CN102263880B - Image scaling method and apparatus thereof - Google Patents
Image scaling method and apparatus thereof Download PDFInfo
- Publication number
- CN102263880B CN102263880B CN201010182441.XA CN201010182441A CN102263880B CN 102263880 B CN102263880 B CN 102263880B CN 201010182441 A CN201010182441 A CN 201010182441A CN 102263880 B CN102263880 B CN 102263880B
- Authority
- CN
- China
- Prior art keywords
- original image
- read
- data line
- image
- baddr
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 82
- 230000005540 biological transmission Effects 0.000 claims abstract description 6
- 238000002156 mixing Methods 0.000 claims description 4
- 230000003139 buffering effect Effects 0.000 abstract description 3
- 230000005055 memory storage Effects 0.000 description 15
- 230000007423 decrease Effects 0.000 description 7
- 238000000605 extraction Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention, which is suitable for the image processing field, provides an image scaling method and an apparatus thereof. The method comprises the following steps: determining interval lines of data lines which need to be read according to a vertical dimension relation between an original image and a target image; determining the data line information read from the original image according to the interval lines and reading the determined data line information from the original image; carrying out interpolation operation to the data line information and storing a interpolation operation result in output buffering. By using embodiments of the invention, data transmission quantity and image scaling processing time can be minimized to the greatest extent so that the output buffering of a display screen controller can be reduced and instantaneity of the display screen can be raised.
Description
Technical field
The invention belongs to image processing field, particularly relate to a kind of method and apparatus of image scaling.
Background technology
When showing the original image in external memory storage by display screen, the viewing area size of usual display screen and the size of original image there are differences, and show after therefore generally needing to carry out convergent-divergent process to original image again.When carrying out convergent-divergent process to original image, in order to ensure the real-time of display screen, generally all need first all or part of raw image data to be read input-buffer from external memory storage, then carry out interpolation arithmetic to the raw image data in input-buffer, obtain destination image data.When need read from external memory storage carry out image scaling process compared with the raw image data of multirow time, not only increase volume of transmitted data, add taking of DMA bandwidth, cause the waste of system resource, and due to the image scaling processing time long, cause the real-time demand needing to increase considerably the space guarantee display screen exporting buffer memory, thus cost is high.
Refer to Fig. 1, for an exemplary plot of the image-scaling method that prior art provides, be summarized as follows: when carrying out image scaling process, by direct memory access (Direct Memory Access, DMA) raw image data stored in external memory storage is read to input block by mode line by line successively, certain interpolation processing is carried out to the raw image data in input block, and by the image data transmission after interpolation processing to output buffer, by certain interface sequence, the image data transmission in output buffer is shown to display screen again.Owing to often writing a line view data in output buffer, all need through reading data to multiple step such as input block, image interpolation from external memory storage, and the defect of prior art is just no matter whether original row data finally participate in interpolation arithmetic, also no matter whether this data line is final useful, this data line is read in in capital, volume of transmitted data will certainly be strengthened like this, increase the image scaling processing time, be meanwhile also easy to cause output buffer to read sky thus cause display screen to show extremely.
Refer to Fig. 2, prior art additionally provides the method for another kind of image scaling, the method is before carrying out convergent-divergent process to original image, first by dynamic pre-decision circuitry, prejudge out in image scaling process the valid data needing to participate in interpolation arithmetic capable, as L1, L3, L4, L6, L7, L9, L10, L11, L12 in Fig. 2.This method decreases the data volume needing transmission to a certain extent, reduces DMA bandwidth occupancy in system.But because the dynamic pre-decision circuitry of the extra increase of needs judges, add hardware resource, and the data line of needs reading is also still often, when reduce in scale is larger, in order to ensure the real-time of display screen, or needs between larger buffer empty.
Summary of the invention
The object of the embodiment of the present invention is a kind of method providing image scaling, is intended to solve that existing image-scaling method volume of transmitted data is large, DMA bandwidth sum spatial cache wastes serious problem.
