CN108769640A - Automatically adjust visual angle shadow casting technique - Google Patents
Automatically adjust visual angle shadow casting technique Download PDFInfo
- Publication number
- CN108769640A CN108769640A CN201811060802.6A CN201811060802A CN108769640A CN 108769640 A CN108769640 A CN 108769640A CN 201811060802 A CN201811060802 A CN 201811060802A CN 108769640 A CN108769640 A CN 108769640A
- Authority
- CN
- China
- Prior art keywords
- user
- visual angle
- condition
- boundary
- information
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/12—Picture reproducers
- H04N9/31—Projection devices for colour picture display, e.g. using electronic spatial light modulators [ESLM]
- H04N9/3179—Video signal processing therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Abstract
The present invention relates to automatic adjustment visual angle shadow casting techniques, face recognition is carried out using infrared camera, susceptibility is adjusted according to visual angle is preset the characteristics of everyone, simultaneously in video content object classification and by frame mark, acquire the perpetual object of user, the viewing experience evaluation participated according to individual carries out the deep learning for having supervision, forms artificial intelligence model.The beneficial effects of the invention are as follows：It is presented in user at the moment with the posture visual angle of user's the most comfortable, and visual angle adjustment is carried out according to the most adaptable susceptibility of user, by the most suitable visual angle of user establish user characteristics, situation model, establish the model that user corresponds to crowd portrayal, and whole crowd corresponds to portrait model in Optimization Algorithms Library, the selection as corresponding crowd's initialization model.
Description
Technical field
The present invention relates to automatic adjustment visual angle shadow casting techniques.
Background technology
As home theater technology develops, people more and more enjoy private video display space.However whether LCD,
The private movie theatre that LED, projection or even 360 degree project, is all to go to watch according to preset visual angle, but watch movie process
It may may become lying posture or other various postures from sitting posture, if still original fixation there are two hour or longer time
Visual angle can bring the organs such as cervical vertebra compressing or discomfort, unhealthful and viewing experience, if the projections such as 360 degree of projections
Area is larger, may miss excellent link, if by user real time hand Dong She Ge, interruption will be brought to viewing process, influences to use
Family is experienced, and is only captured user's posture with camera and carried out angle adjustment, and each user is accustomed to difference, if some people are good
Dynamic, love is turned one's head, and excessively frequent adjustment can allow user at a loss as to what to do.
Invention content
To overcome the defects of present in the prior art, the present invention provides automatic adjustment visual angle shadow casting technique, can solve
State technical problem.
The present invention is achieved through the following technical solutions above-mentioned purpose：
Visual angle shadow casting technique is automatically adjusted, is carried out successively as steps described below：
Step 1：Projecting apparatus by being provided with steering gear carries out line holographic projections and plays influence, and viewer wears acceleration
Acquisition module normally watches influence, and infrared camera is installed to viewing person opposite, by the collected viewing person of infrared camera
Face recognition image, motion images information and the collected acoustic information of microphone and acceleration acquisition information are handed over by network
Changing device passes to host；
Step 2：Image information pretreatment is carried out to the information in step 1, the three of object are built by spatial digitizer
Dimension module, set initial boundary conditions, according to boundary condition carry out threedimensional model Region Decomposition, decomposition obtain in parallel computation
Always into the equal submodel number of number of passes, using initial boundary conditions as design conditions, when boundary condition initial in calculating process
It changes, restarts boundary setting program, the submodel is calculated again, until boundary is stable or calculates son knot
Fruit is constant, corresponding input file in current process is read in, using Concurrent Feature curved line arithmetic to non-thread in governing equation
Property item carry out linearization process, obtain positive definite, symmetrical local linear system, if boundary condition change restarting side
Program is arranged in boundary, then is calculated, until boundary is stable or the sub- result of calculating is permanent；Often complete the meter of certain time step
It calculates, carries out the read-write operation of an output file；
Step 3：It is modeled by the rule of the collected acceleration information of step 1 with analysis module, and passes through something lost
The operation for passing operator provides moving state identification as a result, being used for remote management；
