摘要
针对无人平台在水下复杂环境中的线谱弱目标自主检测问题,提出了一种采用稀疏驱动自适应线谱增强(ALE)为前处理的监督学习目标检测方法。该方法在ALE代价函数中引入稀疏性l;范数,并将稀疏正则化推广到0<p<1;经过稀疏驱动ALE处理使目标声谱的熵特征差异更加明显,利用支持向量机(SVM)的小样本学习能力,对波束声谱的熵特性曲线进行分类,判别目标是否存在。仿真结果表明,输入信噪比为-20 dB情况下,l;稀疏驱动ALE比常规ALE的处理增益高11.5 dB。利用水下无人平台海上拉距试验的数据对算法性能进行验证,在宽带强干扰影响下,该方法可有效检测远距离声源,虚警率为3.5%时,检测率达95.8%,有效提高了对线谱弱目标的检测概率,具有较强的环境适应性。
For the weak line-spectrum target detection of unmanned underwater vehicles in the complex environment,a supervised learning detection method with pre-processing of sparsity-based Adaptive Line Enhancer(ALE) is proposed.This method incorporates a l;-norm sparse penalty into the cost function of ALE,and it also promotes the sparse regularization model to the 0<p<1’s one.After the processing of SALE,the entropy features of target beam spectrum become obviously different.Using the small sample learning ability of Support Vector Machine(SVM),the method classifies the entropy characteristic curve of beam spectrum and determines if the target exists.The simulation result shows that with the-20 dB input SNR,the SNR gain of l;-norm SALE is 11.5 dB higher than that of conventional ALE.The effectiveness of the method is verified by using the Unmanned Underwater Vehicle(UUV) experimental data.Under the influence of wideband strong interferences,the false alarm rate is 3.5% and the detection rate is 95.8%,which improved the detection probability of weak line-spectrum targets.
作者
金盛龙
迟骋
李宇
黄海宁
JIN Shenglong;CHI Cheng;LI Yu;HUANG Haining(Institute of Acoustics,Chinese Academy of Sciences,Beijing 100190;Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing,Chinese Academy of Sciences,Beijing 100190;University of Chinese Academy of Sciences,Beijing 100049)
出处
《声学学报》
EI
CAS
CSCD
北大核心
2021年第6期1059-1069,共11页
Acta Acustica
基金
国防基础科研计划重大项目(JCKY2016206A003)
国家自然科学基金项目(11904386,62001469)资助。
