共查询到19条相似文献，搜索用时 765 毫秒
1.
《科技通报》2015,(8)
在浓雾环境下采集的视觉图像出现突兀点,需要进行平滑处理,提高对浓雾环境下的图像成像和识别能力。传统方法中采用差频控制的浓雾图像突兀点平滑处理算法,图像采集出现视觉偏移时平滑处理效果不好。提出一种基于视觉偏移修正的浓雾图像突兀点平滑处理算法,基于浓雾天气条件下单色大气散射模型,物体表面的反射光由于大气粒子的散射而损失,得到雾点散射损失,采用视觉偏移修正的算法,提高对浓雾图像的视觉偏移修正能力,由于起点坐标和视线方向出现视觉偏移,采用去雾滤波算法提高突兀点的平滑性能,得到浓雾图像的去雾滤波系统函数,通过边缘检测得到图像的突兀点平滑结构,进行Hough变换直线检测,实现视觉偏移修正和突兀点平滑改进。仿真结果表明,该算法具有较好的突兀点平滑处理性能,无论是细节还是浓雾图像的色彩都恢复得比较自然和清晰,去雾效果较好,平滑处理的图像有较高的配准率,展示了该算法的优越性能。 相似文献
2.
三次指数平滑预测法渐近最优性及其预测偏差的进一步研究 总被引：4，自引：1，他引：4
本文在渐近形式指数平滑下，进一步证明三次指数平滑预测法具有线性最优性。在有限形式指数平滑下，进一步分析三次指数平滑预测法的预测偏差。由此说明，在大样本条件下，三次指数平滑法具有渐近最优性，并给出小样本条件下，三次指数平滑预测法预测偏关的校正公式。 相似文献
3.
压缩感知理论是利用信号的稀疏性,采用重构算法通过少量的观测值就可以实现对该信号的精确重构。SL0（Smoothed l0）算法是基于l0范数的稀疏信号重构算法,通过控制参数逐步逼近最优解。针对平滑函数的选取问题,文章提出一种新的平滑函数序列近似l0范数,实现稀疏信号的精确重构。仿真结果表明,在相同实验条件下文章算法较传统算法有着较高的重构概率。 相似文献
4.
一种高阶平滑表面并行提取方法 总被引：1，自引：0，他引：1
针对高阶平滑表面算法计算复杂和数据量大的问题,提出一种加快高阶平滑表面算法速度的并行方法.首先对高阶平滑表面算法进行并行化,然后采用优化技术提高算法性能,同时采用矩阵压缩改善内存空间性能.实验表明,在双核处理器上平均加速比达到1.87. 相似文献
5.
本文主要研究了基于改进指数平滑算法的气温预测问题。首先引入时间序列模型概念,对常用气温预测模型进行简要分析,另外对一阶指数平滑算法进行相关推导,同时提出了自适应指数平滑算法;其次,结合广西容县近30年月均气温实测数据,分别建立BP神经网络预测模型、传统指数平滑算法预测模型以及改进后的基于自适应指数平滑算法的预测模型,对2016年气温数据进行预测并分析模型优势;最后,将改进模型用于预测2017年和2018年中未知月份的月平均气温值,并针对实验结果进行数据分析修正。通过对不同预测模型的比较和仿真实验,结果表明基于自适应指数平滑算法的气温预测模型预测精度较高,实用性强,具有一定的推广性。 相似文献
6.
7.
本文提出了一种利用卡尔曼滤波对负荷测量数据进行平滑的算法,通过预测估计,最小二乘法和卡尔曼滤波平滑等算法解决实际负荷测量中存在的错误. 相似文献
8.
9.
本文对传递对准性能评估技术进行了介绍,并对两种最优平滑估计算法进行了分析比较,最后提出了采用区间平滑算法实现的传递对准评估数学模型及评估工作流程,对于工程应用具有指导意义。 相似文献
10.
一种基于活动围道的纹理图像分割方法 总被引：1，自引：0，他引：1
本文将Gabor滤波器和各向异性扩散方程相结合，提出了一种基于活动围道的无监督纹理图像分割算法。采用基于总变分流的扩散函数，各向异性扩散方程可以有效地在保留纹理图像大尺度边界信息的同时对图像纹理区域进行平滑，获得比原始图像更易分割的简化图像。但是平滑过程中纹理信息的丧失，限制了该方法的通用性和有效性。为了在利用各向异性扩散方法的同时有效地提取和利用纹理信息，我们利用Gabor滤波器提取一组表征纹理方向性和尺度性的特征图像，同时将原始图像作为表征纹理灰度信息的一个特征通道考虑。再利用矢量形式的各向异性扩散方程对特征图像进行边界保持的各向异性平滑。我们将基于区域灰度统计参数估计的活动围道分割方法扩展到矢量空间，来对平滑后的纹理特征量进行分割。实验证明利用该纹理分割算法可以获得较好的效果。 相似文献
11.
Fei Hao 《Journal of The Franklin Institute》2010,347(8):1511-1525
The robust absolute stability problem for norm uncertain and structured uncertain discrete Lur’e systems is considered in this paper by using Lyapunov function method. A sufficient condition of absolute stability for discrete Lur’e systems is established in terms of linear matrix inequalities (LMIs) or the equivalent frequency-domain condition. We compare the result with the Popov-like criterion (Tsypkin criterion) and extended strictly positive real (ESPR) lemma. Furthermore, sufficient conditions on absolute stability for discrete Lur’e systems with norm and structured uncertainties are also presented based on linear matrix inequalities. Estimates of the maximum bounds of all admissible perturbations are given by generalized eigenvalue problems. Finally, several numerical examples are worked out to illustrate the efficiency of the main results. 相似文献
12.
Standard forms are presented which define transfer functions for optimum type 1 and type 2 feedback control systems, where systems with minimum integral of time multiplied absolute value of error in the presence of a step displacement input are considered to be optimum. The ITAE criterion adopted in this paper was previously introduced by Graham and Lathrop.The optimization procedure leading to the standard forms presented here, is based upon an all digital simulation coupled to an unconstrained optimization algorithm to minimize the ITAE criterion value.It is shown with the aid of examples how actual systems can be compensated by use of appropriate standard forms to obtain optimum responses. 相似文献
13.
This paper investigates an evolving split-complex valued neuro-fuzzy (SCVNF) algorithm for Takagi–Sugeno–Kang (TSK) system. In a bid to avoid the contradiction between boundedness and analyticity, splitting technique is traditionally employed to independently process the real part and the imaginary part of weight parameters in the system, which doubles weight dimension and causes oversized structure. For improving efficiency of structural optimization, previous studies have revealed that L1/2-norm regularizer can be effective in such sparse tasks thus is regarded as a representative of Lq (0?<?q?<?1) regularizer. To eliminate oscillation phenomenon and stabilize training procedure, a smoothed L1/2 regularizer learning is facilitated by smoothing the original one at the origin flexibly. It is rigorously proved that the real-valued cost function is monotonic decreasing during learning course, and the sum of gradient norm trends closer to zero. Plus some very general condition, the weight sequence itself is also convergent to a fixed point. Experimental results for the SCVNF are demonstrated, which match the theoretical analysis. 相似文献
14.
Marwan I. Abukhaled 《Journal of The Franklin Institute》2011,348(7):1245-1257
Under the infinite logarithmic matrix norm, a criterion for mean square stability of second-order weak numerical methods for multi-dimensional stochastic differential systems is established. Numerical examples are demonstrated to support the theoretical results. 相似文献
15.
Optimization of grid configurations decreases the discretization error in the numerical solution of field problems. In this paper, the theoretical and algorithmic aspects of optimizing configurations of grids used in equilibrium, potential-type field problems is presented. The criterion for establishing the optimum grid and the steps required to move to the optimum grid are given. Sensitivity network modelling is invoked to systematically form matrices required in the algorithm. One-dimensional examples are presented to illustrate the validity of the approach. 相似文献
16.
《Journal of The Franklin Institute》2021,358(14):7270-7285
Phase retrieval recovers signals from linear phaseless measurements via minimizing a quadratic or amplitude function, while its loss function is generally either non-convex or non-smooth. Existing methods are used to add a truncation procedure or reweighting to the gradient during the gradient descent process to address the non-smooth problem. However, these methods often cause inconsistency in the search direction and increase the sampling complexity. This paperproposes a smoothed amplitude flow-based phase retrieval (SAFPR) algorithm to solve these problems. By introducing the smoothing function into the phase retrieval problem, the loss function is smoothed, significantly reducing the sampling complexity. Moreover, we also develop a stochastic smooth amplitude flow-based phase retrieval (SSAF) algorithm with practical, scalable, and fast in large-scale applications. Experimental results show that whether SAFPR or SSAF, the number of measurements required to reconstruct the signal entirely is better than the existing most advanced phase retrieval algorithms. The proposed methods also perform well in terms of time cost and convergence rate. 相似文献
17.
《Journal of The Franklin Institute》2022,359(3):1274-1302
This article proposes an affine-projection-like maximum correntropy (APLMC) algorithm for robust adaptive filtering. The proposed APLMC algorithm is derived by using the objective function based on the maximum correntropy criterion (MCC), which can availably suppress the bad effects of impulsive noise on filter weight updates. But the overall performance of the APLMC algorithm may be decreased when the input signal is polluted by noise. To compensate for the deviation of the APLMC algorithm in the input noise interference environment, the bias compensation (BC) method is introduced. Therefore, the bias-compensated APLMC (BC-APLMC) algorithm is presented. Besides, the convergence of the BC-APLMC algorithm in the mean and the mean square sense is studied, which provides a constraint range for the step-size. Computer simulation results show that the APLMC, and BC-APLMC algorithms are valid in acoustic echo cancellation and system identification applications. It also shows that the proposed algorithms are robust in the presence of input noise and impulse noise. 相似文献
18.
In this paper, identification of discrete-time power spectra of multi-input/multi-output (MIMO) systems in innovation models from output-only time-domain measurements is considered.A hybrid identification algorithm unifying mixed norm minimization with subspace estimation method is proposed. The proposed algorithm first estimates a covariance matrix from measurements. A significant dimension reduction is achieved in this step. Next, a regularized nuclear norm optimization problem is solved to enforce sparsity on the selection of most parsimonious model structure. A modification of the covariance estimates in the proposed algorithm generates yet another algorithm capable of handling data records with sequentially and intermittently missing values. The new and the modified identification algorithms are tested on a numerical study and a real-life application example concerned with the estimation of joint power spectral density (PSD) of parallel road tracks. 相似文献
19.
Wentao Ma Xinyu Qiu Jiandong Duan Yingsong Li Badong Chen 《Journal of The Franklin Institute》2018,355(4):1596-1613
This work studies the problem of kernel adaptive filtering (KAF) for nonlinear signal processing under non-Gaussian noise environments. A new KAF algorithm, called kernel recursive generalized mixed norm (KRGMN), is derived by minimizing the generalized mixed norm (GMN) cost instead of the well-known mean square error (MSE). A single error norm such as lp error norm can be used as a cost function in KAF to deal with non-Gaussian noises but it may exhibit slow convergence speed and poor misadjustments in some situations. To improve the convergence performance, the GMN cost is formed as a convex mixture of lp and lq norms to increase the convergence rate and substantially reduce the steady-state errors. The proposed KRGMN algorithm can solve efficiently the problems such as nonlinear channel equalization and system identification in non-Gaussian noises. Simulation results confirm the desirable performance of the new algorithm. 相似文献