CN107590811A - Landscape image processing method, device and computing device based on scene cut - Google Patents
Landscape image processing method, device and computing device based on scene cut Download PDFInfo
- Publication number
- CN107590811A CN107590811A CN201710909638.0A CN201710909638A CN107590811A CN 107590811 A CN107590811 A CN 107590811A CN 201710909638 A CN201710909638 A CN 201710909638A CN 107590811 A CN107590811 A CN 107590811A
- Authority
- CN
- China
- Prior art keywords
- scene cut
- landscape image
- network
- convolutional layer
- image
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of landscape image processing method, device, computing device and computer-readable storage medium based on scene cut, this method includes：Obtain pending landscape image；Pending landscape image is inputted into scene cut network, obtains scene cut result corresponding with pending landscape image；According to scene cut result corresponding with pending landscape image, the profile information of special object is determined；According to the profile information of special object, landscaping effect, the landscape image after being handled are added for special object.The technical scheme can quickly and accurately obtain scene cut result corresponding to landscape image, more accurately can add landscaping effect to landscape such as the sky in landscape image, meadows based on scene cut result, improve image display effect.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of landscape image processing side based on scene cut
Method, device, 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 be well to the sky in landscape image, grass
The landscape such as ground add treatment effect, and the display effect of the landscape image 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 landscape image 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 landscape image processing method based on scene cut, this method
Performed based on trained scene cut network, this method includes：
Obtain pending landscape image；Wherein, special object is included in pending landscape image；
Pending landscape image is inputted into 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；Yardstick returns
Return the middle convolutional layer that layer is scene cut network；
Obtain scene cut result corresponding with pending landscape image；
According to scene cut result corresponding with pending landscape image, the profile information of special object is determined；
According to the profile information of special object, landscaping effect, the landscape image after being handled are added for special object.
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 profile information according to special object, landscaping effect, the wind after being handled are added for special object
Scape image further comprises：
According to the profile information of special object, landscaping effect textures, the landscape figure after being handled are added for special object
Picture.
Further, the profile information according to special object, landscaping effect, the wind after being handled are added for special object
Scape image further comprises：
According to the profile information of special object, texture processing, tone processing, contrast processing, light are carried out for special object
According to processing and/or brightness processed, the landscape image after being handled.
Further, in the profile information according to special object, landscaping effect is added for special object, after being handled
After landscape image, this method also includes：
Landscape image after display processing.
Further, the landscape image after display processing further comprises：
Landscape image after real-time display processing.
Further, in the profile information according to special object, landscaping effect is added for special object, after being handled
After landscape image, this method also includes：
The shooting triggered according to user instructs, the landscape image after preservation processing.
Further, in the profile information according to special object, landscaping effect is added for special object, after being handled
After landscape image, this method also includes：
According to user trigger record command, preserve by the landscape image after handling as group of picture into video.
According to another aspect of the present invention, there is provided a kind of landscape image processing unit based on scene cut, the device
Run based on trained scene cut network, the device includes：
Acquisition module, suitable for obtaining pending landscape image；Wherein, special object is included in pending landscape image；
Split module, suitable for pending landscape 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；Scale regression layer is the middle convolutional layer of scene cut network；
Generation module, suitable for obtaining scene cut result corresponding with pending landscape image；
Determining module, suitable for according to scene cut result corresponding with pending landscape image, determining the wheel of special object
Wide information；
Processing module, suitable for the profile information according to special object, landscaping effect is added for special object, after obtaining processing
Landscape image.
Further, segmentation module is further adapted for：
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 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.
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, sample image is inputted to scene cut net
Network, 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 training of scene cut network is realized using scene cut network losses function.
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, 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, 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, processing module is further adapted for：
According to the profile information of special object, landscaping effect textures, the landscape figure after being handled are added for special object
Picture.
Further, processing module is further adapted for：
According to the profile information of special object, texture processing, tone processing, contrast processing, light are carried out for special object
According to processing and/or brightness processed, the landscape image after being handled.
Further, the device also includes：
Display module, suitable for the landscape image after display processing.
Further, display module is further adapted for：
Landscape image after real-time display processing.
Further, the device also includes：
First preserving module, suitable for the shooting instruction triggered according to user, the landscape image after preservation processing.
Further, the device also includes：
Second preserving module, suitable for the record command triggered according to user, preserve by the landscape image after handling as frame
The video of image composition.
