CN109887095A - A kind of emotional distress virtual reality scenario automatic creation system and method - Google Patents
A kind of emotional distress virtual reality scenario automatic creation system and method Download PDFInfo
- Publication number
- CN109887095A CN109887095A CN201910055832.6A CN201910055832A CN109887095A CN 109887095 A CN109887095 A CN 109887095A CN 201910055832 A CN201910055832 A CN 201910055832A CN 109887095 A CN109887095 A CN 109887095A
- Authority
- CN
- China
- Prior art keywords
- label
- mood
- virtual reality
- threedimensional model
- reality scenario
- 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.)
- Pending
Links
- 206010049119 Emotional distress Diseases 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000000463 material Substances 0.000 claims abstract description 107
- 230000036651 mood Effects 0.000 claims abstract description 88
- 230000003993 interaction Effects 0.000 claims abstract description 22
- 230000000694 effects Effects 0.000 claims abstract description 9
- 230000037007 arousal Effects 0.000 claims description 12
- 239000000178 monomer Substances 0.000 claims description 12
- 238000002474 experimental method Methods 0.000 claims description 11
- 230000008451 emotion Effects 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000003058 natural language processing Methods 0.000 claims description 4
- 239000004566 building material Substances 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000000638 stimulation Effects 0.000 claims description 2
- 238000013459 approach Methods 0.000 abstract description 4
- 238000002372 labelling Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 9
- 230000008447 perception Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001671 psychotherapy Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000014860 sensory perception of taste Effects 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Computer Graphics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a kind of emotional distress virtual reality scenario automatic creation systems, include label system module, material library module, human-computer interaction module, virtual reality scenario automatically-generating module；The label system module is used to carry out label to threedimensional model；The material library module is used to provide material to threedimensional model and background music；The human-computer interaction model inputs mood and setting for user；The virtual reality scenario automatically-generating module is used for the mood and setting that inputs according to human-computer interaction module, the label that the material and label system module provided in conjunction with material library module provides, create meet mood build virtual reality scenario；The present invention provides a kind of new approach to build virtual reality emotional distress scene, can generate virtual reality scenario largely with different emotional distress effects in a short time, simple and convenient, saves human resources and time cost；The material database of labeling is also constructed, is more advantageous to the selection of user in build process.
Description
Technical field
The present invention relates to the research field that information technology and cognitive psychology are intersected, in particular to a kind of emotional distress is virtual
Reality scene automatic creation system and method.
Background technique
Mood is the polyesthesia of people, the comprehensive psychology and physiological status generated of thought and act.Its height as human brain
Grade function, guarantees the existence and adaptation of organism.Since mood affects the behavior, study, memory of people to varying degrees
With decision, the mood triggering combined with information technology and emotion assessment game design, experimental study, psychotherapy etc. increasingly at
For following important development direction.
Virtual reality technology is emulation technology and computer graphics human-machine interface technology multimedia technology sensing technology net
The set of the multiple technologies such as network technology mainly includes simulated environment, perception, natural technical ability and sensing equipment etc..Analog loop
Border be generated by computer, dynamic 3 D stereo photorealism in real time.Perception refers to that ideal VR should have all people
Possessed perception.In addition to computer graphics techniques visual perception generated, the sense such as there are also the sense of hearing, tactile, power to feel, movement
Know, or even further includes smell and sense of taste etc., also referred to as more perception.Natural technical ability refers to the head rotation of people, eyes, gesture or
Other human body behavior acts are handled the data adaptable with the movement of participant by computer, and made to the input of user
Real-time response, and feedback arrives the face of user respectively.Sensing equipment refers to three-dimension interaction equipment.Virtual reality mood triggers scene
Integrated use vision and both stimulation mood channels of the sense of hearing, and joined the rendering of light efficiency and camera lens dynamically uses, it is
A kind of effective mood triggering tool, furthermore virtual reality mood triggering scene also overcomes immersing for traditional mood triggering material
Feel not strong disadvantage, more can be effectively carried out mood triggering.
There has been, come the research of stimulating human mood, but developed slowly, main one using virtual reality scenario
It is a the reason is that traditional method for manually building virtual reality emotional distress scene is excessively complicated, have virtual reality scenario production
Skilled person is just few, and Production Time is long, therefore emotional distress virtual reality scenario needs are made by the way of traditional
A large amount of fund cost and time cost.
