基于半动态外观模型的人脸识别

在进行人脸识别时,光照、表情、角度等因素的影响会大幅增加数据计算的时空复杂度。为此,提出一种新的图像外观统计模型,在动态形状模型中引入灰度共生矩阵(GLCM),通过计算图像形状对齐情况下的GLCM,建立半动态外观模型。基于ORL人脸数据库的实验结果表明,该模型相比动态外观模型,识别准确率更高,速度更快。     

利用区域变形和背景更新实现运动对象跟踪

从时域统计的角度出发,提出了一种结合自适应混合背景更新模型的区域变形跟踪算法．该算法以模型更新得到的前景／背景二值分割掩膜作为区域特征,将跟踪问题抽象为一个水平集(Level Set)偏微分方程的数值求解问题,并分析了算法的自适应性．为了进一步提高算法的实现效率,引入了窄带跟踪方案．实验表明,该算法可以对视频序列中的指定运动对象进行快速精确的跟踪。     

Consistent Partial Matching of Shape Collections via Sparse Modeling

Recent efforts in the area of joint object matching approach the problem by taking as input a set of pairwise maps, which are then jointly optimized across the whole collection so that certain accuracy and consistency criteria are satisfied. One natural requirement is cycle‐consistency—namely the fact that map composition should give the same result regardless of the path taken in the shape collection. In this paper, we introduce a novel approach to obtain consistent matches without requiring initial pairwise solutions to be given as input. We do so by optimizing a joint measure of metric distortion directly over the space of cycle‐consistent maps; in order to allow for partially similar and extra‐class shapes, we formulate the problem as a series of quadratic programs with sparsity‐inducing constraints, making our technique a natural candidate for analysing collections with a large presence of outliers. The particular form of the problem allows us to leverage results and tools from the field of evolutionary game theory. This enables a highly efficient optimization procedure which assures accurate and provably consistent solutions in a matter of minutes in collections with hundreds of shapes.     

Deformotion: Deforming Motion,Shape Average and the Joint Registration and Approximation of Structures in Images

International Journal of Computer Vision - What does it mean for a deforming object to be “moving”? How can we separate the overall motion (a finite-dimensional group action) from the...     

面向建模误差PDF形状与趋势拟合优度的动态过程优化建模

本文提出一种新的数据驱动建模思路及方法, 即面向建模误差概率密度函数(Probability density function, PDF)形状与趋势拟合优度(相似度)的动态过程多目标优化建模方法. 首先, 针对均方根误差(Root mean square error, RMSE)等常规一维性能指标不能完全刻画建模误差在时间和空间二维随机动态特性的问题, 引入PDF指标来对动态过程的建模误差在时间和空间进行二维尺度的全面刻画和评价, 并采用核密度估计技术对关于时间的建模误差序列的PDF进行估计; 其次, 为了刻画动态过程数据建模的拟合趋势, 进一步引入趋势拟合优度指标, 从而构造综合描述数据建模误差PDF形状与趋势拟合相似性的多目标性能指标; 在此基础上, 采用NSGA-II算法优化数据模型的参数集, 获取一大类满足上述多目标性能优化的智能模型参数解. 数值仿真及工业数据验证表明, 所提方法的建模误差PDF逼近设定的期望PDF, 并且模型输出与样本数据拟合趋势接近, 好于常规最小化一维RMSE指标的数据建模方法.     

Variational Segmentation of Image Sequences Using Region-Based Active Contours and Deformable Shape Priors

In this paper we address the problem of segmentation in image sequences using region-based active contours and level set methods. We propose a novel method for variational segmentation of image sequences containing nonrigid, moving objects. The method is based on the classical Chan-Vese model augmented with a novel frame-to-frame interaction term, which allow us to update the segmentation result from one image frame to the next using the previous segmentation result as a shape prior. The interaction term is constructed to be pose-invariant and to allow moderate deformations in shape. It is expected to handle the appearance of occlusions which otherwise can make segmentation fail. The performance of the model is illustrated with experiments on synthetic and real image sequences.     

基于先验形状的混杂活动轮廓模型及其在图像分割中的应用

提出了一种新颖的基于先验形状学习的混杂活动轮廓(SHAC)模型,该模型采用变分水平集方法,融合自适应区域信息与边界信息,运用主成分分析的方法从给定的含有目标物体轮廓的训练集学习得到最佳形状信息,并将其作为先验形状。将自适应区域特征和轮廓特征作为局部信息,先验形状作为全局信息,在迭代过程中结合全局和局部信息实现对演化曲线的形变进行指导和约束,达到分割目标物体的目的。通过定量和定性地分析低对比度的乳腺核磁共振图像中的乳腺轮廓的分割,以及具有复杂背景的自然图像中感兴趣区域的分割结果,验证了SHAC模型比传统活动轮廓模型具有更高的准确率,表明了该模型不仅提高了图像分割中对弱边界的识别度,减弱了非目标轮廓的干扰,而且具有良好的抗噪能力。     