Step 4：By the dither noise balance in projection process, filtering and noise reduction, then hierarchical layered dimensionality reduction modeling utilizes
The output data of the acceleration transducer, and judge that human motion type, layering judge whether human body is quiet using medium filtering
Only movement, motive position, type, classification sampling judge the influence of main feature, comprehensive verification emphasis feature, and then judge to turn over
Body such as pushes, gets up at the features such as sleep, when modeling, synthesis amplitude is exported by accelerometer first, in given threshold up and down
Between value, then judge that human body is static；Conversely, then judging that people moves, the accelerometer output synthesis amplitude is：
The upper lower threshold value is respectively：tha min=8m/s, tha max=11m/s, first condition are：
If first condition is judged as static, to be exported without the judgement of second, third condition, accelerometer part
Variance then judges that the body part is static less than given threshold value；Conversely, then judge that the body part moves, the Article 2
Part calculation formula is：
Wherein, thσa=0.5, if second condition is judged as that the body part is static, without sentencing for third condition
It is disconnected, conversely, the third condition calculation formula is：
Wherein,thamax=50, then carry out
The state of movement is sampled calculating and extracts characteristic parameter；
Step 5：To the data characteristics integration modeling in step 2 to step 4, the light sensor for assessing camera obtains
Values of light grade, type of sports, user setting important kind obtain light sensation quality user 5 and divide appraisement system, by having
Supervised classification algorithm-is supervision factor pair ratio with history optimum data, establishes subjective feeling and adaptively projects tune with environmental parameter
Save model；
Step 6：Establish whole crowd and correspond to projection portrait model depth and mutually learn pattern-recognition, according in database
Have registered N class samples, sample inputted into classifier training, according to input value judgement be in (1, N) which kind of, if beyond (1,
N) range, then new registration classification N+1 classes, then update grader again；
Step 7：To calculating sub- result merging treatment, host process reads in the output of each process in current time step respectively
The collected multi-path video stream is carried out split processing, to generate the panoramic video stream for carrying the timestamp, so by file
Result is merged according to the algorithm of Region Decomposition afterwards and is restored, result is kept in ASCLL formats；It is whole that virtual reality is worn in user
When end, whether detection virtual reality terminal is kept in motion, if so, video frequency frame to be played is adjusted according to acceleration, with
It is supplied to user's synchronization video information, by presentation of information in the vision coverage area of virtual reality terminal；
Step 8：The analysis of analysis module through the above steps obtains the best projection angle of current viewing person, adjusts control
The steering gear of projecting apparatus in step 1 processed is to be adjusted to best viewing projection angle；
Step 9：For viewing person constantly repeat step 1 to step 8 process, with the increase SVM of sample amount
Grader can adaptively be continued to optimize to improve inputs new sample every time, according to cross-validation method principle, calculates SVM classifier
Discrimination carries out Fitness analysis, does not set the stop value of genetic algorithm, and end condition is used than supreme people's court, if the knowledge of training
Rate is not higher than existing, is set as optimized parameter, otherwise, executes the operations such as selection, intersection and variation and advanced optimizes training parameter,
Realize the constantly improve for viewing person's personalization projection scheme.
In the present embodiment, the acceleration acquisition module that step 1 viewing person carries uses MEMS (Micro Flectro
MechanicalSystems, MEMS), key component is a kind of intermediate capacitance plate of cantilevered construction, when velocity variations or
When acceleration reaches sufficiently large, the inertia force suffered by it is more than fixed or supports his power, and at this moment it will be moved, with power-on and power-off
Holding the distance between plate will change, therefore upper and lower capacitance will change.Capacitance variations are directly proportional with acceleration.Capacitance variations meeting
It is converted into voltage signal directly output or is exported after digitized processing.
In the present embodiment, the original motion vector group (F1, F2 ..., Fm) of the extraction characteristic parameter in step 4, m is small
In 9, extracting matrix is：
It is most that wherein original vector F1 contains information content, and there is maximum variance, referred to as first principal component, F2 ..., Fm to pass successively
Subtract, referred to as Second principal component, " " ", m principal components.Therefore the process of principal component analysis, which can be regarded as, is to determine weight coefficient aik
(i=1, " " ", m；K=1, " " " 9) process.