The embodiment of the present invention is achieved in that a kind of method of image scaling, and described method comprises the steps:
Obtain the size Simgv of original image vertical direction and the dimension D imgv of target image vertical direction;
Ratio M according to the size Simgv of original image vertical direction and the dimension D imgv of target image vertical direction determines interval line number N, wherein, if L < M≤L+1, then and N=L, wherein L is integer, M=Simgv/Dimgv;
Determine the data line information that will read from original image according to interval line number, and from original image, read the data line information that will read from original image determined;
Interpolation arithmetic is carried out to the data line information read, and interpolation arithmetic result is stored to output buffer memory.
Another object of the embodiment of the present invention is the device providing a kind of image scaling, and described device comprises:
Image reading control unit, for determining the interval line number of the data line that will read according to the vertical dimension relation between original image and target image;
Direct memory access control unit, for the data line information determining to read from original image according to interval line number, and reads the data line information that will read from original image determined from original image;
Input-buffer, for storing the data line information of the original image that described direct memory access control unit reads;
Image interpolation process unit, for carrying out interpolation arithmetic to the data line information read;
Export buffer memory, for storing the interpolation arithmetic result of described image interpolation process unit;
Wherein said image reading control unit comprises:
Dimension acquisition module, for the dimension D imgv of the size Simgv and target image vertical direction that obtain original image vertical direction;
Interval line number computing module, for determining interval line number N according to the ratio M of the size Simgv of described original image vertical direction and the dimension D imgv of target image vertical direction, if wherein L < M≤L+1, determine N=L, wherein L is integer, M=Simgv/Dimgv.
In embodiments of the present invention, by according to the data line information needed in the vertical dimension relation determination convergent-divergent process between original image and target image, established data row information is read again to input-buffer from external memory storage, then according to the data line information in input-buffer, interpolation convergent-divergent is carried out to original image by image interpolation process unit, owing to only reading the data line information needed in convergent-divergent process, thus decrease volume of transmitted data and image scaling processing time to greatest extent, and then decrease the output buffer memory of displaying screen controller, improve the real-time of display screen.
Accompanying drawing explanation
Fig. 1 is the exemplary plot of the method for the image scaling that prior art provides;
Fig. 2 is the exemplary plot of the method for another image scaling that prior art provides;
Fig. 3 is the realization flow figure of the method for the image scaling that the embodiment of the present invention provides;
Fig. 4 is the exemplary plot of the method for the image scaling that the embodiment of the present invention provides;
Fig. 5 is the structured flowchart of the device of the image scaling that the embodiment of the present invention provides.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
In embodiments of the present invention, when the original image convergent-divergent of input is processed into target image, first according to the data line information needed in the vertical dimension relation determination convergent-divergent process between original image and target image, established data row information is read again to input-buffer from external memory storage, then according to the data line information in input-buffer, interpolation convergent-divergent is carried out to original image by image interpolation process unit, owing to only reading the data line information needed in convergent-divergent process, thus decrease volume of transmitted data and image scaling processing time to greatest extent, and then decrease the output buffer memory of displaying screen controller, improve the real-time of display screen.
Fig. 3 shows the realization flow of the method for the image scaling that the embodiment of the present invention provides, and details are as follows:
In step S101, determine the interval line number of the data line that will read according to the vertical dimension relation between original image and target image.
Interpolation judgement and the interpolation arithmetic that DMA bandwidth principal element that is too much and that cause the image scaling processing time long is vertical direction is taken owing to causing transmitting data, therefore, the present invention mainly considers that the size relationship of the vertical direction between original image and target image determines the interval line number of the data line that will read.
Wherein determine according to the size relationship of the vertical direction between original image and target image that the step of the interval line number of the data line that will read is specific as follows:
A, the size Simgv of acquisition original image vertical direction and the dimension D imgv of target image vertical direction.
B, determine interval line number N according to the ratio M of the size Simgv of original image vertical direction and the dimension D imgv of target image vertical direction.Wherein interval line number N refers to and choose a line every N is capable from original image.
In order to ensure the quality of the target image after convergent-divergent process, determine that the concrete mode of N is as follows according to the ratio M of Simgv and Dimgv:
If L < is M≤L+1, then N=L, wherein L is integer, M=Simgv/Dimgv.
In embodiments of the present invention, when the vertical dimension of original image is greater than the vertical dimension of target display, when namely M is greater than 1, certain extraction is carried out to original image, only read the partial row of data information needed in convergent-divergent process; When the vertical dimension of original image is less than or equal to the vertical dimension of target display, when namely M is less than or equal to 1 (N=0), now needs to do to amplify process, then read every data line of original image, do not extract.
