一种窄带雷达舰船目标分类的决策方法  

A Decision-Making Algorithm of Ship Target Classification for Narrow Band Radar

作　　者：王曙光[1,2,3] 田西兰[1,2,3] 

机构地区：[1]中国电子科技集团公司第三十八研究所,安徽合肥230088 [2]孔径阵列与空间探测安徽省重点实验室,安徽合肥230088 [3]智能情报处理重点实验室,安徽合肥230088

出　　处：《雷达科学与技术》2016年第2期159-162,共4页Radar Science and Technology

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.

关 键 词：窄带雷达 舰船目标分类 分类器 决策方法 

分 类 号：TN957[电子电信—信号与信息处理]