Novel detection method for infrared small targets using weighted information entropy

This paper presents a method for detecting the small infrared target under complex background. An algorithm, named local mutation weighted information entropy (LMWIE), is proposed to suppress background. Then, the grey value of targets is enhanced by calculating the local energy. Image segmentation based on the adaptive threshold is used to solve the problems that the grey value of noise is enhanced with the grey value improvement of targets. Experimental results show that compared with the adaptive Butterworth high-pass filter method, the proposed algorithm is more effective and faster for the infrared small target detection.     

Adaptive multi-feature tracking in particle swarm optimization based particle filter framework

This paper proposes a particle swarm optimization(PSO) based particle filter(PF) tracking framework,the embedded PSO makes particles move toward the high likelihood area to find the optimal position in the state transition stage,and simultaneously incorporates the newest observations into the proposal distribution in the update stage.In the proposed approach,likelihood measure functions involving multiple features are presented to enhance the performance of model fitting.Furthermore,the multi-feature weights are self-adaptively adjusted by a PSO algorithm throughout the tracking process.There are three main contributions.Firstly,the PSO algorithm is fused into the PF framework,which can efficiently alleviate the particles degeneracy phenomenon.Secondly,an effective convergence criterion for the PSO algorithm is explored,which can avoid particles getting stuck in local minima and maintain a greater particle diversity.Finally,a multi-feature weight self-adjusting strategy is proposed,which can significantly improve the tracking robustness and accuracy.Experiments performed on several challenging public video sequences demonstrate that the proposed tracking approach achieves a considerable performance.     

Research on infrared dim and small target detection algorithm based on low-rank tensor recovery

In order to rapidly and accurately detect infrared small and dim targets in the infrared image of complex scene collected by virtual prototyping of space-based downward-looking multiband detection, an improved detection algorithm of infrared small and dim target is proposed in this paper. Firstly, the original infrared images are changed into a new infrared patch tensor mode through data reconstruction. Then, the infrared small and dim target detection problems are converted to low-rank tensor r...     

Image segmentation algorithm based on high-dimension fuzzy character and restrained clustering network

An image segmentation algorithm of the restrained fuzzy Kohonen clustering network （RFKCN） based on high- dimension fuzzy character is proposed. The algorithm includes two steps. The first step is the fuzzification of pixels in which two redundant images are built by fuzzy mean value and fuzzy median value. The second step is to construct a three-dimensional （3-D） feature vector of redundant images and their original images and cluster the feature vector through RFKCN, to realize image seg- mentation. The proposed algorithm fully takes into account not only gray distribution information of pixels, but also relevant information and fuzzy information among neighboring pixels in constructing 3- D character space. Based on the combination of competitiveness, redundancy and complementary of the information, the proposed algorithm improves the accuracy of clustering. Theoretical anal- yses and experimental results demonstrate that the proposed algorithm has a good segmentation performance.     

Image processing algorithm acceleration using reconfigurable macro processor model

The concept and advantage of reconfigurable technology is introduced. A kind of processor architecture of re configurable macro processor (RMP) model based on FPGA array and DSP is put forward and has been implemented. Two image algorithms are developed: template-based automatic target recognition and zone labeling. One is estimating for motion direction in the infrared image background, another is line picking-up algorithm based on image zone labeling and phase grouping technique. It is a kind of "hardware" function that can be called by the DSP in high-level algorithm. It is also a kind of hardware algorithm of the DSP. The results of experiments show the reconfigurable computing technology based on RMP is an ideal accelerating means to deal with the high-speed image processing tasks. High real time performance is obtained in our two applications on RMP.     

Modified unscented Kalman filter using modified filter gain and variance scale factor for highly maneuvering target tracking

To improve the low tracking precision caused by lagged filter gain or imprecise state noise when the target highly maneuvers, a modified unscented Kalman filter algorithm based on the improved filter gain and adaptive scale factor of state noise is presented. In every filter process, the estimated scale factor is used to update the state noise covariance Qk, and the improved filter gain is obtained in the filter process of unscented Kalman filter （UKF） via predicted variance Pk｜k-1, which is similar to the standard Kalman filter. Simulation results show that the proposed algorithm provides better accuracy and ability to adapt to the highly maneuvering target compared with the standard UKF.     

