CN108399603A - A kind of atwirl method and device of image - Google Patents
A kind of atwirl method and device of image Download PDFInfo
- Publication number
- CN108399603A CN108399603A CN201710067843.7A CN201710067843A CN108399603A CN 108399603 A CN108399603 A CN 108399603A CN 201710067843 A CN201710067843 A CN 201710067843A CN 108399603 A CN108399603 A CN 108399603A
- Authority
- CN
- China
- Prior art keywords
- image data
- rotation
- polar coordinates
- postrotational
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000011159 matrix material Substances 0.000 claims description 28
- 238000006073 displacement reaction Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 13
- 230000000694 effects Effects 0.000 description 4
- 238000007650 screen-printing Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- HPTJABJPZMULFH-UHFFFAOYSA-N 12-[(Cyclohexylcarbamoyl)amino]dodecanoic acid Chemical compound OC(=O)CCCCCCCCCCCNC(=O)NC1CCCCC1 HPTJABJPZMULFH-UHFFFAOYSA-N 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
- G06T3/604—Rotation of whole images or parts thereof using coordinate rotation digital computer [CORDIC] devices
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention proposes a kind of atwirl method and device of image, by using graphics processor（GPU, Graphics Processing Unit）Multi-core parallel concurrent calculate replace central processing unit（CPU, Central Processing Unit）In data processing to image rotation, greatly increase the efficiency of rotation, and the statistics of operation use time is increased during calculating, enable calling program on different devices or with operation fluency is all ensured as far as possible under equipment different conditions, thus improves the using experience degree of client.
Description
Technical field
The present invention relates to Computer Image Processing fields, and in particular to a kind of atwirl method and device of image.
Background technology
It is more and more to be developed with the relevant software of map with the fast development of cell phone software.When we are making
When making software relevant with map in mobile phone, rotation process inevitably is carried out to map, Rotation Algorithm is numerous, algorithm
Complexity is different with result.It, can for the equipment of better performances if carrying out the rotation of map only with complicated algorithm
Smooth operation completely, but for the poor equipment of performance or in the equipment of busy state, then when being rotated to map
The case where will appear interim card.Therefore we need a kind of rotation side for capableing of high speed processing image rotation and adaptive equipment situation
Case.
Invention content
The purpose of the present invention is to provide a kind of atwirl method and device of image, this method energy high speed processing images
It rotates and being capable of adaptive equipment situation.
Concrete scheme is as follows：
A kind of atwirl method of image, including step：
Complete image data is converted into polar coordinates matrix using bilinear interpolation, obtains user's rotation angle and to pole by S10
Coordinate uses bilinear interpolation conversion polar coordinates to obtain the complete image data after rotation once into line displacement；
S20 exports postrotational complete image data；
S30, statistics execute the duration of step S10, and preset first threshold value repeats to hold if duration is less than preset first threshold
Row step S10 to S20 until complete image data be finally completed with the matched rotation of user rotation angle institute, if duration is more than etc.
In preset first threshold, S40 is thened follow the steps to S50；
The image data that the circumscribed circle range of screen data is included is converted into polar coordinates square by S40 using bilinear interpolation
Battle array, wherein the image data that the circumscribed circle range of screen data is included is denoted as the first image data, removes the external of screen data
Image data except the image data that circle range is included is denoted as the second image data, obtains user's rotation angle and is sat to pole
It marks into line displacement, uses bilinear interpolation conversion polar coordinates to obtain the first image data after rotation once, output first
Image data；It repeats the above process until the first image data is finally completed and the matched rotation of user's rotation angle；
Second image data is converted into polar coordinates matrix by S50 when user terminates image rotation using bilinear interpolation,
It obtains user's rotation angle final after S40 and to polar coordinates into line displacement, is sat using bilinear interpolation conversion pole
It is marked with to obtain final postrotational second image data, it will final postrotational second image data and final postrotational first
Image data is combined, and forms postrotational complete image data for follow-up other calculating.