Summary of the invention
The shortcomings that it is a primary object of the present invention to overcome the prior art and deficiency, provide a kind of emotional distress virtual reality
Scene automatic creation system.Machine learning algorithm and natural language processing technique are combined, to build virtual reality emotional distress
Scene provides a kind of new approach, and compared with prior art, the present invention without technical requirements, can give birth to user in a short time
At largely with different emotional distress effects virtual reality scenario, it is simple and convenient, saved a large amount of human resources and
Time cost.In addition, the present invention also constructs the material database of a labeling, the material in the material database all has three-dimensional emotion
Quantify label, is more advantageous to the selection of user in build process.
Another object of the present invention is to provide a kind of emotional distress virtual reality scenario automatic generation methods.
The main object of the present invention is realized by the following technical solution:
A kind of emotional distress virtual reality scenario automatic creation system, which is characterized in that include label system module, material
Library module, human-computer interaction module, virtual reality scenario automatically-generating module；
The label system module is used to carry out label to threedimensional model；The material library module be used for threedimensional model and
Background music provides material；The human-computer interaction model inputs mood and setting for user；The virtual reality scenario is automatic
Generation module is used for the mood and setting inputted according to human-computer interaction module, the material and label body provided in conjunction with material library module
It is the label that module provides, what wound met mood builds virtual reality scenario.
Further, the label system module includes tree structure label, mood label, attribute tags；
The tree structure label is convenient for man-made index for determining the objective classification of threedimensional model and background music；Institute
Mood label is stated for assessing threedimensional model and background music and quantifying to threedimensional model；The attribute tags are for recording
The feature of threedimensional model；
Further, the tree structure label includes four layers, is respectively as follows: first layer for material and is divided into whole three-dimensional mould
Three type, monolithic three dimensional model, background music classes；Three classes of first layer are respectively divided into several major class by the second layer；Third layer
Each major class of several major class of the second layer is divided into several species；4th layer is divided the middle class of each of several middle classes of third layer
For several groups；The mood label includes pleasure degree, arousal, domination degree；The attribute tags include public attribute, peculiar
Attribute；The public attribute includes threedimensional model color, threedimensional model size, background music language, background music style；It is described
Particular attribute includes people's model gender, occupation, expression, clothes style in threedimensional model；
Further, the categorizing system of the tree structure Tag reference ImageNet picture library；The mood label from
Mood label is added for threedimensional model in IAPS and CAPS, adds mood label, the mood mark from CADS for background music
Label cover eight octants of high/low pleasure degree in the space mood VAD, high/low arousal, high/low domination degree, eight octants point
Not are as follows: HVHAHD, HVHALD, HVLAHD, HVLALD, LVHAHD, LVHALD, LVLAHD, LVLALD；The height of numerical value in each dimension
Low differentiation threshold value is 5；
Further, the material library module includes threedimensional model material database, background music material database；
The threedimensional model material database is for providing suitable threedimensional model；The background music material database is for providing conjunction
Suitable background music；
Further, the material library module needs label system module to determine three-dimensional scenic when building material database
Environment and background, i.e., whole threedimensional model, monolithic three dimensional model, background music, and require with tree structure label, feelings
Thread label, attribute tags；
When threedimensional model material database collects threedimensional model material, the corresponding threedimensional model element of tree structure label is first established
Then material carries out the grading of pleasure degree, three arousal, domination degree dimensions 1 to 9, i.e., by mood SAM scale to threedimensional model
Assessment experiment, carries out the evaluation of VAD value to material after allowing user sufficiently to observe by HMD, carries out at least K user's experiment
Afterwards, obtaining threedimensional model of three dimension variances less than 3 is to be put into threedimensional model material database by grading；
When background music material database collects background music material, the corresponding background music element of tree structure label is first established
Then material carries out the grading of pleasure degree, three arousal, domination degree dimensions 1 to 9, i.e., by mood SAM scale to background music
Assessment experiment, carries out the evaluation of VAD value to material after allowing user to listen to background music, after carrying out at least L user's experiment, obtains
It is close with desired value to three dimension average values of VAD value, then it is put into background music material database；The setting reference of the desired value
Three dimensional mood identification scale (VAD) simultaneously does from section (- 1,1) to (1,9) spatial scaling；
Further, the K > 50；The L > 100.
