CN109698944A - View field's bearing calibration, projection device and computer readable storage medium - Google Patents
View field's bearing calibration, projection device and computer readable storage medium Download PDFInfo
- Publication number
- CN109698944A CN109698944A CN201710990380.1A CN201710990380A CN109698944A CN 109698944 A CN109698944 A CN 109698944A CN 201710990380 A CN201710990380 A CN 201710990380A CN 109698944 A CN109698944 A CN 109698944A
- Authority
- CN
- China
- Prior art keywords
- image
- projection
- view field
- feature
- original
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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]
- H04N9/3141—Constructional details thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Controls And Circuits For Display Device (AREA)
- Transforming Electric Information Into Light Information (AREA)
Abstract
The present invention provides a kind of view field's bearing calibration, projection device and computer readable storage mediums, and wherein method includes: to establish projection scene image local feature index data base;When projection device is opened, the projection scene image of projection device is obtained, projects scene image by view field's image and projection screen image construction;Calculate the first eigenvector of view field's image and the second feature vector of projection screen image;First eigenvector, second feature vector and the class in index data base are compared, identify the first corner points group information of view field's image and the second corner points group information of projection screen image;The mapping relations of view field's image Yu projection screen image are established according to the first corner points group information and the second corner points group information;The view field that projection device is adjusted according to mapping relations, is overlapped the view field of projection device with projection screen.The present invention can calibrate view field during user's viewing automatically, manually adjust without user.
Description
Technical field
The invention belongs to projection art more particularly to a kind of view field's bearing calibrations, projection device and computer
Readable storage medium storing program for executing.
Background technique
With the improvement of living standards, demand of the people to large screen television is more and more, the hair of projection device is promoted
Exhibition, so that projection device also steps into people's lives, projection device can be realized the screen bigger than LCD TV
Curtain size, brings the multimedia recreation more shaken to enjoy.
Since projection device is to project the real picture of image, camera lens on curtain through convex lens lens head by light source
The projected picture that must keep suitable positional relationship that could make projection device with curtain is completely filled with curtain region.However,
In actual use, it many times will appear since the positional relationship between projection device and curtain is improper, cause to throw
The light that shadow equipment projects is spilt into except curtain, affects the visual effect that user watches video.
In view of the above-mentioned problems, in the prior art, user generally requires the side manually adjusted when using projection device
Formula projects the view field of projection device the ideal position of projection screen, and operating process is very cumbersome, and manually adjusts
It is whole after institute energy user drop shadow effect also tend to it is unsatisfactory.
Summary of the invention
In view of this, the present invention provides a kind of view field's bearing calibration, projection device and computer-readable storage mediums
Matter, to solve user in the prior art, when using projection device, the mode for generally requiring manually to adjust is projection device
View field project the ideal position of projection screen, operating process is very cumbersome, and institute can user after manually adjusting
Drop shadow effect also tend to unsatisfactory problem.
The first aspect of the present invention provides a kind of view field's bearing calibration, comprising:
Projection scene image local feature index data base is established, the index data base includes all kinds of corner points each
Index under scale;
When projection device is opened, the projection scene image of projection device is obtained, the projection scene image is by projected area
Area image and projection screen image construction;
Calculate the first eigenvector of view field's image and the second feature vector of the projection screen image;
By the first eigenvector, the second feature vector with all kinds of corner points in the index data base each
Index under scale compares, identify view field's image the first corner points group information and the projection screen Butut
Second corner points group information of picture;
According to the first corner points group information and the second corner points group information establish view field's image with
The mapping relations of the projection screen image;
The view field that the projection device is adjusted according to the mapping relations, make the view field of the projection device with
Projection screen is overlapped.
The second aspect of the present invention provides a kind of projection device, including memory, processor and is stored in described deposit
In reservoir and the computer program that can run on the processor, wherein when the processor executes the computer program
It realizes such as the step of above-mentioned first aspect the method.
The third aspect of the present invention provides a kind of computer readable storage medium, and the computer readable storage medium is deposited
Contain computer program, wherein realize when the computer program is executed by processor such as above-mentioned first aspect the method
Step.
