综合鲁棒特征和在线学习的自适应三维人脸多特征跟踪

提出一种灰度与边强度信息相结合的鲁棒特征并综合在线学习方法来进行自适应视频人脸多特征跟踪.算法思想是利用三维参数化网格模型对人脸及表情进行建模,利用弱透视模型对头部姿态建模,求取归一化后的形状无关灰度和边强度纹理组合成一种鲁棒特征,建立单高斯自适应纹理模型,并采用梯度下降迭代算法进行模型匹配得到姿态和表情参数.实验证明,本方法比单纯利用灰度特征在复杂光线和表情下具有更好的鲁棒性.     

The active geometric shape model: A new robust deformable shape model and its applications

We present a novel approach for fitting a geometric shape in images. Similar to active shape models and active contours, a force field is used in our approach. But the object to be detected is described with a geometric shape, represented by parametric equations. Our model associates each parameter of this geometric shape with a combination of integrals (summations in the discrete case) of the force field along the contour. By iteratively updating the shape parameters according to these integrals, we are able to find the optimal fit of the shape in the image. In this paper, we first explore simple cases such as fitting a line, circle, ellipse or cubic spline contour using this approach. Then we employ this technique to detect the cross-sections of subarachnoid spaces containing cerebrospinal fluid (CSF) in phase-contrast magnetic resonance (PC-MR) images, where the object of interest can be described by a distorted ellipse. The detection results can be further used by an s–t graph cut to generate a segmentation of the CSF structure. We demonstrate that, given a properly configured geometric shape model and force field, this approach is robust to noise and defects (disconnections and non-uniform contrast) in the image. By using a geometric shape model, this approach does not rely on large training datasets, and requires no manual labeling of the training images as is needed when using point distribution models.     

A background robust active appearance model using active contour technique

This paper proposes an active contour-based active appearance model (AAM) that is robust to a cluttered background and a large motion. The proposed AAM fitting algorithm consists of two alternating procedures: active contour fitting to find the contour sample that best fits the face image and then the active appearance model fitting over the best selected contour. We also suggest an effective fitness function for fitting the contour samples to the face boundary in the active contour technique; this function defines the quality of fitness in terms of the strength and/or the length of edge features. Experimental results show that the proposed active contour-based AAM provides better accuracy and convergence characteristics in terms of RMS error and convergence rate than the existing robust AAM. The combination of the existing robust AAM and the proposed active contour-based AAM (AC-R-AAM) had the best accuracy and convergence performances.     

Higher-order derivatives in linear and quadratic programming

An interior method for linear and quadratic programming which makes use of higher derivatives of the logarithm barrier function is presented. A convergence analysis is considered too. Our computational experience shows that the method considered performs quite well and seems to be more reliable and robust than the standard method.Scope and purposeLinear programming problems were, for many years, the exclusive domain of the simplex algorithm developed by G.B. Dantzing in 1947. With the introduction of a new algorithm, developed by N.K. Karmarkar in 1984, an alternative computational approach became available for solving such problems. This algorithm established a new class of algorithms: interior point methods for linear programming. In this paper we introduce a barrier method for solving a linear and quadratic programming problem which [9], [10], [11], [12], [13], [14], [15] makes use of higher-order derivatives. We note that a different approach used to construct higher-order interior point methods is presented in [1], [2], [3], [4]. We think that making use of an approximation of higher-order we may obtain a faster convergence and an algorithm more robust than a method obtained using a second-order approximation.     

Robust control of a general servomechanism problem: The servo compensator

The robust control of a general servomechanism problem, which is an extension to the results of [1], is considered in this paper. Necessary and sufficient conditions, together with a characterization of all robust controllers which enables asymptotic tracking to occur, independent of disturbances in the plant and perturbations in the plant parameters and gains of the system, are obtained. A new type of compensator, introduced in [1], called a servo-compensator which is quite distinct from an observer is shown to play an essential role in the robust servomechanism problem. It is shown that this compensator, which corresponds to an integral controller in classical control theory, must be used in any servomechanism problem to assure that the controlled system is stabilizable and achieves robust control; in particular, it is shown that a robust controller of a general servomechanism problem must consist of two devices (i) a servo-compensator and (ii) a stabilizing compensator. A study of the stabilizing compensator is made; in particular, it is shown that a new type of stabilizing compensator called a complementary controller, may be used together with the servo-compensator to form a robust controller for the servo-mechanism problem.A study of the case when perturbations in the robust controller are also allowed is then made; this leads to the Strong robust servo limitation theorem which imposes a fundamental limitation on the ability of practical servomechanisms to regulate a system.     

基于流形学习的彩色遥感图像分维数估算

目的 纹理特征提取一直是遥感图像分析领域研究的热点和难点。现有的纹理特征提取方法主要集中于研究单波段灰色遥感图像,如何提取多波段彩色遥感图像的纹理特征,是多光谱遥感的研究前沿。方法 提出了一种基于流形学习的彩色遥感图像分维数估算方法。该方法利用局部线性嵌入方法,对由颜色属性所组成的5-D欧氏超曲面进行维数简约处理;再将维数简约处理后的颜色属性用于分维数估算。结果 利用Landsat-7遥感卫星数据和GeoEye-1遥感卫星数据进行实验,结果表明,同Peleg法和Sarkar法等其他分维数估算方法相比,本文方法具有较小的拟合误差。其中,其他4种对比方法所获拟合误差E平均值分别是本文方法所获得拟合误差E平均值的26.2倍、5倍、26.3倍、5倍。此外,本文方法不仅可提供具有较好分类特性的分维数,而且还能提供相对于其他4种对比方法更加稳健的分维数。结论 在针对中低分辨率的真彩遥感图像和假彩遥感图像以及高分辨率彩色合成遥感图像方面,本文方法能够利用不同地物所具有颜色属性信息,提取出各类型地物所对应的纹理信息,有效地改善了分维数对不同地物的区分能力。这对后续研究各区域中不同类型地物的分布情况及针对不同类型地物分布特点而制定区域规划及开发具有积极意义。     

The use of concerns theory in inservice training for computer education

The introduction of computers in the schools represents a dramatic change. Bentzen [1], Goodlad [2], and Hall [3] have documented the important role of the individual in the change process. Our research focused on the personal dimensions of the change process, and on teacher concerns about using microcomputers in the classroom. Eighteen teachers at the senior high school level volunteered to complete the Stages of Concern Questionnaire that reliably yields data on seven distinct stages of concerns (Hall et al. [4]). Based on their SoCQ profiles, three “users” and three “non-users” were interviewed to determine the present and projected uses of computers in teaching. This data base was used to design a set of inservice activities that over a three day period for 15 hours, produced a significant change in teachers' concerns towards microcomputers. A change model assuming a person-level orientation to an innovation is a promising approach to be used in inservicing.     

Intelligent state estimation for fault tolerant nonlinear predictive control

There is growing realization that on-line model maintenance is the key to realizing long term benefits of a predictive control scheme. In this work, a novel intelligent nonlinear state estimation strategy is proposed, which keeps diagnosing the root cause(s) of the plant model mismatch by isolating the subset of active faults (abrupt changes in parameters/disturbances, biases in sensors/actuators, actuator/sensor failures) and auto-corrects the model on-line so as to accommodate the isolated faults/failures. To carry out the task of fault diagnosis in multivariate nonlinear time varying systems, we propose a nonlinear version of the generalized likelihood ratio (GLR) based fault diagnosis and identification (FDI) scheme (NL-GLR). An active fault tolerant NMPC (FTNMPC) scheme is developed that makes use of the fault/failure location and magnitude estimates generated by NL-GLR to correct the state estimator and prediction model used in NMPC formulation. This facilitates application of the fault tolerant scheme to nonlinear and time varying processes including batch and semi-batch processes. The advantages of the proposed intelligent state estimation and FTNMPC schemes are demonstrated by conducting simulation studies on a benchmark CSTR system, which exhibits input multiplicity and change in the sign of steady state gain, and a fed batch bioreactor, which exhibits strongly nonlinear dynamics. By simulating a regulatory control problem associated with an unstable nonlinear system given by Chen and Allgower [H. Chen, F. Allgower, A quasi infinite horizon nonlinear model predictive control scheme with guaranteed stability, Automatica 34(10) (1998) 1205–1217], we also demonstrate that the proposed intelligent state estimation strategy can be used to maintain asymptotic closed loop stability in the face of abrupt changes in model parameters. Analysis of the simulation results reveals that the proposed approach provides a comprehensive method for treating both faults (biases/drifts in sensors/actuators/model parameters) and failures (sensor/ actuator failures) under the unified framework of fault tolerant nonlinear predictive control.     

Discontinuous bubble scheme for elliptic problems with jumps in the solution

We propose a new numerical method to solve an elliptic problem with jumps both in the solution and derivative along an interface. By considering a suitable function which has the same jumps as the solution, we transform the problem into one without jumps. Then we apply the immersed finite element method in which we allow uniform meshes so that the interface may cut through elements to discretize the problem as introduced in [1], [2], [3]. Some convenient way of approximating the jumps of the solution by piecewise linear functions is suggested. Our method can also handle the case when the interface passes through grid points. We believe this paper presents the first resolution of such cases. Numerical experiments for various problems show second-order convergence in L² and first order in H¹-norms. Moreover, the convergence order is very robust for all problems tested.     

改进K-means活动轮廓模型

目的 通过对C-V模型能量泛函的Euler-Lagrange方程进行变形,建立其与K-means方法的等价关系,提出一种新的基于水平集函数的改进K-means活动轮廓模型。方法 该模型包含局部自适应权重矩阵函数,它根据像素点所在邻域的局部统计信息自适应地确定各个像素点的分割阈值,排除灰度非同质对分割目标的影响,进而实现对灰度非同质图像的精确分割。结果 通过分析对合成以及自然图像的分割结果,与传统及最新经典的活动轮廓模型相比,新模型不仅能较准确地分割灰度非同质图像,而且降低了对初始曲线选取的敏感度。结论 提出了包含权重矩阵函数的新活动轮廓模型,根据分割目的和分割图像性质,制定不同的权重函数,该模型具有广泛的适用性。文中给出的一种具有局部统计特性的权重函数,对灰度非同质图像的效果较好,且对初始曲线位置具有稳定性。     

Extracting Microfacet‐based BRDF Parameters from Arbitrary Materials with Power Iterations

We introduce a novel fitting procedure that takes as input an arbitrary material, possibly anisotropic, and automatically converts it to a microfacet BRDF. Our algorithm is based on the property that the distribution of microfacets may be retrieved by solving an eigenvector problem that is built solely from backscattering samples. We show that the eigenvector associated to the largest eigenvalue is always the only solution to this problem, and compute it using the power iteration method. This approach is straightforward to implement, much faster to compute, and considerably more robust than solutions based on nonlinear optimizations. In addition, we provide simple conversion procedures of our fits into both Beckmann and GGX roughness parameters, and discuss the advantages of microfacet slope space to make our fits editable. We apply our method to measured materials from two large databases that include anisotropic materials, and demonstrate the benefits of spatially varying roughness on texture mapped geometric models.     

Real-Time 3D Stereo Tracking and Localizing of Spherical Objects with the iCub Robotic Platform

Visual pattern recognition is a basic capability of many species in nature. The skill of visually recognizing and distinguishing different objects in the surrounding environment gives rise to the development of sensory-motor maps in the brain, with the consequent capability of object reaching and manipulation. This paper presents the implementation of a real-time tracking algorithm for following and evaluating the 3D position of a generic spatial object. The key issue of our approach is the development of a new algorithm for pattern recognition in machine vision, the Least Constrained Square-Fitting of Ellipses (LCSE), which improves the state of the art ellipse fitting procedures. It is a robust and direct method for the least-square fitting of ellipses to scattered data. In this work we applied it to the iCub humanoid robotics platform simulator and real robot. We used it as a base for a circular object localization within the 3D surrounding space. We compared its performance with the Hough Transform and the state of the art ellipse fitting algorithms, in terms of robustness (succes/failure in the object detection) and fitting precision. Our experiments involve robustness against noise, occlusion, and computational complexities analyses.     

Hybrid active learning for reducing the annotation effort of operators in classification systems

Active learning is understood as any form of learning in which the learning algorithm has some control over the input samples due to a specific sample selection process based on which it builds up the model. In this paper, we propose a novel active learning strategy for data-driven classifiers, which is based on unsupervised criterion during off-line training phase, followed by a supervised certainty-based criterion during incremental on-line training. In this sense, we call the new strategy hybrid active learning. Sample selection in the first phase is conducted from scratch (i.e. no initial labels/learners are needed) based on purely unsupervised criteria obtained from clusters: samples lying near cluster centers and near the borders of clusters are expected to represent the most informative ones regarding the distribution characteristics of the classes. In the second phase, the task is to update already trained classifiers during on-line mode with the most important samples in order to dynamically guide the classifier to more predictive power. Both strategies are essential for reducing the annotation and supervision effort of operators in off-line and on-line classification systems, as operators only have to label an exquisite subset of the off-line training data resp. give feedback only on specific occasions during on-line phase. The new active learning strategy is evaluated based on real-world data sets from UCI repository and collected at on-line quality control systems. The results show that an active learning based selection of training samples (1) does not weaken the classification accuracies compared to when using all samples in the training process and (2) can out-perform classifiers which are built on randomly selected data samples.     

An automatic statistical segmentation algorithm for extraction of fire and smoke regions

Estimation of the extent and spread of wildland fires is an important application of high spatial resolution multispectral images. This work addresses a fuzzy segmentation algorithm to map fire extent, active fire front, hot burn scar, and smoke regions based on a statistical model. The fuzzy results are useful data sources for integrated fire behavior and propagation models built using Dynamic Data Driven Applications Systems (DDDAS) concepts that use data assimilation techniques which require error estimates or probabilities for the data parameters. The Hidden Markov Random Field (HMRF) model has been used widely in image segmentation, but it is assumed that each pixel has a particular class label belonging to a prescribed finite set. The mixed pixel problem can be addressed by modeling the fuzzy membership process as a continuous Multivariate Gaussian Markov Random Field. Techniques for estimating the class membership and model parameters are discussed. Experimental results obtained by applying this technique to two Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) images show that the proposed methodology is robust with regard to noise and variation in fire characteristics as well as background. The segmentation results of our algorithm are compared with the results of a K-means algorithm, an Expectation Maximization (EM) algorithm (which is very similar to the Fuzzy C-Means Clustering algorithm with entropy regularization), and an MRF-MAP algorithm. Our fuzzy algorithm achieves more consistent segmentation results than the comparison algorithms for these test images with the added advantage of simultaneously providing a proportion or error map needed for the data assimilation problem.     

A robust hybrid method for nonrigid image registration

A nonrigid registration method is proposed to automatically align two images by registering two sets of sparse features extracted from the images. Motivated by the paradigm of Robust Point Matching (RPM) algorithms [1] and [2], which were originally proposed for shape registration, we develop Robust Hybrid Image Matching (RHIM) algorithm by alternatively optimizing feature correspondence and spatial transformation for image registration. Our RHIM algorithm is built to be robust to feature extraction errors. A novel dynamic outlier rejection approach is described for removing outliers and a local refinement technique is applied to correct non-exactly matched correspondences arising from image noise and deformations. Experimental results demonstrate the robustness and accuracy of our method.     

时变非线性不确定系统H∞鲁棒模型预测控制

针对输入受限的时变不确定非线性系统,提出一种H∞鲁棒模型预测控制策略。假设线性化系统矩阵一致有界,将非凸的无穷时域优化问题转化为带有单个线性矩阵不等式(LMI)约束的凸优化问题,降低控制量求解难度。结合滚动优化原理与H∞控制方法在线极小化性能指标,使得闭环系统满足控制性能和约束。在LMI框架下给出H∞NMPC的求解方法及其鲁棒稳定性充分条件。仿真实验对比验证了该策略的有效性。     

基于三角剖分的人脸纹理映射

采用通用的三维人脸模型和任意的人脸纹理图像,基于Delaunay三角剖分,提出了一种灵活的3D人脸的纹理映射方法。该方法对人脸特征点集做三角剖分,在纹理图像和三维网格之间建立了一个准确的拓扑同构映射关系,从而得到高真实度的纹理映射。该算法不受网格调整精度的影响,同时适用于不同的纹理映射到同一三维人脸模型上。     

Mutual-manifold regularized robust fast latent LRR for subspace recovery and learning

In this paper, we propose a simple yet effective low-rank representation (LRR) and subspace recovery model called mutual-manifold regularized robust fast latent LRR. Our model improves the representation ability and robustness from twofold. Specifically, our model is built on the Frobenius norm-based fast latent LRR decomposing given data into a principal feature part, a salient feature part and a sparse error, but improves it clearly by designing mutual-manifold regularization to encode, preserve and propagate local information between coefficients and salient features. The mutual-manifold regularization is defined by using the coefficients as the adaptive reconstruction weights for salient features and constructing a Laplacian matrix over salient features for the coefficients. Thus, some important local topology structure information can be propagated between them, which can make the discovered subspace structures and features potentially more accurate for the data representations. Besides, our approach also considers to improve the robust properties of subspace recovery against noise and sparse errors in coefficients, which is realized by decomposing original coefficients matrix into an error-corrected part and a sparse error part fitting noise in coefficients, and the recovered coefficients are then used for robust subspace recovery. Experimental results on several public databases demonstrate that our method can outperform other related algorithms.