基于神经网络与D-S证据理论的多传感器目标识别技术

Multi-sensor Target Recognition Technology Based on Neural Network and D-S Evidence Theory

为了满足目标识别的需要,多传感器的数据融合技术已经成为研究的热点。D-S证据理论是多传感器信息融合中最常用的一种处理不确定问题的方法,在基于D-S证据理论的目标识别融合中,基本概率赋值的获取是一个难点。使用神经网络中应用最广泛的BP神经网络来求基本概率赋值,再结合D-S理论进行目标识别。结果表明这种方法可以提高战场目标识别的可靠性,降低识别结果的不确定性。

In order to meet the needs of target recognition,the data fusion technology of multi-sensor has become a research hotspot.D-S evidence theory is the most common method to deal with the uncertain problem in multi-sensor data fusion.In the fusion of target recognition based on D-S evidence theory,acquiring the basic probability assignment is a difficulty.This paper uses the BP neural network which is most widely used in neural network to seek the basic probability assignment,then performs the target identification combining with the D-S theory.The result indicates that this method can increase the reliability of the target recognition in the battlefield and reduce the uncertainty of the recognition results.