CN111028129A - GPU pixel rectangle scaling and flipping algorithm-oriented TLM microstructure - Google Patents
GPU pixel rectangle scaling and flipping algorithm-oriented TLM microstructure Download PDFInfo
- Publication number
- CN111028129A CN111028129A CN201911125671.XA CN201911125671A CN111028129A CN 111028129 A CN111028129 A CN 111028129A CN 201911125671 A CN201911125671 A CN 201911125671A CN 111028129 A CN111028129 A CN 111028129A
- Authority
- CN
- China
- Prior art keywords
- row
- pixel
- scaling
- module
- sent
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
Abstract
The invention relates to the technical field of computer hardware modeling, in particular to a TLM microstructure design facing a GPU pixel rectangle scaling and overturning algorithm. The TLM microstructure facing the GPU pixel rectangle scaling and flipping algorithm comprises a new image position calculating module 1, a row pixel dispatching module 2, a row-direction processing module 3 and a column-direction processing module 4. The invention realizes the function and the structure of a TLM-model-based pixel rectangle scaling and overturning algorithm, realizes the function defined by the glPixelZoom () function defined by the OpenGL API, solves the problem of insufficient performance of GPU hardware scaling and overturning pixel rectangles, and effectively accelerates RTL design development.
Description
Technical Field
The invention relates to the technical field of computer hardware modeling, in particular to a TLM microstructure facing a GPU pixel rectangle scaling and overturning algorithm.
Background
In the design and development of a graphics processor chip (hereinafter referred to as GPU), the correctness and efficiency of an algorithm are important factors determining the function and performance of the GPU. The glpixezoom () function defined by the OpenGL API supports arbitrary zooming in, zooming out, and flipping of an image, but does not define an algorithm for image scaling flipping. If the calculation amount of the algorithm is large and the structural division of the algorithm is unreasonable, the performance of the GPU for realizing scaling and overturning is seriously reduced. Therefore, it is necessary to verify the algorithm and the structure based on the algorithm as early as possible before the hardware logic of the GPU chip is implemented, so as to provide a reference basis for RTL design.
Disclosure of Invention
Based on the problems in the background art, the TLM microstructure facing the GPU pixel rectangle scaling and overturning algorithm can solve the problems of correctness and high efficiency of a rtl simulation pixel rectangle scaling and overturning algorithm and the functional verification of the hardware microstructure of the pixel rectangle scaling and overturning algorithm on a TLM model in advance.
The technical solution of the invention is as follows:
the structure comprises a new image position calculating module 1, a row pixel dispatching module 2, a row direction processing module 3 and a column direction processing module 4;
the processing module 3 in the row direction comprises a sampling original image submodule 31, a calculating new pixel coordinate submodule 32 and a calculating scaling row number submodule 33;
the column-direction processing module 4 comprises a sampling scaling row sub-module 41 and an updating row pixel coordinate sub-module 42;
the new image position calculating module 1 is used for calculating the coordinates and the coverage range of the actual video memory after the image is zoomed and turned over;
the pixel module 2 in the assignment row is used for filtering the pixel rows outside the range of the column direction and then assigning effective pixel rows;
the processing module 3 in the row direction is used for calculating scaling factors to realize scaling sampling pixels, then calculating coordinates of all scaled pixels in each row, and calculating a row number of an image after scaling corresponding to a current scaling row;
and the processing module 4 in the column direction is used for calculating the number of the scaled lines, sampling and selecting the effective lines, and then updating the coordinates of the pixels of the effective lines.
Further, the module 1 for calculating the position of the new image receives the scaling parameter, the flipping parameter, the width and height of the original image, the video memory range and the drawing coordinate,
calculating the new image coordinates and the coverage range of the image in the video memory range after zooming and turning,
the coverage, new map coordinates are sent to the dispatch row pixel module 2 over the TLM interface.
Further, the pixel module 2 for assigning rows receives the original image, the scaling parameter and the flipping parameter, and calculates the coverage and the new map coordinate sent by the new map position module 1,
filtering the pixel rows outside the range of the column direction, then allocating effective pixel rows,
sending the single-line original image, the zooming parameter, the turning parameter, the coverage area, the new image coordinate and the current line number to a processing module 3 in the line direction through a TLM interface;
and simultaneously, the overturning parameters and the new image coordinates are sent to the processing module 4 in the column direction through the TLM interface.
