Gabor-CNN for object detection based on small samples

Object detection models based on convolutional neural networks (CNN) have achieved state-of-the-art performance by heavily rely on large-scale training samples. They are insufficient when used in specific applications, such as the detection of military objects, as in these instances, a large number of samples is hard to obtain. In order to solve this problem, this paper proposes the use of Gabor-CNN for object detection based on a small number of samples. First of all, a feature extraction convolution kernel library composed of multi-shape Gabor and color Gabor is constructed, and the optimal Gabor convolution kernel group is obtained by means of training and screening, which is convolved with the input image to obtain feature information of objects with strong auxiliary function. Then, the k-means clustering algorithm is adopted to construct several different sizes of anchor boxes, which improves the quality of the regional proposals. We call this regional proposal process the Gabor-assisted Region Proposal Network (Gabor-assisted RPN). Finally, the Deeply-Utilized Feature Pyramid Network (DU-FPN) method is proposed to strengthen the feature expression of objects in the image. A bottom-up and a top-down feature pyramid is constructed in ResNet-50 and feature information of objects is deeply utilized through the transverse connection and integration of features at various scales. Experimental results show that the method proposed in this paper achieves better results than the state-of-art contrast models on data sets with small samples in terms of accuracy and recall rate, and thus has a strong application prospect.     

联合生成对抗网络和检测网络的SAR图像目标检测

针对合成孔径雷达图像目标检测中存在的样本获取困难且数量有限问题,提出了联合生成对抗网络和检测网络的学习模型。利用原始训练集对特别设计的超快区域卷积神经网络进行预训练;再通过基于注意力机制的深度学习生成对抗网络生成高质量合成样本,并输入检测网络进行预测;依据预测信息和概率等价类属标签分配策略为新生样本提供注释信息,并以一定占比对原始训练集进行扩充;利用扩充数据集对检测网络进行再训练。多组仿真实验证明,所提框架能够有效提升网络检测效率和性能。     

Visual-attention gabor filter based online multi-armored target tracking

The multi-armored target tracking (MATT) plays a crucial role in coordinated tracking and strike. The occlusion and insertion among targets and target scale variation is the key problems in MATT. Most state-of-the-art multi-object tracking (MOT) works adopt the tracking-by-detection strategy, which rely on compute-intensive sliding window or anchoring scheme in detection module and neglect the target scale variation in tracking module. In this work, we proposed a more efficient and effective spatial-temporal attention scheme to track multi-armored target in the ground battlefield. By simulating the structure of the retina, a novel visual-attention Gabor filter branch is proposed to enhance detection. By introducing temporal information, some online learned target-specific Convolutional Neural Networks (CNNs) are adopted to address occlusion. More importantly, we built a MOT dataset for armored targets, called Armored Target Tracking dataset (ATTD), based on which several comparable experiments with state-of-the-art methods are conducted. Experimental results show that the proposed method achieves outstanding tracking performance and meets the actual application requirements.     

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。     

军事领域细粒度识别技术与应用

战争的信息化程度不断加深对军事侦察提出了更高要求。军事目标识别作为军事侦察的主要任务之一,需要能够处理细粒度军事目标,为人员提供更加详细的目标信息。但传统的粗粒度目标识别方法无法得到目标的细粒度信息。因此,如何识别细粒度目标成为目前军事侦察亟需解决的问题。针对该问题,本文结合军事领域的实际需求,对细粒度识别技术的发展现状进行了分析,提出了军事领域细粒度识别技术应用流程的数据集构建、模型设计和终端部署三个阶段,同时,从无人机侦察、遥感侦察和单兵侦察三个方向分析了细粒度识别的应用前景。经过分析,军事领域细粒度识别技术已经具备实际运用条件,具备良好的应用价值。     

一种定标缺失情况下的高光谱目标识别方法

高光谱遥感图像识别在民用和军事领域有着广泛的应用。在缺乏定标信息、缺乏同步观测大气光学参数情况下,对高光谱图像进行地物识别尚没有系统有效的方法,制约了其在定量遥感方向的应用。对此提出了一种利用粒子群算法优化6S模型参数基础上的高光谱遥感数据校正方法,并将其应用于定标缺失情况下的目标识别中。实验表明:在对遥感图像利用少许先验信息选择参数进行校正后,分类准确率为76.25%。而利用粒子群算法优化参数的6S校正后,分类准确率提高到91.58%,目标识别准确率得到了有效提高。     

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.     

