检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:武光辉[1] 童创明[1,2] 李西敏[1] 彭鹏[1]
机构地区:[1]空军工程大学防空反导学院,陕西西安710051 [2]国家微波毫米波重点实验室,江苏南京210096
出 处:《计算机仿真》2016年第6期9-12,339,共5页Computer Simulation
基 金:国家自然科学基金资助项目(61372033);航空科学基金资助项目(20130196005)
摘 要:逆合成孔径雷达(ISAR)目标成像识别通过在ISAR像中提取目标特征,并对目标进行分类识别,由于应用数字图像合成(DIS)技术的欺骗干扰使得识别真假目标变得十分困难。为了提高识别假目标的能力,提出一种采用纹理特征的假目标识别方法。首先,通过并行物理光学(PO)和等效边缘电磁流(EEC)对目标的宽带电磁散射特性进行快速计算。其次,以步进频率波形(SFW)为雷达发射波形并结合目标的电磁散射特性在信号级进行ISAR成像仿真。最后,将ISAR像进行Gabor多尺度分析,提取Gabor幅值图像的局部二值特征直方图,使用极限学习机(ELM)分类器完成真假目标的识别。针对复杂目标的仿真结果表明,采用纹理特征的假目标识别方法能够有效的对假目标进行识别,提高ISAR抗DIS欺骗式干扰的能力。Inverse synthetic aperture radar (ISAR) target recognition can recognize and classify the moving tar- gets efficiently by extracting the features of ISAR images, but ISAR deception jamming based on digital image syn- thetic (DIS) makes ISAR target recognition become quite difficult. Aiming at improving the ability of recognizing false target, we proposed a new approach to recognize false target by extracting the features of ISAR images. The characteristics of electromagnetic scattering from target were calculated rapidly by the hybrid physical optics ( PO ) and equivalent edge current (EEC) method, which is accelerated with parallel computing technology. Stepped fre- quency wave form (SWF) was chosen as the radar radiation wave form. With the data of electromagnetism scattering from target, the wide - band echo was generated in stepped frequency wave form. Then, the ISAR image was ob- tained in signal level using Range - Doppler algorithm (RDA). Next, the corresponding Gabor magnitude maps of ISAR images were obtain with multi - scale Gabor filters, and the histogram of texture feature was extracted from Ga- bor magnitude maps. Finally, the recognition of false target was implemented using Extreme Learning Machine (ELM) with the texture feature histogram. The simulation indicates that the new approach can recognize the false tar- get efficiently and improve the ability of anti - DIS deceptive jamming.
分 类 号:TN955[电子电信—信号与信息处理]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.249