一种基于知识的港口识别与理解方法

港口识别技术在军事上有着重要的应用前景。采用由上而下的知识驱动策略,充分利用了港口的图像特征,在低层处理中采用自适应平滑技术(Saint-Marc)进行预处理;中层处理提取港口重要对象目标(包括水域、防波堤和港口轮廓),用阈值分割和区域增长相结合的算法提取水域,用结构特征识别防波堤和港口轮廓;最后在高层处理中借用语义树的概念分析港口重要对象间的关系,采用概率松弛法进行港口的目标检测与识别。     

基于PSO-Markov联合模型的无人机路径规划

利用PSO算法对无人机在侦查任务中的路径进行实时规划,将算法与地形、飞行角度、油量等约束条件结合起来,有效地缩减了搜索空间;同时为了在任务中能够更好地掌握无人机完成任务与生存的概率以及整个路径的代价,引入了一种可用于计算风险和评估任务威胁的生存性联合模型,该模型使用了八状态马尔科夫链来描述无人机的状态。仿真实验结果表明,该方法可以有效地检测航路中飞机的各种状态的概率,并以此对整个航路进行评估。     

红外目标分割方法研究

红外目标分割算法对红外目标检测、跟踪具有非常重要的价值。本文利用背景和目标灰度特征,提出一种实现红外目标有效分割的方法,克服红外目标内部温度不稳定造成的误分割问题。本文方法首先采用基于灰度-显著度最大相关准则的二维直方图分割算法进行图像分割;然后,在分割后二值图上进行基于随机种子点选取的区域增长,提取背景;最后,采用形态学方法优化分割结果。相对传统的红外目标检测算法,这种算法具有更好的抗干扰能力,更强的鲁棒性。不仅可以应用于红外图像的目标分割,而且可以应用于其他类似的目标分割问题。     

深度多属性增强水声目标识别方法

被动声纳系统由于其隐蔽性好的特点在军事任务中发挥着重要作用。针对被动水声目标识别问题,开展了水声目标多属性特征提取与识别方法研究。利用深度学习方法从舰船辐射噪声中提取目标多属性特征并识别水声目标。提出了深度多属性增强水声目标识别方法,该方法可以从时域舰船辐射噪声中提取水声目标多属性特征及多属性之间的相关性特征,并用来增强深度模型对水声目标类别属性的表达能力。基于海试实测数据的6类水声目标识别实验结果表明,相比于不考虑多属性的识别方法,提出的深度多属性增强水声目标识别方法的平均正确识别率提高了3.6%~18.2%,并且具有更好的识别稳定性。     

基于航拍视频的车辆目标跟踪方法

以无人机拍摄的运动车辆为研究对象,针对航拍视频中的某一车辆目标,研究其目标跟踪方法。为准确预测车辆在未来帧中出现的位置,提出基于K邻域的目标预测算法,对于车辆目标可能会出现被全部遮挡的情况,提出基于车辆运动状态估计的抗遮挡算法,在目标检测过程中,针对可能会有多个目标被检测出来的情况,提出多特征融合的图像匹配算法以对检测结果进行匹配。将上述算法相结合,形成车辆目标跟踪方法。测试结果表明,提出的目标跟踪方法平均准确率达到了91.1%,准确率相对于常见的目标跟踪算法提升了约6.35%。     

基于动态时间规整算法的车辆目标分类研究

将动态时间规整(Dynamic Time Warping)算法应用于地面车辆目标的分类识别中。基于微多普勒效应原理,建立了轮式车辆和履带式车辆雷达回波模型,对两种车辆目标微多普勒信号的差异性进行了分析,并结合实测数据,验证了理论分析的正确性。在杂波抑制及速度归一化处理的基础上,利用动态时间规整算法,将提取出的车辆目标的累积失真距离作为目标分类识别的依据,实现了轮式车辆和履带式车辆的自动分类。基于实测数据的实验结果表明,该方法在不同信噪比条件下都具有较好的分类性能。     

基于显著性检测与特征匹配的目标识别方法

为加强目标识别的可靠性,提出了一种基于显著性检测与特征匹配的目标识别方法。提出了改进的显著性检测方法提取显著性目标,利用改进的特征检测子与快速视网膜特征描述子(Fast Retina Keypoint,FREAK)对目标与模板库进行并行匹配,最后根据平均匹配率完成目标识别。实验结果表明,改进的显著性检测方法较传统方法具有更高的检测精度和目标完整性,改进的特征检测子较传统方法具有更强的鲁棒性与实时性,基于显著性检测与特征匹配的目标识别方法能够实现可靠性较强的目标实时识别。     

