摘要
主要目的是以机载探测设备为平台,针对机载探测设备自身特性,来设计一种更为有效的融合算法,来对敌机中的危险目标进行识别,在主要方法上运用神经网络技术、Dempster-Shafer(D-S)证据理论将来自于机载SAR雷达、机载前视红外搜索跟踪系统 (IRS)、电子支援措施(ESM)等探测设备多次观察所得到的数据,进行实时的时域和空域融合,对于来自于地面的电子情报(ELINT) 的信息使用主观贝叶斯方法来同机载系统融合后的信息进行融合,从而达到准确的目标识别;最后通过实例仿真证明该算法适合于不同类型传感器不同格式信息之间的融合,其不仅能够适合于复杂的信号环境,并且在观测噪声比较大时,具有优良的性能和广泛的适应性。
Taking the aircraft borne sensor as a platform, in view of aircraft-- borne sensor' s characteristic, designs a kind of more effective fusion algorithm, to make a more accurate identification of the dangerous target of the enemy. The neural network technology, Dempster Shafer (D - S) evidence theory is used to fusion the data acquired from aircraft--borne SAR radar, the aircraft--borne foresight infrared search and track system (IRS), the electronic support measure (ESM) and so on, Regarding data from the ground electronic intelligence (ELINT), subjective Bayes theory will be used to fusion with the data from airborne system , thus achieves the accurate target identification. Finally the simulation proved this algorithm suits the fusion of the different type sensor and different form information, its not only can suit in the complex signal environment, but also when the observation noise is big, it still has fine performance and the widespread compatibility.
出处
《计算机测量与控制》
CSCD
2006年第4期524-527,共4页
Computer Measurement &Control
关键词
目标识别
证据理论
神经网络
主观贝叶斯
target identification
evidence theory
neural network
subjective Bayes