In the present embodiment, the indicatrix algorithm in the step 2 carries out the nonlinear terms in governing equation linear
Change is handled, and obtains positive definite, symmetrical local linear system is：
Wherein, K(i)For local stiffness matrix, U(i)For local known variables, f(i)For known localized external force vector, R(i)
The 0-1 matrixes mapped between local element mark number and whole element number；
Surface degree of freedom equation is as follows：
Wherein,For current area domain internal degree of freedom,Current area field surface and other region border parts are certainly
By spending；
For the corresponding outer force vector of current area domain internal degree of freedom；
For the corresponding outer force vector of current area field surface degree of freedom；
Other K components are that matrix carries out corresponding matrix in block form after elementary row-column transform；It is calculated with balance fore condition iteration
Method solves surface degree of freedom equation, obtainsuBLinear system will be substituted into
System, is obtained using direct method.
The beneficial effects of the invention are as follows：
The present invention carries out face recognition in projection systems, using infrared camera, is regarded according to being preset the characteristics of everyone
Angle adjust susceptibility, while in video content object classification and by frame mark, the perpetual object of user is acquired, according to individual
The viewing experience evaluation of participation carries out the deep learning for having supervision, forms artificial intelligence model.To which user to be most interested in
Viewing object is presented in user at the moment with the posture visual angle of user's the most comfortable, and is regarded according to the most adaptable susceptibility of user
Angle adjust, by the most suitable visual angle of user establish user characteristics, situation model, establish the model that user corresponds to crowd portrayal,
And whole crowd corresponds to portrait model in Optimization Algorithms Library, the selection as corresponding crowd's initialization model.
Description of the drawings
Fig. 1 is the flow chart of the present invention.
Specific implementation mode
The invention will be further described below in conjunction with the accompanying drawings：
As shown in Figure 1, automatic adjustment visual angle shadow casting technique, carries out successively as steps described below：
Step 1：Projecting apparatus by being provided with steering gear carries out line holographic projections and plays influence, and viewer wears acceleration
Acquisition module normally watches influence, and infrared camera is installed to viewing person opposite, by the collected viewing person of infrared camera
Face recognition image, motion images information and the collected acoustic information of microphone and acceleration acquisition information are handed over by network
Changing device passes to host；
Step 2：Image information pretreatment is carried out to the information in step 1, the three of object are built by spatial digitizer
Dimension module, set initial boundary conditions, according to boundary condition carry out threedimensional model Region Decomposition, decomposition obtain in parallel computation
Always into the equal submodel number of number of passes, using initial boundary conditions as design conditions, when boundary condition initial in calculating process
It changes, restarts boundary setting program, the submodel is calculated again, until boundary is stable or calculates son knot
Fruit is constant, corresponding input file in current process is read in, using Concurrent Feature curved line arithmetic to non-thread in governing equation
Property item carry out linearization process, obtain positive definite, symmetrical local linear system, if boundary condition change restarting side
Program is arranged in boundary, then is calculated, until boundary is stable or the sub- result of calculating is permanent；Often complete the meter of certain time step
It calculates, carries out the read-write operation of an output file；
Step 3：It is modeled by the rule of the collected acceleration information of step 1 with analysis module, and passes through something lost
The operation for passing operator provides moving state identification as a result, being used for remote management；
Step 4：By the dither noise balance in projection process, filtering and noise reduction, then hierarchical layered dimensionality reduction modeling utilizes
The output data of the acceleration transducer, and judge that human motion type, layering judge whether human body is quiet using medium filtering
Only movement, motive position, type, classification sampling judge the influence of main feature, comprehensive verification emphasis feature, and then judge to turn over
Body such as pushes, gets up at the features such as sleep, when modeling, synthesis amplitude is exported by accelerometer first, in given threshold up and down
Between value, then judge that human body is static；Conversely, then judging that people moves, the accelerometer output synthesis amplitude is：
The upper lower threshold value is respectively：tha min=8m/s, tha max=11m/s, first condition are：
If first condition is judged as static, to be exported without the judgement of second, third condition, accelerometer part
Variance then judges that the body part is static less than given threshold value；Conversely, then judge that the body part moves, the Article 2
Part calculation formula is：
Wherein, thσa=0.5, if second condition is judged as that the body part is static, without sentencing for third condition