Further, the step S30 is replaced with into S30 ', and further includes step S60 and S70, wherein：
S30 ', statistics execute the duration of step S10, preset first threshold value and second threshold, if duration is less than preset first threshold
Value, then repeat step S10 to S20 until complete image data be finally completed with the matched rotation of user rotation angle institute,
If duration be more than or equal to preset first threshold and be less than preset second threshold, then follow the steps S40 to S50, if when grow up
In equal to preset second threshold, S60 is thened follow the steps to S70；
First image data is converted into polar coordinates matrix using closest interpolation method, obtains user's rotation angle and to pole by S60
Coordinate uses closest interpolation method conversion polar coordinates to obtain the first image data after rotation once, output rotation into line displacement
The first image data after turning；Repeat the above process until the first image data be finally completed it is matched with user rotation angle institute
Rotation, and during last time repeats, after using bilinear interpolation to convert polar coordinates to obtain rotating for the last time
The first image data and export；
Second image data is converted into polar coordinates matrix by S70 when user terminates image rotation using bilinear interpolation,
It obtains user's rotation angle and to polar coordinates into line displacement, is directly obtained using bilinear interpolation conversion polar coordinates postrotational
Final postrotational second image data is combined with final postrotational first image data, forms by the second image data
Postrotational complete image data is for follow-up other calculating.
Further, further include：Step S00 obtains complete image data.
A kind of device, including：
Processor and memory；
The memory is for storing program；
The processor is used to execute the program in the memory so that it is atwirl that described device executes above-mentioned image
Method.
Further, described program includes the first program and the second program,
The processor includes central processing unit and graphics processor,
The central processing unit is for executing first program so that described device executes the atwirl side of above-mentioned image
Step S00 in method；
The graphics processor is for executing second program so that described device executes the atwirl side of above-mentioned image
Method.
Advantageous effect of the present invention：By using graphics processor（GPU, Graphics Processing Unit）Multinuclear
Parallel computation replaces central processing unit（CPU, Central Processing Unit）In data processing to image rotation, greatly
The earth improves the efficiency of rotation, and the statistics of operation use time is increased during calculating so that program can be not
With equipment on or with operation fluency is all ensured under equipment different conditions as far as possible, that thus improves client uses body
Degree of testing.
Description of the drawings
Fig. 1 is one embodiment of the invention method flow diagram.
Specific implementation mode
To further illustrate that each embodiment, the present invention are provided with attached drawing.These attached drawings are that the invention discloses one of content
Point, mainly to illustrate embodiment, and the associated description of specification can be coordinated to explain the operation principles of embodiment.Cooperation ginseng
These contents are examined, those of ordinary skill in the art will be understood that other possible embodiments and advantages of the present invention.Now tie
Closing the drawings and specific embodiments, the present invention is further described.
Embodiment 1 is a kind of atwirl method of image, including step：
Complete image data is converted into polar coordinates matrix using bilinear interpolation, obtains user's rotation angle and to pole by S10
Coordinate uses bilinear interpolation conversion polar coordinates to obtain the complete image data after rotation once into line displacement；
S20 exports postrotational complete image data；
S30, statistics execute the duration of step S10, and preset first threshold value repeats to hold if duration is less than preset first threshold
Row step S10 to S20 until complete image data be finally completed with the matched rotation of user rotation angle institute, if duration is more than etc.
In preset first threshold, S40 is thened follow the steps to S50；
The image data that the circumscribed circle range of screen data is included is converted into polar coordinates square by S40 using bilinear interpolation
Battle array, wherein the image data that the circumscribed circle range of screen data is included is denoted as the first image data, removes the external of screen data
Image data except the image data that circle range is included is denoted as the second image data, obtains user's rotation angle and is sat to pole
It marks into line displacement, uses bilinear interpolation conversion polar coordinates to obtain the first image data after rotation once, output first
Image data；It repeats the above process until the first image data is finally completed and the matched rotation of user's rotation angle；
Second image data is converted into polar coordinates matrix by S50 when user terminates image rotation using bilinear interpolation,
It obtains user's rotation angle and to polar coordinates into line displacement, is directly obtained using bilinear interpolation conversion polar coordinates postrotational
Final postrotational second image data is combined with final postrotational first image data, forms by the second image data
Postrotational complete image data is for follow-up other calculating.