遥测参数数据载荷状态判别集成学习方法

针对载荷单机设备遥测参数维度高、数据量大、存在类别不平衡、无法直观判别单机设备运行情况等问题,考虑到航天任务对可解释性的要求,提出一种基于信息增益参数特征选择和集成学习方法的载荷单机状态快速识别方法。采用统计量性质和信息增益子集搜索方法对遥测数据进行特征筛选降维,通过集成学习模型算法实现载荷单机设备状态的自适应识别分类。所提方法将信息增益的参数分类信息量评价准则和集成学习拟合能力强、类别不平衡下准确率高和抗噪能力强等优点相结合,兼顾模型特征和结果的可解释性,提供了重点参数发现功能。采用科学卫星任务真实载荷遥测参数数据对该方法进行了验证,整体识别准确率高于90%,少数样本亦可准确识别,整体效果可达到在轨任务要求,证明了所提方法的有效性和实用性。     

不确定环境下无人机区域目标搜索及载荷参数影响

针对不确定环境下无人机区域搜索问题,建立了实时探测更新的搜索方法,提出了机载光电载荷参数优化配置策略。建立了基于二维离散网格的无人机区域搜索模型,采用概率地图描述目标信息的实时获取与更新;引入不确定度指标、目标网格的重访和网格探测次数控制,建立搜索目标函数;建立了基于粒子群算法的搜索路径滚动优化方法;通过对任务区域平均探测时间步数和误判概率的估计分析,建立了机载光电载荷参数优化配置策略。使用蒙特卡洛方法验证了区域搜索方法的有效性和光电载荷参数配置对搜索效率、误判概率的影响。     

基于卷积神经网络的无人机图像模糊类型识别

为了提高无人机图像模糊类型识别的准确率,提出一种基于卷积神经网络(Convolutional Neural Network,CNN)的无人机图像模糊类型识别方法。通过样本预处理策略对无人机模糊图像样本进行处理,提高了方法的识别效率,同时降低了错误率。提出一种适用于模糊图像灰度频谱图的卷积神经网络结构,并利用训练样本对网络进行训练,增强了网络结构的针对性,提高了训练模型的识别准确率。利用测试样本对训练的网络模型进行测试,验证方法的鲁棒性。实验结果表明,将卷积神经网络应用于图像模糊类型识别,取得了良好的效果,针对实验环境下的无人机运动、离焦和大气散射3种模糊图像类型的识别准确率较高,所提方法的鲁棒性强、实用价值大。     

Multi-scale traffic vehicle detection based on faster R-CNN with NAS optimization and feature enrichment

It well known that vehicle detection is an important component of the field of object detection. However, the environment of vehicle detection is particularly sophisticated in practical processes. It is compara-tively difficult to detect vehicles of various scales in traffic scene images, because the vehicles partially obscured by green belts, roadblocks or other vehicles, as well as influence of some low illumination weather. In this paper, we present a model based on Faster R-CNN with NAS optimization and feature enrichment to realize the effective detection of multi-scale vehicle targets in traffic scenes. First, we proposed a Retinex-based image adaptive correction algorithm (RIAC) to enhance the traffic images in the dataset to reduce the influence of shadow and illumination, and improve the image quality. Second, in order to improve the feature expression of the backbone network, we conducted Neural Architecture Search (NAS) on the backbone network used for feature extraction of Faster R-CNN to generate the optimal cross-layer connection to extract multi-layer features more effectively. Third, we used the object Feature Enrichment that combines the multi-layer feature information and the context information of the last layer after cross-layer connection to enrich the information of vehicle targets, and improve the robustness of the model for challenging targets such as small scale and severe occlusion. In the imple-mentation of the model, K-means clustering algorithm was used to select the suitable anchor size for our dataset to improve the convergence speed of the model. Our model has been trained and tested on the UN-DETRAC dataset, and the obtained results indicate that our method has art-of-state detection performance.     

自然场景车标数据集的构建及其应用

车标作为车辆身份的关键特征之一,在车辆的监控与辨识中发挥着重要作用。由于自然场景复杂多变,对其中的车标进行准确识别仍具有很大的挑战性。目前公开数据库很少且存在诸多局限,导致研究缺乏可信度和实用性。本文建立了一个面向自然场景的全新数据集,包含多种采集环境下的10 324幅、67类车辆图像。基于此数据集开展应用研究,提出一个目标检测与深度学习相结合的车标识别方法,包括车标区域定位和车标种类预测两大步骤。实验表明,该方法对复杂背景有较强的适应性,在涉及30种车标的分类任务中达到89.0%的总体识别率。     

亚音速飞行目标气动噪声方位角估计技术

亚音速飞行弹道气动声源是宽带非平稳噪声。提出基于小波函数的波达方向估计算法,并采用时频分析方法进行特征分析,获取气动噪声显著目标特性。通过优化时间-空间谱特征,对在时频域空间谱的目标信号进行优化,从而增强目标信号在空间谱上的显著性,最终有效实现亚音速飞行弹道气动声源的角度估计。实验数据验证表明,基于时频分析阵列信号处理模型,可以更好地实现亚音速飞行目标气动噪声方位角估计。     