A kind of emotional distress virtual reality scenario automatic generation method, which comprises the following steps:
S1, with reference to the categorizing system of ImageNet picture library, establishing includes tree structure label, mood label, attribute mark
The complete set label system of label, that is, build label system module；
S2, the tree structure label according to label system collect and screen or voluntarily build threedimensional model and collect back
Scape music, and pass through the tree-shaped classification of file；It is that threedimensional model adds mood label with reference to IAPS, CAPS, is back with reference to CADS
Scape music adds mood label；And required attribute label is added according to the objective attribute of object and background music, with label body
System carries out corresponding relationship, builds perfect threedimensional model material database and background music material database, that is, builds material library module；
S3, user input mood, and setup parameter by human-computer interaction module；
The mood and setting that S4, virtual reality scenario automatically-generating module are inputted according to human-computer interaction module, in conjunction with material
The label that the material and label system module that library module provides provide, creation meet the virtual reality scenario of mood, and record complete
Scape video.
Further, further include that user selects monomer model to carry out appropriate position in determining threedimensional model and put, and
Suitable background music is selected, virtual reality scenario is improved；
Further, the virtual reality scenario includes three kinds of creation methods:
The first, user by screening material, virtual reality scenario automatically-generating module according to the mood label of click and
Attribute tags, from material database selection and specific position generate whole threedimensional model, monolithic three dimensional model, background music, from
And build a virtual reality scenario with corresponding emotional distress effect, wherein whole threedimensional model and background sound Ledu are only
One can be existed simultaneously, monomer model quantity is unlimited；
Second, the text inputted according to user in human-computer interaction carries out natural language processing, extracts user to scene feelings
The demand of thread and kind of object selects from material database and generates background model, monomer model, background music in specific position,
To build a scene with corresponding emotional distress effect, wherein background model and background sound Ledu can only exist simultaneously one
A, monomer model quantity is unlimited；
The third, with association rule algorithm, obtain the pass of different moods and object from existing complete mood scene
It is weight net, then show that the relative position of object model absolute position different objects model oneself is closed with machine learning algorithm
System, according to the single mood requirement of user's input, selects the higher object of weight random on the basis of this from relationship weight net
If extracting Ganlei, and model is generated according to the positional relationship obtained, corresponding background music is added, so that obtaining several groups meets feelings
The scene that thread requires；
Finally, panoramic video is recorded in the incidental video camera path of background model along selection, virtual reality emotion is obtained
Stimulate scene video.
Compared with the prior art, the invention has the following advantages and beneficial effects:
The present invention provides a kind of new approach to build virtual reality emotional distress scene, can generate in a short time
Largely with different emotional distress effects virtual reality scenario, it is simple and convenient, saved a large amount of human resources and when
Between cost.In addition, the present invention also constructs the material database of a labeling, the material in the material database all has three-dimensional emotion amount
Change label, is more advantageous to the selection of user in build process.
Detailed description of the invention
Fig. 1 is a kind of structural block diagram of emotional distress virtual reality scenario automatic creation system of the present invention；
Fig. 2 is SAM scale estimation flow figure in the embodiment of the present invention 1；
Fig. 3 is a kind of method flow diagram of emotional distress virtual reality scenario automatic generation method of the present invention.
Specific embodiment
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
Embodiment 1:
A kind of emotional distress virtual reality scenario automatic creation system, as shown in Figure 1, including label system module, material
Library module, human-computer interaction module, virtual reality scenario automatically-generating module；
The label system module is used to carry out label to threedimensional model；The material library module be used for threedimensional model and
Background music provides material；The human-computer interaction model inputs mood and setting for user；The virtual reality scenario is automatic
Generation module is used for the mood and setting inputted according to human-computer interaction module, the material and label body provided in conjunction with material library module
It is the label that module provides, what wound met mood builds virtual reality scenario.