The beneficial effects of the present invention are:
The present invention is due to pre-establishing projection scene image local feature index data base, the subsequent use in projection device
In the process, by extracting the feature vector of view field's image and projection screen image in projection scene image, and by itself and rope
The feature vector data drawn in database is compared, to obtain the corner of view field and projection screen in projection scene image
Point information, and referring to the view field of the corner points information of the view field and projection screen got adjustment projection device, make
The view field for obtaining projection device is completely coincident with projection screen, so that projection device is during user's viewing
Automatic calibration view field, manually adjusts without user, and it is clear to guarantee that projection device obtains after view field's correction
Clear drop shadow effect improves the viewing experience of user.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is topological diagram when projection device provided in an embodiment of the present invention uses;
Fig. 2 is the implementation process schematic diagram of view field's bearing calibration provided in an embodiment of the present invention;
Fig. 3 is the schematic diagram that scene image is projected in a concrete application scene;
Fig. 4 another embodiment of the present invention provides view field's bearing calibration in step S201 specific implementation flow signal
Figure;
Fig. 5 be another embodiment of the present invention provides view field's bearing calibration in will test a little with its neighborhood in consecutive points
The schematic diagram being compared;
Fig. 6 is the schematic block diagram of projection device provided in an embodiment of the present invention;
Fig. 7 is the schematic block diagram of index data library unit in projection device provided in an embodiment of the present invention;
Fig. 8 be another embodiment of the present invention provides projection device schematic block diagram.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Fig. 1 is the topological diagram of projection device provided in an embodiment of the present invention when in use.It only shows for ease of description
Part related to the present embodiment.
Shown in Figure 1, which includes projection device and curtain, the view that the projection device itself can will play
Frequency image projection is shown on the curtain.Wherein, photographic device is provided on the projection device, inside the projection device
It is provided with the processor of the projection scene image adjustment view field taken according to the photographic device.The projection device exists
In projection process, by the photographic device shoot projection scene image, and by the processor to the projection scene image into
Row processing, and according to the view field of processing result adjusting projection device, so that the view field of projection device and projection screen
It is completely coincident.In embodiments of the present invention, the projection device includes but is not limited to projection TV.
Based on topological diagram shown in FIG. 1, below in conjunction with specific embodiment to projection device provided in an embodiment of the present invention
Atomatic focusing method is described in detail:
Fig. 2 shows the implementation process of view field's bearing calibration provided in an embodiment of the present invention, embodiments shown in Fig. 2
In, the executing subject of process is the projection device in Fig. 1.Details are as follows for the implementation process of this method:
Step S201 establishes projection scene image local feature index data base, all kinds of corner points of index data base
Index under each scale.
In the present embodiment, the projection scene image is by view field's image and projection screen image construction.Such as Fig. 3 institute
Show, to project the schematic diagram of scene image under a concrete application scene.
In the present embodiment, the projection scene image local feature index data base is that preparatory training obtains, the number
According to local feature index of the projection scene image under different scale is wrapped in library, the local feature index under each scale is equal
It include 8 classes, four corner points A ' of respectively described view field's image, B ', C ', D ' and the projection screen image
The index of four corner points A, B, C, D.
Step S202 obtains the projection scene image of projection device, the projection scene image when projection device is opened
By view field's image and projection screen image construction.
In the present embodiment, the projection device can trigger the photographic device being arranged on the projection device when opening
Shoot the projection scene image.
Step S203, calculate view field's image first eigenvector and the projection screen image second
Feature vector.
It in the present embodiment, is color image by the projection scene image that the photographic device takes, in step
Before rapid S203 further include:
The projection scene image is converted to identical by formula Gray=R*0.299+G*0.587+B*0.114
The gray level image of resolution ratio.
In the present embodiment, local shape factor is carried out to the gray level image using SIFT feature algorithm, described in acquisition
Project the first eigenvector of view field's image and the second feature vector of the projection screen image described in scene image.
Wherein, the first eigenvector includes the direction vector of each characteristic point in view field's image, the second feature
Vector includes the direction vector of each characteristic point in the projection screen image.
Step S204, by all kinds of sides in the first eigenvector, the second feature vector and the index data base
Index of the angle point under each scale compares, and identifies the first corner points group information of view field's image and described
Second corner points group information of projection screen image.
In the present embodiment, due to the office in the index data base comprising the projection scene image under different scale
Portion's aspect indexing, the local feature index under each scale includes 8 classes, and four of respectively described view field's image
Corner points A ', B ', C ', D ' and the projection screen image four corner points A, B, C, D index.Therefore, getting
State projection scene image described in view field's image first eigenvector and the projection screen image second feature to
After amount, that is, can be used nearest neighbor algorithm by by the first eigenvector and the second feature vector respectively with the index number
It is compared according to index of the corner points all kinds of in library under each scale, that is, may recognize that throwing described in the projection scene image
First corner points group information of shadow zone area image and second tetra- sides corner points group information A, B, C, D of the projection screen image
Angle point.Wherein, the first corner points group information includes four A ', B ', C ', D ' corner points;The second corner points group information includes
A, tetra- corner points of B, C, D.
