KR20200073160A - Apparatus and method for virtual reality sickness reduction based on virtual reality sickness assessment - Google Patents

Abstract

Disclosed are a virtual reality content sensory fatigue degree reduction device and a method thereof. According to one embodiment of the present invention, the virtual reality content sensory fatigue degree reduction device comprises: a first module extracting feature information for each of motion sickness inducing factors set in advance through analysis of virtual reality content; and a second module determining the motion sickness inducing factors required to reduce motion sickness among the motion sickness inducing factors based on the extracted feature information for each of motion sickness inducting factors and performing the motion sickness reduction for the corresponding feature information by using a pre-learned deep learning neural network for each of the determined motion sickness inducting factors to generate the virtual reality content into the virtual reality content having a motion sickness score which is equal to or less than a preset reference motion sickness score.

Description

Apparatus and method for virtual reality sickness reduction based on virtual reality sickness assessment}

The present invention relates to a technology for reducing cyber motion sickness of virtual reality (VR) content, and more particularly, to an apparatus and method for reducing cyber motion sickness of VR content based on analysis of motion sickness inducer feature information will be.

Recently, with the development of displays such as 3D display and head mount display (HMD), interest in virtual reality (VR) content has increased, and the VR-related market has been greatly expanded to various fields such as games, broadcasting, and entertainment.

VR content refers to content that gives viewers a sense of immersion as if they are actually experiencing the video they are viewing. VR content photographed and produced to provide viewers with a lifelike immersion generally has characteristics such as stereo format, 360-degree video information, and fast and many movements. However, due to these characteristics, when watching VR content with high immersion, about 70-80% of viewers are known to experience severe fatigue or cybersickness.

In addition, when watching VR content, most viewers who have experienced fatigue or motion sickness are known to experience a phenomenon in which these symptoms persist even after viewing. In order to prevent such side effects and to watch and produce VR content safely, it is urgently needed to develop a technology that reduces cyber sickness of VR content.

For VR content viewers, it is possible to receive secure VR content produced through VR content motion sickness reduction technology. In the case of VR content creators, through VR content motion sickness reduction technology, it is possible to produce safer VR content by adjusting the motion sickness level of VR content that causes severe motion sickness. However, there are few studies currently analyzing VR elements and reducing them.

When watching VR content, there are various VR content characteristics that cause fatigue and motion sickness, for example, fast and complex motion, low resolution of the image, and low frame rate of the image.

Therefore, there is a need for a VR content motion sickness reduction technology that can automatically reduce factors that can cause fatigue and the like analyzed by a VR motion sickness analysis and evaluation module from VR content.

Embodiments of the present invention provide an apparatus and a method for reducing cyber motion sickness of VR content based on analysis of motion sickness inducer feature information.

Specifically, embodiments of the present invention, by extracting the feature information of each of the motion sickness inducers through VR content analysis, and using a deep learning neural network based on the extracted feature information to reduce the motion-inducing features of the VR content Provided is an apparatus and method.

An apparatus for reducing motion sickness in virtual reality content according to an embodiment of the present invention includes: a first module for extracting feature information for each of motion sickness inducers preset through analysis of virtual reality content; And determining motion sickness inducers requiring motion sickness reduction among the motion sickness inducers based on feature information for each of the extracted motion sickness inducers, and using a deep learning neural network previously learned for each of the determined motion sickness inducers. And a second module for generating the virtual reality content as virtual reality content having a motion sickness score equal to or less than a preset reference motion sickness score by performing motion sickness reduction on the corresponding characteristic information.

The first module may perform analysis on the virtual reality content based on deep learning, and extract feature information on each of the motion sickness inducers including motion characteristics, resolution characteristics, and frame rate characteristics.

The second module sequentially reduces the motion sickness for the feature information of each of the determined motion sickness inducers in the virtual reality content, so that the virtual reality content becomes virtual reality content having a motion sickness score equal to or less than a preset reference motion sickness score. Can be created.

The second module calculates a motion sickness score of the virtual reality content based on the feature information of each of the motion sickness inducers, calculates a gradient size in each feature information for the calculated motion sickness score, and the By analyzing the influence information of each of the feature information on the motion sickness score based on the calculated gradient size, the motion sickness reduction may be determined as a motion sickness inducer.

