语音识别中的两级MEL域滤波器组维纳滤波方法

欧洲电信标准化协会(European Telecommunications Standards Institute,简称ETSI)于2002年10月发布了分布式语音识别的鲁棒性前端标准。该标准参数的鲁棒性远优于MFCC参数。为了能够在低运算资源的设备上实现鲁棒性前端,在ETSI标准的核心两级维纳滤波算法的基础上,我们提出了一种新方法以提高算法效率。我们首先在Mel域滤波器组幅度上构造维纳滤波器,然后对维纳滤波器系数进行平滑。最后,将维纳滤波器直接应用到Mel域滤波器组幅度上。实验表明,新方法在保持ETSI两级维纳滤波算法出色性能的同时,大大地降低了运算量。     

基于粒子滤波理论的雷达多目标TBD检测

粒子滤波理论适用于在非线性和非高斯环境下的目标跟踪与检测。文中基于序列重要性采样定理,提出了模型环境和多雷达目标检测的递归贝叶斯TBD算法。此算法在基本粒子滤波算法SIR的基础上,采用多模型粒子滤波器实现了多雷达目标的检测。仿真结果表明,算法能够有效地进行目标跟踪与检测。     

Robust Transmitted Waveform and Received Filter Design for Cognitive Radar in the Presence of Signal-Dependent Interference

The problem of robust transmitted waveform and received filter design for cognitive radar in a signal-dependent interference environment is considered. When estimate errors of the target impulse response (TIR) and clutter impulse response (CIR) exist, in order to improve the worst signal-to-clutter ratio (SCR) and signal-to-interference-and-noise ratio (SINR), a robust transmitted waveform and received filter are designed based on the minimax criterion by using the information fed back from the receiver. Using deterministic and random models, the waveform and filter design problem is divided into three optimization problems. The robust waveform and filter are then obtained by solving these problems. In the deterministic model, we prove that the robust waveform and filter impulse response can be generated by a pseudorandom code. In the random model, the robust waveform and filter impulse response can be obtained by an alternative projection algorithm. Numerical results indicate that the worst SINR of the robust waveform and filter is higher than that of the traditional waveform and filter.     

基于极坐标的CMKF定位算法研究

针对经典的推广卡尔曼滤波算法受初值和测量噪声影响大,算法不稳定等缺点,提出了一种新的基于极坐标的转换测量卡尔曼滤波定位算法,计算机仿真结果验证了这种算法具有较好的稳定性和实用性.     

Robust modeling for image restoration using a modified reducedupdate Kalman filter

An algorithm to estimate the original image intensity from a degraded image is developed. The degradation phenomena is a Gaussian noise contaminated by an outlier sequence. The proposed algorithm is a combination of the robust algorithm proposed by Kashyap and Eom (1988) and the reduced update Kalman filter (RUKF) developed by Woods and Radewan (1977). The proposed algorithm is compared to some commonly used techniques such as the median filter, the robust algorithm, and the RUKF     

基于鲁棒卡尔曼滤波的盲自适应多用户检测算法

提出一种新的基于虚拟噪声补偿技术的鲁棒卡尔曼滤波估计异步CDMA系统多用户接收器的最优判决向量的方法,构造出一种收敛速度快、跟踪性能好、数值稳定性好的高性能盲自适应多用户检测算法。仿真实验表明, 该文提出的方法具有很强的抗多址干扰能力和较高的数值鲁棒性。     

Vision-Based Target Tracking and Surveillance With Robust Set-Valued State Estimation

Tracking a target from a video stream (or a sequence of image frames) involves nonlinear measurements in Cartesian coordinates. However, the target dynamics, modeled in Cartesian coordinates, result in a linear system. We present a robust linear filter based on an analytical nonlinear to linear measurement conversion algorithm. Using ideas from robust control theory, a rigorous theoretical analysis is given which guarantees that the state estimation error for the filter is bounded, i.e., a measure against filter divergence is obtained. In fact, an ellipsoidal set-valued estimate is obtained which is guaranteed to contain the true target location with an arbitrarily high probability. The algorithm is particularly suited to visual surveillance and tracking applications involving targets moving on a plane.      