Further, the label system module includes tree structure label, mood label, attribute tags；
The tree structure label, for determining the objective classification of threedimensional model and background music；The mood label is used
In assessment threedimensional model and background music and threedimensional model is quantified；The attribute tags are used to record the spy of threedimensional model
Sign；
Further, the tree structure label includes four layers, is respectively as follows: first layer for material and is divided into whole three-dimensional mould
Three type, monolithic three dimensional model, background music classes；Three classes of first layer are respectively divided into several major class by the second layer；Third layer
Each major class of several major class of the second layer is divided into several species；4th layer is divided the middle class of each of several middle classes of third layer
For several groups；The mood label includes pleasure degree, arousal, domination degree；The attribute tags include public attribute, peculiar
Attribute；The public attribute includes threedimensional model color, threedimensional model size, background music language, background music style；It is described
Particular attribute includes people's model gender, occupation, expression, clothes style in threedimensional model；
Further, the categorizing system of the tree structure Tag reference ImageNet picture library；The mood label from
Mood label is added for threedimensional model in IAPS and CAPS, adds mood label, the mood mark from CADS for background music
Label cover eight octants of high/low pleasure degree in the space mood VAD, high/low arousal, high/low domination degree, eight octants point
Not are as follows: HVHAHD, HVHALD, HVLAHD, HVLALD, LVHAHD, LVHALD, LVLAHD, LVLALD；The height of numerical value in each dimension
Low differentiation threshold value is 5；
Further, the material library module includes threedimensional model material database, background music material database；
The threedimensional model material database is for providing suitable threedimensional model；The background music material database is for providing conjunction
Suitable background music；
Further, the material library module needs label system module to determine three-dimensional scenic when building material database
Environment and background, i.e., whole threedimensional model, monolithic three dimensional model, background music, and require with tree structure label, feelings
Thread label, attribute tags；
Threedimensional model material is collected in threedimensional model material database, (1) is collected from regular approach or self manufacture, is not related to quotient
Industry copyright and intellectual property；(2) according to label system, material should meet corresponding label description, and same specific tree structure
Label corresponds to an at most material, and mood label and attribute tags are without limitation；When collecting threedimensional model material, tree-like knot is first established
Then the corresponding threedimensional model material of structure label carries out pleasure degree, arousal, domination degree three dimensions 1 to 9 to threedimensional model
Grading is assessed by mood SAM scale and is tested, as shown in Fig. 2, carrying out after allowing user sufficiently to observe by HMD to material
The evaluation of VAD value, after carrying out at least 50 users experiment, obtain threedimensional model of three dimension variances less than 3 be by grading,
It is put into threedimensional model material database；
When background music material database collects background music material, the corresponding background music element of tree structure label is first established
Then material carries out the grading of pleasure degree, three arousal, domination degree dimensions 1 to 9, i.e., by mood SAM scale to background music
Assessment experiment, carries out the evaluation of VAD value to material after allowing user to listen to background music, after carrying out at least 100 user's experiments,
Three dimension average values of VAD value are obtained, it is close with desired value, then it is put into background music material database；The setting of the desired value is joined
According to three dimensional mood identification scale (VAD) and do from section (- 1,1) to (1,9) spatial scaling.
Embodiment 2:
A kind of emotional distress virtual reality scenario automatic generation method, as shown in Figure 3, comprising the following steps:
The first step, with reference to the categorizing system of ImageNet picture library, establish comprising tree structure label, mood label, belong to
The complete set label system of property label, that is, build label system module；
Second step, the tree structure label according to label system are collected and screen or voluntarily build threedimensional model and receipts
Collect background music, and passes through the tree-shaped classification of file；It is that threedimensional model adds mood label with reference to IAPS, CAPS, with reference to CADS
Mood label is added for background music；And required attribute label is added according to the objective attribute of object and background music, with mark
Label system carries out corresponding relationship, builds perfect threedimensional model material database and background music material database, that is, builds material library module；
Third step, user select material self assemble scene, input text requirement from combobox by human-computer interaction module
And mood, select a kind of scene creation method, and setup parameter；
The mood and setting that 4th step, virtual reality scenario automatically-generating module are inputted according to human-computer interaction module, in conjunction with
The label that the material and label system module that material library module provides provide, creation meet the virtual reality scenario of mood, generate
Scene have reasonability, such as object not spatially be overlapped or staggeredly, should all not generate and not conform on the ground in addition to special article
The combination of reason, as wild animal appears in city；After generating reasonable virtual reality scenario, panoramic video is recorded；Shoot rail
Mark is directly related by virtual reality scenario, and the video clarity with higher and frame per second shot, to guarantee that user is watching
When do not cause dizziness.