In step s 102, determine the data line information that will read from original image according to interval line number, and from original image, read the data line information that will read from original image determined.
Wherein determine according to interval line number that the detailed process of the data line information that will read from original image is as follows:
The first row view data in original image is defined as the data line that will read;
The first row of original image started, the data line at interval of interval line number is defined as the data line that will read.
The step reading the data line information that will read from original image determined from original image is as follows:
Calculate each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image, and from original image, read the data line information that will read according to each component address of each data line.
In embodiments of the present invention, because original image is generally stored in external memory storage, and the general dma mode that adopts reads the data line information that will read from external memory storage, therefore, the DMA address of each component of each data line that will read in convergent-divergent process is calculated according to the DMA initial address of each component of interval line number N and original image.
When original image is YUV420 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+P*Simgh/4；
V_addr＝V_baddr+P*Simgh/4；
If (N+1) * Snum is odd number, then P=(N+1) * Snum-1; Otherwise, then P=(N+1) * Snum.
When original image is YUV422 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+(N+1)*Simgh*Snum/2；
V_addr＝V_baddr+(N+1)*Simgh*Snum/2；
When original image is YUV444 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+(N+1)*Simgh*Snum；
V_addr＝V_baddr+(N+1)*Simgh*Snum；
Wherein, Y_baddr, U_baddr, V_baddr are respectively the DMA initial address of each component of Y, U, V; Y_addr, U_addr, V_addr are the DMA address of each component of corresponding each row of data; Simgh is the horizontal size of original image; Snum is the line number read, and this value is added up by successive image interpolation process unit.
Owing to calculating the DMA address of each component of the data line that will read, thus the data line that will read can be read from the external memory storage for storing original image according to the DMA address of the capable each component of corresponding data.In embodiments of the present invention, the data line read from original image is stored in input-buffer.
In embodiments of the present invention, when the controller of display screen needs to provide multiple-channel output, to when should have multiple passage, the data line read from original image is stored in the input-buffer of respective channel.
In embodiments of the present invention, when reading the data line information that will read in the original image stored from external memory storage according to each component address of the data line that will read, because each passage only needs the data line information that needs in reading images convergent-divergent process in the original image stored from external memory storage, thus greatly reduce the transmission quantity of data in each passage, and then the real-time saved as ensureing display screen and the spatial cache that additionally increases.
In step s 103, interpolation arithmetic is carried out to the data line information read, and interpolation arithmetic result is stored to output buffer memory, in order to exporting.Wherein prior art is belonged to the detailed process that the data line information read carries out interpolation arithmetic, therefore is summarized as follows:
In embodiments of the present invention, often from input-buffer, read a line raw image data, first carry out the horizontal scaling operation of specifying, the data obtained deposit data inward buffering area, or the horizontal scaling of specifying is operated the zoom operations that the lastrow data stored in the data and row data buffer zone obtained carry out vertical direction, the final result that convergent-divergent produces transfers to output buffer area, transfers to display screen show finally by certain interface sequence.
In embodiments of the present invention, the output policy that buffer memory adopts first in first out (First In First Out, FIFO) is exported.
In embodiments of the present invention, when needs provide multiple-channel output, to when should have multiple passage, respectively interpolation arithmetic is carried out to the data line information in the input-buffer corresponding with each passage, and the interpolation arithmetic result of each passage is mixed, mixed data are stored to and export in buffer memory.
In order to understand the present invention further, with a concrete example, the embodiment of the present invention is described below:
Refer to Fig. 4, the exemplary plot of the Zoom method of the image provided for the embodiment of the present invention.
Suppose that the size Simgv of original image vertical direction is 12, the dimension D imgv of target image vertical direction is 5, and comprise 12 row view data in original image altogether, line number is respectively L1, L2 ..., L12.
Then M=Simgv/Dimgv=12/5=2.4.Due to 2 < M≤2+1, so interval line number N=2, thus the first row data L1 of original image is defined as the data that will read, and by original image from the first row L1, data line L4, L7, L10 at interval of 2 row are defined as the data that will read.The data line that namely will read from original image comprises the capable data of L1, L4, L7, L10 in original image.