It should be understood that the schematic diagram of the projection scene shown in Fig. 3 is only the preferable implementation example that the present invention enumerates,
In other implementation examples, it can also take on midpoint and the projection screen four edges on view field's four edges
Midpoint is respectively as the first corner points group information of the view field and the second corner points group information of the projection screen.
Step S205 establishes the projected area according to the first corner points group information and the second corner points group information
The mapping relations of area image and the projection screen image.
In the present embodiment, after getting the corner points information of the view field and the projection screen, according to this
The position of a little corner points information calculates corner points A ' in view field's image, B ', C ', D ' to the projection screen Butut
The mapping relations of four corner points A, B, C, D of picture obtain the conversion being mapped to the view field on the projection screen
Matrix.
Step S206 adjusts the view field of the projection device according to the mapping relations, makes the projection device
View field is overlapped with projection screen.
In the present embodiment, after getting the mapping relations between view field's image and projection screen image
Each pixel value in view field's image is projected according to the mapping relations, so that view field's image projects on curtain
Tetra- corner points area defined of A, B, C, D are just full of, the requirement that view field is overlapped with projection screen is met.
Above as can be seen that view field's bearing calibration provided in this embodiment is due to pre-establishing projection scene image office
Portion's aspect indexing database, it is subsequent in the use process of projection device, schemed by extracting view field in projection scene image
The feature vector of picture and projection screen image, and it is compared with the feature vector data in index data base, to obtain
The corner points information of view field and projection screen in scene image is projected, and referring to the view field and projection screen got
Corner points information adjustment projection device view field so that the view field of projection device is completely coincident with projection screen,
So that projection device calibrates view field during user's viewing automatically, manually adjusted without user, and
It can guarantee that projection device obtains clearly drop shadow effect after view field's correction, improve the viewing experience of user.
Fig. 4 show another embodiment of the present invention provides view field's bearing calibration in step S201 specific implementation stream
Journey schematic diagram.Shown in Figure 4, in the present embodiment, step S201 may comprise steps of:
Step S401 obtains the original projection scene image of projection device, and the original projection scene image is by original throwing
Shadow zone area image and original projection curtain image construction.
Step S402 carries out gray proces to the original projection area image and the original projection curtain image.Ash
Degree processing mode is identical as the gray proces mode in step S203 in a upper embodiment, and details are not described herein.
Step S403 extracts original projection curtain described in the third feature vector sum of the original projection area image respectively
The fourth feature vector of cloth image.
In the present embodiment, step S430 is specifically included:
Construct scale space;
The original projection area image and the original projection curtain image are detected in the characteristic point of each scale space;
For one 128 dimension directioin parameter of each characteristic point assignment, 128 dimensional feature vectors are formed.
Wherein, the building scale space includes:
Gaussian difference pyrene and the original projection scene image convolution using different scale, generate the height under different scale
This blurred picture;
The Gaussian Blur image of adjacent scale is made the difference, Gauss residual image is obtained.
In the present embodiment, for a width original projection scene image, it is established in the image of different scale, also referred to as son
Octave, this is that is, in any scale can have corresponding characteristic point, the ratio of first sub- octave for scale invariability
Example is the size of original image, behind every sub- octave be a upper sub- octave it is down-sampled as a result, i.e. original image 1/4 (length and width difference
Halve), constitute next sub- octave.
Wherein, the detection original projection area image and the original projection curtain image are in each scale space
Characteristic point include:
Gauss residual image corresponding to each scale space is sampled respectively, by each sampled point respectively with
18 points in its 8 neighborhood and its in adjacent two scales up and down are compared, if sampled point scale space sheet where it
When being maximum value or minimum value in layer and lower upper two layers of 26 points, then it is assumed that the sampled point is the Gauss residual image
A characteristic point under the scale.
In the present embodiment, in order to find corresponding to each scale space the characteristic point in projection scene image, image
On each sampled point will be all with it consecutive points compare, see its whether than it image area and scale domain consecutive points
It is big or small.As shown in figure 5, intermediate test point is with it with 8 consecutive points and neighbouring scale corresponding 9 × 2 of scale
A, totally 26 points compare, to ensure all to detect characteristic point in scale space and two dimensional image space.If a point exists
When being maximum or minimum value in this layer of scale space and bilevel 26 neighborhood consecutive points, then it is assumed that the point is image
A characteristic point under the scale.
