遥感图像信号不相关随机噪声去除方法研究

遥感图像无论在获取还是在传输中都会受到噪声的干扰,影响图像质量和进一步的数据挖掘。因此,在一般数字图像去噪算法的基础上探讨了对遥感图像信号不相关随机噪声的去除方法。由于小波变换理论在图像去噪处理中的应用广泛且效果显著,在此着重研究基于小波变换的小波阈值去噪算法。进而在coif3小波函数下进行仿真实验,结合仿真结果比较硬阈值和软阈值对噪声滤除的效果,同时还在软阈值的基础上尝试了多级软阈值去噪算法。实验结果表明,软阈值处理后的去噪效果要优于硬阈值,而多级软阈值处理后的效果优于纯软阈值处理的效果。

线性离散随机系统最优和稳态Kalman平滑器

对于带非零均值相关噪声的线性离散随机系统,基于Kalman 滤波器和射影理论,提出了新的最优固定点、固定区间和固定滞后 Kalman 平滑器。它们避免了计算估计误差方差阵的逆矩阵,且具有通用性。推广和改进了带零均值的不相关噪声系统的经典结果。还提出了相应的稳态 Kalman 平滑器和极点配置 Kalman平滑器,并证明它们的局部或全局渐近稳定性。

Optimal filtering for uncertain systems with stochastic nonlinearities, correlated noises and missing measurements

The globally optimal recursive filtering problem is studied for a class of systems with random parameter matrices,stochastic nonlinearities, correlated noises and missing measurements. The stochastic nonlinearities are presented in the system model to reflect multiplicative random disturbances, and the additive noises, process noise and measurement noise, are assumed to be one-step autocorrelated as well as two-step cross-correlated.A series of random variables is introduced as the missing rates governing the intermittent measurement losses caused by unfavorable network conditions. The aim of the addressed filtering problem is to design an optimal recursive filter for the uncertain systems based on an innovation approach such that the filtering error is globally minimized at each sampling time. A numerical simulation example is provided to illustrate the effectiveness and applicability of the proposed algorithm.