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
Landscape image 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 make computing device behaviour corresponding to the landscape image processing method based on scene cut as described above
Make.
According to technical scheme provided by the invention, pending landscape image is obtained, pending landscape image is inputted to field
In scape segmentation network, wherein, 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, the second convolution block is obtained, then carries out the volume using the second convolution block
The convolution algorithm of lamination, obtains the output result of the convolutional layer, then obtains scene cut corresponding with pending landscape image
As a result, according to scene cut result corresponding with pending landscape image, the profile information of special object is determined, according to specific right
The profile information of elephant, landscaping effect, the landscape image after being handled are added for special object.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
Scene cut result corresponding to landscape image can quickly and accurately be obtained by cutting network, be effectively improved image scene segmentation
Accuracy rate and treatment effeciency, can be more accurately to the day in landscape image based on resulting scene cut result
The landscape such as sky, meadow add landscaping effect, improve image 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 that the flow of the landscape image processing method according to an embodiment of the invention based on scene cut is shown
It is intended to；
Fig. 2 shows the schematic flow sheet of scene cut network training method according to an embodiment of the invention；
Fig. 3 shows the flow of the landscape image processing method in accordance with another embodiment of the present invention based on scene cut
Schematic diagram；
Fig. 4 shows the structural frames of the landscape image processing unit according to an embodiment of the invention based on scene cut
Figure；
Fig. 5 shows the structure of the landscape image processing unit in accordance with another embodiment of the present invention based on scene cut
Block diagram；
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 that the flow of the landscape image processing method according to an embodiment of the invention based on scene cut is shown
It is intended to, this method is based on trained scene cut network and performed, as shown in figure 1, this method comprises the following steps：
Step S100, obtain pending landscape image.
Specifically, pending landscape image can be the wind in the landscape image or website that user oneself shoots
Scape image, the landscape image that other users are shared is can also be, is not limited herein.In addition, pending landscape image can be
Not only personage had been included but also had included the image of landscape, or not comprising the image for thering is personage only to include landscape.Wherein, treat
Include special object in processing landscape image, special object can be the objects such as sky, meadow, trees, mountain, and special object is also
Can be the objects such as sea, lake.Those skilled in the art can be configured according to being actually needed to special object, not limit herein
It is fixed.
Step S101, pending landscape image is inputted into scene cut network.
Include special object, such as sky, meadow in pending landscape image.In order to being accurately pending wind
The landscape such as sky, meadow in scape image add landscaping effect, it is necessary to enter using scene cut network handles processing landscape image
Row scene cut.Wherein, scene cut network is trained that trained scene cut network can utilize the network
Mesoscale zooms in and out with returning the scale coefficient of layer output to the convolution block of convolutional layer, so as to more precisely defeated to institute
The pending landscape image entered carries out scene cut.Specifically, the sample used in scene cut network training includes：Sample stock
Multiple sample images of storage and mark scene cut result corresponding with sample image.Wherein, mark scene cut result is
Each scene in sample image is through artificial segmentation and the segmentation result obtained by mark.
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 pending landscape 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 pending landscape 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, obtain corresponding with pending landscape image
Scene cut result.
Step S105, according to scene cut result corresponding with pending landscape image, determine that the profile of special object is believed
Breath.
After scene cut result corresponding with pending landscape image has been obtained, so that it may according to pending landscape figure
The scene cut result as corresponding to, determine the profile information of special object.When special object is day space-time, then can basis
Scene cut result, the profile information of sky is determined, to be subsequently that sky adds landscaping effect.
Step S106, according to the profile information of special object, landscaping effect, the wind after being handled are added for special object
Scape image.
For example, when special object is day space-time, landscaping effect can be added for sky according to the profile information of sky, such as
Raising brightness processed is carried out to sky in image, the landscape image after being handled.
