目标跟踪中目标匹配的特征融合算法研究

基于特征融合的目标跟踪中,目标的特征由于某些干扰导致准确度较低。基于贝叶斯框架的特征融合算法进行目标跟踪时,不能达到最佳的跟踪效果。为了更好地融合目标的不同特征来实现不同场景的视频中的目标匹配,提出了一种新的特征融合算法。该算法在特征融合过程中引入特征匹配的置信水平信息作为正确目标选择的依据,然后采用不同于粒子滤波的迭代算法确定匹配的正确目标。实验结果表明,对于参与融合的特征之间有相对高的性能和特征间差异性较大的情况,新的融合算法比基于贝叶斯框架的融合算法在大部分情况下具备更高的匹配准确性。     

简评基于图像融合的目标识别和跟踪算法

传统的目标识别和跟踪算法都是基于单传感器图像的.随着多传感器图像融合技术的深入发展,其在目标识别和跟踪领域的应用也越来越广泛.评述了基于图像融合的目标识别与跟踪算法,包括融合预处理、融合识别和融合跟踪,说明了图像融合思想在目标识别与跟踪领域的优越性.     

用于非线性机动目标跟踪的新型IMM算法

针对在非线性机动目标跟踪中存在的滤波器易发散、机动检测有延迟等问题,把Unscented Kalman Filter(UKF)引进到交互多模型算法(IMM)中,设计了交互多模型UKF滤波器。并利用目标运动模型集概率的相对变化率设计了自适应交互多模型UKF滤波器,最后进行了计算机仿真。蒙特卡罗仿真结果表明,两种滤波算法都具备UKF滤波器精度高、稳定性好、不易发散的优点,同时不需了解目标机动的先验信息,适合于实际应用;并且自适应交互多模型UKF滤波器具有更好的跟踪效果。     

算力限制平台下的长时目标跟踪

为了满足某些算力受到限制的应用场景的长时跟踪需求,如以C64x+DSP为核心的嵌入式系统,提出了一种由连续跟踪环节与目标检测环节两部分构成的低时间复杂度长时跟踪算法,连续跟踪环节基于自适应更新的时空上下文算法（STC）,目标检测环节使用归一化互相关匹配算法。在没有目标出视场、目标快速移动等特殊跟踪场景时,连续跟踪环节输出跟踪结果,在跟踪失败后,目标检测环节对全幅图像进行处理,只要目标出现在图像中,便可以重新锁定目标。经实验验证,目标检测环节可以在目标出现后准确检测到目标,满足了长时跟踪的要求。同时,目标检测环节在跟踪不可靠时的辅助定位也提升了连续跟踪环节的鲁棒性,使用OTB2013数据集测试,本算法的精确度较STC算法提升了4.95%。     

多种跟踪算法对机动目标跟踪的应用研究

通过建立目标运动模型,对多种跟踪滤波器进行了分析仿真。仿真结果表明,混合状态估计交互式多模型算法（IMM）对机动目标跟踪效果比其它类型的滤波器好得多,并且确定了在航迹滤波与机动跟踪方面综合表现性能较高的IMMVCVA跟踪算法。通过外场实际数据验证,表明该算法对现实环境中的目标稳定跟踪具有重要的意义。     

Distributed target classification and tracking in sensor networks

The highly distributed infrastructure provided by sensor networks supports fundamentally new ways of designing surveillance systems. In this paper, we discuss sensor networks for target classification and tracking. Our formulation is anchored on location-aware data routing to conserve system resources, such as energy and bandwidth. Distributed classification algorithms exploit signals from multiple nodes in several modalities and rely on prior statistical information about target classes. Associating data to tracks becomes simpler in a distributed environment, at the cost of global consistency. It may be possible to filter clutter from the system by embedding higher level reasoning in the distributed system. Results and insights from a recent field test at 29 Palms Marine Training Center are provided to highlight challenges in sensor networks.     