It is disconnected, conversely, the third condition calculation formula is：
Wherein,thamax=50, then carry out
The state of movement is sampled calculating and extracts characteristic parameter；
Step 5：To the data characteristics integration modeling in step 2 to step 4, the light sensor for assessing camera obtains
Values of light grade, type of sports, user setting important kind obtain light sensation quality user 5 and divide appraisement system, by having
Supervised classification algorithm one is supervision factor pair ratio with history optimum data, establishes subjective feeling and adaptively projects tune with environmental parameter
Save model；
Step 6：Establish whole crowd and correspond to projection portrait model depth and mutually learn pattern-recognition, according in database
Have registered N class samples, sample inputted into classifier training, according to input value judgement be in (1, N) which kind of, if beyond (1,
N) range, then new registration classification N+1 classes, then update grader again；
Step 7：To calculating sub- result merging treatment, host process reads in the output of each process in current time step respectively
The collected multi-path video stream is carried out split processing, to generate the panoramic video stream for carrying the timestamp, so by file
Result is merged according to the algorithm of Region Decomposition afterwards and is restored, result is kept in ASCLL formats；It is whole that virtual reality is worn in user
When end, whether detection virtual reality terminal is kept in motion, if so, video frequency frame to be played is adjusted according to acceleration, with
It is supplied to user's synchronization video information, by presentation of information in the vision coverage area of virtual reality terminal；
Step 8：The analysis of analysis module through the above steps obtains the best projection angle of current viewing person, adjusts control
The steering gear of projecting apparatus in step 1 processed is to be adjusted to best viewing projection angle；
Step 9：For viewing person constantly repeat step 1 to step 8 process, with the increase SVM of sample amount
Grader can adaptively be continued to optimize to improve inputs new sample every time, according to cross-validation method principle, calculates SVM classifier
Discrimination carries out Fitness analysis, does not set the stop value of genetic algorithm, and end condition is used than supreme people's court, if the knowledge of training
Rate is not higher than existing, is set as optimized parameter, otherwise, executes the operations such as selection, intersection and variation and advanced optimizes training parameter,
Realize the constantly improve for viewing person's personalization projection scheme.
In the present embodiment, the acceleration acquisition module that step 1 viewing person carries uses MEMS (Micro Flectro
MechanicalSystems, MEMS), key component is a kind of intermediate capacitance plate of cantilevered construction, when velocity variations or
When acceleration reaches sufficiently large, the inertia force suffered by it is more than fixed or supports his power, and at this moment it will be moved, with power-on and power-off
Holding the distance between plate will change, therefore upper and lower capacitance will change.Capacitance variations are directly proportional with acceleration.Capacitance variations meeting
It is converted into voltage signal directly output or is exported after digitized processing.
In the present embodiment, the original motion vector group (F1, F2 ..., Fm) of the extraction characteristic parameter in step 4, m is small
In 9, extracting matrix is：
It is most that wherein original vector F1 contains information content, and there is maximum variance, referred to as first principal component, F2 ..., Fm to pass successively
Subtract, referred to as Second principal component, " " ", m principal components.Therefore the process of principal component analysis, which can be regarded as, is to determine weight coefficient aik
(i=1, " " ", m；K=1, " " " 9) process.
In the present embodiment, the indicatrix algorithm in the step 2 carries out the nonlinear terms in governing equation linear
Change is handled, and obtains positive definite, symmetrical local linear system is：
Wherein, K(i)For local stiffness matrix, U(i)For local known variables, f(i)For known localized external force vector, R(i)
The 0-1 matrixes mapped between local element mark number and whole element number；
Surface degree of freedom equation is as follows：
Wherein,For current area domain internal degree of freedom,Current area field surface and other region border parts are certainly
By spending；
For the corresponding outer force vector of current area domain internal degree of freedom；
For the corresponding outer force vector of current area field surface degree of freedom；
Other K components are that matrix carries out corresponding matrix in block form after elementary row-column transform；It is calculated with balance fore condition iteration
Method solves surface degree of freedom equation, obtainsuBLinear system will be substituted into
System, is obtained using direct method.
It should be noted last that：The above embodiments are only used to illustrate and not limit the technical solutions of the present invention, although ginseng
It is described the invention in detail according to above-described embodiment, it will be apparent to an ordinarily skilled person in the art that：It still can be to this
Invention is modified or replaced equivalently, without departing from the spirit or scope of the invention, or any substitutions,
It is intended to be within the scope of the claims of the invention.