基于正交实验设计的UAV编队配系优化方法

针对多无人机执行对地攻击作战任务的背景,建立了编队对地攻击模型,提出了基于正交实验设计的编队配系优化方法。在考虑多机协同作战因素下,构建了编队目标分配的基本模型;以探测、识别和杀伤为基本过程,构建了攻击过程模型;以空袭方付出代价、防空方毁伤程度和作战效率为依据,构建了目标函数模型,分析了模型中中间变量与目标函数之间的关系;利用正交实验设计原理,研究了编队配系优劣的评价方法。实例分析表明,该方法能够在已有的资源约束条件下,给出编队的最优配系方案。     

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.     

Visual-simulation region proposal and generative adversarial network based ground military target recognition

Ground military target recognition plays a crucial role in unmanned equipment and grasping the battlefield dynamics for military applications, but is disturbed by low-resolution and noisy-representation. In this paper, a recognition method, involving a novel visual attention mechanism-based Gabor region proposal sub-network (Gabor RPN) and improved refinement generative adversarial sub-network (GAN), is proposed. Novel central–peripheral rivalry 3D color Gabor filters are proposed to simulate retinal structures and taken as feature extraction convolutional kernels in low-level layer to improve the recognition accuracy and framework training efficiency in Gabor RPN. Improved refinement GAN is used to solve the problem of blurry target classification, involving a generator to directly generate large high-resolution images from small blurry ones and a discriminator to distinguish not only real images vs. fake images but also the class of targets. A special recognition dataset for ground military target, named Ground Military Target Dataset (GMTD), is constructed. Experiments performed on the GMTD dataset effectively demonstrate that our method can achieve better energy-saving and recognition results when low-resolution and noisy-representation targets are involved, thus ensuring this algorithm a good engineering application prospect.     

混合不确定条件下的飞行器级间分离可靠性分析

为量化飞行器级间分离过程随机不确定性和认知不确定性的综合影响,结合概率和区间理论混合模型特点,提出了一种基于随机和区间理论混合模型的飞行器级间分离可靠性分析方法。面向高超声速飞行器分离任务需求,建立分离动力学仿真模型,针对级间分离结构的几何特点,设计了一种快速碰撞检测方法,进而构建了分离任务的可靠性分析混合模型。通 过将该模型转化为随机可靠性分析的无约束优化问题,考虑分离过程中复杂外力及力矩导致功能函数高度非线性的特点,利用高效全局优化和主动学习Kriging方法实现无约束优化问题高效求解。结合实例表明,该方法能够准确描述混合不确定性因素对飞行器分离过程的影响,给出了飞行器分离任务可靠性区间,可为飞行器分离方案的精细化设计提供决策支持。     

基于灰色关联的预警系统目标识别

针对弹道导弹预警系统目标识别任务的特点,通过分析弹道导弹和飞机目标间的运动特性差异,采用灰色关联分析方法建立了目标类型识别模型,给出了进行目标类型识别的具体步骤。该方法直接从雷达测量数据出发,具有简单、准确的优点。具体的算例验证了基于灰色关联分析的目标类型识别模型应用于目标识别的可行性和有效性。     

Bidirectional parallel multi-branch convolution feature pyramid network for target detection in aerial images of swarm UAVs

In this paper, based on a bidirectional parallel multi-branch feature pyramid network (BPMFPN), a novel one-stage object detector called BPMFPN Det is proposed for real-time detection of ground multi-scale targets by swarm unmanned aerial vehicles (UAVs). First, the bidirectional parallel multi-branch convolution modules are used to construct the feature pyramid to enhance the feature expression abilities of different scale feature layers. Next, the feature pyramid is integrated into the single-stage object detection framework to ensure real-time performance. In order to validate the effectiveness of the proposed algorithm, experiments are conducted on four datasets. For the PASCAL VOC dataset, the proposed algorithm achieves the mean average precision (mAP) of 85.4 on the VOC 2007 test set. With regard to the detection in optical remote sensing (DIOR) dataset, the proposed algorithm achieves 73.9 mAP. For vehicle detection in aerial imagery (VEDAI) dataset, the detection accuracy of small land vehicle (slv) targets reaches 97.4 mAP. For unmanned aerial vehicle detection and tracking (UAVDT) dataset, the proposed BPMFPN Det achieves the mAP of 48.75. Compared with the previous state-of-the-art methods, the results obtained by the proposed algorithm are more competitive. The experimental results demonstrate that the proposed algorithm can effectively solve the problem of real-time detection of ground multi-scale targets in aerial images of swarm UAVs.     

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.