The landscape image processing method based on scene cut provided according to the present embodiment, obtains pending landscape image,
Pending landscape image is inputted into scene cut network, wherein, at least one layer of convolutional layer in scene cut network, utilize
The scale coefficient of scale regression layer output zooms in and out processing to the first convolution block of the convolutional layer, obtains the second convolution block, and
The convolution algorithm of the convolutional layer is carried out using the second convolution block afterwards, obtains the output result of the convolutional layer, then obtains and wait to locate
Scene cut result corresponding to managing landscape image, according to scene cut result corresponding with pending landscape image, is determined specific
The profile information of object, according to the profile information of special object, landscaping effect, the landscape after being handled are added for special object
Image.Technical scheme provided by the invention zooms in and out according to scale coefficient to convolution block, realizes to the adaptive of receptive field
Scaling, scene cut result corresponding to landscape image can be quickly and accurately obtained using trained scene cut network,
The accuracy rate and treatment effeciency of image scene segmentation are effectively improved, can be more based on resulting scene cut result
Landscaping effect accurately is added to landscape such as the sky in landscape image, meadows, improves image 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, HAFor the height parameter of the input feature vector figure, WAFor the width parameter of the input feature vector figure, CAFor the input feature vector figure
Port number；Convolutional layer J output characteristic figure isWherein, HBFor the height parameter of the output characteristic figure, WBFor this
The width parameter of output characteristic figure, CBFor the port number of the output characteristic figure；The scale coefficient characteristic pattern of scale regression layer output
ForWherein, HSFor the height parameter of the scale coefficient characteristic pattern, WSJoin for the width of the scale coefficient characteristic pattern
Number, the port number of the scale coefficient characteristic pattern is 1, specifically, HS=HB, and WS=WB。
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 to
Convolutional layer J input feature vector figure isConvolutional layer J output characteristic figure isConvolutional layer J
The first convolution block be Xt, to the first convolution block XtThe second convolution block obtained by zooming in and out after handling is Yt, wherein, typically
In the case of, k=1.Optional position t in output characteristic figure B, corresponding characteristic vector areCharacteristic vector BtFor
The the second convolution block Y corresponded to by this feature vector in input feature vector figure AtObtained with convolution kernel K inner products, wherein, position
First convolution block XtIt it is one with (p in input feature vector figure At,qt) 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 XtIn 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 stIt is the characteristic vector B for corresponding to position t in output characteristic figure B in scale coefficient characteristic patterntYardstick system
Number, stPosition in scale coefficient characteristic pattern is also t, with characteristic vector BtPosition in output characteristic figure B is identical.
Utilize scale coefficient stTo convolutional layer J the first convolution block XtProcessing is zoomed in and out, obtains the second convolution block Yt, the
Two convolution block YtIt it is one with (p in input feature vector figure At,qt) centered on square area, its length of side can be according to scale coefficient
stChange turns toSecond convolution block YtIn 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 stIt is real number value, then the coordinate x' of characteristic vectorijAnd 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 YtMiddle sampling obtains characteristic vector, forms the 3rd convolution block Zt, then for the 3rd convolution block ZtIn each feature
VectorSpecific calculation formula be：
Wherein,If (x'ij,y'ij) beyond input feature vector
Scheme A scope, then corresponding characteristic vector will be set to 0 as filling up.Assuming thatConvolution kernel K with
The convolution vector that corresponding characteristic vector is multiplied and output channel is c, wherein,It is so right in convolution algorithm
Should all passages by element multiplication process can withMatrix multiple expression is carried out, then forward direction passes
Broadcasting (forward propagation) process is
In back-propagation process, it is assumed that from BtGradient g (the B transmittedt), gradient is
G (b)=g (Bt)
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 stIt 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 flow of the landscape image processing method in accordance with another embodiment of the present invention based on scene cut
Schematic diagram, this method is based on trained scene cut network and performed, as shown in figure 3, this method comprises the following steps：
Step S300, obtain pending landscape image.
Wherein, special object is included in pending landscape image, special object can be sky, meadow, trees, mountain etc.
Object.
Step S301, pending landscape 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 the scale coefficient of scale regression layer output, it is more precisely pending to what is inputted
Landscape 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 Yt, the 3rd convolution block is Zt, then for the 3rd convolution block
ZtIn each characteristic vectorSpecific calculation formula be：
Wherein,D is the coefficient of expansion of convolution, stIt is yardstick
Coefficient, 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 pending landscape 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, obtain corresponding with pending landscape image
Scene cut result.
Step S306, according to scene cut result corresponding with pending landscape image, determine that the profile of special object is believed
Breath.
After step S305 has obtained scene cut result corresponding with pending landscape image, so that it may according to waiting to locate
Scene cut result corresponding to managing landscape image, determine the profile information of special object.
Step S307, according to the profile information of special object, landscaping effect, the wind after being handled are added for special object
Scape image.
Specifically, landscaping effect textures can be added for special object, after obtaining processing according to the profile information of special object
Landscape image；In addition, texture processing can also be carried out for special object, tone is handled, right according to the profile information of special object
Than degree processing, photo-irradiation treatment and/or brightness processed, the landscape image after being handled.Those skilled in the art can be according to reality
Need to select the specific mode for adding landscaping effect, do not limit herein.