Embodiment 2
On the basis of embodiment 1, change step S30 is S30 ' and further includes step S60 and S70 embodiment 2, wherein：
S30 ', statistics execute the duration of step S10, preset first threshold value and second threshold, if duration is less than preset first threshold
Value, then repeat step S10 to S20 until complete image data be finally completed with the matched rotation of user rotation angle institute,
If duration be more than or equal to preset first threshold and be less than preset second threshold, then follow the steps S40 to S50, if when grow up
In equal to preset second threshold, S60 is thened follow the steps to S70；
First image data is converted into polar coordinates matrix using closest interpolation method, obtains user's rotation angle and to pole by S60
Coordinate uses closest interpolation method conversion polar coordinates to obtain the first image data after rotation once, output rotation into line displacement
The first image data after turning；Repeat the above process until the first image data be finally completed it is matched with user rotation angle institute
Rotation, and during last time repeats, after using bilinear interpolation to convert polar coordinates to obtain rotating for the last time
The first image data and export；
Second image data is converted into polar coordinates matrix by S70 when user terminates image rotation using bilinear interpolation,
It obtains user's rotation angle and to polar coordinates into line displacement, is directly obtained using bilinear interpolation conversion polar coordinates postrotational
Final postrotational second image data is combined with final postrotational first image data, forms by the second image data
Postrotational complete image data is for follow-up other calculating.
Next the method for embodiment 2 is illustrated in conjunction with another 3 device of embodiment, in example, with map datum
Rotation is shown, it is appreciated that image data includes but not limited to map datum, the device of the present embodiment 3 contains center
Three processor, memory, video card units.The wherein GPU of video card is formant, at least needs to support openCL2.0 or more
Or the multi-thread programming ability of CUDA, main data computing function are realized in GPU, GPU program carries out the used time of processing
Statistics, and different rotation strategies is used by the difference of processing time.Memory is for storing program, and program is obtaining
The data of map and the rotation calculating for completing map datum.Central processing unit is auxiliary unit, is mainly used to obtain the number of map
Operational order is sent out according to and to GPU.In 4 device of other embodiment, including central processing unit and memory, memory storage
Program executes method of the program of memory to complete embodiment 1 and embodiment 2 by central processing unit
From the point of view of hardware aspect, it is contemplated that the multi-core processor of GPU has discrete type, the progress parallel computation of orthogonal data
Natural advantage, and current GPU general-purpose computations technology relative maturity.We will when carrying out the calculating of map datum
CPU processor is replaced to carry out the operation of data using GPU processors, can not only reduce the utilization rate of CPU can also improve number
According to calculating speed.
From the point of view of the Rotation Algorithm of image, the mode of image rotation is numerous at present, each spinning solution has its respective
The rate of feature, the effect and rotation that in general rotate is inversely proportional.So we should be to the equipment of different hardware using not
With algorithm carry out the processing of data.It is understood that the rotation for carrying out image with polar coordinates is a kind of common mode, pole is sat
Mark in the rotation of map with there is special effect, because continuously to export display to the rotation of map.It is revolved with polar coordinates
It only needs offset polar coordinates matrix that can complete the rotation of image during turning, is deviated by the parallel computation of GPU
Time complexity is O (1).The image rotation used time in GPU is counted, two time thresholds t1 and t2 are set（t1<t2）, when
Using the distributed rotation processing for carrying out image when used time is more than t1 and is less than t2, we change polar coordinates rotation when more than t2
When interpolation algorithm, with achieve the effect that reduce operation delay.As shown in Figure 1, the flow chart of the method for the present invention, flow is such as
Under：
1, program is opened, the data in map are obtained.
2, the data in map are imported into GPU cachings.
3, map is switched to by polar coordinates matrix using bilinear interpolation in GPU.
4, the rotation angle of user is obtained.