Robust least mean square adaptive FIR filter algorithm

The authors propose a new robust adaptive FIR filter algorithm for system identification applications based on a statistical approach named the M estimation. The proposed robust least mean square algorithm differs from the conventional one by the insertion of a suitably chosen nonlinear transformation of the prediction residuals. The effect of nonlinearity is to assign less weight to a small portion of large residuals so that the impulsive noise in the desired filter response will not greatly influence the final parameter estimates. The convergence of the parameter estimates is established theoretically using the ordinary differential equation approach. The feasibility of the approach is demonstrated with simulations     

LMS算法的二次稳定性及鲁棒LMS算法

本文在时域内研究LMS算法(least mean square algorithm)的稳定性及鲁棒LMS算法的构造.首先将LMS算法表达式转化为标准的离散时间系统状态方程形式,之后运用线性矩阵不等式(LMI)技术对其二次稳定性进行了分析.针对滤波过程中会出现的输入和测量噪声干扰,本文提出了一种兼顾收敛性、鲁棒稳定性以及鲁棒性能的鲁棒LMS算法,最后给出了仿真算例,通过和一般的LMS算法的比较,体现了这种鲁棒LMS算法的优越性.     

A Robust Step-Size Control Technique Based on Prop ortionate Constraints on Filter Up date for Acoustic Echo Cancellation

One of the m ain di?culties in Acoustic echo cancellation (AEC) is that the filter adaptation needs to vary according to different situations such as near-end interferences and echo path changes. In this paper, we pro-pose a robust step-size control algorithm in frequency do-main. The proposed method is based on the optimization of the square of the bin-wise a posteriori error. Constraint on the filter update is applied, which contributes to ro-bustness to near-end interferences of the algorithm. The learning rate formula is derived first and then the relation-ship between the proposed algorithm and a robust statis-tics based approach is revealed. The method is extended to the Multidelay block frequency domain adaptive filter (MDF) so as to meet the demand of low delay in prac-tical application. Moreover, the values of the constraints are designed to be updated proportionately to improve the convergence property. Simulation results demonstrate the superiority of the proposed algorithm.     

Robust M-estimate adaptive filtering

An M-estimate adaptive filter for robust adaptive filtering in impulse noise is proposed. Instead of using the conventional least-square cost function, a new cost function based on an M-estimator is used to suppress the effect of impulse noise on the filter weights. The resulting optimal weight vector is governed by an M-estimate normal equation. A recursive least M-estimate (RLM) adaptive algorithm and a robust threshold estimation method are derived for solving this equation. The mean convergence performance of the proposed algorithm is also analysed using the modified Huber (1981) function (a simple but good approximation to the Hampel's three-parts-redescending M-estimate function) and the contaminated Gaussian noise model. Simulation results show that the proposed RLM algorithm has better performance than other recursive least squares (RLS) like algorithms under either a contaminated Gaussian or alpha-stable noise environment. The initial convergence, steady-state error, robustness to system change and computational complexity are also found to be comparable to the conventional RLS algorithm under Gaussian noise alone     

多站无源跟踪边缘化卡尔曼滤波算法

多站无源跟踪量测方程非线性强,对跟踪算法的稳定性及精度提出了更高的要求。为实现稳定高精度跟踪,提出了新的基于边缘化卡尔曼滤波（MKF）的多机无源跟踪算法。该算法将非线性的量测方程表示为p阶Hermite多项式的加权和,将加权矩阵的先验分布建模为高斯过程,求得其后验分布后对其进行积分来消除加权矩阵的影响,最终可得对状态及其协方差矩阵估计的闭式解。以只测角跟踪为例对所提算法性能进行验证,仿真结果表明,相对于扩展卡尔曼滤波（EKF）算法、不敏卡尔曼滤波（UKF）算法及容积卡尔曼滤波（CKF）算法,所提算法具有更好的跟踪性能。      

基于中值移位的粒子滤波多目标跟踪算法

针对传统粒子滤波多目标跟踪过程中的发散问题,提出了一种基于中值移位的粒子滤波多目标跟踪算法。该算法采用具有优良特性的中值移位方法对重要性重采样后的中间结果进行聚类分析,得到相应的粒子子群,从而获得各个目标的最优状态估计,提高滤波精度,并对目标的进出场景和遮挡问题进行有效处理。视频跟踪仿真试验表明该算法是稳健的,能够在复...     

Convergence of a ML parameter-estimation algorithm for DS/SS systems in time-varying channels with strong interference

An unbiased, maximum-likelihood (ML), channel parameter-estimation algorithm for direct-sequence spread-spectrum systems with strong interference is discussed in this paper. The algorithm includes correcting terms to the extended Kalman filter (EKF) based on the gradient of the negative log-likelihood function of the output of a conventional matched filter. By an asymptotic analysis, the algorithm is shown to determine the actual parameters. A complete implementation of the algorithm is given, and its transient behavior is examined by computer simulations. Results show the ML algorithm, albeit optimal in the sense of unbiased parameter estimation, is less robust than the modified EKF described in the first reference.     