Further, further include that user selects monomer model to carry out appropriate position in determining threedimensional model and put, and
Suitable background music is selected, virtual reality scenario is improved；
Further, the virtual reality scenario includes three kinds of creation methods:
The first, user by screening material, virtual reality scenario automatically-generating module according to the mood label of click and
Attribute tags, from material database selection and specific position generate whole threedimensional model, monolithic three dimensional model, background music, from
And build a virtual reality scenario with corresponding emotional distress effect, wherein whole threedimensional model and background sound Ledu are only
One can be existed simultaneously, monomer model quantity is unlimited；
Second, the text inputted according to user in human-computer interaction carries out natural language processing, extracts user to scene feelings
The demand of thread and kind of object selects from material database and generates background model, monomer model, background music in specific position,
To build a scene with corresponding emotional distress effect, wherein background model and background sound Ledu can only exist simultaneously one
A, monomer model quantity is unlimited；
The third, with association rule algorithm, obtain the pass of different moods and object from existing complete mood scene
It is weight net, then show that the relative position of object model absolute position different objects model oneself is closed with machine learning algorithm
System, according to the single mood requirement of user's input, selects the higher object of weight random on the basis of this from relationship weight net
If extracting Ganlei, and model is generated according to the positional relationship obtained, corresponding background music is added, so that obtaining several groups meets feelings
The scene that thread requires；
Finally, panoramic video is recorded in the incidental video camera path of background model along selection, virtual reality emotion is obtained
Stimulate scene video.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (10)
1. a kind of emotional distress virtual reality scenario automatic creation system, which is characterized in that include label system module, material database
Module, human-computer interaction module, virtual reality scenario automatically-generating module；
The label system module is used to carry out label to threedimensional model；The material library module is used for threedimensional model and background
Music provides material；The human-computer interaction model inputs mood and setting for user；The virtual reality scenario automatically generates
Module is used for the mood and setting inputted according to human-computer interaction module, the material and label system mould provided in conjunction with material library module
The label that block provides, what wound met mood builds virtual reality scenario.
2. a kind of emotional distress virtual reality scenario automatic creation system according to claim 1, which is characterized in that described
Label system module includes tree structure label, mood label, attribute tags；
The tree structure label, for determining the objective classification of threedimensional model and background music；The mood label is for commenting
Estimate threedimensional model and background music and threedimensional model is quantified；The attribute tags are used to record the feature of threedimensional model.
3. a kind of emotional distress virtual reality scenario automatic creation system according to claim 2, which is characterized in that described
Tree structure label includes four layers, is respectively as follows: first layer for material and is divided into whole threedimensional model, monolithic three dimensional model, background sound
Happy three classes；Three classes of first layer are respectively divided into several major class by the second layer；Third layer is every by several major class of the second layer
A major class is divided into several species；The middle class of each of several middle classes of third layer is divided into several groups by the 4th layer；The mood mark
Label include pleasure degree, arousal, domination degree；The attribute tags include public attribute, particular attribute；The public attribute includes
Threedimensional model color, threedimensional model size, background music language, background music style；The particular attribute includes threedimensional model
Middle people's model gender, occupation, expression, clothes style.
4. a kind of emotional distress virtual reality scenario automatic creation system according to claim 3, which is characterized in that described
The categorizing system of tree structure Tag reference ImageNet picture library；The mood label is threedimensional model from IAPS and CAPS
Mood label is added, adds mood label from CADS for background music, the mood label covers in the space mood VAD
High/low pleasure degree, high/low arousal, eight octants of high/low domination degree, eight octants be respectively as follows: HVHAHD, HVHALD,
HVLAHD,HVLALD,LVHAHD,LVHALD,LVLAHD,LVLALD；It is 5 that the height of numerical value, which distinguishes threshold value, in each dimension.
5. a kind of emotional distress virtual reality scenario automatic creation system according to claim 1, which is characterized in that described
Material library module includes threedimensional model material database, background music material database；
The threedimensional model material database is for providing suitable threedimensional model；The background music material database is suitable for providing
Background music.
6. a kind of emotional distress virtual reality scenario automatic creation system according to claim 5, which is characterized in that described
Material library module needs label system module to determine the environment and background of three-dimensional scenic when building material database, i.e., whole three-dimensional
Model, monolithic three dimensional model, background music, and require with tree structure label, mood label, attribute tags；
When threedimensional model material database collects threedimensional model material, the corresponding threedimensional model material of tree structure label is first established,
Then the grading that pleasure degree, three arousal, domination degree dimensions 1 to 9 are carried out to threedimensional model, i.e., comment by mood SAM scale
Estimate experiment, the evaluation of VAD value is carried out to material after allowing user sufficiently to observe by HMD, after carrying out at least K user's experiment,
Obtaining threedimensional model of three dimension variances less than 3 is to be put into threedimensional model material database by grading；
When background music material database collects background music material, the corresponding background music material of tree structure label is first established,
Then the grading that pleasure degree, three arousal, domination degree dimensions 1 to 9 are carried out to background music, i.e., comment by mood SAM scale
Estimate experiment, the evaluation of VAD value is carried out to material after allowing user to listen to background music, after carrying out at least L user's experiment, obtains
Three dimension average values of VAD value, it is close with desired value, then it is put into background music material database；The setting of the desired value is referring to three
Dimension Emotion identification scale (VAD) simultaneously does from section (- 1,1) to (1,9) spatial scaling.
