Real‐Time Nanomicroscopy via Three‐Dimensional Single‐Particle Tracking

We developed a new method for real‐time, three‐dimensional tracking of fluorescent particles. The instrument is based on a laser‐scanning confocal microscope where the focus of the laser beam is scanned or orbited around the particle. Two confocal pinholes are used to simultaneously monitor regions immediately above and below the particle and a feedback loop is used to keep the orbit centered on the particle. For moderate count rates, this system can track particles with 15 nm spatial resolution in the lateral dimensions and 50 nm in the axial dimension at a temporal resolution of 32 ms. To investigate the interaction of the tracked particles with cellular components, we have combined our orbital tracking microscope with a dual‐color, wide‐field setup. Dual‐color fluorescence wide‐field images are recorded simultaneously in the same image plane as the particle being tracked. The functionality of the system was demonstrated by tracking fluorescent‐labeled artificial viruses in tubulin‐eGFP expressing HUH7 cells. The resulting trajectories can be used to investigate the microtubule network with super resolution.     

非局部变分修复法去除高密度椒盐噪声

分析了中值滤波及其改进型算法在处理高密度椒盐噪声时效果不理想的原因,采用变分修复方法来去除高密度椒盐噪声,基于现有的全变差修复模型提出了非局部全变差修复模型。该模型利用椒盐噪声特点(均匀分布、灰度值为0或255),将噪声点看成是图像中遗失或是破损的点,首先在图像中寻找与噪声点邻域相似的区域,将相似区域的中心像素作为噪声点新的邻域然后对其插值,把图像降噪问题转化为图像修复问题,从而达到去除高密度噪声的目的。实验结果表明:该模型对噪声密度为90%的彩色和灰度图像去噪后,其峰值信噪比为22.85和28.77,在客观评价标准方面优于中值滤波及其改进型算法。该模型能有效去除高密度下的椒盐噪声并较好地恢复图像细节,为图像去除高密度噪声提供了一种新的途径。     

Choice Functions and Extensive Operators

The paper puts forth a theory of choice functions in a neat way connecting it to a theory of extensive operators and neighborhood systems. We consider classes of heritage choice functions satisfying conditions M, N, W, and C, or combinations of these conditions. In terms of extensive operators these classes can be considered as generalizations of symmetric, anti-symmetric and transitive binary relations. Among these classes we meet the well-known classes of matroids and convex geometries. Using a ‘topological’ language we discuss these classes of monotone extensive operators (or heritage choice functions) in terms of neighborhood systems. A remarkable inversion on the set of choice functions is introduced. Restricted to the class of heritage choice functions the inversion turns out to be an involution, and under this involution the axiom N is auto-inverse, whereas the axioms W and M change places. This research was supported in part by NWO–RFBR grant 047.011.2004.017, by RFBR grant 05-01-02805 CNRSL_a, and the grant NSh-929.2008.6, School Support. We want to thank B. Monjardet, the editor and a referee for discussions and useful suggestions.     

Connectivity preserving transformations for higher dimensional binary images

An N-dimensional digital binary image (I) is a function I:Z^N→{0,1}. I is connected if and only if its black pixels and white pixels are each (3^N−1)-connected. I is only connected if and only if its black pixels are (3^N−1)-connected. For a 3-D binary image, the respective connectivity models are and . A pair of (3^N−1)-neighboring opposite-valued pixels is called interchangeable in a N-D binary image I, if reversing their values preserves the original connectedness. We call such an interchange to be a (3^N−1)-local interchange. Under the above connectivity models, we show that given two binary images of n pixels/voxels each, we can transform one to the other using a sequence of (3^N−1)-local interchanges. The specific results are as follows. Any two -connected 3-dimensional images I and J each having n black voxels are transformable using a sequence of O((c₁+c₂)n²) 26-local interchanges. Here, c₁ and c₂ are the total number of 8-connected components in all 2-dimensional layers of I and J respectively. We also show bounds on connectivity under a different interchange model as proposed in [A. Dumitrescu, J. Pach, Pushing squares around, Graphs and Combinatorics 22 (1) (2006) 37-50]. Next, we show that any two simply connected images under the , connectivity model and each having n black voxels are transformable using a sequence of O(n²) 26-local interchanges. We generalize this result to show that any two , -connected N-dimensional simply connected images each having n black pixels are transformable using a sequence of O(Nn²)(3^N−1)-local interchanges, where N>1.     

基于小波变换的图像去噪方法的研究

小波变换能有效的去除高斯噪声,中值滤波能有效的去除脉冲噪声,两者结合可以更有效的去除高斯噪声和脉冲噪声的混合噪声.当医学图像去除混合噪声时,先进行中值滤波再进行小波去噪的方法优于先进行小波去噪后再进行中值滤波的方法,且去噪后图像视觉效果较好,而且图像均方误差(M SE)也较小.在图像去噪处理中这种方法具有实际应用价值.     

Fuzzy guaranteed cost controller for trajectory tracking in nonlinear systems

In this paper, we propose a fuzzy logic based guaranteed cost controller for trajectory tracking in nonlinear systems. Takagi–Sugeno (T–S) fuzzy model is used to represent the dynamics of a nonlinear system and the controller design is carried out using this fuzzy model. State feedback law is used for building the fuzzy controller whose performance is evaluated using a quadratic cost function. For designing the fuzzy logic based controller which satisfies guaranteed performance, linear matrix inequality (LMI) approach is used. Sufficient conditions are derived in terms of matrix inequalities for minimizing the performance function of the controller. The performance function minimization problem with polynomial matrix inequalities is then transformed into a problem of minimizing a convex performance function involving standard LMIs. This minimization problem can be solved easily and efficiently using the LMI optimization techniques. Our controller design method also ensures that the closed-loop system is asymptotically stable. Simulation study is carried out on a two-link robotic manipulator tracking a reference trajectory. From the results of the simulation study, it is observed that our proposed controller tracks the reference trajectory closely while maintaining a guaranteed minimum cost.     

一种结合Mean—shift和粒子滤波的视频跟踪算法

提出一种结合均值偏移算法和粒子滤波理论的视频跟踪算法,解决了目标旋转、部分遮挡和运动速度过快的问题．通过均值偏移对粒子滤波中的粒子集进行进一步寻优,增加了粒子的有效性,极大减少了粒子采样的数量,且解决了经过多次重采样后粒子多样性降低的问题．新的粒子通过与观测值之间的巴氏系数来决定重要性权重．实验证明：本算法可以完成实时地对视频目标进行部分遮挡以及目标旋转下的跟踪,具有较强的鲁棒性．     

一种基于三角形区域生长的图像篡改检测方法

针对现有的多数图像篡改检测算法中存在着的对旋转、缩放等篡改失效和计算量大等问题,利用三角形具有抗平移、旋转、尺度缩放的优越特性,提出了一种新的图像篡改检测算法.首先,利用Delaunay三角剖分算法对提取的Harris特征角点进行三角剖分,进行相似三角形的初始匹配.然后,以匹配的相似三角形顶点为种子点,建立三角形组,再进行一次相似三角形的匹配,实现对篡改区域的三角形生长.最后,利用区域面积阈值和数学形态学准确定位出篡改区域.实验结果表明,该算法与同类算法相比不仅能有效地对抗旋转、缩放,噪声等后期处理操作,而且对篡改区域有很好的检测和定位效果并具有计算复杂度低的特点.     

基于几何矩预分类的无人机遥感图像自动配准方法

图像配准技术是近些年来图像处理领域发展迅速的研究方向之一.在遥感领域内,图像配准更是实现图像融合、运动检测、图像校正、图像拼接等应用的一个关键步骤.尽管国内外目前在图像配准方面提出了很多方法,但不同方法适用的图像范围不同,很多时候需要人工干预进行方法的选择.尤其对于无人机这种快速、实时获取图像的新型遥感平台,如何集合不同方法的优点以实现图像自动配准成为了关键性问题.本文在比较分析了基于SIFT和SURF特征提取图像配准方法的各自优势后,提出基于几何矩的方法对图像进行预先分类,从而决定将其分配给何种方法进行配准,实现全程自动化.实验证明,这种图像自动配准方法在拓宽了图像应用范围的同时保证了良好的配准效果.     

基于相关因素的遥感影像辐射质量度量模型研究

目前遥感影像辐射质量评价多以目视判读为主,具有很强的主观性。针对如何客观、全面地评价遥感影像辐射质量这一问题,本文研究了一种利用质量相关因素来评价遥感影像辐射质量的度量模型。该模型提取遥感影像的四个因素指标,即亮度、清晰度、信息量和纹理特征,采用相关分析法计算各个因素指标的权值。对于清晰度指标,通过改进梯度函数,研究了新的清晰度提取方法。实验证明,对于多种不同类型的遥感影像,本模型所得的评价结果可较好地符合人眼的视觉感受。该遥感影像辐射质量度量模型能够客观、定量地分析遥感影像辐射质量,同时与主观评价具有一致性。