The second module may include a first deep neural network that generates a frame of the virtual reality content as a frame less than or equal to a preset reference motion when the virtual reality content has a motion characteristic equal to or greater than a preset reference motion sickness score, and the virtual reality content is the A second deep neural network that upscales the resolution of a frame of the virtual reality content to a preset high resolution when the resolution has a standard motion sickness score and the virtual reality content when the virtual reality content has a frame rate of the reference motion sickness score or higher. It may include a third deep neural network for generating an interpolation frame for the frames of the.

A method for reducing motion sickness in virtual reality content according to an embodiment of the present invention comprises: extracting feature information for each of the motion sickness inducers preset through analysis of the virtual reality content; Determining a motion sickness-inducing factor requiring motion sickness reduction among the motion sickness-inducing factors based on feature information on each of the extracted motion sickness-inducing factors; And by performing motion sickness reduction for the feature information by using the deep learning neural network previously learned for each of the determined motion sickness inducer, the virtual reality content to the virtual reality content having a motion sickness score below the preset reference motion sickness score And generating.

The extracting may perform analysis on the virtual reality content based on deep learning, and extract feature information for each of the motion sickness inducers including motion characteristics, resolution characteristics, and frame rate characteristics.

The generating step sequentially reduces the motion sickness of the feature information of each of the determined motion sickness inducers for the virtual reality content, so that the virtual reality content becomes virtual reality content having a motion sickness score below a preset reference motion sickness score. Can be created.

The determining step calculates the motion sickness score of the virtual reality content based on the feature information of each of the motion sickness inducers, calculates a gradient size in each feature information for the calculated motion sickness score, and the By analyzing the influence information of each of the feature information on the motion sickness score based on the calculated gradient size, the motion sickness reduction may be determined as a motion sickness inducer.

In the generating step, when the virtual reality content has a motion characteristic equal to or greater than a preset reference motion sickness score, the first deep neural network generating the frame of the virtual reality content as a frame equal to or less than a preset reference motion, the virtual reality content being the A second deep neural network that upscales the resolution of a frame of the virtual reality content to a preset high resolution when the resolution has a standard motion sickness score and the virtual reality content when the virtual reality content has a frame rate of the reference motion sickness score or higher. Motion sickness reduction for the corresponding feature information may be performed using a third deep neural network that generates an interpolation frame for frames of.

According to embodiments of the present invention, feature information of each of the motion sickness inducers may be extracted through VR content analysis, and a deep learning neural network based on the extracted feature information may be used to reduce motion sickness-inducing characteristics of the corresponding VR content. have. That is, the present invention analyzes feature information of each motion sickness inducer that causes fatigue and cyber motion sickness in VR content using a deep learning neural network, and uses the analyzed feature information to set the motion sickness factor of VR content to an appropriate level. Can be reduced.

According to embodiments of the present invention, viewers and VR content creators can effectively respond to VR content causing motion sickness, thereby creating a safe viewing environment.

The present invention proposes a technology for automatically analyzing VR content to reduce motion sickness, thereby providing digital content production, digital content providing platforms, virtual reality, medical facilities, broadcasting and multimedia, entertainment, and viewing safety standardization in the overall VR market. Can be utilized across.

While VR content is capable of providing a user with an immersive feeling that is as real as possible, it can cause fatigue to viewers due to object and camera movement, resolution, and frame rate on the content. Therefore, it is necessary for a VR content production company to produce a VR content that balances the immersion of the content and the user's fatigue. In the case of using the present invention, VR content production companies can reduce motion sickness of VR content produced by companies to a desired level quickly and efficiently without consuming labor or long time.

In the case of content that may cause extreme fatigue by using the present invention, motion sickness inducers, for example, by adjusting a low resolution, can create a user-safe VR content.

VR content platform companies can provide VR content viewers with motion sickness reduction, allowing viewers to reduce motion sickness directly to the desired level, enabling VR content viewing with a balance of appropriate immersion and fatigue to suit individual tastes.

For viewers who are sensitive to VR motion sickness using the present invention, it is possible to watch safe VR content by controlling the level of VR motion sickness to be low by using a reduction function provided by a VR content platform company.

When VR content is played through VR playback equipment, VR equipment companies reduce motion sickness factors identified through the present invention in a playback device when the content is an image that causes extreme fatigue, for example, resolution and frame rate. By heightening, it is possible to provide a user with a viewing safety function that shows VR content in which motion sickness inducers are relaxed.

