Sea fog detection based on unsupervised domain adaptation

Sea fog detection with remote sensing images is a challenging task. Driven by the different image characteristics between fog and other types of clouds, such as textures and colors, it can be achieved by using image processing methods. Currently, most of the available methods are datadriven and relying on manual annotations. However, because few meteorological observations and buoys over the sea can be realized, obtaining visibility information to help the annotations is difficult. Considering t...     

样本标签污染条件下的雷达辐射源个体识别技术

针对辐射源个体识别(Specific Emitter Identification,SEI)中由于数据集存在错误标签导致识别率下降的问题,提出了 1种有监督和无监督融合的错误标签识别和纠正方法。首先采用无监督密度峰值聚类方法将数据集中出现的标签错误样本找出,再使用 K折交叉实验对这些标签异常的样本进行预测投票,将得票数多的标签作为错误标签纠正的结果。经过清洗的数据集再通过卷积神经网络进行训练,得到 1个较为理想的辐射源个体识别的网络模型,保证了在样本污染条件下,辐射源个体识别网络仍能具有较好的识别率。文章所提方法的识别率相比未经处理的数据集的识别率在标签错误率小于 30%时平均提高 3.3%;在标签错误率大于 30%时,也能使个体识别率达到 90%左右,验证了文章所提方法在对错误标签的识别和纠正上可以取得较好的效果。     

An online ensemble semi-supervised classification framework for air combat target maneuver recognition

Online target maneuver recognition is an important prerequisite for air combat situation recognition and maneuver decision-making. Conventional target maneuver recognition methods adopt mainly supervised learning methods and assume that many sample labels are available. However, in real-world applications, manual sample labeling is often time-consuming and laborious. In addition, airborne sensors collecting target maneuver trajectory information in data streams often cannot process information in real time. To solve these problems, in this paper, an air combat target maneuver recognition model based on an online ensemble semi-supervised classification framework based on online learning, ensemble learning, semi-supervised learning, and Tri-training algorithm, abbreviated as Online Ensemble Semi-supervised Classification Framework (OESCF), is proposed. The framework is divided into four parts: basic classifier offline training stage, online recognition model initialization stage, target maneuver online recognition stage, and online model update stage. Firstly, based on the improved Tri-training algorithm and the fusion decision filtering strategy combined with disagreement, basic classifiers are trained offline by making full use of labeled and unlabeled sample data. Secondly, the dynamic density clustering algorithm of the target maneuver is performed, statistical information of each cluster is calculated, and a set of micro-clusters is obtained to initialize the online recognition model. Thirdly, the ensemble K-Nearest Neighbor (KNN)-based learning method is used to recognize the incoming target maneuver trajectory instances. Finally, to further improve the accuracy and adaptability of the model under the condition of high dynamic air combat, the parameters of the model are updated online using error-driven representation learning, exponential decay function and basic classifier obtained in the offline training stage. The experimental results on several University of California Irvine (UCI) datasets and real air combat target maneuver trajectory data validate the effectiveness of the proposed method in comparison with other semi-supervised models and supervised models, and the results show that the proposed model achieves higher classification accuracy.     

A Sequential Approach to Target Discrimination

The Wald sequential probability ratio test is applied to the discrimination of targets observed by a radar or other sensor and a form for the classifier involving linear predictive filtering is developed. In this sequential approach, a target is illuminated with consecutive pulses until a classification of the target can be made to within a prescribed probability of error. Because of the linear-predictive formulation, the computational and storage requirements for the classifier are related only to the number of returns necessary to predict the target signature and not to the length of signature observed; a classifier with modest storage and computational requirements can be employed to process signatures consisting of an arbitrarily large number of returns. The classifier is based on some well-known results in mean-square filtering theory and has a simple intuitive interpretation. The classifier structure can also be related to autoregressive time series analysis and innovations process concepts and has an interpretation in the frequency domain in terms of the maximum entropy and maximum likelihood spectral estimates for the target signatures.     