Further, the processing module 3 in the row direction receives the original image of the single row sent by the pixel module 2 in the assigned row, the scaling parameter, the flipping parameter, the coverage, the new image coordinate, the current row number,
a scaling factor is calculated based on the scaling parameter,
the row pixel coordinates for each row are calculated from the new map coordinates and the current row number,
calculating a scaled line number based on the scaling factor and the current line number,
and then the scaled row pixels, the row pixel coordinates and the scaled row number are sent to the processing module 4 in the column direction through the TLM interface.
Further, the original image sampling sub-module 31 receives the original image of a single line, the coverage, the scaling parameter, and the flipping parameter sent by the pixel module 2 of the assigned line,
the scaling factor is calculated by calculating the scaling factor,
then samples are taken in the original image line and the sampled pixels are sent to the calculate new pixel coordinates sub-module 32 and the scaling factor is sent to the calculate scaling line number sub-module 33.
Further, the calculate new pixel coordinate submodule 32 receives the scaling parameter, the flipping parameter, the coverage, the new image coordinate sent by the pixel module 2 of the assigned row, and the sampled pixel sent by the sample original image submodule 31,
the new pixel coordinates are calculated and,
the new pixel coordinates and the sampled pixels are then sent to the processing modules 4 in the column direction.
Further, the calculate scaling sub-module 33 receives the flipping parameter sent by the pixel module 2 in the assigned row, the current row number, and the scaling factor sent by the sample original image sub-module 31,
calculating the corresponding post-zoom line number of the current zoom line,
the scaled row number is then sent to the column-wise processing module 4.
Further, the processing module 4 in the column direction receives the scaled row pixels, the row pixel coordinates, and the scaled row number sent by the processing module 3 in the row direction, and assigns the flipping parameters and the new image coordinates sent by the row pixel module 2,
the effective number of lines is selected by scaling the post-line number samples,
and updating the coordinates of the pixels of the effective row, and finishing the scaling and overturning of the GPU pixel rectangle.
Further, the sampling scaling sub-module 41 receives the scaled line number sent by the processing module 3 in the line direction,
the effective scaled line number is sampled by the scaled line number,
the valid zoom line number is sent to the update line pixel coordinates submodule 42.
Further, the row pixel coordinate updating submodule 42 receives the scaling parameter and the new map coordinate sent by the scaling and flipping 2 in the row direction, the scaled row pixel, the row pixel coordinate and the scaled row number sent by the processing module 3 in the row direction, and the effective scaled row number sent by the sampling and scaling row submodule 41,
the corresponding row pixels are selected by comparing the effective scaling row numbers,
and then updating the pixel coordinates of the effective row, and finishing the scaling and overturning of the GPU pixel rectangle.
The invention has the beneficial effects that:
the invention realizes the function and the structure of a TLM-model-based pixel rectangle scaling and overturning algorithm, realizes the function defined by the glPixelZoom () function defined by the OpenGL API, solves the problem of insufficient performance of GPU hardware scaling and overturning pixel rectangles, and effectively accelerates RTL design development.
Drawings
FIG. 1 is a block diagram of a hardware TLM micro-architecture for a pixel rectangle scaling flipping algorithm of the present invention;
Detailed Description
The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and the specific embodiments. It is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than the whole embodiments, and that all other embodiments, which can be derived by a person skilled in the art without inventive step based on the embodiments of the present invention, belong to the scope of protection of the present invention.