1 shows a configuration for a VR content sickness reduction system according to an embodiment of the present invention.
Figure 2 shows an exemplary diagram for explaining the operation of the system of the present invention.
3 shows an exemplary diagram for a motion stabilization deep neural network for reducing motion sickness caused by rapid motion.
4 shows an exemplary diagram of a high-resolution deep neural network for reducing motion sickness caused by low resolution.
5 shows an exemplary diagram of a frame interpolation deep neural network for reducing motion sickness caused by a low frame rate.
6 is a flowchart illustrating an operation of a method for reducing motion sickness in VR according to an embodiment of the present invention.

Advantages and features of the present invention, and methods for achieving them will be clarified with reference to embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains. It is provided to completely inform the person having the scope of the invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing the embodiments, and is not intended to limit the present invention. In the present specification, the singular form also includes the plural form unless otherwise specified in the phrase. As used herein, "comprises" and/or "comprising" refers to the components, steps, operations and/or elements mentioned above, the presence of one or more other components, steps, operations and/or elements. Or do not exclude additions.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings commonly understood by those skilled in the art to which the present invention pertains. In addition, terms defined in the commonly used dictionary are not ideally or excessively interpreted unless explicitly defined.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The same reference numerals are used for the same components in the drawings, and duplicate descriptions for the same components are omitted.

The embodiments of the present invention, to reduce the cyber sickness of VR content based on motion sickness inducer analysis is the gist.

At this time, the present invention analyzes VR motion sickness inducers, for example, motion characteristics, resolution characteristics, frame rate characteristics, etc. through analysis of VR content, and analyzes the VR motion sickness inducers in advance, for example, an image processing technology, By using a deep learning neural network, etc., the temporal motion sickness factor and the spatial motion sickness factor can be reduced to a predetermined level, thereby reducing cybersickness of VR content.

The present invention is based on a recursive motion sickness reduction framework that repeatedly reduces the motion to a desired level of motion sickness according to the motion sickness measured by the VR motion sickness analysis and evaluation module, and various dips based on motion sickness inducer feature information of the analyzed VR content image. It may include a VR motion sickness reduction module that reduces each motion sickness-inducing feature by utilizing a running image processing technology.

1 shows a configuration for a VR content sickness reduction system according to an embodiment of the present invention.

Referring to FIG. 1, a VR content motion sickness reduction system according to an embodiment of the present invention includes a deep learning based VR motion sickness analysis and evaluation module and a deep learning based VR motion sickness reduction module.

The VR motion sickness analysis and evaluation module analyzes VR content to reduce motion sickness, for example, when a 360-degree VR video image is input or received, and inputs VR content based on deep learning to obtain feature information for each VR motion sickness inducer. It is extracted and judged whether the VR motion sickness score evaluated based on the extracted feature information is below a reference score of a level desired to be reduced. Here, when the evaluated VR motion sickness score is higher than the reference score, motion sickness reduction is necessary, and thus characteristic information of each motion sickness inducer extracted by the VR motion sickness reduction module is provided. On the other hand, if the evaluated VR motion sickness score is below the reference score, motion sickness reduction is determined to a desired level, and the motion sickness factor is saved as the reduced final VR content. The final VR content with reduced motion sickness elements can help viewers view VR content and content creators create VR content. For example, content viewers can reduce the level of motion sickness to an appropriate level in content that is likely to cause fatigue or cybersickness, and watch content that is safe for their personal characteristics. By adjusting the degree of cybersickness to an appropriate level, it can help to create safer VR content.

The VR motion sickness reduction module generates VR content with reduced motion sickness factors by reducing motion sickness inducers of VR content based on deep learning.

At this time, the VR motion sickness reduction module reduces each motion sickness inducer based on deep learning based on feature information of each motion sickness inducer received from the VR motion sickness analysis and evaluation module, so that motion sickness factors are reduced through reduction of motion sickness inducers. Reduced VR content can be created.

VR content with reduced motion sickness is analyzed again through the VR motion sickness analysis and evaluation module to determine whether the motion sickness score has reached the reference score, and if it is determined that the motion sickness has been reduced to a desired level, the reduction process is terminated. Otherwise, the reduction process is repeated. The process of reducing motion sickness elements in VR content using the VR motion sickness reduction system is automatic.