Real-time object tracking via least squares transformation in spatial and Fourier domains for unmanned aerial vehicles

This paper addresses the problem of real-time object tracking for unmanned aerial vehicles. We consider the task of object tracking as a classification problem. Training a good classifier always needs a huge number of samples, which is always time-consuming and not suitable for realtime applications. In this paper, we transform the large-scale least-squares problem in the spatial domain to a series of small-scale least-squares problems with constraints in the Fourier domain using the correlation filter technique. Then, this problem is efficiently solved by two stages. In the first stage, a fast method based on recursive least squares is used to solve the correlation filter problem without constraints in the Fourier domain. In the second stage, a weight matrix is constructed to prune the solution attained in the first stage to approach the constraints in the spatial domain. Then, the pruned classifier is used for tracking. To evaluate proposed tracker's performance, comprehensive experiments are conducted on challenging aerial sequences in the UAV123 dataset. Experimental results demonstrate that proposed approach achieves a state-ofthe-art tracking performance in aerial sequences and operates at a mean speed of beyond 40 frames/s. For further analysis of proposed tracker's robustness, extensive experiments are also performed on recent benchmarks OTB50, OTB100, and VOT2016.     

基于加权模糊C均值聚类的图像分割算法

模糊C均值(FCM)算法用于灰度图像分割是一种非监督模糊聚类后再标定的过程,适合灰度图像中存在着模糊和不确定性的特点。但是这种算法存在着本质上的缺陷,就是仅利用了图像的灰度信息,而没有考虑像素的空间信息,使得其对于实际的含有噪声的图像分割效果不理想。因此,提出了一种新的加权模糊C均值聚类算法,实践证明,该方法可以有效地、实时地把目标从背景中分割出来,并具有较强的鲁棒性。     

基于1-DISVM的聚类模型及直升机齿轮箱故障诊断应用

针对当前故障诊断中存在的训练样本少、知识难获取的问题,结合SVM小样本学习的特点,提出一种基于SVM的自学习聚类模型。通过改进无监督1-SVM算法上的不足,形成一种改进决策1-SVM(1-DISVM)算法,由此构建了多模式训练与分类算法,并设计出基于1-DISVM的自学习聚类模型。最后对其进行仿真验证,并应用于直升机齿轮箱的故障诊断,结果表明该方法能从少量样本中自学习输入模式的内在规律,自适应地对未知故障模式进行准确地分类识别。     

A linear ADRC-based robust high-dynamic double-loop servo system for aircraft electro-mechanical actuators

Compared with traditional hydraulic actuators, an Electro-Mechanical Actuator(EMA)is small in size and light in weight, so it has become more widely used. Aerodynamic load on aircraft control surface varies dramatically, and a change of flight environment leads to uncertainties of motor parameters. Therefore, high-dynamic response and strong anti-disturbance capability of an EMA are of great significance for aircraft rudder control and flight attitude adjustment. In order to improve dynamic response and disturbance rejection of an EMA and simplify control parameters tuning, a robust high-dynamic servo system based on Linear Active Disturbance Rejection Control(LADRC) is proposed for an EMA employing a Permanent Magnet Synchronous Motor(PMSM).Firstly, total disturbances of the EMA are analyzed, including parameter uncertainties, load variation, and static friction. A disturbance observer based on a reduced-order Extended State Observer(ESO) is designed to improve the anti-interference ability and dynamic performance. Secondly, the servo control architecture is simplified to a double-loop system, and a composite control of position and speed with acceleration feed-forward is presented to improve the EMA frequency bandwidth.Thirdly, the ideal model of the EMA is transformed into a simple cascade integral form with a disturbance observer, which makes it convenient to analyze and design the controller. Robustness performance comparisons are realized in frequency domain. Finally, simulation and experimental results have verified the effectiveness of the proposed strategy for EMAs.     

Multiple-model estimation with variable structure- part VI: expected-mode augmentation

A new class of variable-structure (VS) algorithms for multiple-model (MM) estimation is presented, referred to as expected-mode augmentation (EMA). In the EMA approach, the original set of models is augmented by a variable set of models intended to match the expected value of the unknown true mode. These models are generated adaptively in real time as (globally or locally) probabilistically weighted sums of mode estimates over the model set. This makes it possible to cover a large continuous mode space by a relatively small number of models at a given accuracy level. The paper presents new theoretical results for model-set design, a general formulation of the EMA approach, along with theoretical analysis and justification, and three algorithms for its practical implementation. The performance of the proposed EMA algorithms is evaluated via simulation of a generic maneuvering target tracking problem.     