For example, including sky in pending landscape image, but sky seems, some are murky, and user wishes this is waited to locate
The sky addition landscaping effect in landscape image is managed, sky is seemed azure, then special object can be arranged to sky, according to
Scene cut result corresponding with pending landscape image, the profile information of sky is determined, then can believed according to the profile of sky
Breath, blue sky effect textures are added for sky, sky is seemed azure, so as to the landscape image after being handled.
And for example, meadow is included in pending landscape image, user wishes to add the meadow in the pending landscape image
Add landscaping effect, then special object can be arranged to meadow, according to scene cut result corresponding with pending landscape image,
The profile information on meadow is determined, then can carry out texture processing according to the profile information on meadow for meadow, and it is overall for its addition
Lighting effect, the processing such as be adjusted to tone, contrast, brightness etc., make its overall effect more natural, attractive in appearance, from
And the landscape image after being handled.
Step S308, the landscape image after real-time display processing.
Landscape image after obtained processing is shown in real time, user can directly be seen that to pending landscape image
The landscape image obtained after processing.After the landscape image after being handled, replaced treat using the landscape image after processing at once
Processing landscape image is shown, is typically replaced within 1/24 second, for a user, relative due to replacing the time
Short, human eye is not discovered significantly, equivalent to the landscape image after real-time display processing.
Step S309, the shooting triggered according to user instruct, the landscape image after preservation processing.
After landscape image after display processing, the shooting that can also be triggered according to user instructs, the wind after preservation processing
Scape image.Such as the shooting push button of user's click camera, triggering shooting instruction, the landscape image after the processing of display is protected
Deposit.
Step S310, according to user trigger record command, preserve by the landscape image after handling as group of picture into
Video.
During landscape image after display processing, the record command that can also be triggered according to user, after preserving by handling
Landscape image as group of picture into video.As user clicks on the recording button of camera, triggering record command, by the place of display
Landscape image after reason is preserved as the two field picture in video, so as to preserve the landscape image after multiple processing as frame figure
As the video of composition.
Step S309 and step S310 is the optional step of the present embodiment, and in the absence of perform sequencing, according to
The different instruction selection of family triggering performs corresponding step.
The landscape image processing method based on scene cut provided according to the present embodiment, not only in accordance with scale coefficient to volume
Product block zooms in and out, and realizes the self adaptive pantographic to receptive field, but also using linear interpolation method to being rolled up after scaling processing
Product block is further processed, and solves and is asked for coordinate in convolution block after scaling processing for the selection of the characteristic vector of non-integer
Topic；And it can quickly and accurately obtain scene cut knot corresponding to landscape image using trained scene cut network
Fruit, the accuracy rate and treatment effeciency of image scene segmentation are effectively improved, can based on resulting scene cut result
Landscaping effect accurately more is added to landscape such as the sky in landscape image, meadows, image display effect is improved, optimizes
Picture processing mode.
Fig. 4 shows the structural frames of the landscape image processing unit according to an embodiment of the invention based on scene cut
Figure, the device is based on trained scene cut network and run, as shown in figure 4, the device includes：Acquisition module 410, divide
Cut module 420, generation module 430, determining module 440 and processing module 450.
Acquisition module 410 is suitable to：Obtain pending landscape image.
Wherein, special object is included in pending landscape image, special object can be sky, meadow, trees, mountain etc.
Object.
Segmentation module 420 is suitable to：Pending landscape image is inputted into scene cut network, wherein, in scene cut
At least one layer of convolutional layer in network, the scale coefficient exported using scale regression layer are contracted to the first convolution block of the convolutional layer
Processing is put, obtains 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.
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 pending landscape image.
Determining module 440 is suitable to：According to scene cut result corresponding with pending landscape image, special object is determined
Profile information.
Processing module 450 is suitable to：According to the profile information of special object, landscaping effect is added for special object, is obtained everywhere
Landscape image after reason.
The landscape image processing unit based on scene cut provided according to the present embodiment, can be according to scale coefficient to volume
Product block zoom in and out, realize the self adaptive pantographic to receptive field, using trained scene cut network can quickly, standard
Scene cut result corresponding to landscape image really is obtained, is effectively improved the accuracy rate and processing effect of image scene segmentation
Rate, more accurately the landscape such as the sky in landscape image, meadow can be added based on resulting scene cut result beautiful
Change effect, improve image display effect.