Wherein, described is one 128 dimension directioin parameter of each characteristic point assignment, forms 128 dimensional feature vectors and includes:
The direction vector that each characteristic point is calculated using the gradient direction distribution characteristic of key point neighborhood territory pixel, has operator
Standby rotational invariance;
Each characteristic point is described using 16 sub-regions, forms 16 seed points, and each seed point uses 8 directions
Description vectors are carried out in all directions using the Euclidean distance in the direction of vector and its principal direction in the direction for carrying out description vectors
Amplitude size forms 128 dimensional feature vectors.Preferably, in the present embodiment, 8 directions are respectively 0, π/4, pi/2, and 3 π/
4, π, 5 π/4,3 pi/2s, 2 π.
Preferably, in the present embodiment, described for one 128 dimension directioin parameter of each characteristic point assignment, 128 dimension of formation
Before feature vector further include:
The original projection area image and the original projection curtain image are removed in the characteristic point of each scale space
Included in low contrast characteristic point and unstable skirt response point.
In the present embodiment, institute in the original projection scene image is removed using approximate Harris Corner detector
Matching stability can be enhanced in the characteristic point for the low contrast for including and unstable skirt response point in this way, improves anti-noise energy
Power.
Step S404, by PCA, ((Principal Components Analysis, principal component analysis) is to the third
Feature vector and the fourth feature vector carry out dimension-reduction treatment, remove fourth feature vector described in the third feature vector sum
In minimal eigenvalue corresponding to ingredient.
In the present embodiment, since the eigenmatrix information content of 128 dimensional feature vectors formation is bigger, in order to accelerate information
The speed compared does maximum eigenvalue decomposition to data on orthogonal basis by PCA, carries out dimension-reduction treatment, in vector matrix,
Remove ingredient corresponding to minimal eigenvalue, ingredient corresponding to the biggish characteristic value of retention factor.
Step S405, by SVD (Singular value decomposition, singular value decomposition) respectively by described
N dimensional feature in three feature vectors and the fourth feature vector is mapped to m dimensional feature, obtains the original projection scene image
Feature descriptor vector, wherein n > m, and n, m are positive integer.In the present embodiment, n dimensional feature is mapped to m dimensional feature,
Mainly realized by SVD Orthogonal Decomposition.
Step S406 repeats above-mentioned process, the feature descriptor for all original projection scene images that will acquire
Vector is added in the projection scene image local feature index data base.
Step S407, by K-means algorithm to the feature in the projection scene image local feature index data base
Descriptor is divided into k cluster, and wherein k is positive integer.
Preferably, in the present embodiment, step S407 is specifically included:
It chooses k seed point in all feature descriptor vectors in vector at random, other vectors is asked to arrive this k kinds respectively
The distance of son point, which seed point distance of vector distance closely just return class where whose which seed point;
The point group center (i.e. particle center) for being subordinated to it is arrived at the center of class where mobile seed point, repeats the above steps directly
To particle center do not need it is mobile based on, k cluster can be obtained.
It should be noted that in the present embodiment the implementation of other steps with the implementation phase in a upper embodiment
Together, therefore details are not described herein.
Thus, it will be seen that view field's bearing calibration provided in this embodiment can equally make projection device with
View field is calibrated automatically during the viewing of family, is manually adjusted without user, and projection device can be guaranteed in projected area
Clearly drop shadow effect is obtained after the correction of domain, improves the viewing experience of user.
Fig. 6 is the schematic diagram of projection device provided in an embodiment of the present invention.For ease of description, it illustrate only and this reality
Apply the relevant part of example.
Shown in Figure 6, projection device 6 provided in this embodiment includes:
Index data base establishes unit 61, for establishing projection scene image local feature index data base;
Scene image acquiring unit 62 is projected, for obtaining the projection scene figure of projection device when projection device is opened
Picture, the projection scene image is by view field's image and projection screen image construction;
Fisrt feature extraction unit 63, for calculate view field's image feature vector and the projection screen
The feature vector of image;
Characteristic matching unit 64 is used for the first eigenvector, the second feature vector and the index data
Class in library compares, identify view field's image the first corner points group information and the projection screen image
Second corner points group information;
Mapping relations computing unit 65, for according to the first corner points group information and the second corner points group information
Establish the mapping relations of view field's image Yu the projection screen image;
View field's adjustment unit 66 makes for adjusting the view field of the projection device according to the mapping relations
The view field of the projection device is overlapped with projection screen.