7. a kind of emotional distress virtual reality scenario automatic creation system according to claim 6, which is characterized in that described
K > 50；The L > 100.
8. a kind of emotional distress virtual reality scenario automatic generation method, which comprises the following steps:
S1, with reference to the categorizing system of ImageNet picture library, establish comprising tree structure label, mood label, attribute tags
Complete set label system builds label system module；
S2, the tree structure label according to label system collect and screen or voluntarily build threedimensional model and collect background sound
It is happy, and pass through the tree-shaped classification of file；It is that threedimensional model adds mood label with reference to IAPS, CAPS, is background sound with reference to CADS
Happy addition mood label；And according to the objective attribute of object and background music add required attribute label, with label system into
Row corresponding relationship builds perfect threedimensional model material database and background music material database, that is, builds material library module；
S3, user input mood, and setup parameter by human-computer interaction module；
The mood and setting that S4, virtual reality scenario automatically-generating module are inputted according to human-computer interaction module, in conjunction with material database mould
The label that the material and label system module that block provides provide, creation meet the virtual reality scenario of mood, and record aphorama
Frequently.
9. a kind of emotional distress virtual reality scenario automatic generation method according to claim 8, which is characterized in that also wrap
It includes, user's selection monomer model carries out appropriate position in determining threedimensional model and puts, and selects suitable background music, complete
Kind virtual reality scenario.
10. a kind of emotional distress virtual reality scenario automatic generation method according to claim 8, which is characterized in that institute
Stating virtual reality scenario includes three kinds of creation methods:
The first, user by screening material, virtual reality scenario automatically-generating module is according to the mood label and attribute of click
Label, from material database selection and specific position generate whole threedimensional model, monolithic three dimensional model, background music, to take
Build a virtual reality scenario with corresponding emotional distress effect, wherein whole threedimensional model and background sound Ledu can only be same
When there are one, monomer model quantity is unlimited；
Second, the text inputted according to user in human-computer interaction carries out natural language processing, extract user to scene mood and
The demand of kind of object selects from material database and generates background model, monomer model, background music in specific position, thus
A scene with corresponding emotional distress effect is built, wherein background model and background sound Ledu can only exist simultaneously one,
Monomer model quantity is unlimited；
The third, with association rule algorithm, the relationship that different moods and object are obtained from existing complete mood scene is weighed
Net again, then obtain with machine learning algorithm the relative positional relationship of object model absolute position different objects model oneself,
On the basis of this, according to the single mood requirement of user's input, the higher object of weight is selected to randomly select from relationship weight net
If Ganlei, and model is generated according to the positional relationship obtained, corresponding background music is added, is wanted to obtain several groups and meet mood
The scene asked；
Finally, panoramic video is recorded in the incidental video camera path of background model along selection, the stimulation of virtual reality emotion is obtained
Scene video.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910055832.6A CN109887095A (en) | 2019-01-22 | 2019-01-22 | A kind of emotional distress virtual reality scenario automatic creation system and method |
| PCT/CN2019/112884 WO2020151273A1 (en) | 2019-01-22 | 2019-10-23 | System and method for automatically generating virtual reality scene that stimulates emotions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910055832.6A CN109887095A (en) | 2019-01-22 | 2019-01-22 | A kind of emotional distress virtual reality scenario automatic creation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109887095A true CN109887095A (en) | 2019-06-14 |
