【摘要】 含有点状运动目标的红外图像序列情况下,在研究杂波运动机理和数理模型的基础上,假定杂波是时空非平稳随机过程,采用时空非参数预测(时域衰减正弦、空域Gabor加权函数)技术来抑制了动态背景杂波。另外,杂波抑制后,残留噪声的高斯性和独立性通过Kendall秩相关法和计算Friedman统计量的方法来进行了验证,其结果表明本文所研究的算法思路的可行性。更多还原

【Abstract】 A nonparametric spatial-temporal moving clutter elimination method as an important counterpart of target de-tection procedures was presented.In this method,after the rejection of clutter,the original spatially correlated imaging sensor data were reduced to independent identical distribution random variables from pixel to pixel.In the case where the statistics of the residuals(targets or noise) were not known in sufficient details,the employment of nonparametric detec-tor is often desirable.This technique can be characterized by their suitability for real-time processing and extreme sim-plicity in implementation that it is very useful in many practical applications.And Gaussianity and independency of residuals are also verified using Kendall rank correlation and Friedman statistic methods.更多还原