An infrared target intrusion detection method based on feature fusion and enhancement

Infrared target intrusion detection has significant applications in the fields of military defence and intelligent warning. In view of the characteristics of intrusion targets as well as inspection difficulties, an infrared target intrusion detection algorithm based on feature fusion and enhancement was proposed. This algorithm combines static target mode analysis and dynamic multi-frame correlation detection to extract infrared target features at different levels. Among them, LBP texture analysis can be used to effectively identify the posterior feature patterns which have been contained in the target library, while motion frame difference method can detect the moving regions of the image, improve the integrity of target regions such as camouflage, sheltering and deformation. In order to integrate the advantages of the two methods, the enhanced convolutional neural network was designed and the feature images obtained by the two methods were fused and enhanced. The enhancement module of the network strengthened and screened the targets, and realized the background suppression of infrared images. Based on the experiments, the effect of the proposed method and the comparison method on the background suppression and detection performance was evaluated, and the results showed that the SCRG and BSF values of the method in this paper had a better performance in multiple data sets, and it’s detection performance was far better than the comparison algorithm. The experiment results indicated that, compared with traditional infrared target detection methods, the proposed method could detect the infrared invasion target more accurately, and suppress the background noise more effectively.     

Evaluation of infrared camouflage effectiveness via a multi-fractal method

This paper reports an alternative approach to the evaluation of infrared camouflage effectiveness via a multi-fractal method. By calculating multi-fractal spectra of the target region and the background re-gions in an infrared image, the spectrum shape features and the discrete Fréchet distances among these spectra were used to analyze the camouflage effectiveness of the target qualitatively and quantitatively, and the correlation coefficients of the spectra were further used as the index of camouflage effectiveness. It was found that the camouflaged target had better camouflage effectiveness than the target without camouflage in the same one background, and the same one camouflaged target had different camouflage effectiveness in different backgrounds. On the whole, the target matching well with its background had high camouflage effectiveness value. This approach can expand the application of multi-fractal theory in infrared camouflage technology, which should be useful for the research of infrared camouflage mate-rials, the design of camouflage patterns as well as the deployment of military equipment in battlefield.     

装备保障配置地域伪装防护效能定量评估

以易评定或可测量的因素作为评估指标,建立了装备保障配置地域伪装防护效能评估指标体系,运用模糊数学的方法,构造客观的隶属函数,根据给定的特征值参照表,确定了模糊关系矩阵,并在此基础上,结合层次分析法实现了对装备保障配置地域伪装防护效能的定量评估,同时避免了单纯使用专家评估法带来的主观性和评估周期过长等缺点。     

基于转置卷积神经网络的翼型结冰冰形图像化预测方法

结冰问题严重影响飞机飞行安全,结冰智能预测是飞机智能防除冰系统设计和安全设计的重要依据和支撑。为解决复杂冰形在翼面同一位置的法线方向冰形厚度存在多值的问题,提出基于转置卷积神经网络的翼型结冰冰形图像化预测方法。设计预测模型的神经网络结构、损失函数、数据规范等,直接将影响飞机结冰的飞行和大气条件作为输入,以灰度化的冰形图像作为输出。基于NACA0012翼型,通过数值模拟方法生成冰形数据集,同时利用风洞试验结果对数值模拟方法进行验证,以确保生成数据的可信度。构建以飞行速度、温度、液态水含量、平均水微滴直径和结冰时长5项参数作为输入的预测模型,并进行仿真训练和验证。仿真结果表明:所提翼型结冰预测模型不仅能够快速预测翼型冰形,而且在冰体轮廓、结冰上下极限、冰角位置、结冰厚度等主要特征方面也与数值计算结果符合较好。     

MF-CFI: A fused evaluation index for camouflage patterns based on human visual perception

The evaluation index of camouflage patterns is important in the field of military application. It is the goal that researchers have always pursued to make the computable evaluation indicators more in line with the human visual mechanism. In order to make the evaluation method more computationally intelligent, a Multi-Feature Camouflage Fused Index (MF-CFI) is proposed based on the comparison of grayscale, color and texture features between the target and the background. In order to verify the effectiveness of the proposed index, eye movement experiments are conducted to compare the proposed index with existing indexes including Universal Image Quality Index (UIQI), Camouflage Similarity Index (CSI) and Structural Similarity (SSIM). Twenty-four different simulated targets are designed in a grassland background, 28 observers participate in the experiment and record the eye movement data during the observation process. The results show that the highest Pearson correlation coefficient is observed between MF-CFI and the eye movement data, both in the designed digital camouflage patterns and large-spot camouflage patterns. Since MF-CFI is more in line with the detection law of camouflage targets in human visual perception, the proposed index can be used for the comparison and parameter optimization of camouflage design algorithms.     