After each component address according to the data line that will read calculated, the capable data of L1, L4, L7, L10 can be read successively in input-buffer from original image.
The data line read in input-buffer carries out interpolation arithmetic successively, and the result of interpolation arithmetic is temporary in output buffer memory.Namely capable according to L1, L4, L7, L10 data carry out interpolation arithmetic, obtain 5 row data of target image.Illustrate as follows:
Using L1 directly as the first row data D1 of target image; L1 and L4 is carried out bilinear interpolation computing, obtains the second row data D2 of target image; L4 and L7 is carried out bilinear interpolation computing, obtains the third line data D3 of target image; L7 and L10 is carried out bilinear interpolation computing, obtains the fourth line data D4 of target image; L7 and L10 is carried out bilinear interpolation computing simultaneously, obtain the fifth line data D5 of target image.
Namely the method that the embodiment of the present invention provides only needs from original image, read the common four lines data of L1, L4, L7, L10 can be processed into target image by original image convergent-divergent.And the prior art shown in Fig. 1 method need read from original image all data lines totally 12 row data original image convergent-divergent could be processed into target image.And the prior art shown in Fig. 2 method need read from original image L1, L3, L4, L6, L7, L9, L10, L11, L12 totally 9 row data original image convergent-divergent could be processed into target image.Therefore, relative to prior art, the method that the embodiment of the present invention provides can reduce volume of transmitted data and image scaling processing time to greatest extent, and then reduces output buffer memory, improves the real-time of display screen.
Fig. 5 shows the structure of the device of the image scaling that the embodiment of the present invention provides, and illustrate only the part relevant to the embodiment of the present invention for convenience of explanation.
This device may be used for displaying screen controller, the displaying screen controller of such as mobile terminal, the displaying screen controller etc. of handheld device, it can be the unit that software unit, hardware cell or the software and hardware run in these equipment combines, also can be integrated in these equipment as independently suspension member or run in the application system of these equipment, wherein:
Image reading control unit 1 determines the interval line number of the data line that will read according to the vertical dimension relation between original image and target image.
This image reading control unit 1 comprises dimension acquisition module 11 and interval line number computing module 12.Wherein:
Dimension acquisition module 11 obtains the size Simgv of original image vertical direction and the dimension D imgv of target image vertical direction.
Interval line number computing module 12 determines interval line number N according to the ratio M of the size Simgv of original image vertical direction and the dimension D imgv of target image vertical direction.Wherein interval line number N refers to and choose a line at interval of N is capable from original image.
In order to ensure the quality of the target image after convergent-divergent process, determine that the concrete mode of N is as follows according to the ratio M of Simgv and Dimgv:
If L < is M≤L+1, then N=L, wherein L is integer, M=Simgv/Dimgv.
In embodiments of the present invention, when the vertical dimension of original image is greater than the vertical dimension of target display, when namely M is greater than 1, certain extraction is carried out to original image, only read the partial row of data information needed in convergent-divergent process; When the vertical dimension of original image is less than or equal to the vertical dimension of target display, when namely M is less than or equal to 1 (N=0), now needs to do to amplify process, then read every data line of original image, do not extract.
Direct memory access control unit 2 determines the data line information that will read from original image according to interval line number, and from original image, read the data line information that will read from original image determined.
The first row view data in original image is defined as the data line that will read by this direct memory access control unit 2, and the first row of original image is started, and the data line at interval of interval line number is defined as the data line that will read.
The step reading the data line information that will read from original image determined from original image is as follows:
Calculate each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image, and from original image, read the data line information that will read according to each component address of each data line.
In embodiments of the present invention, because original image is generally stored in external memory storage, and the general dma mode that adopts reads the data line information that will read from external memory storage, therefore, the DMA address of each component of each data line that will read in convergent-divergent process is calculated according to the DMA initial address of each component of interval line number N and original image.
In the original image of wherein various form, the DMA address computing formula of each component of each data line that read is described above, does not repeat them here.
Input-buffer 3 stores the data line information of the original image that direct memory access control unit 2 reads.