Compressive sensing for small moving space object detection in astronomical images

It is known that detecting small moving objects in astronomical image sequences is a significant research problem in space surveillance.The new theory,compressive sensing,provides a very easy and computationally cheap coding scheme for onboard astronomical remote sensing.An algorithm for small moving space object detection and localization is proposed.The algorithm determines the measurements of objects by comparing the difference between the measurements of the current image and the measurements of the background scene.In contrast to reconstruct the whole image,only a foreground image is reconstructed,which will lead to an effective computational performance,and a high level of localization accuracy is achieved.Experiments and analysis are provided to show the performance of the proposed approach on detection and localization.     

一种新的自适应机动目标跟踪算法

在＂当前＂统计（CS）模型基础上,提出了一种新的机动目标自适应滤波算法,当前统计模型-修正强跟踪滤波（CS-MSTF）算法。新算法在保留＂当前＂统计模型及强跟踪滤波器（STF）对一般机动目标跟踪精度高的优点的同时,作出以下改进：针对强跟踪滤波器在机动部分获得完美性能的同时,非机动部分的精度却不理想的缺陷,对预测误差协方差及渐消因子的计算作出修正,同时改进机动部分和非机动部分的精度;将目前常用的估计误差协方差的计算公式采用更加可靠的Joseph公式,增强了数值的稳定性和算法的鲁棒性。蒙特卡罗仿真表明,新算法的性能优于当前统计模型-强跟踪滤波（CS-STF）算法,能够进行有效估计。

Abstract：

Based on the ＂current＂ statistical model,a new adaptive maneuvering target tracking algorithm,CS-MSTF,was proposed. The new algorithm,keeping the merits of high tracking precision that the ＂current ＂ statistical model and strong tracking filter（STF） have in tracking maneuvering target has made the modifications as such：First,STF has the defect that it achieves the perfert performance in maneuvering segment at a cost of the precision in non-naneuvering segment,so the new algorithm modifies the prediction error covariance matrix and the fading factor to improve the tracking precision both of the maneuvering segment and non-maneuvering segment; The estimation error covariance matrix was calculated using the Joseph form,which is more stable and robust in numerical. The Monte-Carlo simulation shows that the CS-MSTF algorithm has a more excellent performance than CS-STF and can esitmate efficiently.     

A nonmonotone filter line search technique for the MBFGS method in unconstrained optimization

This paper presents a new nonmonotone filter line search technique in association with the MBFGS method for solving unconstrained minimization. The filter method, which is traditionally used for constrained nonlinear programming （NLP）, is extended to solve unconstrained NLP by converting the latter to an equality constrained minimization. The nonmonotone idea is employed to the filter method so that the restoration phrase, a common feature of most filter methods, is not needed. The global convergence and fast local convergence rate of the proposed algorithm are established under some reasonable conditions. The results of numerical experiments indicate that the proposed method is efficient,     

一种改进的不敏粒子滤波算法

提出了一种改进的不敏粒子滤波（UPF,Unscented Particle Filter）算法。和传统的UPF相比,该算法有两点改进,首先,在形成＂粒子云＂时,直接采用当前时刻各粒子的UKF（Unscented Kalman Filter）估计作为粒子,在保证粒子有效性的同时,减少了UKF之后的重采样过程;然后,结合新的粒子产生办法,重新定义了权值计算方法,避免了对各粒子重要概率的复杂计算。仿真表明,改进算法在减少计算量的同时,有效地提高了跟踪稳定性和跟踪精度。

Abstract：

An improved Unscented Particle Filter （UPF） algorithm was proposed.Compared with traditional UPF,it has been improved at two points.First,when producing particle cloudy,it directly uses the current particle estimation of Unscented Kalman Filter （UKF） as new particle,which guarantees the validity of particles and eliminates the re-sampling process after UKF as well;then,according to the new particle-producing method,a weight-calculating formula is re-defined,so as to avoid the complicated computation of proposal probability of every particle.A simulation shows that the Improved UPF （I-UPF） can effectively enhance the tracking stability and tracking precision and reduce computational cost at the same time.     