Preferably, shown in Figure 7, the index data base establishes unit 61 and includes:
Original scene image acquisition unit 611, for obtaining the original projection scene image of projection device, the original throwing
Shadow scene image is by original projection area image and original projection curtain image construction;
Gray scale processing unit 612, for being carried out to the original projection area image and the original projection curtain image
Gray proces;
Second feature extraction unit 613, for extracting the third feature vector of the original projection area image respectively
With the fourth feature vector of the original projection curtain image;
Principal component analysis unit 614, for special to the described in the third feature vector sum the 4th by PCA principal component analysis
It levies vector and carries out dimension-reduction treatment, remove corresponding to the minimal eigenvalue in fourth feature vector described in the third feature vector sum
Ingredient;
Singular value decomposition unit 615, for by SVD singular value decomposition respectively by described in the third feature vector sum the
N dimensional feature in four feature vectors is mapped to m dimensional feature, obtains the feature descriptor vector of the original projection scene image,
Wherein n > m, and n, m are positive integer;
Database writing unit 616, for repeating above-mentioned process, all original projection scene images that will acquire
Feature descriptor vector be added in the projection scene image local feature index data base;
Feature points clustering unit 617, for passing through K-means algorithm to the projection scene image local feature index number
K cluster is divided into according to the feature descriptor in library.
Preferably, the second feature extraction unit 613 includes:
Scale space construction unit 6131, for constructing scale space;
Characteristic point detection unit 6132, for detecting the original projection area image and the original projection curtain image
In the characteristic point of each scale space;
Characteristic point assignment unit 6133 forms 128 Wei Te for being one 128 dimension directioin parameter of each characteristic point assignment
Levy vector.
Preferably, the scale space construction unit 6131 is specifically used for:
Gaussian difference pyrene and the original projection scene image convolution using different scale, generate the height under different scale
This blurred picture;
The Gaussian Blur image of adjacent scale is made the difference, Gauss residual image is obtained.
Preferably, the characteristic point detection unit 6132 is specifically used for:
Gauss residual image corresponding to each scale space is sampled respectively, by each sampled point respectively with
18 points in its 8 neighborhood and its in adjacent two scales up and down are compared, if sampled point scale space sheet where it
When being maximum value or minimum value in layer and lower upper two layers of 26 points, then it is assumed that the sampled point is the Gauss residual image
A characteristic point under the scale.
Preferably, the characteristic point assignment unit 6133 is specifically used for:
The direction vector that each characteristic point is calculated using the gradient direction distribution characteristic of key point neighborhood territory pixel, has operator
Standby rotational invariance;
Each characteristic point is described using 16 sub-regions, forms 16 seed points, and each seed point uses 8 directions
Description vectors are carried out in all directions using the Euclidean distance in the direction of vector and its principal direction in the direction for carrying out description vectors
Amplitude size forms 128 dimensional feature vectors.
Preferably, 8 directions are respectively 0, π/4, pi/2,3 π/4, π, 5 π/4,3 pi/2s, 2 π.
Preferably, the second feature vector extraction unit further include:
Characteristic point filter element, for removing the original projection area image and the original projection curtain image each
The characteristic point of low contrast included in the characteristic point of a scale space and unstable skirt response point.
It should be noted that each unit of above-mentioned projection device provided in an embodiment of the present invention, due to side of the present invention
Method embodiment is based on same design, and bring technical effect is identical as embodiment of the present invention method, and particular content can be found in this
Narration in inventive method embodiment, details are not described herein again.
Therefore, it can be seen that projection device provided in an embodiment of the present invention is also due to pre-establish projection scene image office
Portion's aspect indexing database, it is subsequent in the use process of projection device, schemed by extracting view field in projection scene image
The feature vector of picture and projection screen image, and it is compared with the feature vector data in index data base, to obtain
The corner points information of view field and projection screen in scene image is projected, and referring to the view field and projection screen got
Corner points information adjustment projection device view field so that the view field of projection device is completely coincident with projection screen,
So as to calibrate view field automatically during user's viewing, manually adjusted without user, and can guarantee throwing
Clearly drop shadow effect is obtained after shadow regional correction, improves the viewing experience of user.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Fig. 8 be another embodiment of the present invention provides projection device schematic diagram.As shown in figure 8, the projection of the embodiment
Equipment includes: processor 80, memory 81 and is stored in the memory 81 and can run on the processor 80
Computer program 82.The processor 80 realizes the step in above-mentioned each embodiment of the method when executing the computer program 82
Suddenly, such as step 201 shown in FIG. 1 is to 206.Alternatively, the processor 80 realized when executing the computer program 82 it is above-mentioned
The function of each module/unit in each Installation practice, such as the function of module 61 to 66 shown in Fig. 6.