Family
ID=66926446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910055832.6A Pending CN109887095A (en) | 2019-01-22 | 2019-01-22 | A kind of emotional distress virtual reality scenario automatic creation system and method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109887095A (en) |
| WO (1) | WO2020151273A1 (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110018738A (en) * | 2019-03-04 | 2019-07-16 | 华南理工大学 | A kind of emotion converting system based on real scene emotional expression |
| CN110648264A (en) * | 2019-09-30 | 2020-01-03 | 彭春姣 | Courseware containing or hanging emotion regulating component, method and device for regulating emotion |
| CN111063037A (en) * | 2019-12-30 | 2020-04-24 | 北京中网易企秀科技有限公司 | Three-dimensional scene editing method and device |
| WO2020151273A1 (en) * | 2019-01-22 | 2020-07-30 | 华南理工大学 | System and method for automatically generating virtual reality scene that stimulates emotions |
| WO2021115311A1 (en) * | 2020-05-29 | 2021-06-17 | 平安科技（深圳）有限公司 | Song generation method, apparatus, electronic device, and storage medium |
| CN113011504A (en) * | 2021-03-23 | 2021-06-22 | 华南理工大学 | Virtual reality scene emotion recognition method based on visual angle weight and feature fusion |
| CN113075996A (en) * | 2020-01-06 | 2021-07-06 | 京东方艺云科技有限公司 | Method and system for improving user emotion |
| CN113284256A (en) * | 2021-05-25 | 2021-08-20 | 成都威爱新经济技术研究院有限公司 | MR mixed reality three-dimensional scene material library generation method and system |
| CN115665461A (en) * | 2022-10-13 | 2023-01-31 | 聚好看科技股份有限公司 | Video recording method and virtual reality equipment |
| CN116211303A (en) * | 2022-12-06 | 2023-06-06 | 北京师范大学 | System for constructing scenerized psychological stress evaluation model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030028383A1 (en) * | 2001-02-20 | 2003-02-06 | I & A Research Inc. | System for modeling and simulating emotion states |
| CN101706842A (en) * | 2009-08-25 | 2010-05-12 | 浙江大学 | Method for creating Chinese emotion picture system |
| CN106502425A (en) * | 2016-11-30 | 2017-03-15 | 宇龙计算机通信科技(深圳)有限公司 | A kind of construction method of virtual reality scenario and device |
| CN107578807A (en) * | 2017-07-17 | 2018-01-12 | 华南理工大学 | A kind of creation method of virtual reality emotion stimulating system |
| CN108846887A (en) * | 2018-06-20 | 2018-11-20 | 首都师范大学 | The generation method and device of VR video |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101887489A (en) * | 2010-05-24 | 2010-11-17 | 陈益强 | Method for interactive influence of characters in real world and virtual world |
| WO2018022808A1 (en) * | 2016-07-27 | 2018-02-01 | Warner Bros. Entertainment Inc. | Control of social robot based on prior character portrayal in fiction or performance |
| CN106991172B (en) * | 2017-04-05 | 2020-04-28 | 安徽建筑大学 | Method for establishing multi-mode emotion interaction database |
| CN109887095A (en) * | 2019-01-22 | 2019-06-14 | 华南理工大学 | A kind of emotional distress virtual reality scenario automatic creation system and method |
-
2019
- 2019-01-22 CN CN201910055832.6A patent/CN109887095A/en active Pending
- 2019-10-23 WO PCT/CN2019/112884 patent/WO2020151273A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030028383A1 (en) * | 2001-02-20 | 2003-02-06 | I & A Research Inc. | System for modeling and simulating emotion states |
| CN101706842A (en) * | 2009-08-25 | 2010-05-12 | 浙江大学 | Method for creating Chinese emotion picture system |
| CN106502425A (en) * | 2016-11-30 | 2017-03-15 | 宇龙计算机通信科技(深圳)有限公司 | A kind of construction method of virtual reality scenario and device |
| CN107578807A (en) * | 2017-07-17 | 2018-01-12 | 华南理工大学 | A kind of creation method of virtual reality emotion stimulating system |
| CN108846887A (en) * | 2018-06-20 | 2018-11-20 | 首都师范大学 | The generation method and device of VR video |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020151273A1 (en) * | 2019-01-22 | 2020-07-30 | 华南理工大学 | System and method for automatically generating virtual reality scene that stimulates emotions |
| CN110018738B (en) * | 2019-03-04 | 2021-09-21 | 华南理工大学 | Emotion conversion system based on real scene emotion expression |
| CN110018738A (en) * | 2019-03-04 | 2019-07-16 | 华南理工大学 | A kind of emotion converting system based on real scene emotional expression |