Fig. 5 shows the structure of the landscape image processing unit in accordance with another embodiment of the present invention based on scene cut
Block diagram, the device is based on trained scene cut network and run, as shown in figure 5, the device includes：Acquisition module 510,
Scene cut network training module 520, segmentation module 530, generation module 540, determining module 550, processing module 560, display
Module 570, the first preserving module 580 and the second preserving module 590.
Acquisition module 510 is suitable to：Obtain pending landscape image.
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：Pending landscape image is inputted into scene cut network, wherein, in scene cut
At least one layer of convolutional layer in network, the scale coefficient exported using scale regression layer are contracted to the first convolution block of the convolutional layer
Processing is put, obtains the second convolution block, then using linear interpolation method, is sampled from the second convolution block and obtains characteristic vector, group
Into the 3rd convolution block；Convolution kernel according to the 3rd convolution block and the convolutional layer carries out convolution algorithm, obtains the output of the convolutional layer
As a result.
Generation module 540 is suitable to：Obtain scene cut result corresponding with pending landscape image.
Determining module 550 is suitable to：According to scene cut result corresponding with pending landscape image, special object is determined
Profile information.
Processing module 560 is suitable to：According to the profile information of special object, landscaping effect is added for special object, is obtained everywhere
Landscape image after reason.
Alternatively, processing module 560 is further adapted for：It is beautiful for special object addition according to the profile information of special object
Change effect textures, the landscape image after being handled.
Alternatively, processing module 560 is further adapted for：According to the profile information of special object, line is carried out for special object
Reason processing, tone processing, contrast processing, photo-irradiation treatment and/or brightness processed, the landscape image after being handled.
Display module 570 is suitable to：Landscape image after display processing.
Alternatively, display module 570 is further adapted for：Landscape image after real-time display processing.Display module 570 is incited somebody to action
To processing after landscape image shown that user can directly be seen that to being obtained after the processing of pending landscape image in real time
Landscape image.After the landscape image after processing module 560 is handled, display module 570 is at once using the landscape after processing
Image is replaced pending landscape image and shown, is typically replaced within 1/24 second, for a user, due to replacing
Time is relatively short, and human eye is not discovered significantly, equivalent to the landscape image after 570 real-time display processing of display module.
First preserving module 580 is suitable to：The shooting triggered according to user instructs, the landscape image after preservation processing.
After landscape image after display processing, the shooting that the first preserving module 580 can trigger according to user instructs, and protects
Deposit the landscape image after processing.Such as the shooting push button of user's click camera, triggering shooting instruction, the first preserving module 580 will show
Landscape image after the processing shown is preserved.
Second preserving module 590 is suitable to：The record command triggered according to user, is preserved by the landscape image conduct after handling
Group of picture into video.
During landscape image after display processing, record command that the second preserving module 590 can trigger according to user is protected
Deposit by the landscape image after handling as group of picture into video.Such as the recording button of user's click camera, triggering recording refers to
Order, the second preserving module 590 is preserved the landscape image after the processing of display as the two field picture in video, so as to preserve
Landscape image after multiple processing as group of picture into video.
According to the first preserving module 580 and the second preserving module 590 corresponding to the different instruction execution that user triggers.
The landscape image processing unit based on scene cut provided according to the present embodiment, not only in accordance with scale coefficient to volume
Product block zooms in and out, and realizes the self adaptive pantographic to receptive field, but also using linear interpolation method to being rolled up after scaling processing
Product block is further processed, and solves and is asked for coordinate in convolution block after scaling processing for the selection of the characteristic vector of non-integer
Topic；And it can quickly and accurately obtain scene cut knot corresponding to landscape image using trained scene cut network
Fruit, the accuracy rate and treatment effeciency of image scene segmentation are effectively improved, can based on resulting scene cut result
Landscaping effect accurately more is added to landscape such as the sky in landscape image, meadows, image display effect is improved, optimizes
Picture 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, executable instruction can perform the landscape image processing side based on scene cut in above-mentioned any means embodiment
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 can specifically perform the above-mentioned landscape image processing based on scene cut
Correlation step in embodiment of the method.