复杂自然背景中人造目标的分割研究

在以自然景物为背景的图像中,分形维数特征是一种能有效将人造物体从自然背景中分割出来的一种纹理特征.提出了一种基于Gabor滤波器及差分盒维数的分形纹理特征提取方法,该方法依据不同的滤波器尺度分别采用不同尺寸的滑动窗口来计算分形纹理特征.并利用FCM方法实现了对图像的分割.实验表明该方法能很好地对真实自然背景的图像进行分割,并能由此获得人工目标的轮廓图像.     

一种基于Hough变换的线型群体队型识别方法

作战群体的队型是作战群体的重要属性之一,它往往反映了群体中各成员之间的协作关系,直接体现着该群体近期的作战意图、身份及威胁等态势信息。为了给指挥人员的态势评估及军事指挥提供更多深层次的战场信息,从而为其决策提供更好的支持,重点研究了作战群体线型队型的识别问题。利用Hough变换的点线对偶特性,给出了线型队型的模板建模方法,提出了基于参数点聚类的线型队型特征提取方法,进而给出了基于模板匹配的线型队型识别方法。仿真实验表明,该方法是行之有效的。     

面向人机交互的运动想象脑电信号感知算法研究

脑电信号的特征提取与分类识别是脑机交互领域的核心问题。针对运动想象脑电信号的多分类问题,以更好利用包含有用信息的脑电信号频带为目的,提出了基于小波包变换(WPD)和一对多共空间模式(CSP)的特征提取算法。首先使用WPD算法将原始脑电信号分解成一系列子频带,筛选与运动想象活动相关的子频带。然后使用一对多CSP算法进行特征提取。最后对各子频带的特征进行组合并使用BP神经网络进行分类。算法的有效性通过BCI竞赛的基准数据集进行了测试,相交于竞赛结果有了明显提升。     

基于神经网络的柴油机技术状态主元信息提取方法

在柴油机技术状态监测时,表征其技术状态的特征参数有很多,合理提取状态主元信息是一项关键的任务。分析研究了人工神经网络的信息提取原理和方法。以某型坦克柴油机为例,通过柴油机性能检测试验测取了能够反映柴油机技术状态变化的典型特征,建立了O ja神经网络信息提取模型,提取了柴油机技术状态的主元信息。分析结果表明:提取的主元信息能够反映柴油机技术状态随柴油机使用时间的变化趋势。该方法为坦克柴油机的技术状态监测与故障诊断提供了有效手段。     

基于LDA算法的一维距离像特征提取

在线性分辨分析(LDA)基础上,通过遗传算法寻找Fisher准则下最优的线性映射中心和相应的最优映射,使不同模式在特征空间内具有最大的可分离性,并将该算法用于雷达目标一维距离像特征提取与识别中。实验表明,和原算法相比,新算法在特征提取性能和目标正确识别率上有较大提高,说明了算法的有效性。     

基于NNLI技术的齿轮箱故障诊断

将NNLI技术应用到齿轮箱的故障诊断中,提出了基于NNLI的特征提取方法,并将该方法与神经网络结合起来,进一步提出基于NNLI特征提取的神经网络故障诊断方法,给出了两种不同的网络分类器,通过齿轮箱故障诊断实例验证了该方法的有效性。     

Fast-armored target detection based on multi-scale representation and guided anchor

Focused on the task of fast and accurate armored target detection in ground battlefield, a detection method based on multi-scale representation network (MS-RN) and shape-fixed Guided Anchor (SF-GA) scheme is proposed. Firstly, considering the large-scale variation and camouflage of armored target, a new MS-RN integrating contextual information in battlefield environment is designed. The MS-RN extracts deep features from templates with different scales and strengthens the detection ability of small targets. Armored targets of different sizes are detected on different representation features. Secondly, aiming at the accuracy and real-time detection requirements, improved shape-fixed Guided Anchor is used on feature maps of different scales to recommend regions of interests (ROIs). Different from sliding or random anchor, the SF-GA can filter out 80% of the regions while still improving the recall. A special detection dataset for armored target, named Armored Target Dataset (ARTD), is constructed, based on which the comparable experiments with state-of-art detection methods are conducted. Experimental results show that the proposed method achieves outstanding performance in detection accuracy and efficiency, especially when small armored targets are involved.     