基于动态广义直方图均衡的红外图像增强方法

针对直方图均衡法进行红外图像增强时存在的问题,提出了动态广义直方图均衡方法。首先,广义直方图通过基于局部复杂度计算的分数值计数,体现了图像的不同区域特性,防止了过增强和放大噪声。然后,对广义直方图利用SG算法平滑滤波后,采用GK聚类算法实现对直方图的动态划分,避免高概率灰度背景对低概率灰度目标的影响。最后,动态分配目标和背景的输出灰度区间,突出目标细节,控制增强效果。实验结果表明,算法能有效克服传统直方图均衡法丢失目标细节、不能控制增强效果和过分放大噪声的不足,是一种有效的红外图像增强方法。     

基于PDAF和线性预测的实时小目标跟踪算法

根据红外图像中小目标的典型特征提出了一种新的小目标检测算法。利用图像小目标的微分几何特性,计算图像的最小法向曲率,并以此为阈值,获得小目标的候选区对象,以实现目标检测。针对复杂背景下跟踪过程出现背景杂波干扰或目标受到遮挡时,出现目标消失的问题,提出了一种基于概率数据互联滤波器和线性预测技术相结合的实时跟踪算法,以提高目标跟踪的稳定性和精度。最后,利用实际录制的图像序列进行仿真实验,可准确跟踪信噪比不小于2、运动速度为1帧/像素的目标,验证了算法的有效性和实时性。     

高斯粒子PHD滤波的多个弱小目标TBD算法

针对现有多个弱小目标检测前跟踪(track before detect, TBD)算法存在的跟踪精度低,算法复杂度高等问题,提出一种新的基于概率假设密度(probability hypothesis density, PHD)的TBD算法。所提算法通过高斯粒子滤波对PHD中的各高斯项进行递归运算、进行多帧能量累积,并提取高斯项的均值为目标的状态,达到检测与跟踪多个弱小目标的目的。算法在随机集滤波框架下完成未知数目的多个弱小目标跟踪,不仅充分利用粒子滤波的非线性估计能力,同时避免了传统算法利用模糊聚类进行目标状态提取所带来的跟踪精度低等问题。仿真结果表明,所提算法与传统方法相比,在降低算法复杂度的同时,对多个红外弱小目标具有更加良好的实时检测和跟踪性能。     

基于Top-hat变换的PM模型弱小目标检测

为了实现红外复杂背景下弱点目标的有效检测,提出了形态学Top-hat变换和改进的非线性扩散(以Perona-Malik (PM)的研究为基础)模型相结合的滤波算法,用于增强红外弱小目标信号、抑制复杂背景和噪声。该方法首先利用形态学滤波中的Top-hat算子对图像进行目标增强,然后对形态学滤波后的图像采用改进的PM滤波器进行进一步滤波达到抑制背景突出目标的目的,最终通过阈值分割实现弱小目标的检测。对比实验结果表明,该算法能够在低信噪比(signal-to-noise ratio, SNR)下实现红外弱小目标图像的背景及边缘有效抑制、使图像的信噪比提高20%,检测能力在原有算法上提高了40%。     

基于矩阵S1/2范数的红外目标跟踪

目前使用的很多红外目标跟踪系统在目标背景复杂、目标形体较小、目标受到遮挡等情况下会发生目标丢失现象,针对这一问题,在粒子滤波框架下,提出了一种基于矩阵S_1/2范数的红外目标跟踪算法。首先,围绕上一帧被跟踪目标的状态对当前帧目标粒子进行采样;然后,将采样的目标粒子进行筛选,并将筛选后的粒子整体输入到基于矩阵S_1/2范数和l_1,1范数联合表示的最小化问题模型,并求解其最优解;最后,根据候选目标粒子在目标字典和背景字典表示下系数的差异确定最优目标粒子,即为当前帧跟踪结果。实验结果表明,相比经典的类似目标跟踪算法,该算法能够对复杂背景、目标形体弱小、目标受到遮挡等多种情况下的红外目标进行有效跟踪,并具有更强的鲁棒性和更好的时效性。     

