Adaptive importance sampling in signal processing

In Bayesian signal processing, all the information about the unknowns of interest is contained in their posterior distributions. The unknowns can be parameters of a model, or a model and its parameters. In many important problems, these distributions are impossible to obtain in analytical form. An alternative is to generate their approximations by Monte Carlo-based methods like Markov chain Monte Carlo (MCMC) sampling, adaptive importance sampling (AIS) or particle filtering (PF). While MCMC sampling and PF have received considerable attention in the literature and are reasonably well understood, the AIS methodology remains relatively unexplored. This article reviews the basics of AIS as well as provides a comprehensive survey of the state-of-the-art of the topic. Some of its most relevant implementations are revisited and compared through computer simulation examples.     

Adaptive sampling for generalized probabilistic roadmaps

In this paper,an adaptive sampling strategy is presented for the generalized sampling-based motion planner,generalized probabilistic roadmap (GPRM).These planners are designed to account for stochastic...     

Adaptive sampling immune algorithm solving joint chance-constrained programming

This work investigates one immune optimization algorithm in uncertain environments, solving linear or nonlinear joint chance-constrained programming with a general distribution of the random vector. In this algorithm, an a priori lower bound estimate is developed to deal with one joint chance constraint, while the scheme of adaptive sampling is designed to make empirically better antibodies in the current population acquire larger sample sizes in terms of our sample-allocation rule. Relying upon several simplified immune metaphors in the immune system, we design two immune operators of dynamic proliferation and adaptive mutation. The first picks up those diverse antibodies to achieve proliferation according to a dynamical suppression radius index, which can ensure empirically potential antibodies more clones, and reduce noisy influence to the optimized quality, and the second is a module of genetic diversity, which exploits those valuable regions and finds those diverse and excellent antibodies. Theoretically, the proposed approach is demonstrated to be convergent. Experimentally, the statistical results show that the approach can obtain satisfactory performances including the optimized quality, noisy suppression and efficiency.     

3D hyperbolic Voronoi diagrams

Voronoi diagrams have useful applications in various fields and are one of the most fundamental concepts in computational geometry. Although Voronoi diagrams in the plane have been studied extensively, using different notions of sites and metrics, little is known for other geometric spaces. In this paper, we are interested in the Voronoi diagram of a set of sites in the 3D hyperbolic upper half-space. We first present some introductory results in 3D hyperbolic upper half-space and then give an incremental algorithm to construct Voronoi diagram. Finally, we consider five models of 3D hyperbolic manifolds that are equivalent under isometries. By these isometries we can transform the Voronoi diagram of each model to others.     

玻璃图像实时采集与同步技术研究

分布式的多目视觉在线检测系统中如何解决图像采集与处理时的同步问题是一个关键任务。对玻璃质量在线检测系统中图像实时采集时的同步问题、分级打标与图像采集的同步问题进行了研究。采用光电编码器与外部同步器实现了多台线阵CCD相机的同步图像采集;采用SNTP同步协议,并通过外部时钟同步信号与软件时钟同步相结合的方法实现了分布式检测系统中的时钟同步;实现了玻璃检测中的图像采集与打标分级处理之间的帧同步与版同步,分析了作为同步信号的帧周期信号与版周期信号,判定玻璃切割的落刀信号（版周期信号）具有更高的优先级。该技术研究已经成功应用于工业现场。     

基于BEMD和自适应滤波的医学图像增强

针对医学图像存在低对比度和质量差的主要问题,本文提出了一种基于BEMD和自适应滤波的医学图像增强新算法。首先,对医学图像进行BEMD分解,然后用自适应滤波对频率域进行去噪,再使用不同的加权值提高子带图像的高频系数,最后对图像进行重构得到增强图像。实验表明,该方法不仅提高了图像的细节信息,而且有效地保留了图像的边缘特征。     

基于非参数化采样的单幅图像深度估计

针对传统单幅图像深度估计线索不足及深度估计精度不准的问题,提出一种基于非参数化采样的单幅图像深度估计方法。该方法利用非参数化的学习手段,将现有RGBD数据集中的深度信息迁移到输入图像中去。首先计算输入图像和现有RGBD数据集多尺度的高层次图像特征;然后,在现有RGBD数据集中,基于高层次的图像特征通过kNN最近邻搜索找到若干与输入图像特征最匹配的候选图像,并将这些候选图像对通过SIFT流形变到输入图像进行对齐。最后,对候选深度图进行插值和平滑等优化操作便可以得到最后的深度图。实验结果表明,与现有算法相比,该方法估计得到的深度图精度更高,对输入图像的整体结构保持得更好。     

一个基于深度图像的三维模型检索算法

三维模型检索是现在的研究热点,提出一种基于深度图像的三维模型检索算法。对三维模型进行规范化处理,采用基于正交投影的方法计算三维模型在其包围立方体的六个面上的深度图像;提取深度图像的边界方向直方图和Zernike矩特征;利用特征距离度量进行三维模型检索,并采用相关反馈技术实现权值的调整,得到用户最满意的目标检索模型。对比实验表明,该算法避免了传统视觉图像丢失三维模型空间信息的缺点,有效地提高了检索的精确性和鲁棒性。     

基于改进测地线模型的医学图像分割

提出了一种由测地线活动轮廓模型GAC（Geodesic Active Contour）和局部区域信息相结合的图像分割新方法LGAC（Local Geodesic Active Contour）。构造了基于图像局部信息的演化曲线符号压力函数和演化模型,用水平集方法演化实现,零水平集能准确地在目标边缘收敛,对目标背景对比度较低的图像的分割达到理想效果。利用高斯核函数对水平集函数平滑处理以维持演化稳定,节省了计算时间。实验结果证明了该方法的可行性。     

CMOS image sensor with optimal video sampling scheme

Time-varying illumination on the focal plane is a three-dimensional signal.Multidimensional sam-pling theory proves that the temporal resolution can be optimally improved by a factor of 2～(1/2) while the spatial resolution is reserved by changing the sampling scheme.Based on the theory,a prototype multi-field CMOS image sensor (CIS) is designed for a 0.35-μm 2P4M CMOS process.Corresponding pixels in 4×4-pixel clusters are assembled into 16 fields over the whole array.Control pins (resets and shutters) of pixels are separated which provides the ability of sampling the illumination with the optimal sampling scheme.     

自适应Mean Shift算法的彩色图像平滑与分割算法

采用Mean shift算法对图像进行平滑和分割处理时, 带宽和采样点权重的选择直接影响平滑和分割的效果. 带宽分为空域带宽和值域带宽. 本文根据图像颜色分布的丰富程度定义了自适应空域带宽. 在此基础上, 通过最小化局部方差函数和最大化频域结构相似度函数获得自适应值域带宽. 此外, 通过定义采样点权重, 克服了图像过平滑问题. 通过随机选取大量的图像进行实验, 结果表明运用本文所选择的带宽和权重, 可以得到正确的图像区域分割结果.     

Adaptive tree similarity learning for image retrieval

Learning-enhanced relevance feedback is one of the most promising and active research directions in content-based image retrieval in recent years. However, the existing approaches either require prior knowledge of the data or converge slowly and are thus not coneffective. Motivated by the successful history of optimal adaptive filters, we present a new approach to interactive image retrieval based on an adaptive tree similarity model to solve these difficulties. The proposed tree model is a hierarchical nonlinear Boolean representation of a user query concept. Each path of the tree is a clustering pattern of the feedback samples, which is small enough and local in the feature space that it can be approximated by a linear model nicely. Because of the linearity, the parameters of the similartiy model are better learned by the optimal adaptive filter, which does not require any prior knowledge of the data and supports incremental learning with a fast convergence rate. The proposed approach is simple to implement and achieves better performance than most approaches. To illustrate the performance of the proposed approach, extensive experiments have been carried out on a large heterogeneous image collection with 17,000 images, which render promising results on a wide variety of queries.An early version of part of the system was reported in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition 2001.     

基于图变换的图像压缩采样与分类

提出一种基于图论表示的正交变换基,并在此基础上对图像进行压缩采样与压缩域直接分类.首先,充分利用图像的边缘特性和像素关系,给出一种图像的图论表示方法;然后,通过图Laplacian矩阵的特征值分解得到其特征向量矩阵作为正交变换基,由此得到图像的图变换域稀疏表示;最后,利用随机投影后的压缩采样特征向量直接对分类器进行训练和测试,不仅保持了与原空间相当的分类精度,还大量地减少了训练和测试时间以及计算/存储代价.     

基于小波变换的权重自适应图像分割模型

针对灰度不均匀且含噪声图像的分割问题,提出了全局和局部灰度信息的权重参 数自适应水平集分割模型。首先,利用图像的全局和局部灰度信息构造全局能量项和局部能量 项;然后,利用小波变换和小波阈值去噪方法,构造对噪声不敏感的边缘信息刻画矩阵,定义包含 图像边缘信息的自适应权重系数矩阵;最后,利用定义的权重系数矩阵组合全局和局部能量项, 得到分割模型的能量泛函。使用变分法得到了水平集函数演化方程,利用有限差分法实现数值 求解。实验结果表明,该模型兼有 Chan-Vese 模型和 Local Binary Fitting 模型的优点,能够有效 地分割灰度不均匀含噪图像,并对活动轮廓曲线的初始位置和初始形状具有很强的鲁棒性。     

面向图像集复合质量的压缩采样分配算法

对于一个航拍图像集的压缩感知编码,现有方案只能采用固定的测量分配机制对其中每幅图像进行压缩采样,未考虑图像之间的差异性以及图像集的整体重构质量,因此难以充分利用有限的采样资源。在总的采样资源约束下,如何为航拍图像集中不同图像分配合理的采样率是一个需要解决的问题。首先,根据航拍图像集的通用需求提出了图像集复合质量的评价指标,用以计算图像集的整体重构质量;随后,根据图像集中不同图像的相对复杂度建立了一个图像方差模型,并基于该模型提出了一种图像集的压缩采样分配算法。实验结果表明相比于现有方案,在相同的采样资源约束下,所提算法有效地提升了航拍图像集的整体重构质量。     

Topological model for 3D image representation: Definition and incremental extraction algorithm

In this paper, we define the three-dimensional topological map, a model which represents both the topological and geometrical information of a three-dimensional labeled image. Since this model describes the image’s topology in a minimal way, we can use it to define efficient image processing algorithms. The topological map is the last level of map hierarchy. Each level represents the region boundaries of the image and is defined from the previous level in the hierarchy, thus giving a simple constructive definition. This model is an extension of the similar model defined for 2D images. Progressive definition based on successive map levels allows us to extend this model to higher dimension. Moreover, with progressive definition, we can study each level separately. This simplifies the study of disconnection cases and the proofs of topological map properties. Finally, we provide an incremental extraction algorithm which extracts any map of the hierarchy in a single image scan. Moreover, we show that this algorithm is very efficient by giving the results of our experiments made on artificial images.     

Adaptive sampling design for multi-task learning of Gaussian processes in manufacturing

Approximation models (or surrogate models) have been widely used in engineering problems to mitigate the cost of running expensive experiments or simulations. Gaussian processes (GPs) are a popular tool used to construct these models due to their flexibility and computational tractability. The accuracy of these models is a strong function of the density and locations of the sampled points in the parametric space used for training. Previously, multi-task learning (MTL) has been used to learn similar-but-not-identical tasks together, thus increasing the effective density of training points. Also, several adaptive sampling strategies have been developed to identify regions of interest for intelligent sampling in single-task learning of GPs. While both these methods have addressed the density and location constraint separately, sampling design approaches for MTL are lacking. In this paper, we formulate an adaptive sampling strategy for MTL of GPs, thereby further improving data efficiency and modeling performance in GP. To this end, we develop variance measures for an MTL framework to effectively identify optimal sampling locations while learning multiple tasks simultaneously. We demonstrate the effectiveness of the proposed method using a case study on a real-world engine surface dataset. We observe that the proposed method leverages both MTL and intelligent sampling to significantly outperform state-of-the-art methods which use either approach separately. The developed sampling design strategy is readily applicable to many problems in various fields.     

Adaptive pixon represented segmentation (APRS) for 3D MR brain images based on mean shift and Markov random fields

In this paper, we proposed an adaptive pixon represented segmentation (APRS) algorithm for 3D magnetic resonance (MR) brain images. Different from traditional method, an adaptive mean shift algorithm was adopted to adaptively smooth the query image and create a pixon-based image representation. Then K-means algorithm was employed to provide an initial segmentation by classifying the pixons in image into a predefined number of tissue classes. By using this segmentation as initialization, expectation-maximization (EM) iterations composed of bias correction, a priori digital brain atlas information, and Markov random field (MRF) segmentation were processed. Pixons were assigned with final labels when the algorithm converges. The adoption of bias correction and brain atlas made the current method more suitable for brain image segmentation than the previous pixon based segmentation algorithm. The proposed method was validated on both simulated normal brain images from BrainWeb and real brain images from the IBSR public dataset. Compared with some other popular MRI segmentation methods, the proposed method exhibited a higher degree of accuracy in segmenting both simulated and real 3D MRI brain data. The experimental results were numerically assessed using Dice and Tanimoto coefficients.