基于KP CA的作战仿真实验数据特征提取方法

针对作战仿真分析过程中各作战要素的复杂性与非线性,研究了一种基于KPCA的作战仿真实验数据特征提取方法。该方法描述了KPCA特征提取的原理和算法,并将其应用于作战仿真实验数据的空间降维,根据累积贡献率确定新特征的数量。仿真结果表明,该方法与PCA相比具有主成份特征明显、贡献率集中等优点,能够有效综合原始数据的非线性特征,降低原始数据的维数。     

基于KPCA的作战仿真实验数据特征提取方法

针对作战仿真分析过程中各作战要素的复杂性与非线性,研究了一种基于KPCA的作战仿真实验数据特征提取方法。描述了KPCA特征提取的原理和算法,并将其应用于作战仿真实验数据的空间降维,根据累积贡献率确定新特征的数量。仿真结果表明,该方法与PCA相比具有主成份特征明显、贡献率集中等优点,能够有效综合原始数据的非线性特征,降低原始数据的维数。     

Fuzzy recognition of missile borne multi-line array infrared detection based on size calculating

In order to improve the infrared detection and discrimination ability of the smart munition to the dy-namic armor target under the complex background, the multi-line array infrared detection system is established based on the combination of the single unit infrared detector. The surface dimension features of ground armored targets are identified by size calculating solution algorithm. The signal response value and the value of size calculating are identified by the method of fuzzy recognition to make the fuzzy classification judgment for armored target. According to the characteristics of the target signal, a custom threshold de-noising function is proposed to solve the problem of signal preprocessing. The multi-line array infrared detection can complete the scanning detection in a large area in a short time with the characteristics of smart munition in the steady-state scanning stage. The method solves the disadvan-tages of wide scanning interval and low detection probability of single unit infrared detection. By reducing the scanning interval, the number of random rendezvous in the infrared feature area of the upper surface is increased, the accuracy of the size calculating is guaranteed. The experiments results show that in the fuzzy recognition method, the size calculating is introduced as the feature operator, which can improve the recognition ability of the ground armor target with different shape size.     

基于云模型的地空导弹武器假目标伪装效果评价

地空导弹武器假目标伪装效果评价中定性指标具有不确定性,云模型理论是定性概念与其定量表示之间的不确定性转换的数学工具,因此在构建地空导弹假目标伪装效果评价指标体系的基础上,提出基于云模型的假目标伪装效果评价方法,以解决评价指标的不确定性问题．通过实例的计算结果,验证了基于云模型的评价方法的可行性．研究结论表明应用云模型的评价结果具有直观性和科学性,该方法对伪装评价研究有一定的参考价值．     

基于粗糙集和支持向量机的火炮内膛疵病识别方法

火炮内膛疵病智能识别是火炮内膛窥测的最终目标,它涉及到内膛疵病的特征提取和疵病识别两方面。首先建立了包括疵病形状、纹理与颜色特征的火炮内膛疵病特征体系;并采用模糊粗糙集理论分析了各疵病特征对疵病识别的敏感性,由此优化了疵病特征体系,降低了疵病特征维数;建立了最小二乘支持向量机小样本、非线性数据特征的多疵病分类器,提高了疵病识别效率和质量。     

矩阵变换特征与码序列联合学习的卷积码识别方法

现有基于深度学习的卷积码识别方法仍存在参数规模较大、识别性能较弱等不足。针对该问题,提出了一种基于矩阵变换特征与码序列联合学习的卷积码识别方法。将接收到的码字序列排列成矩阵形式,利用软信息剔除可靠性较低的码字,通过一种新的矩阵变换算法得到特征矩阵。在识别时,将原始码字矩阵和特征矩阵输入到具有多模态数据联合学习能力的网络模型,在神经网络中完成特征的提取融合与卷积码的识别。仿真结果表明,所提方法性能明显优于现有基于深度学习的识别方法,特别是对于高码率卷积码;当码率较低时,同样优于传统识别方法。当信噪比达到5 dB时,25种不同参数卷积码的识别率均可达到100%。     

无监督特征学习的人体活动识别

针对人的局限性可能会导致在提取特征中丢失重要信息,从而影响最终的识别效果问题,提出无监督特征学习技术的惯性传感器特征提取方法。其核心思想是使用无监督特征学习方法学习多个特征映射,再将所有特征映射拼接起来形成最终的特征计算方法。其优点是不会造成重要信息的损失,而且可以显著减少所使用的无监督特征学习模型的规模。为了验证所提出的特征提取方法在活动识别中的有效性,运用一个公开的活动识别数据集,使用三种常用无监督模型进行特征提取,并使用支持向量机进行活动识别。实验结果表明,特征提取方法取得了良好的效果,与其他方法相比具有一定的优势。     

参照化流形空间融合学习的敏感特征提取与异常检测方法

针对遥测振动信号冲击强、响应周期短、共振频带宽和小样本等特点导致异类模式识别率低的问题,提出基于参照化流形空间融合学习的敏感特征提取与异常检测方法。采用多尺度分析方法将信号正交无遗漏地分解到各尺度带中,提取多尺度特征构造高维特征集；以相同的正常信号样本结合相同类型的异常样本建立专属参照化模型单元,采用线性流形学习获取各参照化模型单元多尺度流形特征差异,增强异常特征的敏感性。融合各参照化模型单元的投影矩阵对原始特征集进行升维再学习,获取低维多尺度敏感流形特征；输入到分类器实现对未知样本状态辨识。实测信号处理结果验证了算法的有效性。