Claims (4)
1. automatically adjusting visual angle shadow casting technique, it is characterised in that：It carries out successively as steps described below：
Step 1：Projecting apparatus by being provided with steering gear carries out line holographic projections and plays influence, and viewer wears acceleration acquisition
Module normally watches influence, and infrared camera is installed to viewing person opposite, by the collected viewing person's face of infrared camera
Identification image, motion images information and the collected acoustic information of microphone and acceleration acquisition information are filled by network exchange
It sets and passes to host；
Step 2：Image information pretreatment is carried out to the information in step 1, the three-dimensional mould of object is built by spatial digitizer
Type, set initial boundary conditions, according to boundary condition carry out threedimensional model Region Decomposition, decomposition obtain in parallel computation always into
The equal submodel number of number of passes, using initial boundary conditions as design conditions, when boundary condition initial in calculating process occurs
Change then restarts boundary setting program, calculates again the submodel, is until boundary is stable or calculates sub- result
Constant reads in corresponding input file in current process, using Concurrent Feature curved line arithmetic to the nonlinear terms in governing equation
Linearization process is carried out, positive definite, symmetrical local linear system are obtained, boundary is set if boundary condition changes restarting
Program is set, then is calculated, until boundary is stable or the sub- result of calculating is permanent；The calculating of certain time step is often completed,
Carry out the read-write operation of an output file；
Step 3：It is modeled by the rule of the collected acceleration information of step 1 with analysis module, and is calculated by heredity
The operation of son provides moving state identification as a result, being used for remote management；
Step 4：By the dither noise balance in projection process, filtering and noise reduction, then hierarchical layered dimensionality reduction models, using described
The output data of acceleration transducer, and judge that human motion type, layering judge the whether static fortune of human body using medium filtering
Dynamic, motive position, type, classification sampling judge the influence of main feature, comprehensive verification emphasis feature, and then judge to turn over, push away
The features such as sleep such as move, get up, when modeling, synthesis amplitude is exported by accelerometer first, in given upper lower threshold value it
Between, then judge that human body is static；Conversely, then judging that people moves, the accelerometer output synthesis amplitude is：
The upper lower threshold value is respectively：tha min=8m/s, tha max=11m/s, first condition are：
If first condition is judged as static, to be exported without the judgement of second, third condition, accelerometer part side
Difference then judges that the body part is static less than given threshold value；Conversely, then judge that the body part moves, the second condition
Calculation formula is：
Wherein, thσa=0.5, if second condition is judged as that the body part is static, without the judgement of third condition, instead
It, the third condition calculation formula is：
Wherein,thamax=50, then moved
State be sampled calculating and extract characteristic parameter；
Step 5：To the data characteristics integration modeling in step 2 to step 4, the light sensor acquisition of camera is assessed
Values of light grade, type of sports, user setting important kind obtain light sensation quality user 5 and divide appraisement system, by there is supervision
Sorting algorithm-is supervision factor pair ratio with history optimum data, establishes subjective feeling and adaptively projects adjusting mould with environmental parameter
Type；
Step 6：It establishes whole crowd's correspondence projection portrait model depth and mutually learns pattern-recognition, registered according in database
N class samples, classifier training is inputted by sample, according to input value judgement be in (1, N) which kind of, if exceeding (1, N) model
It encloses, then new registration classification N+1 classes, then update grader again；
Step 7：To calculating sub- result merging treatment, host process reads in the output file of each process in current time step respectively,
The collected multi-path video stream is subjected to split processing, to generate the panoramic video stream for carrying the timestamp, is then pressed
Result is merged into reduction according to the algorithm of Region Decomposition, result is kept in ASCLL formats；Virtual reality terminal is worn in user
When, whether detection virtual reality terminal is kept in motion, if so, video frequency frame to be played is adjusted according to acceleration, to carry
User's synchronization video information is supplied, by presentation of information in the vision coverage area of virtual reality terminal；
Step 8：The analysis of analysis module through the above steps obtains the best projection angle of current viewing person, adjusting control step
The steering gear of projecting apparatus in rapid one is to be adjusted to best viewing projection angle；
Step 9：For viewing person constantly repeat step 1 to step 8 process, with the increase svm classifier of sample amount
Device can adaptively be continued to optimize to improve inputs new sample every time, according to cross-validation method principle, calculates SVM classifier identification
Rate carries out Fitness analysis, does not set the stop value of genetic algorithm, and end condition is used than supreme people's court, if the discrimination of training
Higher than existing, it is set as optimized parameter, otherwise, selection is executed, intersects and the operations such as variation advanced optimize training parameter, realize
For the constantly improve of viewing person's personalization projection scheme.