一种基于改进核主成分分析的SAR图像识别方法研究

针对传统核主成分分析方法识别SAR图像时,存在图像像素之间关联性差、对目标姿态角依赖性强等局限性,研究了一种基于改进核主成分分析的SAR图像识别方法。其研究思想是,结合SAR图像的特点提出了一种基于局部特征核主成分分析的特征提取方法,并设计了一种基于灰关联分析的双分类器对提取特征进行分类。NSTAR仿真实验表明：该方法不仅可以增强图像像素之间的相关性,而且对目标姿态角不存在依赖性,仿真结果验证了方法的有效性和可行性。     

Target classification approach based on the belief function theory

A theoretical framework is presented for target classification based on the belief theory on the continuous space. The proposed approach is applicable when class-conditioned densities of feature/attribute measurements are known only partially, as subjective models of a potential "betting" behaviour. Prior class probabilities may also be unknown. Numerical examples are provided to illustrate how the proposed approach is more cautious in decision making and produces very different results from those obtained using the Bayesian classifier.     

Coordinated target localization base on pseudo measurement for clustered space robot

This paper presents a coordinated target localization method for clustered space robot.According to the different measuring capabilities of cluster members,the master-slave coordinated relative navigation strategy for target localization with respect to slavery space robots is proposed;then the basic mathematical models,including coordinated relative measurement model and cluster centralized dynamics,are established respectively.By employing the linear Kalman flter theorem,the centralized estimator based on truth measurements is developed and analyzed frstly,and with an intention to inhabit the initial uncertainties related to target localization,the globally stabilized estimator is designed through introduction of pseudo measurements.Furthermore,the observability and controllability of stochastic system are also analyzed to qualitatively evaluate the convergence performance of pseudo measurement estimator.Finally,on-orbit target approaching scenario is simulated by using semi-physical simulation system,which is used to verify the convergence performance of proposed estimator.During the simulation,both the known and unknown maneuvering acceleration cases are considered to demonstrate the robustness of coordinated localization strategy.     

Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey

In practical mechanical fault detection and diagnosis, it is difficult and expensive to collect enough large-scale supervised data to train deep networks. Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task, which performs well on small data and reduces the demand for high computation power. However, the detection performance is significantly reduced by the direct transfer due to the domain difference. Domain adaptation (DA) can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data. In this survey, we review various current DA strategies combined with deep learning (DL) and analyze the principles, advantages, and disadvantages of each method. We also summarize the application of DA combined with DL in the field of fault diagnosis. This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.     

边缘图像自适应编码方法

边缘特征常被视作无人机视觉系统中的重要信息（比如在视觉导航时需用边缘特征识别障碍物），在实践中会遇到边缘图像数据量大的情况。针对边缘图像高效压缩问题，提出了边缘图像自适应编码方法。首先以边缘打包法的压缩比和边缘点所占比例为特征，建立Logistic回归模型，然后利用图像数据库对该模型进行离线训练获取模型参数，最后利用Logistic回归模型建立分类器，自适应地在边缘打包法和链码编码法中选择压缩比最高的方法对边缘图像进行压缩。对VOC2012图像数据库的测试结果表明，与常用压缩方法相比，提出的算法能提高压缩比5%左右，有效减少了数据量。     

Target localization method of non-cooperative spacecraft on on-orbit service

With the explosion of the number of meteoroid/orbital debris in terrestrial space in recent years, the detection environment of spacecraft becomes more complex. This phenomenon causes most current detection methods based on machine learning intractable to break through the two difficulties of solving scale transformation problem of the targets in image and accelerating detection rate of high-resolution images. To overcome the two challenges, we propose a novel non-cooperative target detection method using the framework of deep convolutional neural network.Firstly, a specific spacecraft simulation dataset using over one thousand images to train and test our detection model is built. The deep separable convolution structure is applied and combined with the residual network module to improve the network’s backbone. To count the different shapes of the spacecrafts in the dataset, a particular prior-box generation method based on K-means cluster algorithm is designed for each detection head with different scales. Finally, a comprehensive loss function is presented considering category confidence, box parameters, as well as box confidence. The experimental results verify that the proposed method has strong robustness against varying degrees of luminance change, and can suppress the interference caused by Gaussian noise and background complexity. The mean accuracy precision of our proposed method reaches 93.28%, and the global loss value is 13.252. The comparative experiment results show that under the same epoch and batchsize, the speed of our method is compressed by about 20% in comparison of YOLOv3, the detection accuracy is increased by about 12%, and the size of the model is reduced by nearly 50%.     