The invention provides a GPU pixel rectangle scaling and flipping algorithm-oriented TLM microstructure, which comprises a new image position calculating module 1, a row pixel dispatching module 2, a row direction processing module 3 and a column direction processing module 4;
the new image position calculating module 1 is used for calculating the coordinates and the coverage range of the actual video memory after the image is zoomed and turned over;
the module for calculating the position of the new image 1 receives the zooming parameter, the turning parameter, the width and the height of the original image, the video memory range and the drawing coordinate,
calculating the new image coordinates and the coverage range of the image in the video memory range after zooming and turning,
the coverage range and the new image coordinate are sent to a pixel module 2 of an assignment line through a TLM interface;
the pixel module 2 in the assignment row is used for filtering the pixel rows outside the range of the column direction and then assigning effective pixel rows;
the pixel module 2 for distributing rows receives the original image, the scaling parameter and the flipping parameter, and calculates the coverage and the new map coordinate sent by the new map position module 1,
filtering the pixel rows outside the range of the column direction, then allocating effective pixel rows,
sending the single-line original image, the zooming parameter, the turning parameter, the coverage area, the new image coordinate and the current line number to a processing module 3 in the line direction through a TLM interface;
meanwhile, the overturning parameters and the new image coordinates are sent to the processing module 4 in the column direction through the TLM interface;
the processing module 3 in the row direction comprises a sampling original image submodule 31, a calculating new pixel coordinate submodule 32 and a calculating scaling row number submodule 33;
the processing module 3 in the row direction is used for calculating scaling factors to realize scaling sampling pixels, then calculating coordinates of all scaled pixels in each row, and calculating a row number of an image after scaling corresponding to a current scaling row;
the processing module 3 in the row direction receives the single-row original image, the scaling parameter, the flipping parameter, the coverage area, the new image coordinate and the current row number sent by the pixel module 2 in the assigned row,
a scaling factor is calculated based on the scaling parameter,
the row pixel coordinates for each row are calculated from the new map coordinates and the current row number,
calculating a scaled line number based on the scaling factor and the current line number,
and then the scaled row pixels, the row pixel coordinates and the scaled row number are sent to the processing module 4 in the column direction through the TLM interface. The sampling original image sub-module 31 receives the single-row original image, the coverage, the scaling parameter and the flipping parameter sent by the pixel module 2 of the assigned row,
the scaling factor is calculated by calculating the scaling factor,
then samples are taken in the original image line and the sampled pixels are sent to the calculate new pixel coordinates sub-module 32 and the scaling factor is sent to the calculate scaling line number sub-module 33.
The calculate new pixel coordinates submodule 32 receives the scaling parameter, the flipping parameter, the coverage, the new map coordinates sent by the pixel module 2 of the assigned row, and the sampled pixels sent by the sample original image submodule 31,
the new pixel coordinates are calculated and,
the new pixel coordinates and the sampled pixels are then sent to the processing modules 4 in the column direction.
The calculate zoom line number submodule 33 receives the flipping parameter and the current line number sent by the pixel module 2 of the assigned line, and the zoom factor sent by the sample original image submodule 31,
calculating the corresponding post-zoom line number of the current zoom line,
the scaled row number is then sent to the column-wise processing module 4.
And the processing module 4 in the column direction is used for calculating the number of the scaled lines, sampling and selecting the effective lines, and then updating the coordinates of the pixels of the effective lines.
The column-direction processing module 4 comprises a sampling scaling row sub-module 41 and an updating row pixel coordinate sub-module 42;
the processing module 4 in the column direction receives the scaled row pixels, the row pixel coordinates and the scaled row number sent by the processing module 3 in the row direction, and the flipping parameters and the new image coordinates sent by the assigned row pixel module 2,
the effective number of lines is selected by scaling the post-line number samples,
and updating the coordinates of the pixels of the effective row, and finishing the scaling and overturning of the GPU pixel rectangle.
The sample scaling row sub-module 41 receives the scaled row number sent by the processing module 3 in the row direction,
the effective scaled line number is sampled by the scaled line number,
the valid zoom line number is sent to the update line pixel coordinates submodule 42.
The sub-module 42 for updating the row pixel coordinate receives the transmission flipping parameter and the new map coordinate of the zoom flipping 2 in the row direction, the post-zoom row pixel, the row pixel coordinate and the post-zoom row number transmitted by the processing module 3 in the row direction, and the effective zoom row number transmitted by the sub-module 41 for sampling the zoom row,
the corresponding row pixels are selected by comparing the effective scaling row numbers,
and then updating the pixel coordinates of the effective row, and finishing the scaling and overturning of the GPU pixel rectangle.
Example (b):
the invention is described in further detail below with reference to the accompanying drawings, which refer to fig. 1.
