摘要

为了根据光谱特征维度对点目标机动模式进行辨识，建立了点目标机动模式与光谱信号的映射关系，研究了目标机动过程中观测方向点目标的多光谱辐射特性。提取多光谱辐射信号特征，构建了双色比特征空间模型。利用高斯混合模型的聚类方法，深入分析了双色比特征空间的迁移和可分性特性，得到了点目标不同机动模式特征子空间迁移矢量和相邻矢量夹角余弦的变化规律，并得到特征子空间可分的最小姿态角变化量Δα=6.25°，可分距离阈值Dth=2.6，这为辨识点目标机动模式提供了依据。根据双色比特征子空间的特性，提出了基于时序特征子空间的点目标机动模式辨识方法，仿真验证结果表明，该方法简单可行，对点目标的机动模式辨识具有较高的灵敏性和可分性，这对获取超视距作战环境中点目标的机动信息具有重大意义。

Abstract

To recognize the point target maneuvering mode from the spectral characteristic dimension, the mapping relationship between the point target maneuvering mode and the spectral signals is built, and the multi-spectral radiation characteristics of point target with a maneuvering status in the direction of observation are investigated. The features of multi-spectral radiation signals are extracted to establish a dual-color-ratio-feature spatial model. The clustering method based on the Gaussian mixture model is used to analyze deeply the features of migration and separability of the dual-color-ratio-feature space. The migration vectors of feature sub-space of different maneuvering modes and the change of the cosine of adjacent vector angle are obtained. In addition, the smallest attitude angle change of feature sub-space and the separable distance threshold are obtained as Δα=6.25° and Dth=2.6, respectively. It provides the basis and feasibility for the recognition of point target maneuvering modes. According to the characteristics of dual-color-ratio-feature sub-space, a method for the recognition of point target maneuvering modes based on sequential-feature sub-space is proposed, which is verified by simulation as simple and feasible as well as possesses high sensitivity and separability in the recognition of point target maneuvering modes. These results have great significance for the acquisition of point target maneuvering information in the beyond-visual-range air combat.

补充资料

中图分类号：TN215

DOI：10.3788/aos201838.1204001

所属栏目：探测器

基金项目：国家自然科学基金(61172038)

收稿日期：2018-06-21

修改稿日期：2018-07-18

网络出版日期：2018-08-07

作者单位    点击查看

联系人作者：寇添(shanxiakkt@163.com)

【1】Sun J B, Xu R H, Liu F. Research on the key technologies and the process of air combat in informationalized conditions［J］. Flight Dynamics, 2007, 25(1): 80-83,88.
孙金标, 徐荣红, 刘峰. 信息化条件下空战的关键技术及空战过程研究［J］. 飞行力学, 2007, 25(1): 80-83, 88.

【2】Melinger J S, Laman N, Grischkowsky D. The underlying terahertz vibrational spectrum of explosives solids［J］. Applied Physics Letters, 2008, 93(1): 011102.

【3】Li J M, Wang G. High-speed target recognition positioning system based on multi-spectral radiation characteristics［J］. Spectroscopy and Spectral Analysis, 2014, 34(11): 3147-3152.
李建民, 王高. 基于多光谱辐射特性的高速目标识别定位系统［J］. 光谱学与光谱分析, 2014, 34(11): 3147-3152.

【4】Wang Q, Zhu G K, Yuan Y. Multi-spectral dataset and its application in saliency detection［J］. Computer Vision and Image Understanding, 2013, 117(12): 1748-1754.

【5】Liu F, Shen T S, Ma X X. Convolutional neural network based multi-band ship target recognition with feature fusion［J］. Acta Optica Sinica, 2017, 37(10): 1015002.
刘峰, 沈同圣, 马新星. 特征融合的卷积神经网络多波段舰船目标识别［J］. 光学学报,2017, 37(10): 1015002.

【6】Wang T, Tong C M, Li X M. Research on extended micro-motion target echo simulation and characteristic extraction［J］. Acta Physica Sinica, 2015, 64(21): 210301.
王童, 童创明, 李西敏. 扩展性微动目标回波模拟与特征参数提取研究［J］. 物理学报, 2015, 64(21): 210301.

