基于人工智能的线谱检测技术

A Technique of Line-spectrum Detection Based on Artificial Intelligence

本文主要讨论在被动声呐中窄带信号的自动检测问题 ,通过模拟声呐兵在LOFAR图中检测和提取谱线的双门限检测过程 ,提出了低信噪比下自动检测线谱的智能方法。此方法将线谱识别、线谱检测和线谱跟踪融合在一起 ,能在低信噪比和不知道窄带信号的数量、起止时间的情况下 ,自动地以高检测概率和低虚警概率检测线谱。

The paper deals with the problem of automatic detection of narrow-band signals which is encountered in a passive sonar system.An intelligent line-spectrum detection technique is presented,which imitates a sonar operator implementing a double thresholds detection while he detects spectral lines in a lofargram.The proposed method combines the line-spectrum recognition,line-spectrum tracing and line-spectrum detection together and can automatically detect line-spectrum in lofargram with high detection probability and low false probability at low signal-to noise ratio and with no knowing the number of narrow band signals and their birth moment and death moment.