图象序列中机动目标的形心跟踪

从边检测边跟踪的角度探讨了图象序列中机动目标的形心跟踪问题,深入分析了强高斯噪声背景下目标形心估计的统计性质及用于形心估计的图象预处理方法。指出经典的图象二值化变换分割后作形心估计的方法面临着估计偏差和方差的矛盾,提出了用自适应交互三模型(ATIMM)跟踪图象序列中机动目标的方法,同时发现在了解目标形状的条件下,空间匹配滤波,二值变换点集聚类和 ATIMM三者的结合对图象序列中的机动目标具有最好的跟踪性能。     

基于空域特性的低空空域雷达目标检测

为实现基于非相参雷达的低空空域监视,提出一种基于空域特性的杂波抑制算法,通过构造"最优分类面"来区分复杂低空空域雷达图像中的小弱目标和杂波,极大改善了非相参雷达的低空探测能力。首先,采用背景差分与固定阈值分割建立前景和背景统计模型。然后,基于该模型提取空域特性,建立马尔可夫随机场模型,从而自适应地调节"最优分类面"中的阈值。前景模型数据反映了待检测像素的聚集程度,背景模型数据反映了其相对位置。将本算法分别应用于X波段和S波段航海雷达获取的图像序列。检测结果表明:本算法在检测到低空空域小弱目标的同时,能够将虚警率保持在较低的水平,优于恒虚警检测等经典算法。最后,将本算法与已经实现的目标跟踪算法相结合,实现了一整套完整的低空空域雷达目标检测与跟踪算法。     

基于约束序贯M估计的时空域融合红外杂波抑制

针对红外弱小目标检测中的强背景杂波干扰抑制问题进行研究,提出了一种基于参数约束序贯M估计的时空域融合自适应杂波抑制算法.该算法首先在分析序列图像帧间失配的基础上建立了一种改进的时空域融合背景预测模型,结合二维离散傅里叶快速变换图像配准和双线性插值方法进行灰度值估计;然后,基于约束序贯M估计方法进行模型参数的自适应估计,...     

基于时空显著性建模的空中飞行器跟踪方法

以复杂背景下空中飞行器的鲁棒视觉跟踪问题为研究背景，为解决现有跟踪方法目标表征模型不够精确，算法鲁棒性严重受到目标形变、宽高比变化、复杂背景等因素干扰的问题，提出了建模跟踪场景中独立物体的显著性特性，用于构建精确的目标模型。提出的显著性估计方法有别于传统的单帧检测方法，利用跟踪算法提供的背景先验知识以及多帧图像观测数据，使用时空联合的方式进行建模估计，其结果用来指导目标跟踪算法选取有效视觉特征，建立精确目标表征模型，减小背景区域对算法模型的干扰。实验表明，提出的方法为上述难点问题提供了有效的解决方案，对空中飞行器的跟踪精度与鲁棒性优于大多数最先进的主流方法，在其他类型的目标跟踪任务中也有十分优越的性能表现。     

基于邻帧差分近邻反相特征的红外运动点目标检测算法

基于运动点目标在邻帧差分图像中所具有的近邻反相特征,即运动点目标的两个位置相邻近、灰度值一正一负,提出一种在复杂背景下,基于红外序列图像的运动点目标检测算法.本算法利用该特征在邻帧差分图像中检测反相点对,进而构造反相点对矢量图,最后依据累积反相点对矢量图中多矢量首位相接的连续性检测出运动的点目标.文中给出并证明应用本算法能以概率1检测到运动点目标的收敛性定理.对典型复杂背景下10幅1000帧图像的仿真结果表明,当信噪比大于或等于1.5时,可以有效检测出运动点目标.     

航拍视频帧间快速配准算法

 为应对相机运动的影响,提出了一种快速有效的无人机(UAV)视频相邻帧图像配准算法。通过空间分布约束和角点量限制来筛选有效的FAST特征点,引入自适应阈值提高特征点检测的环境适应性,采用训练得到的不相关采样点集对特征点进行二值描述,以获得准确快速的特征描述,并通过最近邻算法根据汉明距离获得特征匹配对,最后运用RANSAC方法得到帧间仿射变换模型参数,消除相机运动带来的影响,为后续运动目标检测与跟踪提供保障。实验结果表明该算法快速、稳定,具有较高的环境适应性,能够满足无人机系统视频图像配准的要求。     

UMVE对数单元平均恒虚警检测器性能分析

利用无偏最小方差估计(UMVE)算法分析了UMVE对数单元平均恒虚警检测器的性能.它的前沿和后沿均采用UMVE算法产生局部估计,再对两者求和得到背景功率水平.在SwerlingⅡ模型下,给出UMVE对数单元平均恒虚警检测器虚警概率和检测概率解析表达式.与对数单元平均恒虚警检测器相比,UMVE对数单元平均恒虚警检测器的性能得到了改善.     