A GPU-oriented TLM microstructure of a pixel rectangle scaling and flipping algorithm comprises a new image position calculating module 1, a row pixel dispatching module 2, a row-direction processing module 3 and a column-direction processing module 4;
the new image position calculating module 1 is used for calculating the coordinates and the coverage range of the actual video memory after the image is zoomed and turned over;
the module for calculating the position of the new image 1 receives the zooming parameter, the turning parameter, the width and the height of the original image, the video memory range and the drawing coordinate,
calculating the new image coordinates and the coverage range of the image in the video memory range after zooming and turning,
the coverage range and the new image coordinate are sent to a pixel module 2 of an assignment line through a TLM interface;
the pixel module 2 in the assignment row is used for filtering the pixel rows outside the range of the column direction and then assigning effective pixel rows;
the pixel module 2 for distributing rows receives the original image, the scaling parameter and the flipping parameter, and calculates the coverage and the new map coordinate sent by the new map position module 1,
filtering the pixel rows outside the range of the column direction, then allocating effective pixel rows,
sending the single-line original image, the zooming parameter, the turning parameter, the coverage area, the new image coordinate and the current line number to a processing module 3 in the line direction through a TLM interface;
meanwhile, the overturning parameters and the new image coordinates are sent to the processing module 4 in the column direction through the TLM interface;
the processing module 3 in the row direction comprises a sampling original image submodule 31, a calculating new pixel coordinate submodule 32 and a calculating scaling row number submodule 33;
the processing module 3 in the row direction is used for calculating scaling factors to realize scaling sampling pixels, then calculating coordinates of all scaled pixels in each row, and calculating a row number of an image after scaling corresponding to a current scaling row;
the processing module 3 in the row direction receives the single-row original image, the scaling parameter, the flipping parameter, the coverage area, the new image coordinate and the current row number sent by the pixel module 2 in the assigned row,
a scaling factor is calculated based on the scaling parameter,
the row pixel coordinates for each row are calculated from the new map coordinates and the current row number,
calculating a scaled line number based on the scaling factor and the current line number,
and then the scaled row pixels, the row pixel coordinates and the scaled row number are sent to the processing module 4 in the column direction through the TLM interface. The sampling original image sub-module 31 receives the single-row original image, the coverage, the scaling parameter and the flipping parameter sent by the pixel module 2 of the assigned row,
the scaling factor is calculated by calculating the scaling factor,
then samples are taken in the original image line and the sampled pixels are sent to the calculate new pixel coordinates sub-module 32 and the scaling factor is sent to the calculate scaling line number sub-module 33.
The calculate new pixel coordinates submodule 32 receives the scaling parameter, the flipping parameter, the coverage, the new map coordinates sent by the pixel module 2 of the assigned row, and the sampled pixels sent by the sample original image submodule 31,
the new pixel coordinates are calculated and,
the new pixel coordinates and the sampled pixels are then sent to the processing modules 4 in the column direction.
The calculate zoom line number submodule 33 receives the flipping parameter and the current line number sent by the pixel module 2 of the assigned line, and the zoom factor sent by the sample original image submodule 31,
calculating the corresponding post-zoom line number of the current zoom line,
the scaled row number is then sent to the column-wise processing module 4.
And the processing module 4 in the column direction is used for calculating the number of the scaled lines, sampling and selecting the effective lines, and then updating the coordinates of the pixels of the effective lines.
The column-direction processing module 4 comprises a sampling scaling row sub-module 41 and an updating row pixel coordinate sub-module 42;
the processing module 4 in the column direction receives the scaled row pixels, the row pixel coordinates and the scaled row number sent by the processing module 3 in the row direction, and the flipping parameters and the new image coordinates sent by the assigned row pixel module 2,
the effective number of lines is selected by scaling the post-line number samples,
and updating the coordinates of the pixels of the effective row, and finishing the scaling and overturning of the GPU pixel rectangle.
The sample scaling row sub-module 41 receives the scaled row number sent by the processing module 3 in the row direction,
the effective scaled line number is sampled by the scaled line number,
the valid zoom line number is sent to the update line pixel coordinates submodule 42.
The sub-module 42 for updating the row pixel coordinate receives the transmission flipping parameter and the new map coordinate of the zoom flipping 2 in the row direction, the post-zoom row pixel, the row pixel coordinate and the post-zoom row number transmitted by the processing module 3 in the row direction, and the effective zoom row number transmitted by the sub-module 41 for sampling the zoom row,
the corresponding row pixels are selected by comparing the effective scaling row numbers,
and then updating the pixel coordinates of the effective row, and finishing the scaling and overturning of the GPU pixel rectangle.