In an alternative embodiment of the invention, when displaying screen controller needs to provide multiple-channel output, to when should have multiple passage, then input-buffer 3 comprises the input-buffer corresponding with each passage, and the input-buffer corresponding with each passage stores the data line information of the original image corresponding with this passage that direct memory access control unit 2 reads.Illustrate as follows:
When displaying screen controller provides 3 tunnels to export, respectively when corresponding YUV1 passage, YUV2 passage and RGB passage, then input-buffer 3 comprises the YUV1 input-buffer corresponding with YUV1 passage, the YUV2 input-buffer corresponding with YUV2 passage and the RGB input-buffer corresponding with RGB passage.
Image interpolation process unit 4 carries out interpolation arithmetic to the data line information read, and obtains the view data after interpolation arithmetic.
This image interpolation process unit 4 comprises horizontal scaling processing module 41, row data buffer zone 42 and vertically scale processing module 43.Wherein:
When horizontal scaling processing module 41 often inputs a line raw image data in input-buffer 3, to the horizontal scaling process that raw image data is specified, obtain the view data after horizontal scaling process.
Row data buffer zone 42 stores the view data after horizontal scaling process.
The lastrow view data stored in view data after horizontal scaling processing module 41 processes by vertically scale processing module 43 and row data buffer zone 42 carries out the convergent-divergent process of vertical direction.
View data after the interpolation arithmetic that output buffer memory 5 memory image interpolation process unit 4 obtains.
In embodiments of the present invention, the output policy that buffer memory 5 adopts first in first out (First In First Out, FIFO) is exported.
In an alternative embodiment of the invention, when displaying screen controller needs to provide multiple-channel output, to when should have multiple passage, image interpolation process unit 4 comprises the image interpolation process unit corresponding respectively with each passage, and the data line information read in the image interpolation process unit corresponding respectively with each passage pair and its corresponding input-buffer carries out interpolation arithmetic.Illustrate as follows:
When displaying screen controller provides 3 tunnels to export, respectively when corresponding YUV1 passage, YUV2 passage and RGB passage, then input-buffer 3 comprises the YUV1 input-buffer corresponding with YUV1 passage, the YUV2 input-buffer corresponding with YUV2 passage and the RGB input-buffer corresponding with RGB passage.Image interpolation process unit 4 comprises the YUV1 image interpolation process unit be connected with YUV1 input-buffer, the YUV2 image interpolation process unit be connected with YUV2 input-buffer, the RGB image interpolation process unit that is connected with RGB input-buffer.
Now, this device also comprises image-blending unit 6.View data after the interpolation arithmetic that each image interpolation process unit corresponding with each passage that this image-blending unit 6 pairs of image interpolation process unit 4 comprise obtains mixes.
Now, export buffer memory image-blending unit 6 carry out mixed processing after view data.
One of ordinary skill in the art will appreciate that, the all or part of step realized in above-described embodiment method is that the hardware that can carry out instruction relevant by program has come, described program can be stored in computer read/write memory medium, described storage medium, as ROM/RAM, disk, CD etc.
In embodiments of the present invention, when the original image convergent-divergent of input is processed into target image, first according to the data line information needed in the vertical dimension relation determination convergent-divergent process between original image and target image, established data row information is read again to input-buffer from external memory storage, then according to the data line information in input-buffer, interpolation convergent-divergent is carried out to original image by image interpolation process unit, owing to only reading established data row information, thus decrease volume of transmitted data and image scaling processing time to greatest extent, and then decrease the output buffer memory of displaying screen controller, improve the real-time of display screen.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (6)
1. a method for image scaling, is characterized in that, described method comprises the steps:
Obtain the size Simgv of original image vertical direction and the dimension D imgv of target image vertical direction;
Ratio M according to the size Simgv of original image vertical direction and the dimension D imgv of target image vertical direction determines interval line number N, wherein, if L<M≤L+1, then and N=L, wherein L is integer, M=Simgv/Dimgv;
The data line information that will read from original image is determined according to interval line number, and from original image, read the data line information that will read from original image determined, wherein, read the data line information that will read from original image determined in described original image to be specially:
Calculate each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image, and from original image, read the data line information that will read according to each component address of each data line;
When original image is YUV420 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+P*Simgh/4；
V_addr＝V_baddr+P*Simgh/4；
If (N+1) * Snum is odd number, then P=(N+1) * Snum-1; Otherwise, then P=(N+1) * Snum;
When original image is YUV422 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+(N+1)*Simgh*Snum/2；
V_addr＝V_baddr+(N+1)*Simgh*Snum/2；
When original image is YUV444 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+(N+1)*Simgh*Snum；
V_addr＝V_baddr+(N+1)*Simgh*Snum；
Wherein, Y_baddr, U_baddr, V_baddr are respectively the DMA initial address of each component of Y, U, V; Y_addr, U_addr, V_addr are the DMA address of each component of corresponding each row of data; Simgh is the horizontal size of original image; Snum is the line number read, and this value is added up by successive image interpolation process unit;
Interpolation arithmetic is carried out to the data line information read, and interpolation arithmetic result is stored to output buffer memory.