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 landscape image processing method cut.The specific implementation of each step may refer to the above-mentioned landscape based on scene cut in program 610
Corresponding description in corresponding steps and unit in image procossing embodiment, will not be described here.Those skilled in the art can
To be well understood, for convenience and simplicity of description, the equipment of foregoing description and the specific work process of module, may be referred to
Corresponding process description in preceding method embodiment, 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 construed to title.
Claims (10)
1. a kind of landscape image processing method based on scene cut, methods described be based on trained scene cut network and
Perform, methods described includes：
Obtain pending landscape image；Wherein, special object is included in the pending landscape image；
The pending landscape image is inputted into the scene cut network, wherein, at least one in scene cut network
Layer convolutional layer, the scale coefficient exported using scale regression layer are zoomed in and out processing to the first convolution block of the convolutional layer, obtained
Second convolution block, the convolution algorithm of the convolutional layer is then carried out using the second convolution block, obtain the output knot of the convolutional layer
Fruit；The scale regression layer is the middle convolutional layer of the scene cut network；
Obtain scene cut result corresponding with pending landscape image；
According to scene cut result corresponding with pending landscape image, the profile information of special object is determined；
According to the profile information of the special object, landscaping effect, the landscape image after being handled are added for special object.
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：
Using linear interpolation method, sampled from the second convolution block and obtain characteristic vector, form the 3rd convolution block；
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：
Sample image is inputted to scene cut network, obtains 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 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 landscape image processing unit based on scene cut, described device be based on trained scene cut network and
Operation, described device include：
Acquisition module, suitable for obtaining pending landscape image；Wherein, special object is included in the pending landscape image；
Split module, suitable for the pending landscape image is inputted into the scene cut network, wherein, in scene cut
At least one layer of convolutional layer in network, the scale coefficient exported using scale regression layer are contracted to the first convolution block of the convolutional layer
Processing is put, obtains 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；The scale regression layer is the middle convolutional layer of the scene cut network；
Generation module, suitable for obtaining scene cut result corresponding with pending landscape image；
Determining module, suitable for according to scene cut result corresponding with pending landscape image, determining that the profile of special object is believed
Breath；
Processing module, suitable for the profile information according to the special object, landscaping effect is added for special object, after obtaining processing
Landscape image.
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 landscape image 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 behaviour corresponding to the landscape image processing method based on scene cut of the computing device as any one of claim 1-7
Make.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710909638.0A CN107590811B (en) | 2017-09-29 | 2017-09-29 | Scene segmentation based landscape image processing method and device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710909638.0A CN107590811B (en) | 2017-09-29 | 2017-09-29 | Scene segmentation based landscape image processing method and device and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107590811A true CN107590811A (en) | 2018-01-16 |
| CN107590811B CN107590811B (en) | 2021-06-29 |
Family
ID=61052249
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710909638.0A Active CN107590811B (en) | 2017-09-29 | 2017-09-29 | Scene segmentation based landscape image processing method and device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107590811B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109035260A (en) * | 2018-07-27 | 2018-12-18 | 京东方科技集团股份有限公司 | A kind of sky areas dividing method, device and convolutional neural networks |
| CN109089040A (en) * | 2018-08-20 | 2018-12-25 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus and terminal device |
| CN109151575A (en) * | 2018-10-16 | 2019-01-04 | Oppo广东移动通信有限公司 | Multimedia data processing method and device, computer readable storage medium |
| CN109151318A (en) * | 2018-09-28 | 2019-01-04 | 成都西纬科技有限公司 | A kind of image processing method, device and computer storage medium |
| CN110288607A (en) * | 2019-07-02 | 2019-09-27 | 数坤（北京）网络科技有限公司 | Divide optimization method, system and the computer readable storage medium of network |
