On the asymmetry in the PSD for 2-D linear prediction

被引:1
|
作者
Odendaal, JW
Barnard, E
Pistorius, CWI
机构
关键词
asymmetric peaks; single quadrant model; 2-D AR process;
D O I
10.1016/S0165-1684(97)00063-7
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The skewness in the peaks of the two-dimensional power spectral density (PSD) using the quadrant regions of support is investigated, In practice, limited data records or deviation from the assumed white noise hypothesis causes non-ideal approximations in the autoregressive process. If only a limited number of data samples is available, the correlation matrix is an estimate of the true correlation matrix. The autoregressive process is also based on additive white Gaussian noise, therefore any variation in noise will cause an approximation. This deviation from ideal is demonstrated to be the cause of the skewness in the power spectral density. (C) 1997 Elsevier Science B.V.
引用
收藏
页码:43 / 49
页数:7
相关论文
共 50 条