An Adaptive Data Compression Algorithm for Video Data

사진데이타를 위한 한 Adaptive Data Compression 방법

This paper presents an adaptive data compression algorithm for video data. The coling complexity due to the high correlation in the given data sequence is alleviated by coding the difference data, sequence rather than the data sequence itself. The adaptation to the nonstationary statistics of the data is confined within a code set, which consists of two constant length cades and six modified Shannon.Fano codes. lt is assumed that the probability distributions of tile difference data sequence and of the data entropy are Laplacian and Gaussion, respectively. The adaptive coding performance is compared for two code selection criteria: entropy and $P_r$[difference value=0]=$P_0$. It is shown that data compression ratio 2 : 1 is achievable with the adaptive coding. The gain by the adaptive coding over the fixed coding is shown to be about 10% in compression ratio and 15% in code efficiency. In addition, $P_0$ is found to he not only a convenient criterion for code selection, but also such efficient a parameter as to perform almost like entropy.

본 논문은 사진데이타에 쉽게 적용할수있는 한 adaptive data compression 방법을 노표시하였다. 이웃 sample data 사이의 높은 correlation때문에 발생할 부호화 복잡성을 간편한 sample difference data로 대처하였으며, 자단의 statistical nonstationarity에 적응키 위해서 여덟가지 부호(code)로 구성된 code set중에서 최적부호를 선택토록 하였다. code erst는 두가지 등장부호와 여섯가지 보완형 Shannon-Fanro 부호로 되었다. difference data의 확률분포는 Laplacian model로, entropy의 확률분포는 Gaussian model대 하였다. 부호선별 Paranleter로서 entropy와 Pr[차이값=0]=Po를 비교하였다. 콤퓨타 실험결과 이 adaptive coding 방법으로 2대 1의 데이타 감축비를 얻었다. 이 방법은 fixed coding에 비해서 데이타 감축비와 부호화효율에서 약 10%와 15%의 이득을 주었다. 또한 도는 entropy보다 휠신 편리한 부호선별 parameter인 중시에 entropy 경우와 1% 내외의 좋은 결과를 얻을수 있음이 확인되었다. This paper presents an adaptive data compression algorithm for video data. The coling complexity due to the high correlation in the given data sequence is alleviated by coding the difference data, sequence rather than the data sequence itself. The adaptation to the nonstationary statistics of the data is confined within a code set, which consists of two constant length cades and six modified Shannon·Fano codes. lt is assumed that the probability distributions of tile difference data sequence and of the data entropy are Laplacian and Gaussion, respectively. The adaptive coding performance is compared for two code selection criteria: entropy and pr[difference value=0]=po. It is shown that data compression ratio 2 : 1 is achievable with the adaptive coding. The gain by the adaptive coding over the fixed coding is shown to be about 10% in compression ratio and 15% in code efficiency. In addition, po is found to he not only a convenient criterion for code selection, but also such efficient a parameter as to perform almost like entropy.