多光电跟踪设备异步序贯分布式目标跟踪算法

针对多光电跟踪设备组网后出现的异步测量问题，提出了一种异步分布式序贯目标跟踪算法。该算法由局部滤波器和融合滤波器构成，先利用状态转换方法，将多光电跟踪设备节点及其邻节点的异步测量对齐到融合时刻，得到拟测量方程。随后，利用射影原理对拟测量方程和目标运动状态方程构成的目标跟踪系统，提出异步序贯局部滤波器来计算较为精确的局部滤波值。再以协方差交叉算法为基础，提出基于扩散策略的融合滤波器，对局部估计值进行融合计算，来提高目标跟踪精度，并降低组网后各光电跟踪设备节点融合估计值的差异程度。最后对所提出的算法进行了仿真实验，以验证其有效性。     

Array architectures for iterative algorithms

Regular mesh-connected arrays are shown to be isomorphic to a class of so-called regular iterative algorithms. For a wide variety of problems it is shown how to obtain appropriate iterative algorithms and then how to translate these algorithms into arrays in a systematic fashion. Several "systolic" arrays presented in the literature are shown to be specific cases of the variety of architectures that can be derived by the techniques presented here. These include arrays for Fourier Transform, Matrix Multiplication, and Sorting.     

Sequential Monte Carlo methods for multiple target tracking anddata fusion

The classical particle filter deals with the estimation of one state process conditioned on a realization of one observation process. We extend it here to the estimation of multiple state processes given realizations of several kinds of observation processes. The new algorithm is used to track with success multiple targets in a bearings-only context, whereas a JPDAF diverges. Making use of the ability of the particle filter to mix different types of observations, we then investigate how to join passive and active measurements for improved tracking     

多传感器数据融合目标识别算法综述

多传感器数据融合作为一种特殊的数据处理手段在目标识别领域得到了较大的重视和发展.在介绍多传感器数据融合目标识别基本原理及其算法理论依据基础上,从概念分类方面,对目前多传感器数据融合目标识别算法进行了全面综述,包括参数分类算法、基于认识模型的算法、物理模型算法及多类算法综合识别法等,说明了各算法特点及对其的进一步改进,列举了目前国内外一些已经发表的重要算法,为下一步多传感器融合目标识别研究提供了一定的理论依据.     

红外/毫米波雷达双模制导跟踪融合算法的优化

双模制导是导弹武器系统实现精确打击的关键技术之一,对双模制导跟踪融合算法进行优化研究具有一定的理论价值和工程应用价值。根据红外/毫米波雷达双模制导跟踪融合算法的工程应用要求,从算法的实时性、鲁棒性、抗干扰性等要求出发,设计了跟踪融合算法优化方案：一是构造基于特征层的空情特征,并利用决策层提供的决策可信度因子,对跟踪融合算法进行了相应改进;二是根据模糊神经网络及双模传感器在飞行中的不同特征提供的决策信息,对跟踪融合算法进行了优化调用。进行了相应的仿真分析,证明了方案的可行性。     

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。     

基于Mean Shift的目标跟踪算法性能比较研究

针对目前尚未有对基于Mean Shift的各类目标跟踪算法在同一数据集下进行性能比较这一问题,选取了七种具有代表性的基于Mean Shift的目标跟踪算法,分别从算法时效性、跟踪成功率和跟踪精确度三个方面对算法在25段包括多种复杂场景的图像序列上的性能进行了仿真实验比较。实验结果给出了算法在不同评价指标以及不同图像场景下的性能表现。由实验得出的结论可以为基于Mean Shift的目标跟踪算法的进一步优化改进提供参考。     

基于嵌入式平台的低时间复杂度目标跟踪算法

针对嵌入式平台往往算力受限的应用背景,提出了一种低时间复杂度的、适用于复杂场景的目标跟踪算法CTSTC算法。算法由自适应更新的时空上下文目标跟踪环节和自适应更新的压缩感知目标辅助定位环节两部分构成,当时空上下文跟踪结果不可靠时,启动压缩感知目标辅助定位环节,如果辅助定位后的结果可靠,则采用辅助定位结果校正时空上下文跟踪环节。算法运行速度与时空上下文算法（STC）接近,I5CPU下测试可达每秒1 577帧,远高于其他常用算法,是一种运算速度极高的目标跟踪算法,但算法在复杂环境下的鲁棒性却有所提升。使用OTB2013数据集进行测试,较STC算法,CTSTC精度提升12.8%,成功率提升27.5%。算法在以DM6437为核心的小型目标跟踪系统上进行测试,可以实现实时稳定跟踪。     

