一种基于多特征自适应融合的运动目标跟踪算法

针对复杂背景下的运动目标跟踪问题,提出了一种基于多特征自适应融合的运动目标跟踪算法。通过构建目标与背景的图像特征分布方差的比值函数来衡量目标与背景间的区分度,采用各特征的区分度对特征集进行线性加权自适应表示运动目标并集成在基于核的跟踪方法中。为了克服模板更新过程中的漂移,通过计算前后相邻两帧间目标模型的相似度函数,对跟踪模板进行自适应更新。基于生物视觉认知理论,目标的颜色、边缘特征以及纹理特征被用来实现基于多特征自适应融合的运动目标跟踪算法。仿真实验表明:采用本文算法能有效地对复杂背景下的运动目标进行跟踪。     

基于多特征自适应融合的均值迁移目标跟踪算法

针对复杂环境下,均值迁移算法只使用 颜色特征跟踪目标鲁棒性差的问题,提出一种多特征自适应融合的MS目标跟踪算法。算法在 跟踪场景的动态变化过程中,通过选择对目标和背景区分能 力强的特征描述目标,建立多特征 融合目标模型,并设置特征重要性权值。给出了多特征融合目标定位公式。通过 动态评估不同特征在不同跟踪场 景中的可靠性,对特征权值进行动态更新以及多特征自适应融合。依据不同特征的权值给出 一种选择性模板更新机制,以减 轻目标模型的漂移。实验结果表明,提出的算法在复杂场景下,具有更高的鲁棒性和跟踪效 率。     

可视化目标特征提取及动态跟踪算法验证系统

介绍了基于图像处理的目标特征提取和跟踪算法的验证、评估系统。该系统由图像预处理、目标分割、目标特征提取、特征稳定性分析和跟踪算法等模块构成,集成了诸多的典型算法,对不同的目标和背景进行处理,选择特定目标和背景的最优算法组合,并以动态跟踪形式对算法集进行验证。     

DSiamMFT: An RGB-T fusion tracking method via dynamic Siamese networks using multi-layer feature fusion

The task of object tracking is very important since its various applications. However, most object tracking methods are based on visible images, which may fail when visible images are unreliable, for example when the illumination conditions are poor. To address this issue, in this paper a fusion tracking method which combines information from RGB and thermal infrared images (RGB-T) is presented based on the fact that infrared images reveal thermal radiation of objects thus providing complementary features. Particularly, a fusion tracking method based on dynamic Siamese networks with multi-layer fusion, termed as DSiamMFT, is proposed. Visible and infrared images are firstly processed by two dynamic Siamese Networks, namely visible and infrared network, respectively. Then, multi-layer feature fusion is performed to adaptively integrate multi-level deep features between visible and infrared networks. Response maps produced from different fused layer features are then combined through an elementwise fusion approach to produce the final response map, based on which the target can be located. Extensive experiments on large datasets with various challenging scenarios have been conducted. The results demonstrate that the proposed method shows very competitive performance against the-state-of-art RGB-T trackers. The proposed approach also improves tracking performance significantly compared to methods based on images of single modality.     

一种基于多传感器数据融合的目标跟踪算法

在制导与跟踪系统中．雷达和红外成像传感器所固有的优缺点,决定了其自身的局限性。为综合利用上述传感器信息,提高目标跟踪精度,提出了一种基于雷达和红外成像传感器数据融合的交互多模目标跟踪算法,算法首先对红外图像进行处理,然后基于上述处理结果．利用交互多模算法对雷达观测信息进行目标跟踪,最后采用分布式数据融合算法得到最终目标的跟踪结果。在有效提高跟踪精度的同时,减少了运算量。     

基于特征融合和注意力机制的目标分割跟踪算法

在当前的目标跟踪领域,现有的基于分割的算法没有充分利用目标的长距离依赖信息和各个特征层的不同特性,前背景判别能力不强,对目标的多尺度估计不足。针对此问题,提出了自适应特征融合模块和混合域注意力模块,以提高网络对目标的多尺度估计能力和对目标的前背景辨别能力,并将其集成到当前基于视频分割的算法中,提出了一种新的目标跟踪算法,在各大公开数据集上的实验结果证明其达到了领先水平。     

一种基于颜色特征的自适应目标跟踪算法

针对目标跟踪中出现的不可恢复的形变,运动模糊和尺度变化等问题,容易发生漂移,漏跟和错跟等现象,为此,文中提出一种基于颜色特征的自适应目标跟踪算法。首先,考虑到如何对目标进行描述,颜色特征是目标在运动过程中的一个不变量,采用PCA对目标颜色特征进行降维,得到目标的低维颜色特征。其次,在跟踪过程中,目标的尺度可能会发生变化,从而引入一种自适应尺度估计的方法,减少由于尺度变化而引入干扰信息。最后,结合颜色特征与尺度金字塔的方法,提出一种基于颜色特征的自适应目标跟踪算法。实验表明,提出的算法在跟踪的准确率与成功率这两方面都有明显的提高,在摄像机摇晃等复杂运动场景下,具有较好的鲁棒性。     

