Robust design of the LMS algorithm

A method to optimize the step size of the LMS algorithm when it is used to identify a time-varying system is proposed. The formulation allows uncertain specifications of the input excitation and the plant variation. The method is robust in that it minimizes the mean square error for the worst-case data of these variables     

多投影仪自由立体显示系统中的特征点检测及几何校正

几何校正是多投影仪自由立体显示系统实现无缝拼接显示的关键,而特征点检测是多投影仪组合显示进行几何校正的基础.自由立体显示系统中三维立体显示屏幕的各向异性反射特性使得基于亮度阈值分割的特征点检测方法效果不佳,为此,我们提出了基于轮廓检测的特征点检测方法:采用基于Hough变换的圆检测方法检测特征点的位置,以特征点集的凸包为基准插入及补充漏检的特征点,然后使用两次最小二乘直线拟合方法矫正误差.最后,利用特征点网格,实现了自由立体显示系统的几何校正.实验证明,我们的特征点检测方法鲁棒性好,精度较高,自动地实现了投影显示图像的高精度几何校正.     

Detection of moving objects in video using a robust motionsimilarity measure

This correspondence deals with the segmentation of a video clip into independently moving visual objects. This is an important step in structuring video data for storage in digital libraries. The method follows a bottom-up approach. The major contribution is a new well-founded measure for motion similarity leading to a robust method for merging regions. The improvements with respect to existing methods have been confirmed by experimental results.     

A robust adaptive weighted constant modulus algorithm for blind equalization of wireless communications systems under impulsive noise environment

A robust adaptive weighted constant modulus algorithm is proposed for blind equalization of wireless communication systems under impulsive noise environment. The influence of the impulsive noise is analyzed based on numerical analysis method. Then an adaptive weighted constant modulus algorithm is constructed to adaptively suppress impulsive noise. Theoretical analysis is provided to illustrate that the proposed algorithm has a robust equalization performance since the impulsive noise is adaptively suppressed. Moreover, the proposed algorithm has stable and quick convergence due to avoidance of large misadjuntment and adoption of large step size. Simulation results are presented to show the robust equalization performance and the fast convergence speed of the proposed algorithm under both impulsive noise and Gaussian noise environments.     

基于一种超分辨率算法的 三维散射中心提取方法

针对转台-弧形导轨测量方法,在二维MEMP方法的基础上,提出一种适用于三维散射中心提取的超分辨率算法.该方法利用Hankel矩阵的结构特性,以及子空间不变技术等,实现对信号三维参数的正确估计,并且无需额外的配对步骤.对八个散射点组成的立方体模型的数值仿真表明,该算法可以正确估计信号参数对,并对噪声的鲁棒性较强.进一步将三维参数估计问题扩展到N维情况,给出了具有较普遍意义的N维参数估计公式.     

Robust active appearance models and their application to medical image analysis

Active appearance models (AAMs) have been successfully used for a variety of segmentation tasks in medical image analysis. However, gross disturbances of objects can occur in routine clinical setting caused by pathological changes or medical interventions. This poses a problem for AAM-based segmentation, since the method is inherently not robust. In this paper, a novel robust AAM (RAAM) matching algorithm is presented. Compared to previous approaches, no assumptions are made regarding the kind of gray-value disturbance and/or the expected magnitude of residuals during matching. The method consists of two main stages. First, initial residuals are analyzed by means of a mean-shift-based mode detection step. Second, an objective function is utilized for the selection of a mode combination not representing the gross outliers. We demonstrate the robustness of the method in a variety of examples with different noise conditions. The RAAM performance is quantitatively demonstrated in two substantially different applications, diaphragm segmentation and rheumatoid arthritis assessment. In all cases, the robust method shows an excellent behavior, with the new method tolerating up to 50% object area covered by gross gray-level disturbances.     

一种基于RFID原理的交通信息获取系统与车辆定位方法

 车辆的无线定位技术已成为近年来的一个研究热点。该文首先提出了一种基于RFID(射频识别)技术的交通信息获取系统,并在此基础上,提出了一种新的多基站TDOA(到达时间差)车辆定位方法。该方法是一种基于鲁棒性估计的两步定位方法。第1步利用多个基站的TDOA信息通过鲁棒性估计找到车辆的大致位置,然后进一步采用与车辆距离最近的3个基站的TDOA信息对车辆进行精确定位。该方法可有效地克服传统Chan算法当信号衰减引起TDOA估计误差较大时性能迅速恶化的问题。仿真实验结果表明该方法的定位精度优于传统的Chan算法和基于直接平均的2次定位法,可满足交通信息获取系统中对机动车辆定位的要求。     

