresponding with current frame image, the profile information of the special object is determined；

According to the profile information of the special object, personalized special efficacy is added, obtains frame processing image；

Frame processing image is covered into the video data after the current frame image is handled；

Video data after display processing.

2. according to the method for claim 1, wherein, the convolution that the convolutional layer is carried out using the second convolution block is transported Calculate, the output result for obtaining the convolutional layer further comprises：

Convolution algorithm is carried out according to the convolution kernel of the 3rd convolution block and the convolutional layer, obtains the output result of the convolutional layer.

3. method according to claim 1 or 2, wherein, the sample used in the scene cut network training includes：Sample Multiple sample images of library storage and mark scene cut result corresponding with sample image.

4. according to the method described in claim any one of 1-3, wherein, the training process of the scene cut network passes through multiple Iteration is completed；During an iteration, sample image and mark corresponding with sample image are extracted from the Sample Storehouse Scene cut result, utilize the training of the sample image and the existing scene cut network of mark scene cut fructufy.

5. according to the method described in claim any one of 1-4, wherein, the training process of the scene cut network passes through multiple Iteration is completed；Wherein an iteration process includes：

Lost according to the segmentation between the sample scene cut result and the mark scene cut result, obtain scene cut Network losses function, the training of scene cut network is realized using the scene cut network losses function.

6. according to the method described in claim any one of 1-5, wherein, the training step of the scene cut network includes：

Sample image and mark scene cut result corresponding with sample image are extracted from the Sample Storehouse；

The sample image is inputted into the scene cut network and is trained, wherein, in scene cut network at least One layer of convolutional layer, using the scale coefficient or initial gauges coefficient of last iterative process scale regression layer output to the convolution First convolution block of layer zooms in and out processing, obtains the second convolution block, then carries out the convolutional layer using the second convolution block Convolution algorithm, obtain the output result of the convolutional layer；

Obtain sample scene cut result corresponding with sample image；

Lost according to the segmentation between the sample scene cut result and the mark scene cut result, obtain scene cut Network losses function, the weight parameter of the scene cut network is updated according to the scene cut network losses function；

Iteration performs the training step of the scene cut network, until meeting predetermined convergence condition.

7. according to the method described in claim any one of 1-6, wherein, the predetermined convergence condition includes：Iterations reaches Default iterations；And/or the output valve of the scene cut network losses function is less than predetermined threshold value.

8. a kind of video data real-time processing device based on scene cut, described device is based on trained scene cut net Network and run, described device includes：

Acquisition module, suitable for captured by real-time image acquisition collecting device and/or in the video recorded comprising special object Current frame image；Or the current frame image that special object is included in currently played video is obtained in real time；

Split module, suitable for the current frame image is inputted into the scene cut network, wherein, in scene cut network Middle at least one layer of convolutional layer, the scale coefficient exported using scale regression layer zoom in and out place to the first convolution block of the convolutional layer Reason, is obtained the second convolution block, the convolution algorithm of the convolutional layer is then carried out using the second convolution block, obtains the convolutional layer Output result；The scale regression layer is the middle convolutional layer of the scene cut network；

Determining module, suitable for according to scene cut result corresponding with current frame image, determining that the profile of the special object is believed Breath；

Processing module, suitable for the profile information according to the special object, personalized special efficacy is added, obtain frame processing image；

Overlay module, suitable for frame processing image is covered into the video data after the current frame image is handled；

Display module, suitable for the video data after display processing.

9. a kind of computing device, including：Processor, memory, communication interface and communication bus, the processor, the storage Device and the communication interface complete mutual communication by the communication bus；

The memory is used to deposit an at least executable instruction, and the executable instruction makes the computing device such as right will Ask operation corresponding to the video data real-time processing method based on scene cut any one of 1-7.

10. a kind of computer-readable storage medium, an at least executable instruction, the executable instruction are stored with the storage medium Make video data real-time processing method based on scene cut of the computing device as any one of claim 1-7 corresponding Operation.