The GPU-oriented pixel rectangle scaling and flipping algorithm based on the TLM microstructure comprises the following steps:
step 1, calculating the position and range of the zoomed and overturned image, and calculating the drawing range of a new image according to the original width and height of the image, zooming parameters and overturning parameters; then, judging the drawing initial positions of the new image in the x direction and the y direction, if the drawing initial positions of the new image in the x direction and the y direction are smaller than the boundary, assigning the new image coordinate in the corresponding direction to be 0, and if the drawing initial positions of the new image in the x direction and the y direction are not smaller than the boundary, assigning the new image coordinate in the corresponding direction to; and finally, calculating the coverage range according to the new image coordinate and the video memory range.
And 2, allocating effective pixel rows, filtering invalid pixel rows according to the new drawing range, and then allocating effective pixel rows.
And 3, scaling and turning in the row direction, firstly, calculating a scaling factor in the x direction, and reversely deducing the sampling position of the original pixel row according to the scaling position and the scaling factor to sample the pixel. And then, calculating the coordinates of the pixels in the video memory according to the zooming parameter, the overturning parameter, the new image coordinates and the current line number. And finally, calculating the line number of the zoomed image corresponding to the current zoom line according to the current line number and the zoom parameter.
And 4, zooming and overturning in the column direction, sampling effective zooming rows through zoomed row numbers, and then updating coordinates of zoomed row pixels according to zooming parameters, overturning parameters and row pixel coordinates. And finishing the GPU pixel rectangle scaling and overturning.
Claims (10)
1. A GPU-pixel rectangle scaling and flipping algorithm-oriented TLM microstructure is characterized in that: the structure comprises a new image position calculating module 1, a row pixel distributing module 2, a row direction processing module 3 and a column direction processing module 4;
the processing module 3 in the row direction comprises a sampling original image submodule 31, a calculating new pixel coordinate submodule 32 and a calculating scaling row number submodule 33;
the column-direction processing module 4 comprises a sampling scaling row sub-module 41 and an updating row pixel coordinate sub-module 42;
the new image position calculating module 1 is used for calculating the coordinates and the coverage range of the actual video memory after the image is zoomed and turned over;
the pixel module 2 in the assignment row is used for filtering the pixel rows outside the range of the column direction and then assigning effective pixel rows;
the processing module 3 in the row direction is used for calculating scaling factors to realize scaling sampling pixels, then calculating coordinates of all scaled pixels in each row, and calculating a row number of an image after scaling corresponding to a current scaling row;
and the processing module 4 in the column direction is used for calculating the number of the scaled lines, sampling and selecting the effective lines, and then updating the coordinates of the pixels of the effective lines.
2. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the module for calculating the position of the new image 1 receives the zooming parameter, the turning parameter, the width and the height of the original image, the video memory range and the drawing coordinate,
calculating the new image coordinates and the coverage range of the image in the video memory range after zooming and turning,
the coverage, new map coordinates are sent to the dispatch row pixel module 2 over the TLM interface.
3. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the pixel module 2 for distributing rows receives the original image, the scaling parameter and the flipping parameter, and calculates the coverage and the new map coordinate sent by the new map position module 1,
filtering the pixel rows outside the range of the column direction, then allocating effective pixel rows,
sending the single-line original image, the zooming parameter, the turning parameter, the coverage area, the new image coordinate and the current line number to a processing module 3 in the line direction through a TLM interface;
and simultaneously, the overturning parameters and the new image coordinates are sent to the processing module 4 in the column direction through the TLM interface.
4. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the processing module 3 in the row direction receives the single-row original image, the scaling parameter, the flipping parameter, the coverage area, the new image coordinate and the current row number sent by the pixel module 2 in the assigned row,
a scaling factor is calculated based on the scaling parameter,
the row pixel coordinates for each row are calculated from the new map coordinates and the current row number,
calculating a scaled line number based on the scaling factor and the current line number,
and then the scaled row pixels, the row pixel coordinates and the scaled row number are sent to the processing module 4 in the column direction through the TLM interface.
5. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the sampling original image sub-module 31 receives the single-row original image, the coverage, the scaling parameter and the flipping parameter sent by the pixel module 2 of the assigned row,
the scaling factor is calculated by calculating the scaling factor,
then samples are taken in the original image line and the sampled pixels are sent to the calculate new pixel coordinates sub-module 32 and the scaling factor is sent to the calculate scaling line number sub-module 33.
6. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the calculate new pixel coordinates submodule 32 receives the scaling parameter, the flipping parameter, the coverage, the new map coordinates sent by the pixel module 2 of the assigned row, and the sampled pixels sent by the sample original image submodule 31,
the new pixel coordinates are calculated and,
the new pixel coordinates and the sampled pixels are then sent to the processing modules 4 in the column direction.
7. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the calculate zoom line number submodule 33 receives the flipping parameter and the current line number sent by the pixel module 2 of the assigned line, and the zoom factor sent by the sample original image submodule 31,
calculating the corresponding post-zoom line number of the current zoom line,
the scaled row number is then sent to the column-wise processing module 4.
8. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the processing module 4 in the column direction receives the scaled row pixels, the row pixel coordinates and the scaled row number sent by the processing module 3 in the row direction, and the flipping parameters and the new image coordinates sent by the assigned row pixel module 2,
the effective number of lines is selected by scaling the post-line number samples,
and updating the coordinates of the pixels of the effective row, and finishing the scaling and overturning of the GPU pixel rectangle.
9. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the sample scaling row sub-module 41 receives the scaled row number sent by the processing module 3 in the row direction,
the effective scaled line number is sampled by the scaled line number,
the valid zoom line number is sent to the update line pixel coordinates submodule 42.
10. The GPU-pixel-rectangle-scaling-flipping-algorithm-oriented TLM microstructure of claim 1, wherein:
the sub-module 42 for updating the row pixel coordinate receives the transmission flipping parameter and the new map coordinate of the zoom flipping 2 in the row direction, the post-zoom row pixel, the row pixel coordinate and the post-zoom row number transmitted by the processing module 3 in the row direction, and the effective zoom row number transmitted by the sub-module 41 for sampling the zoom row,
the corresponding row pixels are selected by comparing the effective scaling row numbers,
and then updating the pixel coordinates of the effective row, and finishing the scaling and overturning of the GPU pixel rectangle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911125671.XA CN111028129B (en) | 2019-11-18 | 2019-11-18 | TLM microstructure for GPU pixel rectangular scaling and turning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911125671.XA CN111028129B (en) | 2019-11-18 | 2019-11-18 | TLM microstructure for GPU pixel rectangular scaling and turning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111028129A true CN111028129A (en) | 2020-04-17 |
| CN111028129B CN111028129B (en) | 2023-09-15 |
Family
ID=70200395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911125671.XA Active CN111028129B (en) | 2019-11-18 | 2019-11-18 | TLM microstructure for GPU pixel rectangular scaling and turning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111028129B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050226539A1 (en) * | 2004-03-30 | 2005-10-13 | Dialog Semiconductor Gmbh | Zoom algorithm |
| CN101950523A (en) * | 2010-09-21 | 2011-01-19 | 上海大学 | Adjustable rectangular window image scaling method and device |
| CN102800049A (en) * | 2012-08-08 | 2012-11-28 | 广东威创视讯科技股份有限公司 | Image reduction method and device |
| CN102831571A (en) * | 2011-07-08 | 2012-12-19 | 图芯芯片技术（上海）有限公司 | Design method of five-order filter for realizing graphic image resizing and rotation in one step in flow-line manner |
| US20130222386A1 (en) * | 2012-02-23 | 2013-08-29 | Canon Kabushiki Kaisha | Image processing for projection on a projection screen |
