声/地震动目标融合识别

英文篇名：ACOUSTIC AND SEISMIC TARGETS FUSION IDENTIFICATION
中文刊名：弹道学报
英文刊名：Journal of Ballistics
作者：唐海峰 ; 李豪杰 ; 张河
英文作者：Tang Haifeng Li Haojie Zheng He (Mech. Eng. College ; NUST ; Nanjing ; 210094)
中文关键词：小波变换 ; FOBW编码 ; D-S证据理论 ; 模式识别
英文关键词：D-S evidential theory ; wavelet transform ; FOBW coding ; pattern recognition
出版日期：2002-06-30
机构：南京理工大学机械工程学院,南京理工大学机械工程学院,南京理工大学机械工程学院南京210094 ,南京210094 ,南京210094
年：2002
期：02
出版单位：弹道学报

摘要

根据声 /地震动目标信号的特点 ,提出运用小波变换对信号进行特征提取 ,并对数据进行统一的 FOBW子带编码 .在此基础上 ,运用 D- S证据理论对目标进行融合识别 .对比单一传感器的识别结果表明 ,该方法能明显提高识别能力 ,同时降低识别的不确定性 ,提高识别的实时性
Wavelet transform and FOBW coding are used to extract the target's signal of acoustic and seismic features. And then D-S evidential theory is used to identify the target based on wavelet transform and FOBW coding. By comparing the simulation results of targets identification based on separate data and fusion data respectively, the advantages of this algorithm are testified because of its higher identification rate and better real-time.

引文

1XiaojunJi,TingLi.Feature vector ofAR model parameters and recognition effect analysis.3rdInternationalSymposium onTestandMeasurement,Xi'an,China,1999:333-336
    2段俊峰,李科杰,张中民等.基于神经网络的战场被动声/地震动目标识别方法.探测与控制学报,2001,23(3):25-27
    3Chapa,JosephO R,RaghuveerM.Algorithms fordesigning wavelets to match a specified signal.IEEE Trans.onSignalProcessing,2000,48:3395-3406
    4管淑伟.快速目标识别系统的软硬件技术研究:[硕士学位论文].南京:南京理工大学,2000
    5LeungH,YifengLi.Improved multiple target tracking using dempster-shafter identification.SPIE,1997,3068:218-227
    6HongyanSun,ShiyiMao.Multisensor data fusion for target identification.ChineseJournal ofElectronics,1995,4(3):78-84
    7ZhangY.Distributed sequential nearestneighbormultitargettracking algorithm.IEEE Pro-Radar,SonarNav-ing,1996,143(4):255-260
    8RajagopalR.Adaptive bearing estimation and tracking of multiple targets in a realistic passive sonar scenario.SPIE,1997,3086:139-150