Arbitrary-oriented target detection in large scene sar images

Target detection in the field of synthetic aperture radar (SAR) has attracted considerable attention of researchers in national defense technology worldwide, owing to its unique advantages like high resolution and large scene image acquisition capabilities of SAR. However, due to strong speckle noise and low signal-to-noise ratio, it is difficult to extract representative features of target from SAR images, which greatly inhibits the effectiveness of traditional methods. In order to address the above problems, a framework called contextual rotation region-based convolutional neural network (RCNN) with multilayer fusion is proposed in this paper. Specifically, aimed to enable RCNN to perform target detection in large scene SAR images efficiently, maximum sliding strategy is applied to crop the large scene image into a series of sub-images before RCNN. Instead of using the highest-layer output for proposal generation and target detection, fusion feature maps with high resolution and rich semantic information are constructed by multilayer fusion strategy. Then, we put forwards rotation anchors to predict the minimum circumscribed rectangle of targets to reduce redundant detection region. Furthermore, shadow areas serve as contextual features to provide extraneous information for the detector identify and locate targets accurately. Experimental results on the simulated large scene SAR image dataset show that the proposed method achieves a satisfactory performance in large scene SAR target detection.     

基于部件模型的无人机系统小样本车辆目标识别方法

对地目标检测与识别是无人机系统典型任务之一,但受限于任务特殊性,往往难以获取足够的目标样本数据以实现高可靠的目标识别。为此,结合人的认知特性,提出一种基于部件模型的小样本车辆目标识别方法,可有效提高无人机感知能力。采用视觉显著性检测与物体性检测相结合的检测方法,提取目标可能区域;采用基于图论的GrabCut方法与最大类间方差法相结合的分割方法,分割目标并提取目标内部件;采用基于概率图模型的部件识别方法,通过将部件轮廓稀疏表示为条件随机场,并进行概率推理实现部件识别;采用基于贝叶斯的目标识别方法完成目标是否为车辆的判断。通过无人机拍摄的车辆图像验证表明,算法可在样本较少、光照变化、存在遮挡等情况下,以较高准确率检测并识别出车辆目标,同时识别算法具有一定可解释性。     

低分辨雷达的目标特征提取方法

基于现役低分辨警戒雷达 ,研究了进行目标分类和识别的途径 ,提出了基于波形特征和时间谱信息的目标分类和识别方法 ,试验分析了基于目标波形信息的特征 ,得出目标波形信息可用于目标识别的结论。现场试验表明 ,该方法对目标大小分类和架次识别有好的效果。     

【专题】基于深度学习及FPGA的装备目标检测研究

本文应用深度学习技术实现海天背景下基于可见光、红外方式成像的舰船及角反、烟幕干扰的目标检测,这也是反舰导弹作战使用的关键技术之一。采集的可见光与红外成像目标检测数据集涵盖实施典型干扰下的态势场景,贴近实战;结合四种不同的目标检测机制,选取YOLOV3、Faster R-CNN、SSD及CenterNet四种典型模型分别进行训练与验证,通过对比分析进一步提高弱小目标、复杂干扰态势的的检测,可以实现端到端的高精度装备目标检测模型。在确保精度的前提下基于现场可编程门阵列（FPGA）进行软硬件协同设计,通过对比分析选定基于Vitis AI的实施方案,经过模型的量化、编译与优化,可在保证检测效率的前提下快速实现模型的小型化部署,便于进行装备移植。研究结果表明,该研究内容可有效提高现役反舰导弹目标检测的准确率。     

Combined proportional navigation law for interception of high-speed targets

A new proportional navigation (PN) guidance law, called combined proportional navigation (CPN), is proposed. The guidance law is designed to intercept high-speed targets, which is a common case for ballistic targets. The range of target-to-interceptor speed ratio during target interception is derived when guidance laws are applied in high-speed targets interception, and the effectiveness of negative navigation ratio in the PN-based guidance law is proven analytically in some lemmas. Based on the lemmas, the lateral acceleration command of CPN is defined, and the solution to the appearance of singularity in time-varying navigation ratio is given. The simulation results show that CPN can determine head-on engagement (as PN) or tail-chase engagement (as RPN) through initial path angle compared with PN and retro proportional navigation (RPN), and can adjust the value of navigation ratio for head-on engagement or tail-chase engagement. Therefore, the capture region of CPN is larger than that of other guidance laws using PN-based methods.     

