KR20010039192A - Data compressing/decompressing apparatus and method for effective use of memory - Google Patents

Abstract

PURPOSE: A data compression/decompression device and a method for effective usage of a memory are provided to reduce the dimension of the memory by compressing/storing video data in recording the data in the memory and decompressing the data in reading CONSTITUTION: The data compression/decompression device compresses a compressor(102), a memory controller(108) and a decompressor(104). The compressor(102) compresses digital video data with a predetermined compression rate. The memory controller(108) stores the compressed digital video data input from the compressor(102) in a frame memory(110) by a frame unit. The decompressor(104) decompresses the compressed digital video data read/applied from the frame memory(110) into the digital video data before compressed under the control of the memory controller(108).

Description

DATA COMPRESSING / DECOMPRESSING APPARATUS AND METHOD FOR EFFECTIVE USE OF MEMORY}

The present invention relates to a data compression and decompression method for efficient use of a memory, and more particularly, to a data compression and decompression method for memory efficient use in a frame memory for storing image data.

In general, an image signal processing apparatus converts an applied image signal into digital data, stores it in a frame memory in a frame unit, reads out the stored data, converts it into an analog image signal, and displays the image on a screen. At this time, the video signal is compressed by various compression techniques such as predictive encoding, transform encoding, subband encoding, etc. in digital data.

However, when storing the digital image data compressed and input in the frame memory as described above, the input digital image data is stored in the frame memory as it is in units of frames without a separate compression process. That is, a separate compression technique is not used for the memory used for data processing. As a result, the size of the frame memory is inevitably increased, resulting in a large chip size of the image signal processing ASIC having the frame memory.

As described above, the memory used in the conventional data processing does not have a separate compression technique, so the size of the memory is inevitably increased. As a result, the size of the image signal processing ASIC chip using the memory for image data processing is also increased. There was a problem.

Accordingly, an object of the present invention is to compress data when recording image data in memory in a chip or other system using the memory, and to restore data when storing and reading data. / Restoring apparatus and method.

1 is a block diagram of a data compression / restore apparatus according to an embodiment of the present invention;

FIG. 2 is a detailed circuit diagram of the data compression / restoration compression unit of FIG. 1; FIG.

3 is a detailed circuit diagram illustrating a data compression / restoration restoration unit of FIG. 1;

4 is an example of a codeword table according to an embodiment of the present invention;

5 is a graph illustrating probability distribution functions of difference values according to an exemplary embodiment of the present invention.

The present invention for achieving the above object in the compression and decompression of data for the efficient use of the memory, when recording the image data in the memory in the ASIC chip or other image signal processing system using the memory to compress and store the data When the data is read, the data can be restored, thereby reducing the amount of memory required and at the same time reducing the memory access time so that the memory can be used efficiently.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Many specific details are set forth in the following description and in the accompanying drawings, in order to provide a more thorough understanding of the present invention. It will be apparent to those skilled in the art that the present invention may be practiced without these specific details. And a detailed description of known functions and configurations that may unnecessarily obscure the subject matter of the present invention will be omitted.

1 is a block diagram of a data compression / restore apparatus of an image resize system according to an exemplary embodiment of the present invention. Referring to FIG. 1, the horizontal filter and the resizer 100 may perform filtering in the horizontal direction to convert the size of the effective pixel of the output image to the size of the effective pixel of the input image data. Resizing is performed. The compressor 102 compresses the horizontally filtered and resized image data from the horizontal filter and the resizer 100 at a predetermined compression rate. The memory controller 108 stores image data compressed by the compression unit 102 at a predetermined compression rate in a frame memory 110 in units of frames. The frame memory 110 stores image data input in units of frames under the control of the memory controller 108. The decompressor 104 restores the compressed digital image data read and applied from the frame memory 110 to the image data before compression under the control of the memory controller 108. The vertical filter and resizer 106 performs vertical filtering and resizing while reading the pixels in the vertical direction of the image data restored to the original image data from the reconstructor 104.

FIG. 2 illustrates a detailed circuit configuration of the compression unit 102 of FIG. 1. The compression unit 102 predicts a current pixel by using a differential PCM (DPCM) when image data is input. The output from the subtractor 202 is subtracted to obtain a difference value, and the coding unit 204 codes the difference value. In this case, the coding unit 204 reads a variable-length-code corresponding to the difference value from a codeword table 206 using variable-length-coding. Will be coded out. An example of the codeword table 206 is illustrated in FIG. 4. Referring to FIG. 4, it can be seen that variable length codes are made different for each difference value. This is because the probability of occurrence of each value is different as shown in FIG. 5, which shows a general probability distribution function p (x) of each difference value of the difference signal. In addition, the difference value may actually occur in the range of -255 to 255, but as shown in the probability density function of FIG. 5, since most of the energy is concentrated in a small absolute value, the variable length code corresponding to the large difference value Can be escaped (ESC). That is, when a large difference value occurs, the variable length code corresponding to the ESC and the difference value are transmitted as it is.

3 illustrates a detailed circuit configuration of the restoration unit 104 of FIG. 1, in which the restoration unit 104 receives compressed image data from the frame memory 110 under the control of the memory control unit 108. The variable length encoded image data is decoded by the decoding unit 302 with reference to the codeword table 300. The output from the predictor 306 predicting the current pixel is added by the adder 304 to restore the original image data signal.

Therefore, the image data input by using the compression unit 102 and the restoration unit 104 can be compressed and stored in the frame memory 110, read out from the frame memory 110, and then output after being restored. Therefore, it is possible to reduce the small memory required when storing / processing data in the memory inside the ASIC.

Meanwhile, in the above description of the present invention, specific embodiments have been described, but various modifications may be made without departing from the scope of the present invention. In particular, although the embodiment of the present invention has been described with an image resizing system as an example, the same may be applied to a chip or other image processing system that uses a memory for recording and reading image data. Therefore, the scope of the invention should not be defined by the described embodiments, but should be determined by the equivalent of the claims and claims.

As described above, the present invention can reduce the amount of memory required by compressing, storing, and restoring data when recording image data in the memory in a chip or other system using the memory and restoring the data when reading the data. This has the advantage of reducing the time required.

Claims (2)

In the device for compressing / restore data for efficient use of memory, A compression unit which inputs digital image data and compresses the data at a predetermined predetermined compression rate; A memory controller configured to store the compressed digital image data input from the compression unit in a frame memory on a frame basis; And a restoring unit for restoring the compressed digital image data read and applied from the frame memory to the digital image data before being compressed under the control of the memory control unit. In a data compression / restore device including at least a compression unit, a reconstruction unit, a memory control unit, and a frame memory, a method of compressing / restore data for efficient use of the memory Compressing the image data at a predetermined predetermined compression ratio through the compression unit when digital image data is input; Storing the compressed image data in the frame memory on a frame basis; Compressing the data for efficient use of the memory, characterized in that when the compressed image data from the frame memory is read out to restore the digital image data stored in the frame memory to the digital image data before compression to the output; How to restore.