Furthermore, the VR motion sickness reduction module calculates motion sickness scores of VR content based on each feature information of motion sickness inducers, and calculates the gradient size in each feature information about motion sickness scores using an algorithm such as guided backpropagation. By analyzing the degree of influence of each feature information on motion sickness scores, it is determined that reduction is performed on the feature when the degree of influence of the feature exceeds a predetermined reference value, and the feature information of the determined motion sickness inducer is reduced to VR Motion sickness can be reduced.

Here, the VR motion sickness reduction module uses a method of returning to the motion sickness score by applying fully connected layers after concatenation of feature vectors corresponding to the feature information of each motion sickness inducer, thereby reducing the motion sickness score of VR content. Can be calculated.

FIG. 2 shows an exemplary view for explaining the operation of the system of the present invention, and shows an exemplary view for explaining the operation in each module illustrated in FIG. 1 in detail.

As shown in FIG. 2, the VR motion sickness analysis and evaluation module analyzes motion motion, resolution, and frame rate, respectively, and extracts feature information based on deep learning do. That is, the VR motion sickness analysis and evaluation module analyzes and extracts VR motion sickness trigger factors 1 to VR motion sickness trigger factors 1 to VR motion sickness trigger factors N through pre-set motion sickness factors, for example, VR motion sickness trigger factors 1 to Feature information of each VR motion sickness inducer N is extracted. For example, the VR motion sickness analysis and evaluation module analyzes and extracts features of VR motion sickness inducer 1 from VR content, extracts VR motion sickness feature 1, for example, rapid motion, and features of VR motion sickness trigger 2 from VR content. By analyzing and extracting, VR motion sickness-causing feature 2, for example, extracting a resolution lower than the reference resolution, and analyzing and extracting features of VR motion sickness-inducer N from VR content, VR motion sickness-causing feature N, for example A frame rate lower than the frame rate is extracted. In addition, the motion sickness score of the VR content may be calculated using the feature information of each of the extracted motion sickness inducers. Here, the VR motion sickness analysis and evaluation module can provide frame information and feature information for each motion sickness inducer through analysis of VR content as a result, and the VR motion sickness score can be calculated using the result provided as such. It can be used as input information of VR motion sickness reduction module.

The VR motion sickness reduction module is composed of a part that determines whether motion sickness inducing factors are reduced and a part that performs reduction for each motion sickness inducing feature. The deep learning based VR motion sickness reduction module receives as input the feature information and VR content of motion sickness inducers extracted by the VR motion sickness analysis and evaluation module.

At this time, the feature information of each of the motion sickness inducers may include sudden movement, low resolution and low frame rate, and the motion sickness triggerers are not limited to the above, and all motion sickness triggers that can cause VR motion sickness It can contain.

The discrimination unit for determining whether motion sickness inducing factors are reduced is determined by receiving feature information of motion sickness inducers extracted by the VR motion sickness analysis and evaluation module as input, and determining whether to perform reduction for the feature. In order to determine whether reduction is necessary for each feature, it is necessary to consider how much each motion-causing feature affects a high motion sickness score.

를 넘었을 때 해당 특징에 대해 저감을 수행한다고 판별할 수 있다. 예컨대, 판별부는 멀미유발인자 각각의 특징 정보에 기초하여 VR 컨텐츠의 멀미 점수를 계산하고, 각각의 특징 정보에 대하여 계산된 멀미 점수의 비중을 분석하여 멀미유발인자 각각의 특징 정보에 비중이 미리 설정된 기준치 이상인 멀미유발인자를 판별할 수 있다.At this time, the discrimination unit can analyze how much each motion sickness-causing feature had an effect on the predicted high VR motion sickness score using an algorithm such as guided backpropagation, and a reference value in which the influence level of the feature was set in advance

When it exceeds, it can be determined that reduction is performed on the corresponding characteristic. For example, the discrimination unit calculates motion sickness scores of VR content based on each feature information of motion sickness inducers, analyzes the weight of motion sickness scores calculated for each feature information, and sets weights in advance to each feature information of motion sickness inducers Motion sickness-inducing factors above the standard value can be identified.

The reduction unit that performs reduction for each feature considers whether the VR content and the corresponding feature determined by the discrimination unit are reduced, and performs motion sickness reduction for each feature information of motion sickness inducers based on deep learning.