Resampling algorithms and architectures for distributed particle filters

In this paper, we propose novel resampling algorithms with architectures for efficient distributed implementation of particle filters. The proposed algorithms improve the scalability of the filter architectures affected by the resampling process. Problems in the particle filter implementation due to resampling are described, and appropriate modifications of the resampling algorithms are proposed so that distributed implementations are developed and studied. Distributed resampling algorithms with proportional allocation (RPA) and nonproportional allocation (RNA) of particles are considered. The components of the filter architectures are the processing elements (PEs), a central unit (CU), and an interconnection network. One of the main advantages of the new resampling algorithms is that communication through the interconnection network is reduced and made deterministic, which results in simpler network structure and increased sampling frequency. Particle filter performances are estimated for the bearings-only tracking applications. In the architectural part of the analysis, the area and speed of the particle filter implementation are estimated for a different number of particles and a different level of parallelism with field programmable gate array (FPGA) implementation. In this paper, only sampling importance resampling (SIR) particle filters are considered, but the analysis can be extended to any particle filters with resampling.     

VLSI array algorithms and architectures for RSA modularmultiplication

We present two novel iterative algorithms and their array structures for integer modular multiplication. The algorithms are designed for Rivest-Shamir-Adelman (RSA) cryptography and are based on the familiar iterative Horner's rule, but use precalculated complements of the modulus. The problem of deciding which multiples of the modulus to subtract in intermediate iteration stages has been simplified using simple look-up of precalculated complement numbers, thus allowing a finer-grain pipeline. Both algorithms use a carry save adder scheme with module reduction performed on each intermediate partial product which results in an output in carry-save format. Regularity and local connections make both algorithms suitable for high-performance array implementation in FPGA's or deep submicron VLSI. The processing nodes consist of just one or two full adders and a simple multiplexor. The stored complement numbers need to be precalculated only when the modulus is changed, thus not affecting the performance of the main computation. In both cases, there exists a bit-level systolic schedule, which means the array can be fully pipelined for high performance and can also easily be mapped to linear arrays for various space/time tradeoffs     

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.     

Parallel algorithms/architectures for neural networks

This paper advocates digital VLSI architectures for implementing a wide variety of artificial neural networks (ANNs). A programmable systolic array is proposed, which maximizes the strength of VLSI in terms of intensive and pipelined computing and yet circumvents the limitation on communication. The array is meant to be more general purpose than most other ANN architectures proposed. It may be used for a variety of algorithms in both the retrieving and learning phases of ANNs: e.g., single layer feedback networks, competitive learning networks, and multilayer feed-forward networks. A unified approach to modeling of existing neural networks is proposed. This unified formulation leads to a basic structure for a universal simulation tool and neurocomputer architecture. Fault-tolerance approach and partitioning scheme for large or non-homogeneous networks are also proposed. Finally, the implementations based on commercially available VLSI chips (e.g., Inmos T800) and custom VLSI technology are discussed in great detail.     

Graph-based detection algorithms for layered space-time architectures

We consider a unified framework to develop various graph-based detection algorithms for layered space-time architectures. We start with a factor graph representation for the communication channel, apply a belief propagation (BP) based algorithm for channel detection, and show that the detector achieves a near optimal performance even when number of receive antennas is smaller than number of transmit antennas. Based on this baseline algorithm, we further develop three different extensions of the BP detector that provide a good complexity/performance trade-off, which are especially useful for systems with a large number of antennas or when we encounter a frequency-selective fading channel with a long ISI span. Moreover, all the proposed detectors are soft-input soft-output in nature and they can be directly applied for use in turbo processing without any additional modifications. We study the performance of the new detectors via both simulations and convergence analysis using the measure of average mutual information.     

Optimization of image coding algorithms and architectures usinggenetic algorithms

This paper addresses the application of genetic algorithm (GA)-based optimization techniques to problems in image and video coding, demonstrating the success of GAs when used to solve real design problems with both performance and implementation constraints. Issues considered include problem representation, problem complexity, and fitness evaluation methods. For offline problems, such as the design of two-dimensional filters and filter banks, GAs are shown to be capable of producing results superior to conventional approaches. In the case of problems with real-time constraints, such as motion estimation, fractal search and vector quantization codebook design, GAs can provide solutions superior to those reported using conventional techniques with comparable implementation complexity. The use of GAs to jointly optimize algorithm performance in the context of a selected implementation strategy is emphasized throughout and several design examples are included