Illustratively, the computer program 82 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 81, and are executed by the processor 80, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 82 in the projection device is described.For example, the computer program 82 can be divided
It is cut into index data base and establishes unit 61, projection scene image acquiring unit 62, fisrt feature extraction unit 63, characteristic matching list
Member 64, mapping relations computing unit 65 and view field's adjustment unit 66, each unit concrete function are as follows:
Index data base establishes unit 61, for establishing projection scene image local feature index data base;
Scene image acquiring unit 62 is projected, for obtaining the projection scene figure of projection device when projection device is opened
Picture, the projection scene image is by view field's image and projection screen image construction;
Fisrt feature extraction unit 63, for calculate view field's image feature vector and the projection screen
The feature vector of image;
Characteristic matching unit 64 is used for the first eigenvector, the second feature vector and the index data
Class in library compares, identify view field's image the first corner points group information and the projection screen image
Second corner points group information;
Mapping relations computing unit 65, for according to the first corner points group information and the second corner points group information
Establish the mapping relations of view field's image Yu the projection screen image;
View field's adjustment unit 66 makes for adjusting the view field of the projection device according to the mapping relations
The view field of the projection device is overlapped with projection screen.
The projection device may include, but be not limited only to, processor 80, memory 81.Those skilled in the art can manage
Solution, Fig. 8 is only the example of projection device, does not constitute the restriction to terminal device 8, may include more more or less than illustrating
Component, perhaps combine certain components or different components, such as the terminal can also include input-output equipment, net
Network access device, bus etc..
Alleged processor 80 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 81 can be the internal storage unit of the projection device, such as the hard disk or interior of projection device
It deposits.What the memory 81 was also possible to be equipped on the External memory equipment of the projection device, such as the projection device inserts
Connect formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash memory
Block (Flash Card) etc..Further, the memory 81 can also both include the internal storage unit of the projection device
It also include External memory equipment.The memory 81 is for other journeys needed for storing the computer program and the terminal
Sequence and data.The memory 81 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device
Or the INDIRECT COUPLING or communication connection of unit, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..Computer-readable Jie
Matter may include: can carry the computer program code any entity or device, recording medium, USB flash disk, mobile hard disk,
Magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electric carrier signal and
Telecommunication signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of view field's bearing calibration characterized by comprising
Projection scene image local feature index data base is established, the index data base includes all kinds of corner points in each scale
Under index;
The projection scene image of projection device is obtained, the projection scene image is by view field's image and projection screen image structure
At;
Calculate the first eigenvector of view field's image and the second feature vector of the projection screen image;
By all kinds of corner points in the first eigenvector, the second feature vector and the index data base in each scale
Under index compare, identify view field's image the first corner points group information and the projection screen image
Second corner points group information;
The each picture of view field's image is established according to the first corner points group information and the second corner points group information
The mapping relations of vegetarian refreshments and each pixel of projection screen image;
The view field that the projection device is adjusted according to the mapping relations makes view field and the projection of the projection device
Curtain is overlapped.
2. view field's bearing calibration as described in claim 1, which is characterized in that the foundation projection scene image local is special
Levying index data base includes:
The original projection scene image of projection device is obtained, the original projection scene image is by original projection area image and original
Beginning projection screen image construction;
Gray proces are carried out to the original projection area image and the original projection curtain image;
The 4th of original projection curtain image described in the third feature vector sum of the original projection area image is extracted respectively
Feature vector;
Dimension-reduction treatment is carried out to fourth feature vector described in the third feature vector sum by principal component analysis, removes described the
Ingredient corresponding to minimal eigenvalue in three feature vectors and the fourth feature vector;
The n dimensional feature in fourth feature vector described in the third feature vector sum is mapped to m respectively by singular value decomposition
Dimensional feature obtains the feature descriptor vector of the original projection scene image, wherein n > m, and n, m are positive integer;
Above-mentioned process is repeated, the feature descriptor vector for all original projection scene images that will acquire is added to described
It projects in scene image local feature index data base;
K is divided into the feature descriptor in the projection scene image local feature index data base by K-means algorithm
A cluster, wherein k is positive integer.
3. view field as claimed in claim 2 bearing calibration, which is characterized in that described to extract the original projection respectively
The fourth feature vector of original projection curtain image described in the third feature vector sum of area image includes:
Construct scale space;
The original projection area image and the original projection curtain image are detected in the characteristic point of each scale space;
For one 128 dimension directioin parameter of each characteristic point assignment, 128 dimensional feature vectors are formed.