2. automatic adjustment visual angle shadow casting technique according to claim 1, it is characterised in that：What step 1 viewing person carried adds
Speed acquisition module uses MEMS (Micro Flectro MechanicalSystems, MEMS), and key component is one
The intermediate capacitance plate of kind of cantilevered construction, when velocity variations or acceleration reach sufficiently large, the inertia force suffered by it is more than to fix
Or his power is supported, at this moment it will be moved, and will be changed with the distance between upper and lower capacitor board, therefore upper and lower capacitance will become
Change.Capacitance variations are directly proportional with acceleration.Capacitance variations can be converted into voltage signal directly output or pass through digitized processing
After export.
3. automatic adjustment visual angle shadow casting technique according to claim 1, it is characterised in that：Extraction feature ginseng in step 4
Several original motion vector groups (F1, F2 ..., Fm), m are less than 9, and extraction matrix is：
It is most that wherein original vector F1 contains information content, and there is maximum variance, referred to as first principal component, F2 ..., Fm to pass successively
Subtract, referred to as Second principal component, " " ", m principal components.Therefore the process of principal component analysis, which can be regarded as, is to determine weight coefficient aik
(i=1, " " ", m；K=1, " " " 9) process.
4. automatic adjustment visual angle shadow casting technique according to claim 1, it is characterised in that：Feature in the step 3 is bent
Line algorithm carries out linearization process to the nonlinear terms in governing equation, obtains positive definite, symmetrical local linear system is：
Wherein, K(i)For local stiffness matrix, U(i)For local known variables, f(i)For known localized external force vector, R(i)For office
The 0-1 matrixes mapped between portion's element mark number and whole element number；
Surface degree of freedom equation is as follows：
Wherein,For current area domain internal degree of freedom,Current area field surface and other region border some freedoms；
For the corresponding outer force vector of current area domain internal degree of freedom；
For the corresponding outer force vector of current area field surface degree of freedom；
Other K components are that matrix carries out corresponding matrix in block form after elementary row-column transform；With balance pre conditioning iteration pair
Surface degree of freedom equation is solved, and is obtaineduBLinear system will be substituted into, will be adopted
It is obtained with direct method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811060802.6A CN108769640A (en) | 2018-09-11 | 2018-09-11 | Automatically adjust visual angle shadow casting technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811060802.6A CN108769640A (en) | 2018-09-11 | 2018-09-11 | Automatically adjust visual angle shadow casting technique |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108769640A true CN108769640A (en) | 2018-11-06 |
Family
ID=63968032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811060802.6A Pending CN108769640A (en) | 2018-09-11 | 2018-09-11 | Automatically adjust visual angle shadow casting technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108769640A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110312170A (en) * | 2019-07-12 | 2019-10-08 | 青岛一舍科技有限公司 | A kind of video broadcasting method and device at adjustment visual angle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103584840A (en) * | 2013-11-25 | 2014-02-19 | 天津大学 | Automatic sleep stage method based on electroencephalogram, heart rate variability and coherence between electroencephalogram and heart rate variability |
| CN103679809A (en) * | 2013-12-24 | 2014-03-26 | 中山大学 | Data parallel treatment based virtual reality 3D simulation method and system |
| CN103968827A (en) * | 2014-04-09 | 2014-08-06 | 北京信息科技大学 | Wearable human body gait detection self-localization method |
| CN104931049A (en) * | 2015-06-05 | 2015-09-23 | 北京信息科技大学 | Movement classification-based pedestrian self-positioning method |
| CN106971059A (en) * | 2017-03-01 | 2017-07-21 | 福州云开智能科技有限公司 | A kind of wearable device based on the adaptive health monitoring of neutral net |
| CN107018399A (en) * | 2017-03-28 | 2017-08-04 | 北京犀牛数字互动科技有限公司 | Image data transfer method and device |