基于ASM和K近邻算法的人脸脸型分类

针对人脸特征分类问题,提出一种基于主动形状模型(ASM)和K近邻算法的人脸脸型分类方法。将Hausdorff距离作为K近邻算法的距离函数,利用ASM算法提取待测图像的特征点,对点集进行归一化后计算人脸轮廓特征点与样本库中所有样本点集的Hausdorff距离,根据该距离值,通过K近邻算法实现待测图像的脸型分类。实验结果证明,该方法分类正确率高、速度快、易于实现。     

无尾扑翼无人机动力学建模及仿真

近年来,仿生无人机在战场侦察和飞行巡逻等方面应用广泛,使其成为无人机领域的研究热门,传统仿生无尾扑翼无人机的飞行建模问题通常较为复杂,计算难度较大,因此亟待对此类无人机进行飞行控制的研究。文章针对仿昆虫无尾扑翼无人机的动力学建模问题进行了研究,基于叶素法、准稳态假设模型以及刚体动力学建模方法,对机翼运动进行受力分析,得到机翼的动力学模型;机体采用刚体动力学方法,建立无人机飞行模型。仿昆虫无尾扑翼无人机系统采用PID控制模型对机体纵向动力学模型控制,以俯仰角、阶跃输入方式,通过实验表明,系统的超调量分别为和,调节时间分别为0.5和1,稳态误差符合实验要求。     

The Use of Geometric Algebra for 3D Modeling and Registration of Medical Data

We present a new approach to model 2D surfaces and 3D volumetric data, as well as an approach for non-rigid registration; both are developed in the geometric algebra framework. The approach for modeling is based on marching cubes idea using however spheres and their representation in the conformal geometric algebra; it will be called marching spheres. Note that before we can proceed with the modeling, it is needed to segment the object we are interested in; therefore, we include an approach for image segmentation, which is based on texture and border information, developed in a region-growing strategy. We compare the results obtained with our modeling approach against the results obtained with other approach using Delaunay tetrahedrization, and our proposed approach reduces considerably the number of spheres. Afterward, a method for non-rigid registration of models based on spheres is presented. Registration is done in an annealing scheme, as in Thin-Plate Spline Robust Point Matching (TPS-RPM) algorithm. As a final application of geometric algebra, we track in real time objects involved in surgical procedures.

基于模糊形状上下文与局部向量相似性约束的配准算法

非刚性点集配准研究是模式识别领域的一项重要基础研究.本文在当前流行的非刚性点集配准算法的基础上提出了两个主要贡献: 1)模糊形状上下文(Fuzzy shape context, FSC)特征; 2)基于局部向量特征的局部空间向量相似性约束项.本文首先进行基于特征互补的对应关系评估, 在这一步骤中定义了模糊形状上下文特征, 然后基于模糊形状上下文特征差异和全局特征差异设计了特征互补的高斯混合模型.其次, 进行基于约束互补的空间变化更新.在这一步骤中, 定义了局部向量特征, 建立了局部空间向量相似性约束项.本文算法通过使用特征互补的高斯混合模型进行对应关系评估, 并将配准问题转化为可以用期望最大化(Expectation maximization, EM)算法解决的参数优化问题, 通过创建包含局部空间向量相似性约束项的能量方程优化了空间变换更新.本文首先测试了模糊形状上下文特征的检索率, 然后采用公开数据集测试了算法在点集配准与图像配准的性能.在与当前流行的十种算法的对比实验中, 本文算法均给出了精确的配准结果, 并在大部分实验中精度超过了当前流行算法.     

Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance

We address the problem of estimating the three-dimensional shape and complex appearance of a scene from a calibrated set of views under fixed illumination. Our approach relies on a rank condition that must be satisfied when the scene exhibits specular + diffuse reflectance characteristics. This constraint is used to define a cost functional for the discrepancy between the measured images and those generated by the estimate of the scene, rather than attempting to match image-to-image directly. Minimizing such a functional yields the optimal estimate of the shape of the scene, represented by a dense surface, as well as its radiance, represented by four functions defined on such a surface. These can be used to generate novel views that capture the non-Lambertian appearance of the scene.This research was performed while Hailin Jin was with Computer Science Department, University of California at Los Angeles.     

Stochastic Motion and the Level Set Method in Computer Vision: Stochastic Active Contours

Based on recent work on Stochastic Partial Differential Equations (SPDEs), this paper presents a simple and well-founded method to implement the stochastic evolution of a curve. First, we explain why great care should be taken when considering such an evolution in a Level Set framework. To guarantee the well-posedness of the evolution and to make it independent of the implicit representation of the initial curve, a Stratonovich differential has to be introduced. To implement this differential, a standard Ito plus drift approximation is proposed to turn an implicit scheme into an explicit one. Subsequently, we consider shape optimization techniques, which are a common framework to address various applications in Computer Vision, like segmentation, tracking, stereo vision etc. The objective of our approach is to improve these methods through the introduction of stochastic motion principles. The extension we propose can deal with local minima and with complex cases where the gradient of the objective function with respect to the shape is impossible to derive exactly. Finally, as an application, we focus on image segmentation methods, leading to what we call Stochastic Active Contours.     