| CN110648264A (en) * | 2019-09-30 | 2020-01-03 | 彭春姣 | Courseware containing or hanging emotion regulating component, method and device for regulating emotion |
| CN110648264B (en) * | 2019-09-30 | 2023-02-28 | 彭春姣 | Courseware containing or hanging emotion regulating component, method and device for regulating emotion |
| CN111063037A (en) * | 2019-12-30 | 2020-04-24 | 北京中网易企秀科技有限公司 | Three-dimensional scene editing method and device |
| CN113075996B (en) * | 2020-01-06 | 2024-05-17 | 京东方艺云(杭州)科技有限公司 | User emotion improving method and system |
| CN113075996A (en) * | 2020-01-06 | 2021-07-06 | 京东方艺云科技有限公司 | Method and system for improving user emotion |
| WO2021115311A1 (en) * | 2020-05-29 | 2021-06-17 | 平安科技（深圳）有限公司 | Song generation method, apparatus, electronic device, and storage medium |
| CN113011504B (en) * | 2021-03-23 | 2023-08-22 | 华南理工大学 | Virtual reality scene emotion recognition method based on visual angle weight and feature fusion |
| CN113011504A (en) * | 2021-03-23 | 2021-06-22 | 华南理工大学 | Virtual reality scene emotion recognition method based on visual angle weight and feature fusion |
| CN113284256A (en) * | 2021-05-25 | 2021-08-20 | 成都威爱新经济技术研究院有限公司 | MR mixed reality three-dimensional scene material library generation method and system |
| CN113284256B (en) * | 2021-05-25 | 2023-10-31 | 成都威爱新经济技术研究院有限公司 | MR (magnetic resonance) mixed reality three-dimensional scene material library generation method and system |
| CN115665461A (en) * | 2022-10-13 | 2023-01-31 | 聚好看科技股份有限公司 | Video recording method and virtual reality equipment |
| CN115665461B (en) * | 2022-10-13 | 2024-03-22 | 聚好看科技股份有限公司 | Video recording method and virtual reality device |
| CN116211303A (en) * | 2022-12-06 | 2023-06-06 | 北京师范大学 | System for constructing scenerized psychological stress evaluation model |
| CN116211303B (en) * | 2022-12-06 | 2024-03-12 | 北京师范大学 | System for constructing scenerized psychological stress evaluation model |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020151273A1 (en) | 2020-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109887095A (en) | A kind of emotional distress virtual reality scenario automatic creation system and method | |
| Roesch et al. | FACSGen: A tool to synthesize emotional facial expressions through systematic manipulation of facial action units | |
| Happy et al. | The Indian spontaneous expression database for emotion recognition | |
| CN108961369B (en) | Method and device for generating 3D animation | |
| CN107392783A (en) | Social contact method and device based on virtual reality | |
| Ravetto-Biagioli | The Digital Uncanny | |
| Wei et al. | BNU-LSVED 2.0: Spontaneous multimodal student affect database with multi-dimensional labels | |
| Lomas | Cellular forms: an artistic exploration of morphogenesis. | |
| CN116050284B (en) | Fashion redesign system utilizing AIGC technology | |
| Alabbasi et al. | Real time facial emotion recognition using kinect V2 sensor | |
| Randhavane et al. | Modeling data-driven dominance traits for virtual characters using gait analysis | |
| Ochs et al. | 18 facial expressions of emotions for virtual characters | |
| Basori | Emotion walking for humanoid avatars using brain signals | |
| Wang et al. | Wuju opera cultural creative products and research on visual image under VR technology | |
| Mu et al. | User attention and behaviour in virtual reality art encounter | |
| US11270070B1 (en) | Method and apparatus for improved presentation of information | |
| US11113453B1 (en) | Method and apparatus for improved presentation of information | |
| Cui et al. | Virtual human: A comprehensive survey on academic and applications | |
| US11645352B1 (en) | Method and apparatus for improved presentation of information | |
| Gilroy et al. | An affective model of user experience for interactive art | |
| Berov et al. | Visual hallucination for computational creation | |
| Kasiran et al. | Facial expression as an implicit customers' feedback and the challenges | |
| Ryokai et al. | Personal laughter archives: reflection through visualization and interaction | |
| US11989757B1 (en) | Method and apparatus for improved presentation of information | |
| Tarnowski et al. | Anthropometric facial features in emotion recognition |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |
|
| RJ01 | Rejection of invention patent application after publication |