5, in GPU to polar coordinates into line displacement, deviate a pixel every time.
6, the polar coordinates matrix after deviating converts back cartesian coordinate matrix using bilinear interpolation, obtains postrotational
Cartographic information.
7, postrotational cartographic information is exported, step 5 is returned to and is rotated until completing.
8, timing is carried out to step 3- steps 6, exceed schedule time t1, and the circumscribed circle with regard to screen printing data is included
Data（It is denoted as A）Rotated, after user stops rotating again to A except data B calculate.
9, if it exceeds the fitting algorithm in rotary course, is just changed to closest to differential technique by stipulated time t2.
9.1, the fitting for first carrying out a bilinearity difference arithmetic to A after user stops rotating exports after having been calculated
To screen.Then again to data B into using bilinearity difference arithmetic to calculate.
In other one embodiment, method is only set there are one stipulated time t1, and do not include step 9 and
9.1。
It is in GPU the specific implementation process is as follows：
Also having the arithmetic between a large amount of image, this part in whole flow process is very suitable for using at parallel method
Reason, because being all the operation between pixel.For this part, realized using the method for thread parallel.Thread number in GPU
(id) it is total Thread Count (b) in thread block by thread block number (a), thread 3 part of thread number (c) composition in the block.So will
There are id=a × b+c, wherein the value range of id is exactly from 0 to total Thread Count.Set total Thread Count to the pixel of image
Value, then each pixel in image is just assigned with a thread, as long as per thread has executed an arithmetic, then right
The operation of one entire image is also just completed.
The first step copies to data in GPU video memorys from CPU memories.
Memory headroom in second step, application GPU needed for polar coordinates.
Third step starts timing.
4th step, the total Thread Counts of GPU are defined as the pixel value of polar coordinates matrix, and each of polar coordinates matrix point is distributed
To a thread, polar conversion is carried out using bilinear interpolation.
5th step, when image shift, create a matrix, the total Thread Counts of GPU are defined as the pixel of new matrix
Value, a thread is allocated to by each of new matrix point.
6th step, the assignment that different initial position progress corresponding points are selected according to the difference of offset.
7th step, setting synchronize, and calculating of the polar coordinates to rectangular coordinate system is carried out using bilinear interpolation.
8th step terminates timing.
9th step outputs image to CPU for showing.
The 6th step to the 9th step is repeated, until completing to rotate.
Statistic procedure three arrives the time t of step 8, judges the relationship with threshold value t1, t2.
Work as t1<t<It is made an amendment since second step when t2,
Second step：The data that screen printing size circumscribed circle is included in the caching of GPU, are denoted as A.
Third walks：The total Thread Counts of GPU are defined as the pixel value of polar coordinates matrix corresponding to A, and A is passed through bilinear interpolation
Method switchs to polar coordinates matrix, is denoted as A '.
4th step：Thread is distributed, to A ' into line displacement.
5th step：A ' after offset bilinearity differential techniques are switched into rectangular co-ordinate matrix, output is shown to CPU.
The 4th step and the 5th step are repeated, until completing to rotate.
6th step：By the region other than A after user's rotation（It is denoted as B）It is rotated again.
Work as t>When=t2
Second step：The data that screen printing size circumscribed circle is included in the caching of GPU, are denoted as A.
Third walks：The total Thread Counts of GPU are defined as the pixel value of polar coordinates matrix corresponding to A, and A is passed through closest interpolation
Method switchs to polar coordinates matrix, is denoted as A '.
4th step：Thread is distributed, to A ' into line displacement.
5th step：The closest interpolation methods of A ' after offset are switched into rectangular co-ordinate matrix, output is shown to CPU.
The 4th step and the 5th step are repeated, until completing to rotate.
6th step：Rectangular co-ordinate matrix is switched to final A ' bilinear interpolations, obtains preferable rotated image,
Output display.
7th：By the region other than A（It is denoted as B）It is rotated again.