地基观测红外目标二维经验模式分解检测方法及应用

针对复杂条件下的地基观测红外图像目标检测问题,引入二维经验模式分解(BEMD)方法对复杂条件下的目标红外实测图像进行了处理分析:首先对目标观测原始红外图像进行中值滤波,对原始红外图像进行噪声抑制预处理;然后利用BEMD算法对预处理后红外图像进行自适应分解,获得按频段分布的二维基本模式分量与残余图像,并对分解后的红外图像进行有效重构,获取处理后的红外目标图像;最后利用点锐度方法定量评估目标红外图像处理效果,并与原始红外图像进行比对分析。基于实测红外图像处理结果表明,BEMD方法有效抑制了云层背景杂波噪声,且有效检测出清晰的红外目标,处理后的红外图像清晰度较原始红外图像显著提高。     

基于双边截断的双参数海上风电站 SAR图像 CFAR检测

文章提出了 1种基于双边截断的双参数海上风电站 SAR图像 CFAR检测器 DTCS-TPCFAR,目的是提高在具有多个目标海上区域和石油泄漏区域等环境下对海上风电站的检测性能。DTCS-TPCFAR所提出的双边截断杂波的方法,能够同时消除高强度和低强度异常值的干扰,同时保留真实的杂波样本。通过使用最大似然估计计算双边截断后样本的均值和标准差,然后通过这 2个参数估计值计算出截断阈值,最后再结合指定的虚警率(Probability of False Alarm,PFA)来对测试单元(Test Cell,TC)进行判断,完成最终的目标检测。这也是首次将 CFAR检测器用于检测海上风电站。文章通过 Sentinel-1数据集来验证该方法的有效性。实验结果表明,文章所提出的算法在相同指定虚警率下,具有更高的检测率(Detection Rate,DR)和更低的误报率(False Alarm Rate,FAR)。     

基于子空间投影的未知背景航拍高光谱图像恒虚警目标检测

针对航拍高光谱图像中未知背景地物特征条件下小目标的检测问题,给出一种检测算法。利用目标的低概率特性,通过模糊聚类获取高光谱图像中背景的光谱特性;然后将高光谱数据向背景光谱信号的正交子空间及目标信号子空间投影以抑制背景和噪声信号;最后在特征层利用广义似然比检验构造出具有恒虚警特性的检测器,完成融合检测过程。理论分析和实验结果表明了算法的有效性。     

基于帧差和背景建模的卫星视频目标检测

传统单一的目标检测方法运用在卫星视频时不能得到理想的检测效果,特别针对一些目标纹理特征匮乏,背景变化明显的卫星视频来说适用性更差。文章提出一种结合背景模型更新的混合高斯背景建模和多帧差分的算法,通过抽取吉林一号卫星视频中某2帧的2个不同场景,对比了多帧差分法、单高斯背景建模法和本文提出的算法,较好地解决了卫星视频微小目标检测中易产生检测率低、虚警率高的问题,提高了检测的正确度、完整度和质量,在遥感卫星视频运动目标检测中具有良好的应用潜力。     

Passive ranging of a low observable ballistic missile in agravitational field

In this paper we present an estimation algorithm for tracking the motion of a low-observable target in a gravitational field, for example, an incoming ballistic missile (BM), using angle-only measurements. The measurements, which are obtained from a single stationary sensor, are available only for a short time. Also, the low target detection probability and high false alarm density present a difficult low-observable environment. The algorithm uses the probabilistic data association (PDA) algorithm in conjunction with maximum likelihood (ML) estimation to handle the false alarms and the less-than-unity target detection probability. The Cramer-Rao lower bound (CRLB) in clutter, which quantifies the best achievable estimator accuracy for this problem in the presence of false alarms and nonunity detection probability, is also presented. The proposed estimator is shown to be efficient, that is, it meets the CRLB, even for low-observable fluctuating targets with 6 dB average signal-to-noise ratio (SNR). For a BM in free flight with 0.6 single-scan detection probability, one can achieve a track detection probability of 0.99 with a negligible probability of false track acceptance     

Automatic spectral target recognition in hyperspectral imagery

Automatic target recognition (ATR) in hyperspectral imagery is a challenging problem due to recent advances of remote sensing instruments which have significantly improved sensor's spectral resolution. As a result, small and subtle targets can be uncovered and extracted from image scenes, which may not be identified by prior knowledge. In particular, when target size is smaller than pixel resolution, target recognition must be carried out at subpixel level. Under such circumstance, traditional spatial-based image processing techniques are generally not applicable and may not perform well if they are applied. The work presented here investigates this issue and develops spectral-based algorithms for automatic spectral target recognition (ASTR) in hyperspectral imagery with no required a priori knowledge, specifically, in reconnaissance and surveillance applications. The proposed ASTR consists of two stage processes, automatic target generation process (ATGP) followed by target classification process (TCP). The ATGP generates a set of targets from image data in an unsupervised manner which will subsequently be classified by the TCP. Depending upon how an initial target is selected in ATGP, two versions of the ASTR can be implemented, referred to as desired target detection and classification algorithm (DTDCA) and automatic target detection and classification algorithm (ATDCA). The former can be used to search for a specific target in unknown scenes while the latter can be used to detect anomalies in blind environments. In order to evaluate their performance, a comparative and quantitative study using real hyperspectral images is conducted for analysis.     