| WO2021114500A1 (en) * | 2019-12-09 | 2021-06-17 | 上海传英信息技术有限公司 | Image processing method and apparatus, electronic device, and computer-readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488534A (en) * | 2015-12-04 | 2016-04-13 | 中国科学院深圳先进技术研究院 | Method, device and system for deeply analyzing traffic scene |
| CN106022221A (en) * | 2016-05-09 | 2016-10-12 | 腾讯科技（深圳）有限公司 | Image processing method and processing system |
| WO2016195496A2 (en) * | 2015-06-05 | 2016-12-08 | Universiteit Van Amsterdam | Deep receptive field networks |
-
2017
- 2017-09-29 CN CN201710909638.0A patent/CN107590811B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016195496A2 (en) * | 2015-06-05 | 2016-12-08 | Universiteit Van Amsterdam | Deep receptive field networks |
| CN105488534A (en) * | 2015-12-04 | 2016-04-13 | 中国科学院深圳先进技术研究院 | Method, device and system for deeply analyzing traffic scene |
| CN106022221A (en) * | 2016-05-09 | 2016-10-12 | 腾讯科技（深圳）有限公司 | Image processing method and processing system |
Non-Patent Citations (3)
| Title |
|---|
| LI CHEN ET AL: "Adaptive Local Receptive Field Convolutional Neural Networks for Handwritten Chinese Character Recognition", 《CCPR 2014, PART II》 * |
| VIJAY BADRINARAYANAN ET AL: "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation", 《ARXIV:1511.00561V3[CS.CV]》 * |
| ZHEN WEI ET AL: "Learning Adaptive Receptive Fields for Deep Image Parsing Network", 《2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109035260A (en) * | 2018-07-27 | 2018-12-18 | 京东方科技集团股份有限公司 | A kind of sky areas dividing method, device and convolutional neural networks |
| US11151403B2 (en) | 2018-07-27 | 2021-10-19 | Boe Technology Group Co., Ltd. | Method and apparatus for segmenting sky area, and convolutional neural network |
| CN109089040A (en) * | 2018-08-20 | 2018-12-25 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus and terminal device |
| CN109089040B (en) * | 2018-08-20 | 2021-05-14 | Oppo广东移动通信有限公司 | Image processing method, image processing device and terminal equipment |
| CN109151318A (en) * | 2018-09-28 | 2019-01-04 | 成都西纬科技有限公司 | A kind of image processing method, device and computer storage medium |
| CN109151575A (en) * | 2018-10-16 | 2019-01-04 | Oppo广东移动通信有限公司 | Multimedia data processing method and device, computer readable storage medium |
| CN109151575B (en) * | 2018-10-16 | 2021-12-14 | Oppo广东移动通信有限公司 | Multimedia data processing method and device and computer readable storage medium |
| CN110288607A (en) * | 2019-07-02 | 2019-09-27 | 数坤（北京）网络科技有限公司 | Divide optimization method, system and the computer readable storage medium of network |
| WO2021114500A1 (en) * | 2019-12-09 | 2021-06-17 | 上海传英信息技术有限公司 | Image processing method and apparatus, electronic device, and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107590811B (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107590811A (en) | Landscape image processing method, device and computing device based on scene cut | |
| CN107610146A (en) | Image scene segmentation method, apparatus, computing device and computer-readable storage medium | |
| CN107730514A (en) | Scene cut network training method, device, computing device and storage medium | |
| Pathak et al. | Context encoders: Feature learning by inpainting | |
| CN107563497B (en) | Computing device and operation method for sparse artificial neural network | |
| KR102309702B1 (en) | Method and device for encoding image and testing method and testing device using the same | |
| CN107644423A (en) | Video data real-time processing method, device and computing device based on scene cut | |
| CN109685202A (en) | Data processing method and device, storage medium and electronic device | |
| CN108288067A (en) | Training method, bidirectional research method and the relevant apparatus of image text Matching Model | |
| CN107563357A (en) | Live dress ornament based on scene cut, which is dressed up, recommends method, apparatus and computing device | |
| CN107679489A (en) | Automatic Pilot processing method, device and computing device based on scene cut | |
| CN108961253A (en) | A kind of image partition method and device | |
| CN112639828A (en) | Data processing method, method and equipment for training neural network model | |
| CN108304921A (en) | The training method and image processing method of convolutional neural networks, device | |
| CN110874636B (en) | Neural network model compression method and device and computer equipment | |
| CN107766803A (en) | Video personage based on scene cut dresss up method, apparatus and computing device | |
| CN112561028A (en) | Method for training neural network model, and method and device for data processing | |
| CN107610149A (en) | Image segmentation result edge optimization processing method, device and computing device | |
| CN110148088A (en) | Image processing method, image rain removing method, device, terminal and medium | |
| Ge et al. | Neural-sim: Learning to generate training data with nerf | |
| CN114897136A (en) | Multi-scale attention mechanism method and module and image processing method and device | |
| CN109583586A (en) | A kind of convolution kernel processing method and processing device | |
| Yang et al. | Hidden path selection network for semantic segmentation of remote sensing images | |
| CN107622498A (en) | Image penetration management method, apparatus and computing device based on scene cut | |
| CN106203442B (en) | A kind of copy image feature extracting method based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |