An overlapping tree approach to multiscale stochastic modeling andestimation

Recently, a class of multiscale stochastic models has been introduced in which random processes and fields are described by scale-recursive dynamic trees. A major advantage of this framework is that it leads to an extremely efficient, statistically optimal algorithm for least-squares estimation. In certain applications, however, estimates based on the types of multiscale models previously proposed may not be adequate, as they have tended to exhibit a visually distracting blockiness. We eliminate this blockiness by discarding the standard assumption that distinct nodes on a given level of the multiscale process correspond to disjoint portions of the image domain; instead, we allow a correspondence to overlapping portions of the image domain. We use these so-called overlapping-tree models for both modeling and estimation. In particular, we develop an efficient multiscale algorithm for generating sample paths of a random field whose second-order statistics match a prespecified covariance structure, to any desired degree of fidelity. Furthermore, we demonstrate that under easily satisfied conditions, we can "lift" a random field estimation problem to one defined on an overlapped tree, resulting in an estimation algorithm that is computationally efficient, directly produces estimation error covariances, and eliminates blockiness in the reconstructed imagery without any sacrifice in the resolution of fine-scale detail.     

Modeling Human Physiology: The IUPS/EMBS Physiome Project

The Physiome Project is an international collaboration to provide a framework for understanding human physiology, from proteins and cells to tissues and organs, with multiscale models that use computational techniques derived from engineering and software approaches from computer science. With the increasing interest in modeling living systems from research scientists in many branches of mathematics, physics, and engineering, it is timely to review what has been achieved, what lessons can be learned from the efforts so far, and what needs to be done to facilitate the international collaboration that is essential to the project's success. In particular, we review the development of models at spatial scales from genes and proteins to the whole body, and the development of standards, tools, and databases to facilitate multiscale modeling. Some applications of the physiome models are described, including applications in medical diagnostics, the design of medical devices, virtual surgery, surgical training, and medical education.     

Multiscale autoregressive processes. I. Schur-Levinsonparametrizations

In many applications it is of interest to analyze and recognize phenomena occurring at different scales. The recently introduced wavelet transforms provide a time-and-scale decomposition of signals that offers the possibility of such analysis. A corresponding statistical framework to support the development of optimal, multiscale statistical signal processing algorithms is described. The theory of multiscale signal representation leads naturally to models of signals on trees, and this provides the framework for investigation. In particular, the class of isotropic processes on homogeneous trees is described, and a theory of autoregressive models is developed in this context. This leads to generalizations of Schur and Levinson recursions, associated properties of the resulting reflection coefficients, and the initial pieces in a system theory for multiscale modeling     

Structural similarity quality metrics in a coding context: exploring the space of realistic distortions

Perceptual image quality metrics have explicitly accounted for human visual system (HVS) sensitivity to subband noise by estimating just noticeable distortion (JND) thresholds. A recently proposed class of quality metrics, known as structural similarity metrics (SSIM), models perception implicitly by taking into account the fact that the HVS is adapted for extracting structural information from images. We evaluate SSIM metrics and compare their performance to traditional approaches in the context of realistic distortions that arise from compression and error concealment in video compression/transmission applications. In order to better explore this space of distortions, we propose models for simulating typical distortions encountered in such applications. We compare specific SSIM implementations both in the image space and the wavelet domain; these include the complex wavelet SSIM (CWSSIM), a translation-insensitive SSIM implementation. We also propose a perceptually weighted multiscale variant of CWSSIM, which introduces a viewing distance dependence and provides a natural way to unify the structural similarity approach with the traditional JND-based perceptual approaches.     

Switched reluctance generators and their control

This paper discusses how the switched reluctance generator (SRG) converts energy as directed by a controller. Beginning with a review of the electromechanics of generation, the paper identifies the implications of the energy conversion process on how the SRG is controlled. The structure of the SRG controller for speed-control and power-control applications is discussed. Practical implementation details for commutation of the SRG are reviewed. Concepts are illustrated with a 6-kW SRG designed to serve as a starter/alternator in automotive applications     

Hierarchical stochastic modeling of SAR imagery forsegmentation/compression

There has been a growing interest in synthetic aperture radar (SAR) imaging on account of its importance in a variety of applications. One attribute leading to its gain in popularity is its ability to image terrain at extraordinary rates. Acquiring data at such rates, however, has drawbacks in the form of exorbitant costs in data storage and transmission over relatively slow channels; thus, addressing these problems is clearly important. To abate these and related costs, we propose a segmentation-driven compression technique using hierarchical stochastic modeling within a multiscale framework. Our approach to SAR image compression is unique in that we exploit the multiscale stochastic structure inherent in SAR imagery. This structure is well captured by a set of scale auto-regressive (AR) models that accurately characterize the evolution in scale of homogeneous regions of different classes of terrain. We thus use them to generate a multiresolution segmentation of the image. The segmentation is subsequently used in tandem with the corresponding models in a pyramid encoder to provide a robust, hierarchical compression technique that, in addition to coding the segmentation, achieves high compression ratios with impressive image quality     

SAR图像压缩的多尺度自回归滑动平均模型方法

本文研究在无需SAR图像先验知识条件下,基于多尺度自回归滑动平均MARMA模型的SAR图像压缩方法.该方法首先对SAR图像建立MARMA模型,依据MARMA模型对原始图像进行预测,然后对预测的残量进行数据压缩.将此方法用于实际SAR图像压缩,并将基于MARMA模型和多尺度自回归MAR模型的压缩结果与相应的JPEG结果进行比较和分析,说明基于MARMA模型的SAR图像压缩方法既能达到较高的压缩比,又能取得较好的保真度,是一种很有潜力的压缩方法.     

基于小波变换的多尺度建模和估计理论概述

在许多应用领域中,通常要对出现在不同尺度的现象进行分析和辨识,最近引入的多尺度框架使这一分析成为可能.本文简单介绍了多尺度建模和估计理论的发展概况,分析了多尺度模型、平滑误差模型以及两类多尺度实现模型,并指出了目前急需解决的问题.     

Can multiscale traffic analysis be used to differentiate Internet applications?

An accurate mapping of Internet traffic to applications can be important for a broad range of network management and measurement tasks, including traffic engineering, service differentiation, performance/failure monitoring and security. Traditional mapping approaches have become increasingly inaccurate because many applications use non-default or ephemeral port numbers, use well-known port numbers associated with other applications, change application signatures or use traffic encryption. In this paper we will demonstrate that multiscale traffic analysis based on multi-order wavelet spectrum can be used as a discriminator of Internet applications traffic profiles. By performing clustering analysis over the multiscale wavelet spectrum coefficients that are inferred from the measured traffic, the proposed methodology is able to efficiently differentiate different IP applications without using any payload information. This characteristic will allow the differentiation of traffic flows in unencrypted and encrypted scenarios. In order to compare the differentiating potential of different traffic application data, upload, download and joint upload and download flow statistics are considered to evaluate the identification approach for each selected protocol. Moreover, we also evaluate which timescales and spectrum orders are more relevant for the traffic differentiation. From the analysis of the obtained results we can conclude that the proposed methodology is able to achieve good identification results using a small set of timescales of a single order wavelet spectrum of a general raw traffic statistic.     

Fast multiscale modeling of cardiac electrophysiology including Purkinje system

In this paper, we present a modeling methodology to couple the cardiac conduction system to cardiac myocytes through a model of Purkinje-ventricular junctions to yield fast and realistic electrical activation of the ventricles. A patient-specific biventricular geometry is obtained from processing computed tomography scan data. A one-manifold implementation of the fast marching method based on Eikonal-type equations is used for modeling heart electrophysiology, which facilitates the multiscale 1-D-3-D coupling at very low computational costs. The method is illustrated in in-silico experiments where we analyze and compare alternative pacing strategies on the same patient-specific anatomy. We also show very good agreement between the results from the proposed approach and more detailed and comprehensive biophysical models for modeling cardiac electrophysiology. The effect of atrioventricular delay on the distribution of activation time in myocardium is studied with two experiments. Given the reasonable computational times and realistic activation sequences provided by our method, it can have an important clinical impact on the selection of optimal implantation sites of pacing leads or placement of ablation catheter's tip in the context of cardiac rhythm management therapies.     

Construction of a computational anatomical model of the peripheral cardiac conduction system

A methodology is presented here for automatic construction of a ventricular model of the cardiac conduction system (CCS), which is currently a missing block in many multiscale cardiac electromechanic models. It includes the His bundle, left bundle branches, and the peripheral CCS. The algorithm is fundamentally an enhancement of a rule-based method known as the Lindenmayer systems (L-systems). The generative procedure has been divided into three consecutive independent stages, which subsequently build the CCS from proximal to distal sections. Each stage is governed by a set of user parameters together with anatomical and physiological constrains to direct the generation process and adhere to the structural observations derived from histology studies. Several parameters are defined using statistical distributions to introduce stochastic variability in the models. The CCS built with this approach can generate electrical activation sequences with physiological characteristics.     

Interaction of specialized cardiac conduction system with antiarrhythmic drugs: a simulation study

The use of antiarrhythmic drugs is common to treat heart rhythm disorders. Computational modeling and simulation are promising tools that could be used to investigate the effects of specific drugs on cardiac electrophysiology. In this paper, we study the multiscale effects of dofetilide, a drug that blocks IKr, from cellular to organ level paying special attention to its effect on heart structures, in particular the specialized cardiac conduction system (CCS). We include a model of the CCS in a patient-specific anatomical ventricular model and study the drug effects in simulations with and without a CCS. Results confirmed the expected effects of dofetilide at cellular level, increasing the action potential duration, and at organ level, prolonging the QT segment. Notable differences are shown between models with and without the CCS on action potential duration distributions. These techniques show the importance of heart heterogeneity and the global effects of the interaction of drugs with cardiac structures.     

基于两种神经网络的SAR图像多尺度分割与分析

基于多尺度回归技术和神经网络提出两种合成孔径雷达(SAR)图像分割的新方法.首先利用多尺度自回归模型(MAR)来描述SAR图像不同尺度间的统计相依性,以此提取SAR图像的多尺度统计特征;然后分别构造自组织特征映射网络和概率神经网络,并利用统计特征作为输入训练两种网络,实现SAR图像的分割.最后通过实验对这两种方法以及其他方法之间进行比较、分析,结果表明本文提出的两种方法的实验结果比较理想.     

Bayesian Inference on Multiscale Models for Poisson Intensity Estimation: Applications to Photon-Limited Image Denoising

We present an improved statistical model for analyzing Poisson processes, with applications to photon-limited imaging. We build on previous work, adopting a multiscale representation of the Poisson process in which the ratios of the underlying Poisson intensities (rates) in adjacent scales are modeled as mixtures of conjugate parametric distributions. Our main contributions include: 1) a rigorous and robust regularized expectation-maximization (EM) algorithm for maximum-likelihood estimation of the rate-ratio density parameters directly from the noisy observed Poisson data (counts); 2) extension of the method to work under a multiscale hidden Markov tree model (HMT) which couples the mixture label assignments in consecutive scales, thus modeling interscale coefficient dependencies in the vicinity of image edges; 3) exploration of a 2-D recursive quad-tree image representation, involving Dirichlet-mixture rate-ratio densities, instead of the conventional separable binary-tree image representation involving beta-mixture rate-ratio densities; and 4) a novel multiscale image representation, which we term Poisson-Haar decomposition, that better models the image edge structure, thus yielding improved performance. Experimental results on standard images with artificially simulated Poisson noise and on real photon-limited images demonstrate the effectiveness of the proposed techniques.      

变分框架下的多尺度图像恢复与重建

变分图像分解,通过极小化能量泛函将图像分解为不同的特征分量,可以被应用到图像的恢复和重建.提出了变分框架下的多尺度图像恢复和重建的思想.基于这种思想,首先提出了一个单参数的（BV,G,E）三元变分分解模型,并且理论分析了参数与不同特征分量的尺度的关系.然后将此模型的参数选为一个二进制序列,得到多尺度的（BV,G,E）变分分解.该多尺度变分分解可以将图像分解为一序列图像结构、纹理和噪声.证明了此多尺度分解的收敛性并且基于对偶理论和交替迭代算法给出了其数值求解方法.最后将提出的多尺度的（BV,G,E）变分分解应用到图像恢复和重建,实验结果证实了理论分析的正确性,显示了将此模型进行图像多尺度恢复和重建的有效性,和与一些其他分解模型相比较的优越性.     

多尺度Markov模型的可适应图像分割方法

本文在图像分割的TSMAP(trainable sequential maximum a posterior)方法基础上,提出基于多尺度Markov模型的可适应ATSMAP(adaptive TSMAP)图像分割方法.在给定训练图像及其基本真实分割(ground truth segmentation,GTS)的基础上,通过直接对原始图像的GTS进行小波变换产生粗尺度上的GTS,进而估计出图像数据的分布参数和Markov四叉树模型参数;上下文模型参数根据上下文的低维特征(类别数量特征)而非上下文本身来估计.该方法具有上下文模型参数估计计算量小,Markov四叉树模型参数可针对特定的待分割图像重新优化等优点(模型适应过程),解决了TSMAP方法易导致过学习的问题,在待分割图像与训练图像的统计特性不匹配的情况下,仍能给出较好的分割结果.对合成图像与SAR图像的实验结果表明,这种方法的分割精度高于TSMAP和其它几种基于多尺度Markov模型的图像分割方法.     

Gray and color image contrast enhancement by the curvelet transform

We present a new method for contrast enhancement based on the curvelet transform. The curvelet transform represents edges better than wavelets, and is therefore well-suited for multiscale edge enhancement. We compare this approach with enhancement based on the wavelet transform, and the multiscale retinex. In a range of examples, we use edge detection and segmentation, among other processing applications, to provide for quantitative comparative evaluation. Our findings are that curvelet based enhancement out-performs other enhancement methods on noisy images, but on noiseless or near noiseless images curvelet based enhancement is not remarkably better than wavelet based enhancement.     

Visual attention on the sphere

Human visual system makes an extensive use of visual attention in order to select the most relevant information and speed-up the vision process. Inspired by visual attention, several computer models have been developed and many computer vision applications rely today on such models. However, the actual algorithms are not suitable to omnidirectional images, which contain a significant amount of geometrical distortion. In this paper, we present a novel computational approach that performs in spherical geometry and thus is suitable for omnidirectional images. Following one of the actual models of visual attention, the spherical saliency map is obtained by fusing together intensity, chromatic, and orientation spherical cue conspicuity maps that are themselves obtained through multiscale analysis on the sphere. Finally, the consecutive maxima in the spherical saliency map represent the spots of attention on the sphere. In the experimental part, the proposed method is then compared to the standard one using a synthetic image. Also, we provide examples of spots detection in real omnidirectional scenes which show its advantages. Finally, an experiment illustrates the homogeneity of the detected visual attention in omnidirectional images.     

A joint multicontext and multiscale approach to Bayesian imagesegmentation

In this paper, a joint multicontext and multiscale (JMCMS) approach to Bayesian image segmentation is proposed. In addition to the multiscale framework, the JMCMS applies multiple context models to jointly use their distinct advantages, and we use a heuristic multistage, problem-solving technique to estimate sequential maximum a posteriori of the JMCMS. The segmentation results on both synthetic mosaics and remotely sensed images show that the proposed JMCMS improves the classification accuracy, and in particular, boundary localization and detection over the methods using a single context at comparable computational complexity