| CN103578077A (en) * | 2013-12-02 | 2014-02-12 | 广东威创视讯科技股份有限公司 | Image zooming method and related device |
| CN104363385A (en) * | 2014-10-29 | 2015-02-18 | 复旦大学 | Line-oriented hardware implementing method for image fusion |
| CN108154477A (en) * | 2017-12-26 | 2018-06-12 | 深圳市兴森快捷电路科技股份有限公司 | A kind of image rotating method based on FPGA |
-
2019
- 2019-11-18 CN CN201911125671.XA patent/CN111028129B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050226539A1 (en) * | 2004-03-30 | 2005-10-13 | Dialog Semiconductor Gmbh | Zoom algorithm |
| CN101950523A (en) * | 2010-09-21 | 2011-01-19 | 上海大学 | Adjustable rectangular window image scaling method and device |
| CN102831571A (en) * | 2011-07-08 | 2012-12-19 | 图芯芯片技术（上海）有限公司 | Design method of five-order filter for realizing graphic image resizing and rotation in one step in flow-line manner |
| US20130222386A1 (en) * | 2012-02-23 | 2013-08-29 | Canon Kabushiki Kaisha | Image processing for projection on a projection screen |
| CN102800049A (en) * | 2012-08-08 | 2012-11-28 | 广东威创视讯科技股份有限公司 | Image reduction method and device |
| CN103578077A (en) * | 2013-12-02 | 2014-02-12 | 广东威创视讯科技股份有限公司 | Image zooming method and related device |
| CN104363385A (en) * | 2014-10-29 | 2015-02-18 | 复旦大学 | Line-oriented hardware implementing method for image fusion |
| CN108154477A (en) * | 2017-12-26 | 2018-06-12 | 深圳市兴森快捷电路科技股份有限公司 | A kind of image rotating method based on FPGA |
Non-Patent Citations (4)
| Title |
|---|
| HEEP-KAP AHN: "Faster algorithms for growing prioritized disks and rectangles", COMPUTERNAL GEOMETRY, vol. 80, pages 23 - 29 * |
| 覃方涛 等: "CUDA并行技术与数字图像几何变换", vol. 19, no. 10, pages 168 - 172 * |
| 阳富民,赵宁,张杰: "基于OpenGL的三维窗口裁剪、拾取算法研究", no. 04, pages 27 - 29 * |
| 黄金凤;陈小娥;: "基于Seam Carving的图像自适应缩放算法研究", no. 05, pages 44 - 50 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111028129B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6323874B1 (en) | System and method for rendering an image | |
| KR100896155B1 (en) | Flexible antialiasing in embedded devices | |
| CN101388157B (en) | Electronic map display method, apparatus and equipment | |
| CN110659664B (en) | SSD-based high-precision small object identification method | |
| JP2020531931A (en) | Image processing methods and devices, storage media, computer devices | |
| CN111145286A (en) | Point nine picture mapping drawing method for edge calculation scene based on GPU | |
| WO2017095617A1 (en) | Writing graphics data from local memory to system memory | |
| CN106548500A (en) | A kind of two-dimension situation image processing method and device based on GPU | |
| CN106251291A (en) | Utilize OpenGL with OpenCL to cooperate and realize the method and system of image scaling | |
| CN106504205A (en) | A kind of image defogging method and terminal | |
| CN111028129B (en) | TLM microstructure for GPU pixel rectangular scaling and turning algorithm | |
| CN108416729A (en) | A kind of realization device and method of line segment anti-aliasing in GPU | |
| CN109741433B (en) | Triangle multidirectional parallel scanning method and structure based on Tile | |
| CN103310409A (en) | Quick triangle partitioning method of Tile-based rendering architecture central processing unit (CPU) | |
| CN111091487A (en) | TLM microstructure for GPU hardware line element rasterization scanning algorithm | |
| CN108280887B (en) | Shadow map determination method and device | |
| CN111047498B (en) | GPU hardware copy buffer algorithm-oriented TLM microstructure | |
| CN108133094B (en) | Layout and wiring display method for field programmable gate array of anti-fuse | |
| CN103106687B (en) | The computer generating method of three-dimensional ocean grid and device thereof in self-adaptation FOV (Field of View) | |
| CN103593822B (en) | The method and apparatus that frosted special effect processing is carried out to data image | |
| CN112132871B (en) | Visual feature point tracking method and device based on feature optical flow information, storage medium and terminal | |
| CN108062793B (en) | Object top processing method, device, equipment and storage medium based on elevation | |
| CN107369194B (en) | Method and device for filling pattern | |
| CN111932566A (en) | Method, device and system for generating model contour map | |
| CN115457432B (en) | Data processing method and device for video frame extraction |
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 |