A Generalized Adaptive Quantization System with a New Reconstruction Method for Noisy Transmission

To cope with the effects of channel errors, robust adaptive quantization schemes contain a leakage parameter in the step-size adaptation algorithm. Unfortunately, this mechanism also introduces its own distortion in the form of reduced dynamic range of the step size which causes the signal-to-noise ratio to drop appreciably at the far ends of the range of input signal intensities typically associated with speech applications. A method for compensating for the leakage-induced distortion is proposed here. It consists of a generalization of the adaptive quantizer with the novelty contained entirely in the decoding procedure. Whereas the reconstruction or decoded values in existing adaptive quantizers are proportional to the adapted step size, with the prespecified and fixed reconstruction parameters{eta_{r}}giving the constants of proportionality, the generalization will have these parameters replaced by reconstruction functions{eta_{r}(bullet)}of the time-evolving step size. The sole time-varying parameter in the generalized quantizer is, as originally, the step size which is adapted in exactly the same manner as in existing robust quantizers. Two straightforward methods for the synthesis of the reconstruction functions are presented. The first is analytic while the second is a method for generating the functions through simulations. Computed results for two examples are presented. In the first example, the input signals are independent, Gaussian random variables. In the second example, the inputs are correlated and generated by a first-order Markov model. The communication system is adaptive differential PCM. In both examples, the generalized systems perform consistently better than existing systems and give significant improvements in SNR for signal intensities at the extremities of a 50 dB range.     

Bayesian Sparse Reconstruction Method of Compressed Sensing in the Presence of Impulsive Noise

The majority of existing recovery algorithms in the framework of compressed sensing are not robust to the impulsive noise. However, the impulsive noise is always present in the actual communication and signal processing system. In this paper, we propose a method named ‘Bayesian sparse reconstruction’ to recover the sparse signal from the measurement vector which is corrupted by the impulsive noise. The Bayesian sparse reconstruction method is composed of five parts, which are the preliminary detection of the location set of impulses, the impulsive noise fast relevance vector machine algorithm, the step of pruning, Bayesian impulse detection algorithm and the maximum a posteriori estimate of the sparse vector. The Bayesian sparse reconstruction method can achieve effective signal recovery in the presence of impulsive noise, depending on the mutual influence of the impulsive noise fast relevance vector machine algorithm, the step of pruning and the Bayesian impulse detection algorithm. Experimental results show that the Bayesian sparse reconstruction method is robust to the impulsive noise and effective in the additive white Gaussian noise environment.     

基于图像配准的潜在痕迹提取

介绍了依据图像配准技术在复杂背景中提取潜在痕迹的一种方法。图像配准是图像处理的一个重要的基础环节，传统的图像配准算法存在着各种不确定性及计算复杂性，而且特征点的选择困难且自动性差。而我们要实现从复杂的背景中提取潜在的痕迹必须要求图像要精确对准到亚像素级。针对传统算法中存在的问题，分别采用了一种从特征点提取、匹配到图像间点变换估计及光学变换估计的鲁棒算法。这些算法经过实验证实是鲁棒的且是实用的。     

Robust speaker recognition: a feature-based approach

This article presents an overview of current speaker-recognition systems and the problems encountered in operation, and it focuses on the front-end feature extraction process of robust speech techniques as a method of improvement. Linear predictive (LP) analysis, the first step of feature extraction, is discussed, and various robust cepstral features derived from LP coefficients are described. Also described is the affine transform, which is a feature transformation approach that integrates mismatch to simultaneously combat both channel and noise distortion     

Fast and robust seam estimation to seamless image stitching

Image stitching has a wide range of applications in computer vision/graphics and virtual reality. Seam estimation is one of the key steps in image stitching. This step can relieve ghosts and artifacts that were generated by misalignment or moving objects in the overlap region. This paper presents a fast and robust seam estimation method (FARSE) by defining gray-weighted distance and gradient-domain region of differences to avoid visible seams and ghosting. The optimal seam is estimated by searching in two weighted matrices, namely cost matrix and value matrix. The proposed method could be simply implemented. Results indicate that the FARSE method is scale-invariant and it is fast and more robust than the other methods.     

数控切绘机中步进电机的控制方法

在数控切绘机系统中,对步进电机的控制直接影响到加工质量.根据数控切绘机中步进电机的运动特性提出步进电机起停控制的改善方法,通过引入自调整比例因子模糊控制方法,改善了步进电机的动、静态特性,从而提高了系统的鲁棒性和控制精度.     

MC-CDMA系统基于子空间跟踪的导频辅助信道估计

基于导频辅助的MC-CDMA系统信道估计方法通过在确定的时频位置发送已知的导频符号来获取信道参数,通常包括导频位置的最小二乘估计和内插滤波两步。为了提高导频位置信道频域特性的估计精度,使得后续内插滤波的精度相应得到提高,本文利用基于Givens旋转的子空间跟踪方法构成了对信道的时变参数的估计和跟踪,得到了较为准确导频信道估计。仿真表明,我们给出的基于子空间跟踪的信道估计方法具有更好的稳定性和更高的估计精度。     

Optimization of the split-step Fourier method in modeling optical-fiber communications systems

We studied the efficiency of different implementations of the split-step Fourier method for solving the nonlinear Schro/spl uml/dinger equation that employ different step-size selection criteria. We compared the performance of the different implementations for a variety of pulse formats and systems, including higher order solitons, collisions of soliton pulses, a single-channel periodically stationary dispersion-managed soliton system, and chirped return to zero systems with single and multiple channels. We introduce a globally third-order accurate split-step scheme, in which a bound on the local error is used to select the step size. In many cases, this method is the most efficient when compared with commonly used step-size selection criteria, and it is robust for a wide range of systems providing a system-independent rule for choosing the step sizes. We find that a step-size selection method based on limiting the nonlinear phase rotation of each step is not efficient for many optical-fiber transmission systems, although it works well for solitons. We also tested a method that uses a logarithmic step-size distribution to bound the amount of spurious four-wave mixing. This method is as efficient as other second-order schemes in the single-channel dispersion-managed soliton system, while it is not efficient in other cases including multichannel simulations. We find that in most cases, the simple approach in which the step size is held constant is the least efficient of all the methods. Finally, we implemented a method in which the step size is inversely proportional to the largest group velocity difference between channels. This scheme performs best in multichannel optical communications systems for the values of accuracy typically required in most transmission simulations.     

Robust Identification from Impulse and Step Responses

A robust identification method that is insensitive to anomalous data is presented to estimate system models from the samples of their impulse and step responses. The power and usefulness of the proposed approach is illustrated with the help of simulated and real-life examples.     

基于视觉的微细对接焊缝检测方法

本文将机器视觉和图像处理技术融入到紧密对接焊缝的检测系统中,提出一种采用LED光源照明的焊缝检测方法。第一步采用Canny算法对焊缝进行边缘处理,第二步采用概率Hough变换提取焊缝中心线。实验结果表明,该方法鲁棒性强,可以精确检测出焊缝中心线,达到了期望的检测精度,解决了微细对接焊缝检测问题,结果令人满意。     

脉冲噪声下基于稀疏表示的韧性DOA估计方法

受相关熵启发,本文提出了一种脉冲噪声下基于稀疏表示的韧性DOA估计新方法.为实现多测量向量下联合稀疏信号的重建,本文提出了一种基于归一化迭代硬阈值的优化算法,讨论了最优步长的选择问题,证明了优化算法的收敛性.仿真结果表明：本文算法能够实现脉冲噪声下多信源的DOA估计,具有比已有算法更高的可分辨概率和估计精度.     

GA-based multiobjective PID control for a linear brushless DC motor

This paper presents a robust output tracking control design method for a linear brushless DC motor with modeling uncertainties. Two frequency-domain specifications directly related to the mixed sensitivity function and control energy consumption are imposed to ensure stability and performance robustness. With regard to time-domain specifications, the rise time, maximum overshoot and steady-state error of the step response are considered. A generalized two-parameters proportional, integral, and derivative (PID) control framework is developed via a genetic searching approach ensuring the specifications imposed. The proposed design method is intuitive and practical that offers an effective way to implement simple but robust solutions covering a wide range of plant perturbation and, in addition, provides excellent tracking performance without resorting to excessive control. Extensive experimental and numerical results for a linear brushless motor confirm the proposed control design approach.     

基于分块和滑动窗口的车牌定位方法

车牌定位是车牌识别系统的关键环节.提出了一种利用分块和滑动窗口快速定位车牌的新方法.首先,进行垂直边缘的检测;然后利用分块和滑动窗口的方法进行搜索,产生车牌候选区域;最后经过判别得到车牌区域,并对边界加以调整.实验结果证明这种算法具有定位准确、效率高、适应性强的特点.