4. view field's bearing calibration as claimed in claim 3, which is characterized in that the building scale space includes:
Gaussian difference pyrene and the original projection scene image convolution using different scale, generate the Gaussian mode under different scale
Paste image;
The Gaussian Blur image of adjacent scale is made the difference, Gauss residual image is obtained.
5. view field's bearing calibration as claimed in claim 4, which is characterized in that the detection original projection administrative division map
Picture and the original projection curtain image include: in the characteristic point of each scale space
Gauss residual image corresponding to each scale space is sampled respectively, by each sampled point respectively with its 8
18 points in neighborhood and its in adjacent two scales up and down are compared, if the sampled point where it this layer of scale space with
And when in lower upper two layers of 26 points being maximum value or minimum value, then it is assumed that the sampled point is the Gauss residual image at this
A characteristic point under scale.
6. view field's bearing calibration as claimed in claim 3, which is characterized in that described is each characteristic point assignment one
128 dimension directioin parameters, forming 128 dimensional feature vectors includes:
The direction vector that each characteristic point is calculated using the gradient direction distribution characteristic of key point neighborhood territory pixel makes operator have rotation
Turn invariance;
Each characteristic point is described using 16 sub-regions, forms 16 seed points, and each seed point is retouched using 8 directions
The amplitude of description vectors in all directions is carried out using the Euclidean distance in the direction of vector and its principal direction in the direction for stating vector
Size forms 128 dimensional feature vectors.
7. view field's bearing calibration as claimed in claim 6, which is characterized in that 8 directions are respectively 0, π/4, π/
2,3 π/4, π, 5 π/4,3 pi/2s, 2 π.
8. view field as claimed in claim 3 bearing calibration, which is characterized in that described for each characteristic point assignment one
128 dimension directioin parameters, form before 128 dimensional feature vectors further include:
Remove the original projection area image and the original projection curtain image institute in the characteristic point of each scale space
The characteristic point for the low contrast for including and unstable skirt response point.
9. a kind of projection device, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 8 when executing the computer program
The step of any one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 8 of realization the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710990380.1A CN109698944B (en) | 2017-10-23 | 2017-10-23 | Projection area correction method, projection apparatus, and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710990380.1A CN109698944B (en) | 2017-10-23 | 2017-10-23 | Projection area correction method, projection apparatus, and computer-readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109698944A true CN109698944A (en) | 2019-04-30 |
CN109698944B CN109698944B (en) | 2021-04-02 |
Family
ID=66225799
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710990380.1A Active CN109698944B (en) | 2017-10-23 | 2017-10-23 | Projection area correction method, projection apparatus, and computer-readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109698944B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110458909A (en) * | 2019-08-05 | 2019-11-15 | 薄涛 | Handle method, server, tutoring system and the medium of projected image |
CN110475108A (en) * | 2019-08-05 | 2019-11-19 | 薄涛 | Projected picture correcting method, terminal device, system and storage medium |
CN110784699A (en) * | 2019-11-01 | 2020-02-11 | 成都极米科技股份有限公司 | Projection processing method, projection processing device, projector and readable storage medium |
CN112598728A (en) * | 2020-12-23 | 2021-04-02 | 成都极米科技股份有限公司 | Projector attitude estimation and trapezoidal correction method and device, projector and medium |
CN112689136A (en) * | 2021-03-19 | 2021-04-20 | 深圳市火乐科技发展有限公司 | Projection image adjusting method and device, storage medium and electronic equipment |
CN113628282A (en) * | 2021-08-06 | 2021-11-09 | 深圳市道通科技股份有限公司 | Pattern projection correction apparatus, method, and computer-readable storage medium |
CN113873208A (en) * | 2021-09-16 | 2021-12-31 | 峰米(北京)科技有限公司 | Gamma curve adjusting method and device for projection equipment |
CN114520895A (en) * | 2020-11-18 | 2022-05-20 | 成都极米科技股份有限公司 | Projection control method, projection control device, projection optical machine and readable storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1701603A (en) * | 2003-08-06 | 2005-11-23 | 三菱电机株式会社 | Method and system for determining correspondence between locations on display surface having arbitrary shape and pixels in output image of projector |