一种新的Gabor小波支持向量机人脸识别算法

提出了一种新的基于Gabor小波特征重组的支持向量机人脸识别方法。该方法首先计算5个尺度和8个方向的Gabor小波变换结果,再把不同人脸中的同一尺度和方向的变换结果进行特征重组,得到40个新特征矩阵,分别利用PCA方法降维去噪,最后构造40个支持向量机分类器并采用选票决策机制决定识别结果。实验结果表明,该方法不仅拓宽了主元分析法中累积方差贡献率可选范围,并在一定程度上解决了核参数选择难的问题,同时取得了理想识别效果。     

基于支持向量机的多分类军事目标识别应用

针对现代战场信息化程度的不断提高,电磁环境日趋复杂,侦查目标难以准确地识别情况,提出了运用支持向量机多分类器对军事侦查目标进行有效识别.结构风险最小化地支持向量机分类方法是小样本情况下统计机器学习的经典,具有速度快、泛化能力强等特点.用该算法建模军事目标的识别问题,达到了较高的识别准确率.所以应用在对侦查目标的识别上具有良好的效果,在军事应用上有较广阔的前景.     

基于多级Sigmoid神经网络的城市交通场景理解

交通场景的理解是交通监控、汽车安全辅助驾驶的基础.提出一种基于多级Sigmoid神经网络的城市交通环境理解方法.将5个3D结构特征与物体外观特征相结合表征城市交通环境,为了提高交通环境识别率,采用多级Sigmoid神经网络(MSNN)进行图像分割与识别.在公共测试视频数据库CamVid dataset 进行实验,实验结果表明了该方法的有效性.     

基于模糊模式识别的战场目标识别

分析战场目标的结构、材料、征候、特征及辐射原理等存在的差异,运用模糊模式识别方法,建立了战场目标识别的数学模型,给出了目标识别的详细步骤和方法:选取目标特征量、构造标准模糊集合、构造待识别模糊集合、应用择近原则进行目标识别,并通过算例,得到一些有价值的结论。模型和方法可供C3I系统快速准确的识别战场目标。     

基于马尔科夫决策的目标选择策略

目标选择是军事计划的关键要素之一。基于马尔科夫决策方法,解决具有复杂目标间关联的多阶段目标选择问题。使用与或树描述目标体系各层状态间的影响关联,并以目标体系整体失效为求解目的,建立了基于离散时间MDP的多阶段打击目标选择模型。在LRTDP算法基础上提出一种启发式方法,通过判断从当前目标体系状态到达体系失效状态的演化过程中的可能资源消耗和失败概率,来提供对当前状态的评估值,该方法能有效排除问题搜索空间中不能到达体系失效目的的中间状态,压缩了由于目标间复杂关联而增长的巨大状态空间。用实验验证了该方法有效性,实验结果表明,该方法直观实用,对目标间具有复杂关联关系的目标打击决策有一定参考价值。     

Gabor二进制编码异源图像匹配方法

异源图像匹配是图像处理领域尚未解决的问题。其中,合成孔径雷达图像与光学图像差异较大,用现有方法匹配通常难以得到满意结果。针对这个问题,提出一种基于Gabor编码的异源图像匹配方法:选取一组Gabor滤波器,分别对大图和小图进行Gabor卷积;采用池化方法对卷积结果进行压缩表示;对池化结果二值化并转换为二进制表示得到Gabor二进制编码特征;采用二进制位操作计算实时图与基准图对应窗口特征的相似性,相似性最大值对应图像匹配结果。本方法采用二进制对图像进行描述,减少了计算量,同时也更好地描述了异源图像间的共性特征。实验结果表明,本方法具有较高的匹配概率,计算时间少于现有方法。     

基于递归神经网络的飞机目标识别方法

针对宽带高距离分辨全极化雷达体制,提出了一种基于实时递归神经网络算法的飞机目标自动识别方法,实现了全极化下五类飞机目标的自动识别。实验结果表明,递归神经网络用于飞机目标识别是有效可行的。     

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.