连续动态手势的时空表观建模及识别

论述了复杂背景下连接动态手势的分割、建模及识别;融合手势运动信息和皮肤颜色信息,进行复杂背景下的手势分割;通过结合手势的时序信息、运动表观以及形状表观,提出动态手势的时空表观模型,并提出基于颜色、运动以及形状等多模式信息的分层次融合策略抽取时空表观模型的参数,最后,提出动态时空规整算法用于手势识别,实验表明,利用上述提出的手势分割、建模、特征参数抽取及识别方法识别１２种手势,平均识别率高达９７％。     

Practical Acquisition of Shape and Plausible Appearance of Reflective and Translucent Objects

We present a practical method for acquisition of shape and plausible appearance of reflective and translucent objects for realistic rendering and relighting applications. Such objects are extremely challenging to scan with existing capture setups, and have previously required complex lightstage hardware emitting continuous illumination. We instead employ a practical capture setup consisting of a set of desktop LCD screens to illuminate such objects with piece-wise continuous illumination for acquisition. We employ phase-shifted sinusoidal illumination for novel estimation of high quality photometric normals and transmission vector along with diffuse-specular separated reflectance/transmission maps for realistic relighting. We further employ neural in-painting to fill gaps in our measurements caused by gaps in screen illumination, and a novel NeuS-based neural rendering that combines these shape and reflectance maps acquired from multiple viewpoints for high-quality 3D surface geometry reconstruction along with plausible realistic rendering of complex light transport in such objects.     

Object tracking via collaborative multi-task learning and appearance model updating

In this paper, we propose a novel visual tracking algorithm using the collaboration of generative and discriminative trackers under the particle filter framework. Each particle denotes a single task, and we encode all the tasks simultaneously in a structured multi-task learning manner. Then, we implement generative and discriminative trackers, respectively. The discriminative tracker considers the overall information of object to represent the object appearance; while the generative tracker takes the local information of object into account for handling partial occlusions. Therefore, two models are complementary during the tracking. Furthermore, we design an effective dictionary updating mechanism. The dictionary is composed of fixed and variational parts. The variational parts are progressively updated using Metropolis–Hastings strategy. Experiments on different challenging video sequences demonstrate that the proposed tracker performs favorably against several state-of-the-art trackers.     

造型比例在机电产品外观设计中的运用

目前我国机电产品的技术已达到世界水准,但在外观设计上远远落后于国外先进产品,成为影响竞争力的一大弊端。由于受到材料、工艺、造型风格等条件的制约,机电产品的外观多以几何形为主,可变化的空间十分有限。鉴于上述情况,在设计机电产品外形的过程中,造型比例作为一种常用的造型手法发挥着关键的作用。通过论述不同的比率运算方式分别在机电产品的整机形体造型比例,部件壳体分割造型比例以及整机色彩与各种装饰元素之间的"视觉比例"中的运用,详细说明造型比例在机电产品外观设计中的重要作用。通过以上3种造型比例的运用,使得我国的机电产品外观呈现一种即坚实、稳重,又活跃、流畅的视觉效果。     

A Theory of Refractive and Specular 3D Shape by Light-Path Triangulation

We investigate the feasibility of reconstructing an arbitrarily-shaped specular scene (refractive or mirror-like) from one or more viewpoints. By reducing shape recovery to the problem of reconstructing individual 3D light paths that cross the image plane, we obtain three key results. First, we show how to compute the depth map of a specular scene from a single viewpoint, when the scene redirects incoming light just once. Second, for scenes where incoming light undergoes two refractions or reflections, we show that three viewpoints are sufficient to enable reconstruction in the general case. Third, we show that it is impossible to reconstruct individual light paths when light is redirected more than twice. Our analysis assumes that, for every point on the image plane, we know at least one 3D point on its light path. This leads to reconstruction algorithms that rely on an “environment matting” procedure to establish pixel-to-point correspondences along a light path. Preliminary results for a variety of scenes (mirror, glass, etc.) are also presented. Part of this research was conducted while K. Kutulakos was serving as a Visiting Scholar at Microsoft Research Asia.     

弹性飞机的建模与模型降阶方法研究

现代大型高速飞机的结构弹性变形日趋严重,而传统的刚性模型不能反映出飞机的结构变形特性,需要在建模时考虑飞机模型是弹性体.研究了基于Lagrange方程与"平均轴"坐标系的弹性飞机建模方法;说明了平衡截断降阶法及其改进方法平衡奇异摄动法的实现算法;以弹性飞机纵向方程为例,通过分析高、低弹性模型与刚性模型的频率响应,说明了弹性变形对飞机建模的影响,并应用平衡截断法和平衡奇异摄动法简化了高弹性飞机模型,得到了实用的低阶模型.最后分析了两种降阶方法的截断误差,指出了各自适用范围.