2. the method for claim 1, is characterized in that, the described data line information determining will to read from original image according to interval line number, and the step reading the data line information that will read from original image determined from original image is specially:
The first row view data in original image is defined as the data line that will read;
The first row of original image started, the data line at interval of interval line number is defined as the data line that will read.
3. the method for claim 1, is characterized in that, when displaying screen controller needs to provide multiple-channel output, to when should have a multiplexer channel, is stored in the input-buffer of respective channel by the data line read from original image; Now,
The described data line information to reading carries out interpolation arithmetic, and step interpolation arithmetic result being stored to output buffer memory is specially:
Respectively interpolation arithmetic is carried out to the data line information in the input-buffer corresponding with each passage, and the interpolation arithmetic result of each passage is mixed, mixed data are stored to and export in buffer memory.
4. a device for image scaling, is characterized in that, described device comprises:
Image reading control unit, for determining the interval line number of the data line that will read according to the vertical dimension relation between original image and target image;
Direct memory access control unit, for the data line information determining to read from original image according to interval line number, and from original image, read the data line information that will read from original image determined, wherein, read the data line information that will read from original image determined in described original image to be specially:
Calculate each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image, and from original image, read the data line information that will read according to each component address of each data line;
When original image is YUV420 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+P*Simgh/4；
V_addr＝V_baddr+P*Simgh/4；
If (N+1) * Snum is odd number, then P=(N+1) * Snum-1; Otherwise, then P=(N+1) * Snum;
When original image is YUV422 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+(N+1)*Simgh*Snum/2；
V_addr＝V_baddr+(N+1)*Simgh*Snum/2；
When original image is YUV444 form, the address computation formula calculating each component address of each data line that will read from original image according to the initial address of each component of interval line number N, original image is as follows:
Y_addr＝Y_baddr+(N+1)*Simgh*Snum；
U_addr＝U_baddr+(N+1)*Simgh*Snum；
V_addr＝V_baddr+(N+1)*Simgh*Snum；
Wherein, Y_baddr, U_baddr, V_baddr are respectively the DMA initial address of each component of Y, U, V; Y_addr, U_addr, V_addr are the DMA address of each component of corresponding each row of data; Simgh is the horizontal size of original image; Snum is the line number read, and this value is added up by successive image interpolation process unit;
Input-buffer, for storing the data line information of the original image that described direct memory access control unit reads;
Image interpolation process unit, for carrying out interpolation arithmetic to the data line information read;
Export buffer memory, for storing the interpolation arithmetic result of described image interpolation process unit;
Wherein said image reading control unit comprises:
Dimension acquisition module, for the dimension D imgv of the size Simgv and target image vertical direction that obtain original image vertical direction;
Interval line number computing module, for determining interval line number N according to the ratio M of the size Simgv of described original image vertical direction and the dimension D imgv of target image vertical direction, if wherein L<M≤L+1, determine N=L, wherein L is integer, M=Simgv/Dimgv.
5. device as claimed in claim 4, it is characterized in that, the first row view data in original image is defined as the data line that will read by described direct memory access control unit, and the first row of original image is started, and the data line at interval of interval line number is defined as the data line that will read.