Although specifically showing and describing the present invention in conjunction with preferred embodiment, those skilled in the art should be bright
In vain, it is not departing from the spirit and scope of the present invention defined by the appended claims, it in the form and details can be right
The present invention makes a variety of changes, and is protection scope of the present invention.
Claims (5)
1. a kind of atwirl method of image, which is characterized in that including step：
Complete image data is converted into polar coordinates matrix using bilinear interpolation, obtains user's rotation angle and to pole by S10
Coordinate uses bilinear interpolation conversion polar coordinates to obtain the complete image data after rotation once into line displacement；
S20 exports postrotational complete image data；
S30, statistics execute the duration of step S10, and preset first threshold value repeats to hold if duration is less than preset first threshold
Row step S10 to S20 until complete image data be finally completed with the matched rotation of user rotation angle institute, if duration is more than etc.
In preset first threshold, S40 is thened follow the steps to S50；
The image data that the circumscribed circle range of screen data is included is converted into polar coordinates square by S40 using bilinear interpolation
Battle array, wherein the image data that the circumscribed circle range of screen data is included is denoted as the first image data, removes the external of screen data
Image data except the image data that circle range is included is denoted as the second image data, obtains user's rotation angle and is sat to pole
It marks into line displacement, uses bilinear interpolation conversion polar coordinates to obtain the first image data after rotation once, output first
Image data；It repeats the above process until the first image data is finally completed and the matched rotation of user's rotation angle；
Second image data is converted into polar coordinates matrix by S50 when user terminates image rotation using bilinear interpolation,
It obtains user's rotation angle final after S40 and to polar coordinates into line displacement, is sat using bilinear interpolation conversion pole
It is marked with to obtain final postrotational second image data, it will final postrotational second image data and final postrotational first
Image data is combined, and forms postrotational complete image data for follow-up other calculating.
2. the atwirl method of image according to claim 1, which is characterized in that replace with the step S30
S30 ', and further include step S60 and S70, wherein：
S30 ', statistics execute the duration of step S10, preset first threshold value and second threshold, if duration is less than preset first threshold
Value, then repeat step S10 to S20 until complete image data be finally completed with the matched rotation of user rotation angle institute,
If duration be more than or equal to preset first threshold and be less than preset second threshold, then follow the steps S40 to S50, if when grow up
In equal to preset second threshold, S60 is thened follow the steps to S70；
First image data is converted into polar coordinates matrix using closest interpolation method, obtains user's rotation angle and to pole by S60
Coordinate uses closest interpolation method conversion polar coordinates to obtain the first image data after rotation once, output rotation into line displacement
The first image data after turning；Repeat the above process until the first image data be finally completed it is matched with user rotation angle institute
Rotation, and during last time repeats, after using bilinear interpolation to convert polar coordinates to obtain rotating for the last time
The first image data and export；
Second image data is converted into polar coordinates matrix by S70 when user terminates image rotation using bilinear interpolation,
It obtains user's rotation angle and to polar coordinates into line displacement, is directly obtained using bilinear interpolation conversion polar coordinates postrotational
Final postrotational second image data is combined with final postrotational first image data, forms by the second image data
Postrotational complete image data is for follow-up other calculating.
3. the atwirl method of image according to claim 1 or 2, which is characterized in that further include：Step S00 is obtained
Complete image data.
4. a kind of device, which is characterized in that including：
Processor and memory；
The memory is for storing program；
The processor is used to execute the program in the memory so that it is any that described device executes the claims 1 to 3
The atwirl method of the image.
