New method of multi-scale multi-sensor state estimation in wavelet domain

被引：0

作者：

School of Electronic Information and Electrical Eng., Shanghai Jiaotong Univ., Shanghai 200030, China ^{[1
]}

机构：

来源：

Shanghai Jiaotong Daxue Xuebao | 2007年 / 11卷 / 1745-1748期

关键词：

Computer simulation - Interference suppression - Monte Carlo methods - Sensor data fusion - Signal filtering and prediction - State estimation - Wavelet transforms;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

The problem of multi-scale parameter estimation was studied. Based on the idea of multi-scale characteristic of signal and wavelet transform, a new multi-scale multi-sensor filtering algorithm was proposed. The concepts of 'total variation' and 'local variation' of functions are introduced to the areas of wavelet transform, and then the concept of 'contraction coefficients' is raised which significantly augments the previous theory that the updating of state estimation merely focuses on the approximations of wavelet decompositions. The Monte Carlo simulation reveals that the accuracy of estimation can be improved notably under the new theory.

引用