混响背景下预白化信号检测

Signal detection by a pre-whitening filter in presence of reverberation

在浅海环境中主动声纳匹配滤波器性能下降的一个重要原因是混响问题,因为混响同样是由发射信号引起的,与发射信号有很强的相关性。预白化抗混响算法是将混响看成局部平稳的有色高斯随机过程,采用AR模型对混响进行建摸,利用AR模型系数对原始数据进行"白化"处理,然后利用修正后的发射信号做拷贝信号进行匹配滤波。预白化处理能够有效抑制混响干扰,降低虚警,提高对运动小目标的探测能力。仿真和湖试数据处理结果验证了该方法的有效性。

The performance of matched filter in active sonar often degrades dramatically because of reverberation in shallow water. Reverberation is caused by the transmitted signal, so it has strong correlation with the transmitted signal. The pre-whitening anti-reverberation algorithm treats reverberation as local stationary colored Gaussian random process, and then models the reverberation with the AR model and prewhiten the original data. The matched filter is implemented by using the corrected transmitted signal. The prewhitening process can reject reverberation, reduce the false alarm and improve the performance of detecting small moving target. The processing results of simulation and trial data show the validity of the algorithm.