CN105704466A (en) * | 2016-01-29 | 2016-06-22 | 北京小鸟科技发展有限责任公司 | A DLP projection method, a DLP projection apparatus and a DLP projector |
CN106101677A (en) * | 2016-08-17 | 2016-11-09 | 郑崧 | Projection Image Adjusting system and method for adjustment |
-
2017
- 2017-10-23 CN CN201710990380.1A patent/CN109698944B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1701603A (en) * | 2003-08-06 | 2005-11-23 | 三菱电机株式会社 | Method and system for determining correspondence between locations on display surface having arbitrary shape and pixels in output image of projector |
CN105704466A (en) * | 2016-01-29 | 2016-06-22 | 北京小鸟科技发展有限责任公司 | A DLP projection method, a DLP projection apparatus and a DLP projector |
CN106101677A (en) * | 2016-08-17 | 2016-11-09 | 郑崧 | Projection Image Adjusting system and method for adjustment |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110475108A (en) * | 2019-08-05 | 2019-11-19 | 薄涛 | Projected picture correcting method, terminal device, system and storage medium |
CN110458909A (en) * | 2019-08-05 | 2019-11-15 | 薄涛 | Handle method, server, tutoring system and the medium of projected image |
CN110784699B (en) * | 2019-11-01 | 2021-06-25 | 成都极米科技股份有限公司 | Projection processing method, projection processing device, projector and readable storage medium |
CN110784699A (en) * | 2019-11-01 | 2020-02-11 | 成都极米科技股份有限公司 | Projection processing method, projection processing device, projector and readable storage medium |
CN114520895A (en) * | 2020-11-18 | 2022-05-20 | 成都极米科技股份有限公司 | Projection control method, projection control device, projection optical machine and readable storage medium |
CN112598728A (en) * | 2020-12-23 | 2021-04-02 | 成都极米科技股份有限公司 | Projector attitude estimation and trapezoidal correction method and device, projector and medium |
CN112598728B (en) * | 2020-12-23 | 2024-02-13 | 极米科技股份有限公司 | Projector attitude estimation, trapezoidal correction method and device, projector and medium |
CN112689136B (en) * | 2021-03-19 | 2021-07-02 | 深圳市火乐科技发展有限公司 | Projection image adjusting method and device, storage medium and electronic equipment |
CN112689136A (en) * | 2021-03-19 | 2021-04-20 | 深圳市火乐科技发展有限公司 | Projection image adjusting method and device, storage medium and electronic equipment |
CN113628282A (en) * | 2021-08-06 | 2021-11-09 | 深圳市道通科技股份有限公司 | Pattern projection correction apparatus, method, and computer-readable storage medium |
WO2023011471A1 (en) * | 2021-08-06 | 2023-02-09 | 深圳市道通科技股份有限公司 | Pattern projection correction apparatus and method, and computer-readable storage medium |
CN113873208A (en) * | 2021-09-16 | 2021-12-31 | 峰米(北京)科技有限公司 | Gamma curve adjusting method and device for projection equipment |
CN113873208B (en) * | 2021-09-16 | 2023-07-25 | 峰米(北京)科技有限公司 | Gamma curve adjusting method and equipment for projection equipment |
Also Published As
Publication number | Publication date |
---|---|
CN109698944B (en) | 2021-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109698944A (en) | View field's bearing calibration, projection device and computer readable storage medium | |
US10867430B2 (en) | Method and system of 3D reconstruction with volume-based filtering for image processing | |
US11055827B2 (en) | Image processing apparatus and method | |
Krig | Computer vision metrics: Survey, taxonomy, and analysis | |
Krig | Computer vision metrics | |
CN105229697B (en) | Multi-modal prospect background segmentation | |
CN109242961A (en) | A kind of face modeling method, apparatus, electronic equipment and computer-readable medium | |
Klose et al. | Sampling based scene-space video processing | |
Matsuyama et al. | 3D video and its applications | |
CN109474780A (en) | A kind of method and apparatus for image procossing | |
CN108694741B (en) | Three-dimensional reconstruction method and device | |
CN108627092A (en) | A kind of measurement method, system, storage medium and the mobile terminal of package volume | |
CN110517319A (en) | A kind of method and relevant apparatus that camera posture information is determining | |
CN108701359A (en) | Across the video frame tracking interest region with corresponding depth map | |
CN106258010A (en) | 2D image dissector | |
CN112270688B (en) | Foreground extraction method, device, equipment and storage medium | |
CN109118544B (en) | Synthetic aperture imaging method based on perspective transformation | |
CN109919971A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
EP3598385A1 (en) | Face deblurring method and device | |
CN111144491B (en) | Image processing method, device and electronic system | |
CN108184075B (en) | Method and apparatus for generating image | |
CN109816706A (en) | A kind of smoothness constraint and triangulation network equal proportion subdivision picture are to dense matching method | |
CN114143528A (en) | Multi-video stream fusion method, electronic device and storage medium | |
Kim et al. | Real-time panorama canvas of natural images | |
CN114596368B (en) | Data processing method and device, computer equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |