摘要
目标识别技术在现代雷达中具有重要的应用价值,由于自身体制的限制,窄带雷达无法提供充足的信息以支撑目标分类识别。针对这种问题,提出了一种基于分类器判决、多帧融合和综合判决的综合决策方法:在分类器判决的基础上进行多帧融合以提高判决结果的稳定性,在综合判决中充分考虑各历史判决的信息以获得可靠的判决结果。以某型雷达对不同舰船目标的实测数据为对象,对提出的方法进行了验证。结果表明,所提方法能够有效提升判决结果的准确性与稳定性。
Target classification has important application value in modern radar.Due to the restriction of narrow-band radar system,sufficient information cannot be provided for target automatic classification.A decision-making algorithm,which combines classifier decision,multi-frame fusion,and hybrid decision-making,is proposed in this paper to solve this problem.Multi-frame fusion based on classifier decision can improve the decision＇s stability,while hybrid decision-making ameliorates its reliability.Classification experiments are made in a narrow-band radar system for the efficiency evaluation of proposed algorithm.The results demonstrate that the proposed algorithm is able to improve the accuracy and stability of the classification results.
出处
《雷达科学与技术》
北大核心
2016年第2期159-162,共4页
Radar Science and Technology
关键词
窄带雷达
舰船目标分类
分类器
决策方法
narrow-band radar
ship target classification
classifier
decision-making algorithm