光电成像制导中地面运动目标检测与跟踪

地面运动目标的自动检测与跟踪是对地精确打击光电成像制导中的核心任务。针对地面运动目标自动检测问题,提出了由粗到精的迭代全局运动补偿算法以补偿动平台引起的背景图像像素位移,基于变化能量测度的独立运动目标检测算法以及基于三帧序列图像的运动目标定位算法。针对地面运动目标跟踪问题,提出了融合运动特征和灰度直方图特征的粒子滤波器目标跟踪算法,实现可靠、稳定跟踪地面运动目标。利用实际航拍视频进行算法验证实验,比较了基于傅里叶-梅林变换 (Fourier-Mellin transform, FMT)、Kanade-Lucas-Tomasi (KLT) 特征跟踪、Harris角点和迭代全局运动补偿算法,验证了基于变化能量测度的独立运动目标检测算法和融合多特征的粒子滤波器跟踪算法的有效性。     

相关序列小目标图像运动跟踪与仿真研究

针对气动光学效应降晰过程的复杂性,提出了一种基于图像相关性的序列小目标图像运动跟踪及去噪算法.该算法结合序列图像的相关性,避免了因采集时间的延长而使得序列图像中的小目标偏移太大.在相关序列图像的基础上,通过滤波技术,结合"小波变换的背景融合"算法,得到对运动目标背景的估计.以此估计背景为基础进行运动小目标的估计、灰度质心计算,得到运动目标的跟踪.仿真研究结果表明该算法实现了气动光学效应相关序列小目标图像的运动跟踪,背景融合技术和目标图像的估计降低了噪声带来的影响,对气动光学效应序列图像研究具有重要价值.     

传统特征和深度特征融合的红外空中目标跟踪

新型红外诱饵的出现,对传统红外成像空空导弹作战效能的发挥造成了严峻挑战。近年来深度学习研究进展迅速,有力促进了目标跟踪领域的发展。以多域学习网络框架为基础,引入传统特征长宽比和均值对比度,将深度特征与传统特征融合在一个跟踪框架中,解决了单一特征在目标跟踪中无法有效对抗面源等复杂干扰的问题。为了评估算法性能,分别在仿真序列和实拍图像序列上进行了测试。实验结果表明,所提出算法的跟踪精度和鲁棒性优于目前经典的跟踪算法,是一种具有较强适应性的红外空中目标跟踪方法。     

基于尺度空间粒子滤波器的多参考#br# 直方图目标跟踪算法

在基于直方图的序列图像目标跟踪算法中,目标的直方图通常都是在跟踪初始化时从目标所在的区域获得,然而单个直方图难以适应跟踪全过程中目标的各种变化。针对事先已知目标几种典型外观的跟踪问题,提出了一种基于粒子滤波器的多直方图尺度空间跟踪算法。利用多个典型直方图的线性加权来表示目标的直方图,根据目标的当前区域估计加权系数,生成下一帧的目标概率分布图,在目标概率分布图上运用尺度空间粒子滤波器,来估计多尺度规范化Laplacian滤波函数的极值,从而实现目标的定位。通过在真实序列上与现有算法的对比,表明了此算法不仅可以适应目标的色彩和明暗变化,而且能更准确地描述目标的大小,显著提高跟踪的精度。     

基于双门滤波的红外点目标检测方法

讨论了红外图像点目标的检测问题。针对红外点目标无形状特征、SNR很低的特点,分析常用的最大中值滤波的优缺点,提出了改进的双门滤波器,并用之来对图像进行目标检测。该算法通过选取合适的目标窗和背景框的大小,分别计算窗、框内的平均值和方差来决定滤波器的输出,在目标窗与背景框间加缓冲带从而降低了目标与背景的误分辨。经过大量实验验证表明,该方法能够较大程度提高目标图像的信噪比,有效地检测出小目标。