基于增量学习的红外目标粒子滤波跟踪方法

针对红外图像序列中目标与背景的对比度低、灰度特征易受噪声影响等特点,提出了一种基于增量学习目标表观模型和粒子滤波的红外目标跟踪方法。通过在线学习机制,利用增量奇异值分解算法对图像特征空间的基向量进行准确更新,从而建立红外目标的鲁棒表观模型。在此基础上,采用粒子滤波对目标状态进行有效预测,实现了红外目标的有效跟踪。实验结果表明,该方法能有效、准确地跟踪红外图像序列中的运动目标。     

加权融合鲁棒增量Kalman滤波器

在一定环境条件下,当系统的量测方程没有进行验证或校准时,使用该量测方程往往会产生未知的系统误差,从而导致较大的滤波误差。同样地,当系统的噪声方差不确定时,滤波的性能也将会变坏,甚至会引起滤波器发散。增量方程的引入可以有效消除系统的未知量测误差,从而带未知量测误差的欠观测系统的状态估计问题可以转换为增量系统的状态估计问题。该文考虑带未知量测误差和未知噪声方差的线性离散系统,首先提出一种基于增量方程的鲁棒增量Kalman滤波器。进而,基于线性最小方差最优融合准则,提出一种加权融合鲁棒增量Kalman滤波算法。仿真实例证明了所提算法的有效性和可行性。     

Cooperative Coevolutionary Genetic Algorithm for Digital IIR Filter Design

A novel algorithm for digital infinite-impulse response (IIR) filter design is proposed in this paper. The suggested algorithm is a kind of cooperative coevolutionary genetic algorithm. It considers the magnitude response and the phase response simultaneously and also tries to find the lowest filter order. The structure and the coefficients of the digital IIR filter are coded separately, and they evolve coordinately as two different species, i.e., the control species and the coefficient species. The nondominated sorting genetic algorithm-II is used for the control species to guide the algorithms toward three objectives simultaneously. The simulated annealing is used for the coefficient species to keep the diversity. These two strategies make the cooperative coevolutionary process work effectively. Comparisons with another genetic algorithm-based digital IIR filter design method by numerical experiments show that the suggested algorithm is effective and robust in digital IIR filter design     

基于Camshift与Particle Filter的运动目标跟踪系统的设计及实现

采用Camshift算法对图像序列中的运动目标进行跟踪,同时根据系统环境及运动目标跟踪的非线性非高斯的特点,引入Particle Filter对跟踪算法进行改进,在保证系统的实时性的前提下提高其鲁棒性。最后在室内环境下验证该跟踪算法的实时性及可靠性,为自动跟踪的智能监控系统提供了一种候选方案。     

专注学习时空关系的相关滤波跟踪算法

传统相关滤波跟踪算法试图引入预定义的正则项,如抑制背景学习或限制相关滤波器的学习率来提高算法的鲁棒性,但在复杂场景下还是容易发生目标跟踪丢失,因为传统相关滤波跟踪算法没有关注相邻两帧之间的信息变化。针对以上问题,本文提出专注学习时空关系的相关滤波跟踪算法,引入相邻两帧的响应图变化作为空间正则项权值的参考权重,而当前帧的响应图的振荡程度确定时间正则项权值,最后本文通过交替方向乘子法(ADMM)迭代优化本文的损失函数。通过在OTB-50、OTB-100和OTB-2013三个基准数据集上进行了实验,验证了本文算法在复杂场景下更具有鲁棒性。      

Optimal tracking of time-varying channels: a frequency domainapproach for known and new algorithms

In this paper, we developed a systematic frequency domain approach to analyze adaptive tracking algorithms for fast time-varying channels. The analysis is performed with the help of two new concepts, a tracking filter and a tracking error filter, which are used to calculate the mean square identification error (MSIE). First, we analyze existing algorithms, the least mean squares (LMS) algorithm, the exponential windowed recursive least squares (EW-RLS) algorithm and the rectangular windowed recursive least squares (RW-RLS) algorithm. The equivalence of the three algorithms is demonstrated by employing the frequency domain method. A unified expression for the MSIE of all three algorithms is derived. Secondly, we use the frequency domain analysis method to develop an optimal windowed recursive least squares (OW-RLS) algorithm. We derive the expression for the MSIE of an arbitrary windowed RLS algorithm and optimize the window shape to minimize the MSIE. Compared with an exponential window having an optimized forgetting factor, an optimal window results in a significant improvement in the h MSIE. Thirdly, we propose two types of robust windows, the average robust window and the minimax robust window. The RLS algorithms designed with these windows have near-optimal performance, but do not require detailed statistics of the channel