摘要
Abstract
Ground-to-air detection systems play a vital role in the fields of air defense early warning,airspace surveillance,battlefield sensing,etc.However,multi-source interference,environmental clutter and system errors in complex backgrounds lead to high false alarm rates,which seriously restricts their combat effectiveness and reliability.Focusing on the core issue of reducing the false alarm rate,this paper systematically analyzes the multiple mechanisms of false alarm generation,proposes a signal processing method based on adaptive filtering,multiple feature fusion and dynamic threshold adjustment,and studies multi-sensor information fusion algorithms,including multi-level fusion at the data level,feature level and decision-level,and combines deep learning technology to build an intelligent identification and false alarm suppression model,in order to provide technical reference for intelligent and high-reliability applications of ground-to-air detection systems.关键词
地空探测/虚警率/多传感器融合/深度学习/信号处理Key words
ground-air detection/false alarm rate/multi-sensor fusion/deep learning/signal processing分类
天文与地球科学
