低信噪比条件下点状运动目标的检测性能在很大程度上依赖于对红外背景杂波的抑制情况。针对遗传算法的全局搜索能力以及神经网络的非线性预测能力,提出了一种基于遗传神经网络的背景杂波抑制技术。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统计量的方法进行了验证。 The detection performance of a point-like moving target under low signal-to-noise ratio greatly depends on the suppression of infrared background clutter. In view of the global search ability of genetic algorithm and the nonlinear predictive ability of neural network, a background clutter suppression technology based on genetic neural network is proposed. After the clutter is suppressed, the Gaussianity and independence of the residual noise are verified by the Kendall rank correlation method and the Friedman statistics method.