Method of reducing JPEG coding and decoding line buffer capacity

Abstract

The invention discloses a method of reducing JPEG coding and decoding line buffer capacity. The method is characterized by comprising steps: in a coding stage, as for a frame of read image, image datafrom a 0th line to a seventh line are sequentially written to a coding line buffer module, an address pointer in the coding line buffer module starts from s=0, one is added to the address pointer s when one piece of pixel data is written; after image data of former eight lines are written, the image data are transmitted out according to 8*8 data units needed by the JPEG coding; at the same time,the coding line buffer module starts to write image data from an eighth line to a fifteenth line, and data access scheduling is controlled through controlling a read-write address change logic; and the decoding stage adopts the same read-write address change logic as the decoding state. The above method reduces the required line buffer space by half, power consumption of the chip is reduced, the chip area is reduced, and reduction of product cost is further realized.

Description

Technical field [0001] The present invention relates to the field of computer technology, and in particular to a method for reducing the line buffer capacity of JPEG encoding and decoding. Background technique [0002] Multimedia technology is one of the hot topics today. A difficult problem faced by multimedia communications and multimedia computers is the storage and transmission of massive data. Among all possible data, the image is the largest. Taking a general color TV signal as an example, if each component is digitized into 8 bits, the data volume is about 100Mb / s, so a CD-ROM (read-only disc) with a capacity of 1GB (=1000MB=800Mb) is only used. It can store about 1 minute of original data (with 2 parity bits attached to each byte). The data volume of High-Definition TV (HDTV) is about 1.2Gb / s. Therefore, a 1GB optical disc can not store HDTV images for less than 7 seconds, and such a large amount of data is not conducive to transmission in the communication network. O...

AI Technical Summary

Problems solved by technology

[0014] It can be seen from the above analysis that two pieces of RAM are required for encoding, each storing 8 lines of image data, and a total of 16 lines of data depth in ram space; decoding also requires two blocks of RAM, a total of 16 lines of data depth in ram space, and a total of 16 lines of data depth in ram space Four RAMs are required; whether it is an embedded system or an application-specific integrated circuit to implement JPEG codec, RAM space is a precious resource, which has an important impact on the cost of the entire chip or embedded system

Images