At this time, for each motion sickness inducer for performing motion reduction, the reduction unit determines the motion sickness by using a neural network of a pre-modeled learning model for performing reduction, for example, a deep learning neural network. It is possible to reduce the characteristic information of the trigger, and this reduction process can be sequentially performed for each of the motion sickness inducers for performing motion sickness reduction.

For example, in FIG. 2, if motion sickness-inducing feature 1, motion sickness-inducing feature 2, and motion sickness-inducing feature N are determined as motion sickness inducers for performing motion sickness reduction, the reduction unit is a deep learning-based neural network for VR content, for example. A deep learning based neural network, for example, for VR content in which motion sickness-causing feature 1 motion-reducing motion sickness elements are reduced using the motion-stabilized deep neural network shown in FIG. Deep learning on VR content with reduced motion sickness factor of VR motion sickness feature 1 and VR motion sickness feature feature 2 using the high resolution deep neural network shown in 4 Based neural network For example, by using the frame interpolation deep neural network shown in FIG. 5, the motion sickness factor of VR motion sickness inducing feature N is reduced, thereby generating VR content with reduced motion sickness factors.

The reduction unit can provide efficiency by performing reduction only when it is determined that reduction is necessary for the corresponding characteristic. At this time, in the reduction unit, motion stabilization, high resolution, and frame interpolation deep neural network structures may be used to alleviate motion-induced features such as rapid motion, low resolution, and low frame rate.

FIG. 3 shows an exemplary diagram of a motion stabilization deep neural network for reducing motion sickness caused by rapid motion, and as shown in FIG. 3, a deep network for stabilizing motion is a spatial feature for extracting spatial features of VR content. Deep network as an encoder, for example, convolutional neural network (CNN), temporal feature for extracting temporal features of VR content. Deep network as an encoder, for example, Conv LSTM (Long Short-Term Memory) and motion from extracted features It may be configured to include a deep network for generating a stabilized frame, for example, a deconvolutional neural network (DeCNN).

Here, in each deep network, a training model for stabilizing motion may be generated through training on motion information of VR content, and motion is stabilized for VR content using a deep network based on each learning model thus generated. Frames can be created.

That is, FIG. 3 may generate a frame of VR content as a frame in which motion characteristics are reduced to have a motion sickness score of less than or equal to a preset reference motion or a motion sickness score of less than a reference motion sickness score when the VR content has motion characteristics of a reference motion sickness score or higher.

FIG. 4 shows an example of a high resolution deep neural network for reducing motion sickness caused by low resolution, and as shown in FIG. 4, a deep network for high resolution is a deep network for extracting spatial features of VR content. For example, it may be configured to include a convolutional neural network (CNN) and a deep network, for example, a deconvolutional neural network (DeCNN) for generating a frame having a higher resolution than the input resolution from the extracted feature. In the deep neural network of FIG. 4, when the resolution of the input image is K×K, upscaled to a resolution of 2K×2K to generate each high-resolution frame, thereby generating high-resolution VR content and through this, may be generated due to low resolution. Reduces motion sickness-inducing factors.

Here, in each deep network, a training model for upscaling each frame through training for high resolution of VR content may be generated, and the resolution of the VR content using the deep network based on each learning model generated as described above may be generated. Can generate upscaled frames.

That is, FIG. 4 can upscale the resolution of a frame of VR content to a preset high resolution when the VR content has a resolution characteristic of a reference motion sickness score or higher.

FIG. 5 shows an exemplary diagram of a frame interpolation deep neural network for reducing motion sickness caused by a low frame rate. As shown in FIG. 5, a deep network for frame interpolation is a spatial feature for extracting spatial features of VR content. Deep network for encoder, for example, convolutional neural network (CNN), deep network for fusion of features of two frames of VR content, for example, Concatenation and CNN, and deep network for generation of interpolated frames from extracted features , Deconvolutional Neural Network (DeCNN).

Here, each deep network may generate a training model for generating an interpolation frame through training to improve the frame rate of VR content, and use the deep network based on each learning model generated as described above for VR content. An interpolation frame can be generated, thereby improving the frame rate of VR content.

That is, FIG. 5 may generate an interpolation frame such that when the VR content has a frame rate characteristic equal to or greater than the reference motion sickness score, the VR content has a motion sickness score equal to or less than a preset reference motion or a reference motion sickness score.