6. device as claimed in claim 4, it is characterized in that, when displaying screen controller needs to provide multiple-channel output, to when should have a multiplexer channel, described input-buffer comprises the input-buffer corresponding with each passage, and the input-buffer corresponding with each passage stores the data line information of the original image corresponding with this passage that described direct memory access control unit reads;
Described image interpolation process unit comprises the interpolation process unit corresponding respectively with each passage, and the data line information read in the interpolation process unit corresponding respectively with each passage pair and its corresponding input-buffer carries out interpolation arithmetic;
Described device also comprises:
Image-blending unit, the view data after the interpolation arithmetic that each image interpolation process unit corresponding with each passage for comprising described image interpolation process unit obtains mixes, and by mixed image data transmission to exporting buffer memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010182441.XA CN102263880B (en) | 2010-05-25 | 2010-05-25 | Image scaling method and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010182441.XA CN102263880B (en) | 2010-05-25 | 2010-05-25 | Image scaling method and apparatus thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102263880A CN102263880A (en) | 2011-11-30 |
| CN102263880B true CN102263880B (en) | 2015-02-11 |
Family
ID=45010319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010182441.XA Active CN102263880B (en) | 2010-05-25 | 2010-05-25 | Image scaling method and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102263880B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103546752B (en) * | 2013-10-15 | 2016-10-05 | 华南理工大学 | A kind of picture size based on hardware concurrent framework compression traversal method |
| CN105243028B (en) * | 2015-09-06 | 2018-04-03 | 珠海全志科技股份有限公司 | A kind of method and apparatus for reducing system peak bandwidth when image down is handled |
| CN106910162A (en) * | 2017-02-07 | 2017-06-30 | 深圳市爱协生科技有限公司 | Image zoom processing method and device based on FPGA |
| WO2019041264A1 (en) * | 2017-08-31 | 2019-03-07 | 深圳市大疆创新科技有限公司 | Image processing apparatus and method, and related circuit |
| CN110060196B (en) * | 2019-03-14 | 2023-09-19 | 爱芯元智半导体(宁波)有限公司 | Image processing method and device |
| CN110248163B (en) * | 2019-06-27 | 2021-04-09 | 湖州米欧康电子科技有限公司 | Image output method and system for monitoring camera shooting |
| CN112532894B (en) * | 2019-09-18 | 2023-01-10 | 西安诺瓦星云科技股份有限公司 | Image processing method, device and system |
| CN111145078B (en) * | 2019-12-27 | 2024-03-08 | 深圳云天励飞技术股份有限公司 | Image preprocessing device and method |
| CN111179883B (en) * | 2020-01-03 | 2022-06-03 | 云谷（固安）科技有限公司 | Image display method and device, mobile terminal, computer equipment and storage medium |
| CN112037118B (en) * | 2020-07-16 | 2024-02-02 | 新大陆数字技术股份有限公司 | Image scaling hardware acceleration method, device and system and readable storage medium |
| CN112053283B (en) * | 2020-08-13 | 2024-05-31 | 深圳市洲明科技股份有限公司 | Image scaling method, storage medium and electronic device |
| CN114327322B (en) * | 2020-10-10 | 2024-05-10 | 西安诺瓦星云科技股份有限公司 | Layer display method and device |
| CN114461112A (en) * | 2022-01-28 | 2022-05-10 | 海宁奕斯伟集成电路设计有限公司 | Image display method and device for screen menu type regulating mode |
| CN114449178A (en) * | 2022-02-17 | 2022-05-06 | 苏州华兴源创科技股份有限公司 | Video signal transmission control method and video signal transmission system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1745575A (en) * | 2003-01-29 | 2006-03-08 | 奥林巴斯株式会社 | Image sensing apparatus |
| CN101546527A (en) * | 2008-03-26 | 2009-09-30 | 深圳安凯微电子技术有限公司 | Liquid crystal display controller and image scaling method |
| CN101562006A (en) * | 2008-04-14 | 2009-10-21 | 深圳安凯微电子技术有限公司 | Method and device for image scaling |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625847B (en) * | 2009-08-06 | 2011-03-30 | 杭州电子科技大学 | Rapid display method of large-size non-compressed digital image |
-
2010
- 2010-05-25 CN CN201010182441.XA patent/CN102263880B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1745575A (en) * | 2003-01-29 | 2006-03-08 | 奥林巴斯株式会社 | Image sensing apparatus |
| CN101546527A (en) * | 2008-03-26 | 2009-09-30 | 深圳安凯微电子技术有限公司 | Liquid crystal display controller and image scaling method |
