多分辨率匹配CRB分析中噪声估计方法

Noise estimation for Cramer-Rao Bound analysis of multi-scale matching

多分辨率目标匹配克拉美-罗界(CRB)分析中,CRB对噪声敏感,噪声估计尤为重要。采用不同阶次有限差分算子构成一组高通滤波器,分别对图像滤波处理,并将四分位间距(IQR)方法与中值滤波原理结合,估计CRB分析中的噪声方差,避免了残留轮廓信息的复杂处理,实验表明算法简单有效。

The Cramer-Rao Bound （CRB） analysis can be used in the transform parameters estimation of multi-scale object matching, and the noise estimation is of crucial importance since the CRB is very sensitive to the input noise. A group of high pass digital filters were constructed by several finite difference operators with different orders, and the image was processed with these operators and the variance was estimated separately from the filtered data with Inter-Quartile Range （IQR） method. Then, by median filter concept, noise variance was approximated by the median of the estimated variances. The supposed approach to noise estimation is simple and effective, which has been verified by the experiments.