基于图像融合的双波段目标跟踪算法研究

针对红外和可见光图像各自的特点以及单一传感器在目标跟踪中的缺陷,提出了基于双波段融合图像的目标跟踪算法。该方法对原始图像进行小波分解后,为了满足目标跟踪的稳定性及实时性,重点考虑目标跟踪时需要的边缘等细节信息,采用对低频系数取零,高频系数基于小波系数绝对值取大的融合方法,然后对融合后的图像采用基于Mean shift算法进行目标跟踪。实验结果表明,此算法可以稳定并且实时跟踪目标,通过对单波段采用相同的跟踪算法进行比较,算法在性能上优于单波段的目标跟踪。     

在线特征融合的均值移位红外目标跟踪

提出了一种改进的均值移位红外目标跟踪算法.首先,针对红外图像低信噪比的特点,采用局部灰度均值特征及局部标准差特征用于目标建模.其次,针对目标低对比度的特点,以目标与局部背景的特征似然比作为核直方图的权值,建立了新的特征表征模型,并将两种特征模型进行线性融合,得到最终的目标表征模型,其中的融合系数由特征似然图对比度自适应确定.最后,在均值移位框架下推导了该模型梯度匹配过程中移位向量的表达形式.同时,基于帧间综合对比度的变化建立了复杂背景条件下的模型更新判别准则.通过基于实测数据的红外目标跟踪实验验证了该算法的可行性.     

An orthogonal regularized CCA learning algorithm for feature fusion

Canonical correlation analysis (CCA) aims at extracting statistically uncorrelated features via conjugate orthonormalization constraints of the projection directions. However, the formulated directions under conjugate orthonormalization are not reliable when the training samples are few and the covariance matrix has not been exactly estimated. Additionally, this widely pursued property is focused on data representation rather than task discrimination. It is not suitable for classification problems when the samples that belong to different classes do not share the same distribution type. In this paper, an orthogonal regularized CCA (ORCCA) is proposed to avoid the above questions and extract more discriminative features via orthogonal constraints and regularized parameters. Experimental results on both handwritten numerals and face databases demonstrate that our proposed method significantly improves the recognition performance.     

一种相控阵雷达自适应数据率目标跟踪算法

为了提高相控阵雷达机动目标跟踪的系统资源利用率,给出了一种高效快速的自适应数据率交互多模型目标跟踪算法（FAIMM）,将目标数据更新时间与模型概率关联起来,使每一节拍的数据更新率随目标的瞬时机动特性自适应调整。仿真结果表明,与AIMM跟踪算法相比,自适应数据率跟踪算法准确率更高,系统资源消耗更少。     

Robust object tracking based on adaptive templates matching via the fusion of multiple features

Moving object tracking under complex scenes remains to be a challenging problem because the appearance of a target object can be drastically changed due to several factors, such as occlusions, illumination, pose, scale change and deformation. This study proposes an adaptive multi–feature fusion strategy, in which the target appearance is modeled based on timed motion history image with HSV color histogram features and edge orientation histogram features. The variances based on the similarities between the candidate patches and the target templates are used for adaptively adjusting the weight of each feature. Double templates matching, including online and offline template matching, is adopted to locate the target object in the next frame. Experimental evaluations on challenging sequences demonstrate the accuracy and robustness of the proposed algorithm in comparison with several state-of-the-art algorithms.     

基于深度降噪自编码器的多特征目标融合跟踪算法

针对在目标遮挡、光线变化、目标模糊等情况下的目标跟踪算法抗干扰能力较差的问题,提出了一种基于深度降噪自动编码器的多特征目标融合跟踪算法。该方法首先引入稳像和图像去雾算法以改善训练集数据和测试集数据的质量;再构建多特征深度降噪自动编码网络,基于深度神经网络的强大学习能力提取目标的颜色特征和均匀模式纹理特征;将两种特征加权融合输入到逻辑回归分类器,获得置信分数,更有效地区分目标和背景。最后,采用粒子滤波算法对目标进行跟踪。实验结果表明,该方法能够更准确地对存在目标遮挡、光线变化、目标模糊等干扰问题的视频进行跟踪。与传统方法相比,该方法成功率在上述三个方面平均分别提升33.73%、9.73%和12.80%;与近年流行算法相比,该方法成功率平均达到90.16%,实时性平均达到49.37 fps。     

MULTISENSOR DISTRIBUTED EXTENDED KALMAN FILTERING ALGORITHM AND ITS APPLICATION TO RADAR/IR TARGET TRACKING

A multisensor distributed extended Kalman filtering algorithm is presented for nonlinear system, in which the dynamic equation of the system and the equations of sensor's measurements are linearized in the global estimate and global prediction respectively and the suboptimal global estimate based on all available information can be reconstructed from the estimates computed by local sensors based solely on their own local information and transmitted to the data fusion center. An analysis of the properties of the algorithm presented here shows that the global estimate has higher precision than the local one and smaller linearization error than the existing method. Finally, an application of the algorithm to radar/IR tracking of a maneuvering target is illustrated. Simulation results show the effectiveness of the algorithm.     