| CN107102728A (en) * | 2017-03-28 | 2017-08-29 | 北京犀牛数字互动科技有限公司 | Display methods and system based on virtual reality technology |
| CN107753026A (en) * | 2017-09-28 | 2018-03-06 | 古琳达姬（厦门）股份有限公司 | For the intelligent shoe self-adaptive monitoring method of backbone leg health |
-
2018
- 2018-09-11 CN CN201811060802.6A patent/CN108769640A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103584840A (en) * | 2013-11-25 | 2014-02-19 | 天津大学 | Automatic sleep stage method based on electroencephalogram, heart rate variability and coherence between electroencephalogram and heart rate variability |
| CN103679809A (en) * | 2013-12-24 | 2014-03-26 | 中山大学 | Data parallel treatment based virtual reality 3D simulation method and system |
| CN103968827A (en) * | 2014-04-09 | 2014-08-06 | 北京信息科技大学 | Wearable human body gait detection self-localization method |
| CN104931049A (en) * | 2015-06-05 | 2015-09-23 | 北京信息科技大学 | Movement classification-based pedestrian self-positioning method |
| CN106971059A (en) * | 2017-03-01 | 2017-07-21 | 福州云开智能科技有限公司 | A kind of wearable device based on the adaptive health monitoring of neutral net |
| CN107018399A (en) * | 2017-03-28 | 2017-08-04 | 北京犀牛数字互动科技有限公司 | Image data transfer method and device |
| CN107102728A (en) * | 2017-03-28 | 2017-08-29 | 北京犀牛数字互动科技有限公司 | Display methods and system based on virtual reality technology |
| CN107753026A (en) * | 2017-09-28 | 2018-03-06 | 古琳达姬（厦门）股份有限公司 | For the intelligent shoe self-adaptive monitoring method of backbone leg health |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110312170A (en) * | 2019-07-12 | 2019-10-08 | 青岛一舍科技有限公司 | A kind of video broadcasting method and device at adjustment visual angle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105426827B (en) | Living body verification method, device and system | |
| CN110531860B (en) | Animation image driving method and device based on artificial intelligence | |
| CN104951773B (en) | A kind of real-time face recognition monitoring system | |
| US20180032135A1 (en) | Method for gaze tracking | |
| El Saddik et al. | The potential of digital twins | |
| CN110460837A (en) | With central fovea display and the electronic equipment for watching prediction attentively | |
| CN109475294A (en) | For treat phrenoblabia movement and wearable video capture and feedback platform | |
| CN109726771A (en) | Abnormal driving detection model method for building up, device and storage medium | |
| CN108875708A (en) | Behavior analysis method, device, equipment, system and storage medium based on video | |
| CN103473801A (en) | Facial expression editing method based on single camera and motion capturing data | |
| KR20160012902A (en) | Method and device for playing advertisements based on associated information between audiences | |
| CA2956508A1 (en) | Method and system for reconstructing obstructed face portions for virtual reality environment | |
| CN108363973A (en) | A kind of unconfined 3D expressions moving method | |
| CN112907406B (en) | Online learning system based on cloud fusion multi-modal analysis | |
| CN108932060A (en) | Gesture three-dimensional interaction shadow casting technique | |
| KR20200012355A (en) | Online lecture monitoring method using constrained local model and Gabor wavelets-based face verification process | |
| CN112259218A (en) | Training method for auditory stimulation of infantile autism based on VR interaction technology | |
| CN110472622A (en) | Method for processing video frequency and relevant apparatus, image processing method and relevant apparatus | |
| CN111026267A (en) | VR electroencephalogram idea control interface system | |
| CN108769640A (en) | Automatically adjust visual angle shadow casting technique | |
| CN110675312A (en) | Image data processing method, image data processing device, computer equipment and storage medium | |
| Zheng et al. | Driver fatigue analysis based on upper body posture and DBN-BPNN model | |
| WO2022024272A1 (en) | Information processing system, data accumulation device, data generation device, information processing method, data accumulation method, data generation method, recording medium, and database | |
| CN109032361A (en) | Intelligent 3D shadow casting technique | |
| He | Multimedia Vision Improvement and Simulation in Consideration of Virtual Reality Reconstruction Algorithms |
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: 20181106 |
|
| RJ01 | Rejection of invention patent application after publication |