【7】Tian J, Cui W, Shen Q, et al. High-speed maneuvering target detection approach based on joint RFT and keystone transform［J］. Science China Information Sciences, 2013, 56(6): 062309.

【8】Cheng J, Li L, Li H S. SAR target recognition based on improved joint sparse representation［J］. EURASIP Journal on Advances in Signal Processing, 2014, 2014: 87.

【9】Zhu Y L, Fan H Q, Lu Z Q. Survey of feature-based algorithms for radar target maneuver detection［J］. Systems Engineering and Electronics, 2011, 33(9): 1913-1921.
祝依龙, 范红旗, 卢再奇. 基于特征的雷达目标机动检测算法综述［J］. 系统工程与电子技术, 2011, 33(9): 1913-1921.

【10】Nie H T, Long K H, Ma J. Fast object recognition under multiple varying background using improved SIFT method［J］. Optics and Precision Engineering, 2015, 23(8): 2349-2357.
聂海涛, 龙科慧, 马军. 采用改进尺度不变特征变换在多变背景下实现快速目标识别［J］. 光学精密工程, 2015, 23(8): 2349-2357.

【11】Cui Z G, Wang H, Li A H. Moving object detection based on optical flow field analysis in dynamic scenes［J］. Acta Physica Sinica, 2017, 66(8): 084203.
崔智高, 王华, 李艾华. 动态背景下基于光流场分析的运动目标检测算法［J］. 物理学报, 2017, 66(8): 084203.

【12】Yuan Z W, Huang S C, Xiong Z G. Application of characteristic plume spectra in recognition of boost phase ballistic target［J］. Acta Optica Sinica, 2017, 37(2): 0230001.
苑智玮, 黄树彩, 熊志刚. 尾焰特征光谱在主动段弹道目标识别中的应用［J］. 光学学报, 2017, 37(2): 0230001.

【13】Kou T, Yu L, Zhou Z L, et al. Spectral radiant characteristic of airborne optoelectronic system detecting aerial maneuver target［J］. Acta Physica Sinica, 2017, 66(4): 049501.
寇添, 于雷, 周中良. 机载光电系统探测空中机动目标的光谱辐射特征研究［J］. 物理学报, 2017, 66(4): 049501.

【14】Sun C M, Zhao F, Yuan Y. Feature extraction and recognition of non-resolved space object from space-based spectral data［J］. Acta Physica Sinica, 2015, 64(3): 034202.
孙成明, 赵飞, 袁艳. 基于光谱的天基空间点目标特征提取与识别［J］. 物理学报, 2015, 64(3): 034202.

【15】Hou Q Y, Wang F G, Zhi X Y. Motion status identification of space object by analyzing time series multi-spectral signal［J］. Acta Optica Sinica, 2015, 35(4): 0401001.
侯晴宇, 王付刚, 智喜洋. 采用时序多谱段信号分析的空间目标运动状态辨识［J］. 光学学报, 2015, 35(4): 0401001.

【16】Zhang T X, Weng W J, Feng J. A novel multi-scale intelligent recursive recognition method for three-dimensional moving targets［J］. Acta Automatica Sinica, 2006, 32(5): 641-658.
张天序, 翁文杰, 冯军. 三维运动目标的多尺度智能递推识别新方法［J］. 自动化学报, 2006, 32(5): 641-658.

【17】Wu H P. Infrared search system［M］. Beijing: National Defense Industry Press, 2013: 80-102.
吴晗平.红外搜索系统［M］.北京: 国防工业出版社, 2013: 80-102.

引用该论文

Kou Tian,Zhou Zhongliang,Liu Hongqiang,Yang Yuanzhi,Ruan Chengwei. Dual-Color-Ratio-Feature Spatial Characteristics and Recognition of Aerial Point Target Maneuvering Modes[J]. Acta Optica Sinica, 2018, 38(12): 1204001

寇添,周中良,刘宏强,杨远志,阮铖巍. 空中点目标机动模式的双色比特征空间特性及辨识[J]. 光学学报, 2018, 38(12): 1204001