An adaptive moving target tracking algorithm for smart antenna systems

In wireless communication environment, the time-varying channel and angular spreads caused by multipath fading and the mobility of Mobile Stations （MS） degrade the performance of the conventional Direction-Of-Arrival （DOA） tracking algorithms. On the other hand, although the DOA estimation methods based on the Maximum Likelihood （ML） principle have higher resolution than the beamforming and the subspace based methods, prohibitively heavy computation limits their practical applications. This letter first proposes a new suboptimal DOA estimation algorithm that combines the advantages of the lower complexity of subspace algorithm and the high accuracy of ML based algorithms, and then proposes a Kalman filtering based tracking algorithm to model the dynamic property of directional changes for mobile terminals in such a way that the association between the estimates made at different time points is maintained. At each stage during tracking process, the current suboptimal estimates of DOA are treated as meas urements, predicted and updated via a Kalman state equation, hence adaptive tracking of moving MS can be carried out without the need to perform unduly heavy computations. Computer simulation results show that this proposed algorithm has better performance of DOA estimation and tracking of MS than the conventional ML or subspace based algorithms in terms of accuracy and robustness.     

基于多传感器异步数据融合的目标跟踪方法

在具有伪测量次优滤波器的基础上，提出多传感器异步融合的目标跟踪算法。通过蒙特卡罗模拟结果证明了该算法的有效性。     

Target tracking by fusion of random measures

In this paper we propose fusion methods for tracking a single target in a sensor network. The sensors use sequential Monte Carlo (SMC) techniques to process the received measurements and obtain random measures of the unknown states. We apply standard particle filtering (SPF) and cost-reference particle filtering (CRPF) methods. For both types of filtering, the random measures contain particles drawn from the state space. Associated to the particles, the SPF has weights representing probability masses, while the CRPF has user-defined costs measuring the quality of the particles. Summaries of the random measures are sent to the fusion center which combines them into a global summary. Similarly, the fusion center may send a global summary to the individual sensors that use it for improved tracking. Through extensive simulations and comparisons with other methods, we study the performance of the proposed algorithms. This work has been supported by the National Science Foundation under Award CCF-0515246 and the Office of Naval Research under Award N00014-06-1-0012.     

基于特征融合的粒子滤波目标跟踪新方法

针对传统粒子滤波(PF)算法采用单一颜色特征建模 跟踪目标性能差的缺陷,提出一种颜色特征与纹理特 征相融合的PF目标跟踪新算法。首先,采用一种具有抗噪声和保护纹理边缘的全局中值二值 模式 (GMBP)纹理算子,对模板图像进行局部差绝对值处理,得到幅 值序列模板,将幅值序列模板内的中值作为模板的阈值,与模板邻域比较获得新的纹理图像 ;然后,与 具有光照不变特性的局部二值模式(LBP)纹理算子结合,形成一种(GMLBP)新的纹理描述算子 。最后,分别计算GMLBP纹理特征粒子权值和HSV颜色特征粒子权 值,并依据权值大小确定融合系数,对纹理特征粒子权值和颜色特征粒子权值进行线 性融合,再对融合后粒子权值进行归一化处理,从而得到目标位置状态的最终估计值。对比 实验结果表明, 相对于单一颜色特征的目标跟踪算法,所提算法捕捉目标位置准确且具有更低的平均跟踪误 差,其平均误差降低了近2倍。     

An adaptive filtering algorithm of velocity estimation

In this paper, a novel adaptive filtering algorithm using real-time deviation of velocity estimation is presented for maneuvering target tracking. This new algorithm will be called adaptive filtering algorithm of velocity estimation. A number of simulation results indicate that the algorithm not only has good performance on tracking maneuvering target, but also greatly improves the capacity for tracking non-maneuvering target. So it is worthy to be applied widely in practice.     

基于三步搜索法的特征相关目标跟踪算法

针对相关匹配跟踪算法,提出一种新的基于三步搜索法的特征相关跟踪算法。该算法利用Moravec算子提取目标灰度特征,并根据特征点选取相应的子模板,然后利用三步搜索法进行多子模板的相关匹配。该方法可以在大幅度缩短相关匹配的搜索过程的基础之上适应运动目标的旋转、缩放等情况。实验证明该算法实际应用的可行性。