激光/红外复合扫描引信目标识别算法  

Target recognition algorithm for laser/infrared composite scanning fuze

作　　者：郭甲崇 刘星[1] 袁俊[2] 吕浩 GUO Jia-chong;LIU Xing;YUAN Jun;LuHao(Xi′an Technological University,Xi′an 710021,China;Kunming Institute of Physics,Kunming 650000,China)

机构地区：[1]西安工业大学,陕西西安710021 [2]昆明物理研究所,云南昆明650000

出　　处：《激光与红外》2020年第2期184-191,共8页Laser & Infrared

摘　　要：针对激光、红外单模引信抗环境干扰能力差、目标识别概率不高的问题,提出了一种基于关联的多元线阵激光/红外复合扫描的模糊识别算法。该算法通过建立激光/红外线阵扫描模型,对目标的顶部三维轮廓与顶部红外辐射图像进行特征提取与关联信息融合,对比真实目标特征参数,设计了基于模糊理论的目标识别算法,得出三组识别特征各自的识别概率,在此基础上对三种识别概率继续进行模糊推理融合得出目标的最终识别概率。仿真结果表明,该复合探测目标识别概率比单模识别方法有较大幅度的提高。Aiming at the problem that laser and infrared single-mode fuze have poor anti-environmental interference ability and low target recognition probability,a fuzzy recognition algorithm based on correlation multivariate linear array laser/infrared composite scanning is proposed.By establishing the laser/infrared array scanning model,the feature extraction and correlation information fusion of the top three-dimensional contour of the target and the top infrared radiation image are carried out,and the target recognition algorithm based on fuzzy theory is designed,then the recognition probability of the three groups of recognition features is obtained.On this basis,the fuzzy inference fusion of three recognition probabilities is carried out to obtain the final recognition probability of the target.Simulation results show that the recognition probability of the composite detection target is greatly improved than that of the single-mode recognition method.

关 键 词：线阵扫描 激光/红外复合 图像处理 顶部轮廓 特征关联 模糊识别 

分 类 号：TN249[电子电信—物理电子学] TJ43+4.2[兵器科学与技术—火炮、自动武器与弹药工程]