基于不同准则函数的雷达目标特征空间变换

为解决雷达目标高分辨距离像的识别问题 ,将 4种基于不同准则推导出的线性特征空间变换进行了归纳。分别用这几种变换方法对 6类飞机缩比目标高分辨距离像数据进行特征空间变换 ,然后用同一分类器判决 ,并对其识别结果加以分析与比较 ,得出在该应用条件下的有益结论。

空间目标特征信息在空间作战中的作用分析

为提高对空间目标特征研究必要性的认识，对空间目标特征信息在空间作战中的作用进行了分析；在详细研究了空间目标特征的概念、分类情况以及研究现状的基础上，对空间目标特征信息在空间作战不同阶段中所发挥的信息支持作用进行了深入分析；最后，依据对空间目标特征信息在空间作战中的作用的分析，提出了对开展空间目标特征研究的建议。

基于空间目标特征信息的空间武器决策支持系统设计

对空间武器决策支持技术进行了比较全面的基础研究,并且以实例来说明如何将决策支持方法应用于空间攻防对抗体系。阐述了空间作战、空间目标特征的概念及其分类;应用决策支持方法对空间攻防对抗系统中的实际应用问题进行了数学建模和仿真分析,并应用Matlab程序语言实现了决策支持系统的人机交互界面。从仿真中看出,文中所采用的决策支持系统可以在不同情况下采取不同的决策,决策也能较好达到目的,应用效果良好。

基于CIRCLE特征变换的点群选取算法

本文在分析了当前地图自动综合算法的基础上,提出了一种基于Circle特征变换的点群选取新算法。文中介绍了该算法中空域中心点的确定、目标特征空间的计算、坐标空间到特征空间的转换、特征空间的聚类以及特征空间的化简等关键步骤。最后就算法的结果进行了分析与评价。

流形群运动目标自动识别与跟踪技术研究——以MCS自动追踪方法为例

从流形群运运目标的形状特征及其本质属性出发 ,提出了多种适合计算机自动识别与跟踪流形群运运目标的匹配模板的构建技术。充分顾及流形群运动目标的区域整体描述、几何形状特征、不变矩特性 ,以及流形群目标的本质属性 (纹理特征 ) ,通过最大欧几里得贴近度的择近原则 ,实现模板匹配 ,完成目标识别 ;通过交替更新匹配模板元素参量及交叉匹配算法 ,实现目标跟踪。应用这种算法 ,对 1 998年 6月至 8月的青藏高原上空中尺度对流系统 (MCS)进行了识别与跟踪实验。实验结果表明 ,这种技术较适合计算机自动识别和跟踪类似MCS的流形群运动目标 ,与专家目测屏幕扫描跟踪法相比 ,准确率达 90 %。同Arnaud等人提出的面积重叠跟踪法相比 。

Kernelized fourth quantification theory for mineral target prediction

This paper presents a nonlinear multidimensional scaling model, called kernelized fourth quantifica- tion theory, which is an integration of kernel techniques and the fourth quantification theory. The model can deal with the problem of mineral prediction without defining a training area. In mineral target prediction, the pre-defined statistical cells, such as grid cells, can be implicitly transformed using kernel techniques from input space to a high-dimensional feature space, where the nonlinearly separable clusters in the input space are ex- pected to be linearly separable. Then, the transformed cells in the feature space are mapped by the fourth quan- tifieation theory onto a low-dimensional scaling space, where the sealed cells can be visually clustered according to their spatial locations. At the same time, those cells, which are far away from the cluster center of the majority of the sealed cells, are recognized as anomaly cells. Finally, whether the anomaly cells can serve as mineral potential target cells can be tested by spatially superimposing the known mineral occurrences onto the anomaly ceils. A case study shows that nearly all the known mineral occurrences spatially coincide with the anomaly cells with nearly the smallest scaled coordinates in one-dimensional sealing space. In the case study, the mineral target cells delineated by the new model are similar to those predicted by the well-known WofE model.

自然场景下的显著性检测优化方法

为满足自然场景下显著性检测精度的要求,提出了一种显著性检测优化方法。该方法采用简单线性迭代聚类分割算法将图像分割为多个超像素区域,并提取颜色区域对比度特征。通过Harris角点检测算法定位目标的大致几何中心,以中心概率的形式表征目标空间分布特征,并进行目标位置自适应的特征融合。基于目标空间分布特征和图像灰度重心,实现抑制背景、增强目标的显著图优化;利用针对显著性值的空间平滑技术,可增加显著图的连续性。实验结果表明,该方法在几个公开的测试集中的测试具有较高的准确率、召回率和较低的平均绝对误差,可应用于复杂自然场景下的显著性检测。

Visible characteristics of space-based targets based on bidirectional reflection distribution function

A precise modeling method of visible characteristics of the space-based target was presented based on bidirectional reflection distribution function (BRDF). The background characteristics of the space-based target were represented to build models of direct solar radiation and reflected radiation of the Earth based on blackbody radiation theory. The geometry characteristics of the target were analyzed to establish a surface equation of each surface based on its body coordinate system. The material characteristics of the target surface were described by introducing a BRDF model which considers the character of surface Gauss statistics and self-shadow and is obtained by measurement and modeling in advance. The relative positions of the space-based target, the background radiation sources and the observation platform were determined based on coordinate con- version to judge contributing surface of the target to observation system. Then a mathematical model on visible characteristics of the space target for the given optical system was built by summing reflection components of all the surfaces. Simulation of visible characteristics of the space-based target in orbit was achieved according to its given geometrical dimensions, physical parameters and orbital parameters. The results show that the method is effective for analysis on visible characteristics of the space-based target when single reflection is considered and its surface is regularly described in a surface equation, which provides a way to real-time calculation of visible characteristics of the space-based target.