临近空间高超声速跳跃滑翔式目标自适应跟踪模型

针对临近空间高超声速跳跃式滑翔目标跟踪问题,在将加速度建模为具有正弦波（SW）自相关随机过程的基础上,提出一种自适应非零均值正弦波相关（ANM-SW）模型。其核心是对正弦波相关模型进行均值补偿构建ANM-SW模型,并推导了模型状态方程;为深入分析均值补偿的作用,分别从时域和频域的角度探讨了自适应非零均值模型的物理本质;此外,为进一步说明模型的适应性问题,结合Kalman滤波推导了SW及ANM-SW模型状态更新的系统动态误差,验证了ANM-SW模型在机动适应方面的优越性;最终仿真表明与SW模型相比,ANM-SW模型在跟踪精度及机动适应能力方面具有一定的优势性。     

基于机器学习的空间翻滚目标实时运动预测

借助监督式机器学习（ML）方法,对空间翻滚目标的运动状态预测问题进行研究,为空间机器人抓捕空间翻滚目标提供可靠的数据依据。基于物理模型的运动预测方法依赖理想的建模假设,需要连续的视觉反馈信息,解决目标预测问题的能力有限。因此,本文采用机器学习中纯数据驱动方式的稀疏伪输入高斯过程（SPGP）回归方法进行空间翻滚目标的运动预测。给定空间翻滚目标运动状态的历史观测数据,通过连续优化真实观测数据,得到稀疏的伪训练数据集,进而在线快速预测目标的运动状态,预测的计算效率达到毫秒级。此外,利用马尔科夫链蒙特卡洛（MCMC）法处理连续优化过程,克服由于随机初始值造成的优化过程陷入局部极小值问题。利用Snelson数据验证了所提稀疏伪输入高斯过程回归方法的正确性,并通过4组仿真算例验证了所提方法对于空间翻滚目标运动预测的有效性和鲁棒性。     

基于序列图像的自动目标识别算法

由于利用单幅二维图像进行三维目标识别存在识别的多义性,提出了一种基于二维序列图像的三维目标自动识别算法。首先以修正的Hu不变矩构造目标的图像识别特征,进而采用BP神经网络分类器构造关于目标融合识别的基本置信指派函数,以神经网络的训练误差构造证据理论不确定性度量,采用基于吸收法的DS证据理论实现高冲突证据的贯序式融合。对各姿态飞机图像识别的仿真表明,该算法对飞机的空间姿态变化具有很强的鲁棒性,能快速地准确识别飞机类型。此外,算法对先验性参数具有一定的鲁棒性。     

基于SVM算法的虚假航迹识别

针对云雨杂波和主被动干扰导致多雷达传感器产生虚假目标航迹的问题,利用支持向量机(SVM)算法的自主学习能力,通过构建基于数据驱动的判别模型进行虚假航迹识别。针对航迹起始得到的目标潜在航迹,利用人工智能数据驱动、自学习的特点,设计了SVM算法。通过对已标记真假的目标航迹样本进行离线学习,形成虚假航迹识别的SVM分类器,实现了基于数据驱动的判别模型代替先验知识规则约束的固定模型,并在工程应用中,利用SVM分类器在线识别虚假航迹,完成实时剔除。通过实测雷达数据实验验证,该算法的目标虚假航迹准确率高达95%以上,完全满足实际的工程应用需求。相比基于阈值或规则进行硬性判断的传统虚假航迹识别方法,所提出的算法不仅提高了准确率,还具有较高的实时性,能够适应复杂多变的杂波环境,在实际应用中具有更强的适应性和实用性。因此,提出的基于SVM算法的虚假航迹识别方法对于密集杂波场景下的虚假航迹剔除问题具有显著的实际应用价值。