| CN101562006A (en) * | 2008-04-14 | 2009-10-21 | 深圳安凯微电子技术有限公司 | Method and device for image scaling |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102263880A (en) | 2011-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102263880B (en) | Image scaling method and apparatus thereof | |
| CN104104888A (en) | Parallel multi-core FPGA digital image real-time zooming processing method and device | |
| KR101490067B1 (en) | Parallel image processing using multiple processors | |
| US8749667B2 (en) | System and method for maintaining maximum input rate while up-scaling an image vertically | |
| EP1519358A2 (en) | Frame rate conversion device, overtaking prediction method for use in the same, display control device and video receiving display device | |
| CN101882302B (en) | Motion blur image restoration system based on multi-core | |
| CN101404151A (en) | Multi-screen splicing apparatus and method | |
| US20060161720A1 (en) | Image data transmission method and system with DMAC | |
| CN104932994B (en) | A kind of data processing method and device | |
| CN106846255B (en) | Image rotation realization method and device | |
| CN103733189A (en) | Image signal processor architecture optimized for low-power, processing flexibility, and user experience | |
| CN105704407A (en) | A display processing apparatus, device and method | |
| CN101562006B (en) | Method and device for image scaling | |
| US20110261061A1 (en) | Method and system for processing image data on a per tile basis in an image sensor pipeline | |
| CN103139509A (en) | On screen display (OSD) control display method and device based on advanced extensible interface (AXI) bus protocol | |
| CN114998087B (en) | Rendering method and device | |
| CN101546527B (en) | Liquid crystal display controller and image scaling method | |
| CN102831571B (en) | Design method of five-order filter for realizing graphic image resizing and rotation in one step in flow-line manner | |
| CN101304533A (en) | Video processing apparatus | |
| CN114697555B (en) | Image processing method, device, equipment and storage medium | |
| CN104918073A (en) | Image display method and terminal | |
| CN111405200B (en) | Video shrinking device, method and system and electronic equipment thereof | |
| CN102263924B (en) | Image processing method based on bicubic interpolation and image display method | |
| CN106658121A (en) | Method and system for set-top box to display fingerprint information | |
| CN202362766U (en) | Liquid crystal splicing wall applicable to synchronously displaying multipath image data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Image-scaling method and device thereof Effective date of registration: 20171102 Granted publication date: 20150211 Pledgee: China Co truction Bank Corp Guangzhou economic and Technological Development Zone sub branch Pledgor: Anyka (Guangzhou) Microelectronics Technology Co., Ltd. Registration number: 2017990001008 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20181227 Granted publication date: 20150211 Pledgee: China Co truction Bank Corp Guangzhou economic and Technological Development Zone sub branch Pledgor: Anyka (Guangzhou) Microelectronics Technology Co., Ltd. Registration number: 2017990001008 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Image-scaling method and device thereof Effective date of registration: 20190130 Granted publication date: 20150211 Pledgee: China Co truction Bank Corp Guangzhou economic and Technological Development Zone sub branch Pledgor: Anyka (Guangzhou) Microelectronics Technology Co., Ltd. Registration number: 2019440000051 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20200320 Granted publication date: 20150211 Pledgee: China Co truction Bank Corp Guangzhou economic and Technological Development Zone sub branch Pledgor: ANYKA (GUANGZHOU) MICROELECTRONICS TECHNOLOGY Co.,Ltd. Registration number: 2019440000051 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 3 / F, C1 area, innovation building, 182 science Avenue, Science City, Guangzhou, Guangdong 510000 Patentee after: Guangzhou Ankai Microelectronics Co.,Ltd. Address before: 3 / F, C1 area, innovation building, 182 science Avenue, Science City, Guangzhou, Guangdong 510000 Patentee before: ANYKA (GUANGZHOU) MICROELECTRONICS TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP02 | Change in the address of a patent holder |
Address after: 510555 No. 107 Bowen Road, Huangpu District, Guangzhou, Guangdong Patentee after: Guangzhou Ankai Microelectronics Co.,Ltd. Address before: 3 / F, C1 area, innovation building, 182 science Avenue, Science City, Guangzhou, Guangdong 510000 Patentee before: Guangzhou Ankai Microelectronics Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder |