用SURE引导自适应采样与采样颜色直方图重构

针对现有采样颜色直方图重构缺少自适应采样方法的问题,提出一种基于Stein’s unbiased risk estimator(SURE)的像素均方误差计算方法.首先对图像空间粗采样;然后在GPU上分块计算SURE来评估图像每个像素的误差度量值,并用该值引导非均匀自适应采样;最后使用非局部多尺度滤波方法重构图像.实验结果表明,不论从图像噪声定量化指标还是视觉效果来看,该方法都极大地改进了图像绘制质量.     

非下采样Contourlet变换自适应图像去噪方法

提出了一种基于非下采样Contourlet变换的自适应图像去噪方法。首先对噪声图像进行非下采样Contourlet变换,得到各个尺度各个方向子带的系数,再根据该系数的能量自适应地调整去噪阈值。实验表明,与Contourlet多尺度阈值去噪、Contourlet自适应阈值去噪相比,该方法在保留图像边缘细节的同时,能提高图像的PSNR值,减少了Gibbs现象。     

一种基于非下采样Contourlet变换的自适应阈值去噪方法

文章提出了一种基于非下采样Contourlet变换的自适应图像去噪方法。首先对噪声图像进行非下采样Contourlet变换,得到各个尺度各个方向子带的系数,再根据该系数的能量自适应地调整Bayes去噪阈值。实验结果表明：与小波阈值去噪方法对比,非下采样Contourlet自适应阈值去噪算法在保留图像边缘细节的同时,不仅能明显提高图像的SNR值,而且还减少了Gibbs现象。     

基于小波域降采样的低比特率图像压缩算法

针对无线传输背景下低比特率图像压缩存在的模糊和振铃问题,提出一种基于小波域降采样和插值的高效图像压缩算法.在编码端,对图像进行小波变换,根据各高频子带特点对其进行自适应降采样处理,并采用基于小波树的小波差分缩减编码算法进行编码.在解码端,采用基于边缘方向的插值方法将解码的高频子带进行放大,对解码重建的图像采用基于强边缘的自适应滤波算法以消除振铃效应.实验结果表明,与基于空域降采样的图像压缩算法相比,该算法具有较高的图像解码质量,可有效抑制低比特率下重建图像的模糊和振铃问题.     

基于NSCT和自适应PCNN的遥感图像融合方法

以全色和多光谱遥感图像为研究对象,提出一种基于非下采样Contourlet变换(NSCT)和自适应脉冲耦合神经网络(PC-NN)的遥感图像融合方法;该方法首先对全色图像和进行过IHS变换的多光谱图像的亮度分量进行NSCT变换,得到低频子带系数和各带通子带系数;其次对低频子带系数采取一种基于边缘的方法以得到融合图像的低频子带系数;然后采用以各带通子带系数的梯度作为PCNN的链接强度β的PCNN图像融合方法来确定融合图像的各带通子带系数;最后经过NSCT逆变换和IHS逆变换得到融合图像;实验结果表明,此方法更好地保留了原遥感图像中的有用信息,并提高了融合图像的质量。     

非下采样Contourlet域自适应阈值面的磁瓦表面缺陷检测

为提高磁瓦表面缺陷人工检测效率、防止缺陷漏检,针对经典缺陷检测算法不能很好地提取颜色暗、对比度低的磁瓦图像缺陷问题,提出一种非下采样Contourlet域自适应阈值面的磁瓦缺陷自动检测方法.该方法根据非下采样Contourlet变换(NSCT)子带系数所在不同区域的特性,采用线扫描的方式对NSCT系数进行阈值处理,给出不同尺度、不同方向的归一化自适应阈值面;并与原始NSCT各子带归一化系数对比分割,以实现对磁瓦图像NSCT系数逐列自适应修正;最后重构NSCT系数提取出磁瓦缺陷.实验结果表明,文中方法能够有效地去除磁瓦表面纹理,提取出磁瓦表面缺陷的准确率可达95%.     

深度图像的分块自适应压缩感知

针对基于空域上下采样的深度编码框架中,由边缘信息损失带来的视点绘制质量下降的问题,提出了一种面向视点绘制质量的深度图像分块自适应压缩采样方法。在基于分块压缩感知和光滑Landweber投影重构的BCS_SPL框架下,利用图像块的方差表征其边缘信息,并据此进行自适应采样,以提高深度图像重构和视点合成质量。结果表明,在相同的采样率下,相比上下采样和BCS_SPL方法,本文提出的分块自适应压缩感知方法在绘制视点的PSNR和主观质量上都有提高。     

一种空间自适应采样和递归线性估计的光线投射算法

光线投射算法因其成像质量高而广泛地用于虚拟内窥镜系统,但成像速度非常缓慢.为此,本文提出了一种自适应采样和递归估计的成像加速算法.首先,根据查找法快速得到的梯度和光线方向信息,自适应地调整采样步长,使得该算法能够以大步长快速跳过体素值变化缓慢的区域,同时在体素值变化剧烈或快接近等值面的区域,能够以小步长进行搜索.其次,以递归线性插值的方法估计投射光线与实际等值面的交点,用于补偿大步长导致交点精度的降低,此举能够显著地提高成像质量.实验结果表明,该算法在保证绘制图像质量的前提下,提高了体绘制速度,取得了比较满意的效果.     

基于自适应八叉树划分的高精度四面体可视化

利用八叉树结构将四面体数据转化为规则网格数据,能有效提高系统的交互性能.八叉树的划分层次越高,绘制效果越好,但数据的存储空间以及处理时间也将大幅增多.提出自适应的规则化表示方法来构建八叉树结构,改进原有的单一采样策略,并结合深度信息将采样结果转换成适用于GPU的八叉树纹理结构.然后采用光线投射算法来对体数据进行绘制,根据各区域深度不一的特点,提出了变步长的采样绘制策略.实验结果表明,本文方法降低了数据的空间存储量和处理时间,同时在绘制质量、绘制效率方面都得到了较大提高.     

基于非下采样Contourlet的多传感器图像自适应融合

提出了一种基于非下采样Contourlet变换的多传感器图像自适应融合方法,采用黄金分割法搜索最优的低频融合权值.自适应地对多传感器图像的低频子带系数进行融合.非下采样Contourlet变换是一种新的图像多尺度、多方向的表示方法,适合表达具有丰富细节信息及方向信息的图像,且该变换具有平移不变性,可以避免一般方法对融合图像引入的振铃效应,它的高频方向子带捕获了多传感器图像的显著特征,文中采用同一尺度下方向子带信息和取大的规则对高频系数进行融合.实验结果表明,与基于拉普拉斯塔、小波、平稳小波和Contourlet变换的方法比较,文中所提出的方法可以获得较好的融合效果.     

KD-tree based parallel adaptive rendering

Multidimensional adaptive sampling technique is crucial for generating high quality images with effects such as motion blur, depth-of-field and soft shadows, but it costs a lot of memory and computation time. We propose a novel kd-tree based parallel adaptive rendering approach. First, a?two-level framework for adaptive sampling in parallel is introduced to reduce the computation time and control the memory cost: in the prepare stage, we coarsely sample the entire multidimensional space and use kd-tree structure to separate it into several multidimensional subspaces; in the main stage, each subspace is refined by a sub kd-tree and rendered in parallel. Second, novel kd-tree based strategies are introduced to measure space’s error value and generate anisotropic Poisson disk samples. The experimental results show that our algorithm produces better quality images than previous ones.     

Parallel processing of an object space for image synthesis using ray tracing

This paper presents a novel parallel processing system for image synthesis using ray tracing. An object space is divided into parts (subspaces), each of which is allocated to a processor. The processor detects, simultaneously the intersections of the surfaces of each object and a fixed number of rays over the whole space, and calculates the local intensity on an object in each subspace. The global intensities of pixels on a screen are calculated by the other kind of processors simultaneously. We also present the optimal data structure, based on an adaptive division algorithm, for parallel processing of the object space.     

Adaptive Control For Robotic Manipulators Executing Multilateral Constrained Task

This paper presents a model‐based adaptive control in task coordinates for robotic manipulators executing multilateral constrained tasks The controller works based on the concept of orthogonality between force and motion in the subspaces derived from the constraints. The control gains are independently adjustable in each subspace. The friction force, depending on the contact force, is compensated adaptively. Asymptotic convergence for both force and motion tracking errors is guaranteed by the Lyapunov‐Like Lemma. Experimental results obtained using a 3 D.O.F. robot are given.     

Self-adaptive sampling rate assignment and image reconstruction via combination of structured sparsity and non-local total variation priors

Compressive sensing (CS) is an emerging approach for acquisition of sparse or compressible signals. For natural images, block compressive sensing (BCS) has been designed to reduce the size of sensing matrix and the complexity of sampling and reconstruction. On the other hand, image blocks with varying structures are too different to share the same sampling rate and sensing matrix. Motivated by this, a novel framework of adaptive acquisition and reconstruction is proposed to assign sampling rate adaptively. The framework contains three aspects. First, a small part of sampling rate is employed to pre-sense each block and a novel approach is proposed to estimate its compressibility only from pre-sensed measurements. Next, two assignment schemes are proposed to assign the other part of the sampling rate adaptively to each block based on its estimated compressibility. A higher sampling rate is assigned to incompressible blocks but a lower one to compressible ones. The sensing matrix is constructed based on the assigned sampling rates. The pre-sensed measurements and the adaptive ones are concatenated to form the final measurements. Finally, it is proposed that the reconstruction is modeled as a multi-objects optimization problem which involves the structured sparsity and the non-local total variation prior together. It is simplified into a 3-stage alternating optimization problem and is solved by an augmented Lagrangian method. Experiments on four categories of real natural images and medicine images demonstrate that the proposed framework captures local and nonlocal structures and outperforms the state-of-the-art methods.     

采用半随机特征采样算法的中文书写纹识别研究

N-gram字符序列能有效捕捉文本中作者的个体风格信息,但其特征空间稀疏度高,且存在较多噪音特征。针对该问题,提出一种基于半随机特征采样的中文书写纹识别算法。该算法首先采用一种离散度准则为每个作者选取一定粒度的个体特征集,然后将个体特征集以一种半随机选择机制划分成多个等维度的特征子空间,并基于每个子空间训练相应的基分类器,最后采取多数投票法的融合策略构造集成分类模型。在中文真实数据集上与基于随机子空间和Bagging算法的集成分类器进行了对比试验,结果表明,该算法在正确率和差异度方面优于随机子空间和Baggrog算法,并且取得了比单分类模型更好的识别性能。     

Multibody grouping by inference of multiple subspaces from high-dimensional data using oriented-frames

Recently, subspace constraints have been widely exploited in many computer vision problems such as multibody grouping. Under linear projection models, feature points associated with multiple bodies reside in multiple subspaces. Most existing factorization-based algorithms can segment objects undergoing independent motions. However, intersections among the correlated motion subspaces will lead most previous factorization-based algorithms to erroneous segmentation. To overcome this limitation, in this paper, we formulate the problem of multibody grouping as inference of multiple subspaces from a high-dimensional data space. A novel and robust algorithm is proposed to capture the configuration of the multiple subspace structure and to find the segmentation of objects by clustering the feature points into these inferred subspaces, no matter whether they are independent or correlated. In the proposed method, an oriented-frame (OF), which is a multidimensional coordinate frame, is associated with each data point indicating the point's preferred subspace configuration. Based on the similarity between the subspaces, novel mechanisms of subspace evolution and voting are developed. By filtering the outliers due to their structural incompatibility, the subspace configurations will emerge. Compared with most existing factorization-based algorithms that cannot correctly segment correlated motions, such as motions of articulated objects, the proposed method has a robust performance in both independent and correlated motion segmentation. A number of controlled and real experiments show the effectiveness of the proposed method. However, the current approach does not deal with transparent motions and motion subspaces of different dimensions.     

Spark下基于PCA和分层选择的随机森林算法

针对大数据背景下随机森林算法中存在协方差矩阵规模较大、子空间特征信息覆盖不足和节点通信开销大的问题,提出了基于PCA和子空间分层选择的并行随机森林算法PLA-PRF（PCA and subspace layer sampling on parallel random forest algorithm）。对初始特征集,提出了基于PCA的矩阵分解策略（matrix factorization strategy,MFS）,压缩原始特征集,提取主成分特征,解决特征变换过程中协方差矩阵规模较大的问题;基于主成分特征,提出基于误差约束的分层子空间构造算法（error-constrained hierarchical subspace construction algorithm,EHSCA）,分层选取信息素特征,构建特征子空间,解决子空间特征信息覆盖不足的问题;在Spark环境下并行化训练决策树的过程中,设计了一种数据复用策略（data reuse strategy,DRS）,通过垂直划分RDD数据并结合索引表,实现特征复用,解决了节点通信开销大的问题。实验结果表明PLA-PRF算法分类效果更佳,并行化效率更高。     

全规整重网格化三维模型的压缩

通过保形自适应重采样,可将三维网格模型转化为规则排列的二维几何图像,从而可借鉴成熟的图像压缩技术对其进行压缩.提出了保形自适应采样算法,根据网格模型表面的有效顶点分布密度自适应地调整采样网格,并可最大限度地通过原始网格顶点进行采样.在不增加采样率的前提下,该压缩方法所得解压模型具有更小的失真度.通过大量实例对文中方法进行了验证,并与同类方法进行对比.实验结果表明该方法是切实可行的,且具有更好的压缩效果.     

基于协同进化博弈的多学科设计优化

复杂系统的设计问题可以非层次分解为并行的多个子空间优化设计问题。多学科优化的迭代过程可看成子空间博弈的过程。各冲突子目标协商一致条件下,子空间合作博弈的均衡点能达成原系统的整体最优,并给出协同进化算法求解博弈的Nash均衡点的计算框架。以某型民用客机的总体优化设计为例,将其分解成气动和重量两个子空间优化。设计变量不重叠地分布于各子空间,两冲突子目标分配相同权值,线性加权组合而形成的单目标作为各子空间共同的优化目标。计算结果表明此方法是有效的。     

基于局部子空间的多标记特征选择算法*

在已有的特征选择算法中,常用策略是通过相关准则选择与标记集合相关性较强的特征,然而该策略不一定是最优选择,因为与标记集合相关性较弱的特征可能是决定某些类别标记的关键特征.基于这一假设,文中提出基于局部子空间的多标记特征选择算法.该算法首先利用特征与标记集合之间的互信息得到一个重要度由高到低的特征序列,然后将新的特征排序空间划分为几个局部子空间,并在每个子空间设置采样比例以选择冗余性较小的特征,最后融合各子空间的特征子集,得到一组合理的特征子集.在6个数据集和4个评价指标上的实验表明,文中算法优于一些通用的多标记特征选择算法.