Each of the reduction network configurations for reducing motion sickness inducers described in FIGS. 3 to 5 is not limited to the above-described specific deep network structure, and includes all neural network structures of a corresponding function, that is, a function capable of reducing motion sickness inducers. Can be used.

As described above, the VR motion sickness reduction module may perform motion sickness factor reduction corresponding to each motion sickness inducing factor, such as smoothing motion of VR content, increasing resolution, and interpolating frames.

As described above, the system or device according to the embodiments of the present invention extracts feature information of each motion sickness inducer through VR content analysis, and uses the deep learning neural network based on the extracted feature information to get motion sickness of the corresponding VR content Induced characteristics can be reduced.

In the prior art, there was an inefficiency in which reduction is applied to elements that do not actually cause motion sickness by reducing all motion sickness-inducing factors based on the final motion sickness score. By adding a discrimination process, the efficiency can be improved by configuring the reduction to be performed only for specific motion sickness-inducing features.

In addition, the system or device according to the embodiments of the present invention can allow viewers and VR content creators to effectively respond to VR content causing motion sickness, thereby creating a safe viewing environment. For example, the present invention may produce motion-prone VR content for a user who is sensitive to VR motion sickness, for example, by adjusting a low resolution in case of content that may cause extreme fatigue. You can also watch safe VR content by adjusting the level of VR motion sickness to a low level using the reduction function provided by.

6 is a flowchart illustrating an operation of a method for reducing motion sickness in VR according to an embodiment of the present invention, and shows an operation flowchart in the apparatus or system of FIGS. 1 to 5.

Referring to FIG. 6, the method according to an embodiment of the present invention extracts feature information of motion sickness inducers through analysis of VR content (S610).

Here, in step S610, when VR content is input, the input VR content is analyzed based on deep learning to analyze motion sickness inducers, for example, motion characteristics, resolution characteristics, frame rate characteristics, and extract feature information from each. Can.

When the feature information of each of the motion sickness inducers is extracted by step S610, the motion sickness inducer that needs to be reduced is determined based on the extracted feature information of the motion sickness inducers (S620).

At this time, step S620 calculates the motion sickness score of the VR content based on the feature information of each of the motion sickness inducers, and analyzes or calculates the weight of the motion sickness score for each feature information, thereby calculating the feature information of each motion sickness inducer. In this case, a motion sickness inducer whose specific gravity is greater than or equal to a predetermined reference value may be determined as a motion sickness inducer requiring reduction.

When the motion sickness inducer requiring reduction is determined in step S620, the feature information of the motion sickness inducer determined to be reduced is reduced based on a deep learning to generate VR content with reduced motion sickness (S630).

At this time, step S630 performs motion sickness reduction for the corresponding feature information using a deep learning neural network previously learned for each of the determined motion sickness inducers, so that VR content having a motion sickness score equal to or less than a preset reference motion sickness score Can be created with

Here, in step S630, motion sickness reduction for each feature information of the determined motion sickness inducer may be sequentially performed on VR content, and a frame of VR content including a motion greater than or equal to a predetermined reference motion is set to a frame below the reference motion. The first deep neural network to be generated, the second deep neural network that upscales the resolution of the frames of the VR content to a preset high resolution, and the frames of the VR content when the frame rate of the VR content is lower than the preset reference frame rate. Motion sickness reduction for the corresponding feature information may be performed using a third deep neural network that generates an interpolation frame.

Although the description of the method of FIG. 6 is omitted, the method of FIG. 6 may include all the contents described in the apparatus or system of FIGS. 1 to 5, which is apparent to those skilled in the art.

The device described above may be implemented with hardware components, software components, and/or combinations of hardware components and software components. For example, the devices and components described in the embodiments include a processor, controller, arithmetic logic unit (ALU), digital signal processor (micro signal processor), microcomputer, field programmable gate array (FPGA), programmable It may be implemented using one or more general purpose computers or special purpose computers, such as a logic unit, microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and/or data may be interpreted by a processing device, or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. Can be embodied in The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. At this time, the medium may continue to store a program executable on a computer, or may be temporarily stored for execution or download. In addition, the medium may be various recording means or storage means in the form of a combination of single or several hardware, and is not limited to a medium directly connected to a computer system, but may be distributed on a network. Examples of the medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks, And program instructions including ROM, RAM, flash memory, and the like. In addition, examples of other media include an application store for distributing applications, a site for distributing or distributing various software, and a recording medium or storage medium managed by a server.