5. a kind of device according to claim 4, which is characterized in that described program includes the first program and the second journey
Sequence, the processor include central processing unit and graphics processor,
The central processing unit is for executing first program so that described device executes the figure described in the claims 3
As the step S00 in atwirl method；
The graphics processor is for executing second program so that described device executes described in the claims 1 or 2
The atwirl method of image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710067843.7A CN108399603B (en) | 2017-02-07 | 2017-02-07 | Method and device for rapidly rotating image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710067843.7A CN108399603B (en) | 2017-02-07 | 2017-02-07 | Method and device for rapidly rotating image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108399603A true CN108399603A (en) | 2018-08-14 |
| CN108399603B CN108399603B (en) | 2022-12-06 |
Family
ID=63093668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710067843.7A Active CN108399603B (en) | 2017-02-07 | 2017-02-07 | Method and device for rapidly rotating image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108399603B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1759812A (en) * | 2004-05-27 | 2006-04-19 | 阿洛卡株式会社 | Ultrasonic diagnostic equipment and image processing method |
| CN103295019A (en) * | 2013-05-21 | 2013-09-11 | 西安理工大学 | Self-adaptive Chinese fragment restoration method based on probability statistics |
| US20160063713A1 (en) * | 2014-09-03 | 2016-03-03 | Ricoh Company, Ltd. | Information terminal apparatus, information processing method, and system |
| CN105450908A (en) * | 2015-12-02 | 2016-03-30 | 厦门雅迅网络股份有限公司 | Method and device for removing black edge from video image |
-
2017
- 2017-02-07 CN CN201710067843.7A patent/CN108399603B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1759812A (en) * | 2004-05-27 | 2006-04-19 | 阿洛卡株式会社 | Ultrasonic diagnostic equipment and image processing method |
| CN103295019A (en) * | 2013-05-21 | 2013-09-11 | 西安理工大学 | Self-adaptive Chinese fragment restoration method based on probability statistics |
| US20160063713A1 (en) * | 2014-09-03 | 2016-03-03 | Ricoh Company, Ltd. | Information terminal apparatus, information processing method, and system |
| CN105450908A (en) * | 2015-12-02 | 2016-03-30 | 厦门雅迅网络股份有限公司 | Method and device for removing black edge from video image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108399603B (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5020393B2 (en) | Processing equipment | |
| CN103077088B (en) | Based on the dynamic feedback of load equalization methods of PKDT tree in Cluster Rendering environment | |
| CN105487848B (en) | A kind of the display method for refreshing and system of 3D application | |
| CN106056529A (en) | Method and equipment for training convolutional neural network used for image recognition | |
| CN103167218A (en) | Super-resolution reconstruction method and equipment based on non-locality | |
| CN102044062B (en) | System for realizing mirroring in x axis and y axis and 180-degree rotation of image based on image block processing | |
| CN110246081B (en) | Image splicing method and device and readable storage medium | |
| CN108416843A (en) | Three-dimensional scene construction method, device, equipment and computer readable storage medium | |
| CN111985597B (en) | Model compression method and device | |
| JPH0737082A (en) | Method and device for rotating multilevel picture 90 degrees | |
| US20220207109A1 (en) | Convolution method, electronic device, and computer-readable storage medium | |
| DE102020108526A1 (en) | ADAPTIVE PIXEL SCAN ORDER FOR DENSE RENDERING | |
| CN102622723A (en) | Image interpolation based on CUDA (compute unified device architecture) and edge detection | |
| CN105023234A (en) | Figure acceleration method based on storage optimization of embedded system | |
| CN112700516A (en) | Video rendering method and device based on deep learning, computer equipment and storage medium | |
| CN115375815A (en) | Shadow rendering method and device, electronic equipment and storage medium | |
| CN106204418A (en) | Image warping method based on matrix inversion operation in a kind of virtual reality mobile terminal | |
| CN106355545B (en) | A kind of processing method and processing device of digital picture geometric transformation | |
| CN110472588A (en) | Anchor point frame determines method, apparatus, computer equipment and storage medium | |
| CN108399603A (en) | A kind of atwirl method and device of image | |
| CN108446455A (en) | A kind of multiple target Method for HW/SW partitioning based on fireworks algorithm | |
| CN116312412A (en) | Bicubic interpolation circuit based on FPGA | |
| CN101452572B (en) | Image rotating VLSI structure based on cubic translation algorithm | |
| CN107146193A (en) | A kind of GPU parallel calculating methods based on double video cards applied to image procossing | |
| CN109410302B (en) | Texture mapping method, texture mapping device, computer equipment and 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 |