An Adaptive Threshold System for Nonstationary Noise Backgrounds

The problem of detecting target signals in an ocean environment using active sonar is complicated by the nonstationary background which usually consists of both ambient ocean noise and reverberation. on. In this paper a signal processing system capable of detecting a signal in nonstationary noise is introduced. This system makes use of the mean and variance time functions of the nonstationary noise background in order to design estimation filters which will cope with the nonstationarity. Appropriate statistics of the noise and signal (tone burst) plus noise have been obtained and are used to determine the probabilities of false alarm and detection and the receiver operating characteristics.     

红外极小目标检测算法研究

低信噪比检测技术是实现红外自动目标识别的基本前提,其性能指标将直接决定系统探测距离的远近,是反映红外低可观测目标识别能力至关重要的一项核心技术。自适应背景估计方法是实现这一目标的有效途径。本文在重点论述几种背景估计常用技术的基础上,提出了红外极小目标的形态滤波优化改进算法,通过理论分析和实验检测表明：该算法简化了形态变...     

Optimal polarimetric detection of radar target in a slowlyfluctuating environment of clutter

It is shown that in a situation where a radar target is distant enough from the radar and is included in a natural or artificial clutter environment in such a manner that the conventional detection methods fail, it is possible to improve the radar detection performance by using appropriate signal processing on two orthogonal polarization states. A CFAR (constant false alarm rate) polarimetric detection system based on the study of the polarization difference between clutter and target is proposed. Since the polarization state of the clutter echoes fluctuates slowly from cell to cell, an autoregressive model can be applied to the components of the polarization vector to predict the detection thresholds needed to follow the polarization state variation. The detection thresholds are determined to maintain a false alarm probability equal to 10^-6. The presence of a target registers as a significant variation of the estimation error of the polarization vector. Results obtained from measurements of simple and canonical targets with artificial clutter are presented, and these results validate the principle of polarimetric detection     

基于改进SSD的舰船目标精细化检测方法

以SSD为代表的主流深度学习方法在目标检测领域取得了显著的成绩,但由于该类方法只能以矩形框给出目标的概略位置,检测结果具有很大的背景冗余区域,特别是港口密集停泊的舰船在图像中会出现区域重叠,导致误检和漏检。针对以上问题,提出了一种具有旋转不变性的舰船目标精细化检测方法,该方法综合利用可变形卷积、可变形池化、旋转的边框回归和旋转的非极大值抑制等模块的优点,借鉴MobileNet架构对网络加速,通过学习密集区域目标的几何形变,有效预测目标的旋转角度,最终以旋转的矩形框给出目标的位置。实验结果表明,该算法可实现多类舰船目标类型区分和目标朝向判定的功能,有效地解决了实际应用中的目标精确定位定向难题,提高了自动目标识别的精确性,并满足工程应用的实时性要求。     

一种新的广义Gamma分布下的SAR图像目标检测算法

针对合成孔径雷达(SAR)图像舰船目标检测中全局广义Gamma分布虚警数量较多的问题,文章采用了一种新的基于核密度估计(KDE)的广义Gamma分布下的SAR图像舰船目标检测算法。新的算法结合了SAR图像的强度分布和空间散布分布,形成新的组合分布。在组合分布的基础上,完成SAR图像目标检测。首先,介绍了广义Gamma的分布模型;然后,通过核密度估计的方法估计各像素点的散布分布,结合散布分布和强度分布形成组合分布,对组合分布采用SISE方程的方法估计广义Gamma分布的参数,根据确定的广义Gamma分布的表达式,求出阈值T的解析式。通过求解逆不完全Gamma函数得到检测阈值,进而完成舰船目标的检测。通过实测SAR图像检测实验,对比文章算法与双参数检测算法和基于广义Gamma分布检测算法,验证了该算法的适用性。     

Stap using knowledge-aided covariance estimation and the fracta algorithm

In the airborne space-time adaptive processing (STAP) setting, a priori information via knowledge-aided covariance estimation (KACE) is employed in order to reduce the required sample support for application to heterogeneous clutter scenarios. The enhanced FRACTA (FRACTA.E) algorithm with KACE as well as Doppler-sensitive adaptive coherence estimation (DS-ACE) is applied to the KASSPER I & II data sets where it is shown via simulation that near-clairvoyant detection performance is maintained with as little as 1/3 of the normally required number of training data samples. The KASSPER I & II data sets are simulated high-fidelity heterogeneous clutter scenarios which possess several groups of dense targets. KACE provides a priori information about the clutter covariance matrix by exploiting approximately known operating parameters about the radar platform such as pulse repetition frequency (PRF), crab angle, and platform velocity. In addition, the DS-ACE detector is presented which provides greater robustness for low sample support by mitigating false alarms from undernulled clutter near the clutter ridge while maintaining sufficient sensitivity away from the clutter ridge to enable effective target detection performance