As described above, although the embodiments have been described by a limited embodiment and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques are performed in a different order than the described method, and/or the components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or other components Alternatively, even if replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (10)

A first module for extracting feature information for each of the motion sickness inducers preset through analysis of virtual reality content; And
Based on the feature information for each of the extracted motion sickness inducers, the motion sickness inducer among the motion sickness inducers is determined, and a deep learning neural network previously learned for each of the determined motion sickness inducers is used. A second module that generates the virtual reality content as virtual reality content having a motion sickness score equal to or less than a preset reference motion sickness score by performing motion sickness reduction on the corresponding feature information
Virtual reality content motion sickness reduction device comprising a.
According to claim 1,
The first module
A device for reducing motion sickness of virtual reality content characterized by performing analysis on the virtual reality content based on deep learning and extracting feature information for each of the motion sickness inducers including motion characteristics, resolution characteristics, and frame rate characteristics .
According to claim 1,
The second module
The motion sickness reduction for each of the determined motion sickness inducer feature information is sequentially performed on the virtual reality content, thereby generating the virtual reality content as virtual reality content having a motion sickness score below a preset reference motion sickness score. Virtual reality content motion sickness reduction device.
According to claim 1,
The second module
Based on the feature information of each of the motion sickness inducers, the motion sickness score of the virtual reality content is calculated, the gradient size in each feature information for the calculated motion sickness score is calculated, and the calculated gradient size A virtual reality content motion sickness reduction device, characterized in that, by analyzing influence information of each of the feature information on the motion sickness score, the motion sickness reduction is determined as a motion sickness inducer.
According to claim 1,
The second module
A first deep neural network that generates a frame of the virtual reality content as a frame less than or equal to a preset reference motion when the virtual reality content has a motion characteristic equal to or greater than a predetermined reference motion sickness score, and a resolution in which the virtual reality content exceeds the reference motion sickness score When having a second deep neural network upscaling the resolution of the frame of the virtual reality content to a preset high resolution and when the virtual reality content has a frame rate equal to or greater than the reference motion sickness score, for the frames of the virtual reality content And a third deep neural network generating an interpolation frame.
Extracting feature information for each of the pre-set motion sickness inducers through analysis of virtual reality content;
Determining a motion sickness-inducing factor requiring motion sickness reduction among the motion sickness-inducing factors based on feature information on each of the extracted motion sickness-inducing factors; And
By generating motion sickness reduction for the corresponding feature information using a deep learning neural network previously learned for each of the determined motion sickness inducers, the virtual reality content is generated as virtual reality content having a motion sickness score below a preset reference motion sickness score. Steps to
Virtual reality content motion sickness reduction method comprising a.
The method of claim 6,
The extracting step
A virtual reality content motion sickness reduction method characterized by performing analysis on the virtual reality content based on deep learning and extracting feature information for each of the motion sickness inducers including motion characteristics, resolution characteristics, and frame rate characteristics .
The method of claim 6,
The generating step
The motion sickness reduction for each of the determined motion sickness inducer feature information is sequentially performed on the virtual reality content, thereby generating the virtual reality content as virtual reality content having a motion sickness score below a preset reference motion sickness score. How to reduce motion sickness in virtual reality content.
The method of claim 6,
The determining step
Based on the feature information of each of the motion sickness inducers, the motion sickness score of the virtual reality content is calculated, the gradient size in each feature information for the calculated motion sickness score is calculated, and the calculated gradient size A virtual reality content motion sickness reduction method, characterized in that, by analyzing influence information of each of the feature information on the motion sickness score, the motion sickness reduction is determined as a motion sickness inducer.
The method of claim 6,
The generating step
A first deep neural network that generates a frame of the virtual reality content as a frame less than or equal to a preset reference motion when the virtual reality content has a motion characteristic equal to or greater than a predetermined reference motion sickness score, and a resolution in which the virtual reality content exceeds the reference motion sickness score When having a second deep neural network upscaling the resolution of the frame of the virtual reality content to a preset high resolution and when the virtual reality content has a frame rate equal to or greater than the reference motion sickness score, for the frames of the virtual reality content A method for reducing motion sickness in virtual reality contents, wherein motion sickness reduction is performed on the corresponding feature information by using a third deep neural network that generates an interpolation frame.

Images