A volumetric fusion technique for surface reconstruction from silhouettes and range data

Optical triangulation, an active reconstruction technique, is known to be an accurate method but has several shortcomings due to occlusion and laser reflectance properties of the object surface, that often lead to holes and inaccuracies on the recovered surface. Shape from silhouette, on the other hand, as a passive reconstruction technique, yields robust, hole-free reconstruction of the visual hull of the object. In this paper, a hybrid surface reconstruction method that fuses geometrical information acquired from silhouette images and optical triangulation is presented. Our motivation is to recover the geometry from silhouettes on those parts of the surface which the range data fail to capture. A volumetric octree representation is first obtained from the silhouette images and then carved by range points to amend the missing cavity information. An isolevel value on each surface cube of the carved octree structure is accumulated using local surface triangulations obtained separately from range data and silhouettes. The marching cubes algorithm is then applied for triangulation of the volumetric representation. The performance of the proposed technique is demonstrated on several real objects.     

面向隶属度修正模糊聚类的参数选择方法

隶属度修正是模糊C-均值聚类算法改进的一个重要方向,该类改进算法引入模糊阈值修正隶属度,极大的加快了算法的收敛.然而其模糊阈值的自适应取值一直是一个较难解决的问题.针对这个问题,从数据对聚类中心的物理吸引和相似关系等角度提出了一种针对隶属度修正类FCM算法的模糊阈值参数选择方法,并从该参数选择公式的单调性、收敛性和鲁棒性等角度理论验证了该方法的有效性.仿真实验表明,该参数选择方法有效并具有较好的自适应效果,在加入离群点时也有着较强的鲁棒性,对于隶属度修正类FCM算法的参数选择有着较高的应用价值.     

Implicit Surface-Based Geometric Fusion

This paper introduces a general purpose algorithm for reliable integration of sets of surface measurements into a single 3D model. The new algorithm constructs a single continuous implicit surface representation which is the zero-set of a scalar field function. An explicit object model is obtained using any implicit surface polygonization algorithm. Object models are reconstructed from both multiple view conventional 2.5D range images and hand-held sensor range data. To our knowledge this is the first geometric fusion algorithm capable of reconstructing 3D object models from noisy hand-held sensor range data.This approach has several important advantages over existing techniques. The implicit surface representation allows reconstruction of unknown objects of arbitrary topology and geometry. A continuous implicit surface representation enables reliable reconstruction of complex geometry. Correct integration of overlapping surface measurements in the presence of noise is achieved using geometric constraints based on measurement uncertainty. The use of measurement uncertainty ensures that the algorithm is robust to significant levels of measurement noise. Previous implicit surface-based approaches use discrete representations resulting in unreliable reconstruction for regions of high curvature or thin surface sections. Direct representation of the implicit surface boundary ensures correct reconstruction of arbitrary topology object surfaces. Fusion of overlapping measurements is performed using operations in 3D space only. This avoids the local 2D projection required for many previous methods which results in limitations on the object surface geometry that is reliably reconstructed. All previous geometric fusion algorithms developed for conventional range sensor data are based on the 2.5D image structure preventing their use for hand-held sensor data. Performance evaluation of the new integration algorithm against existing techniques demonstrates improved reconstruction of complex geometry.     

Neural Representation of Open Surfaces

Neural implicit surfaces have emerged as an effective, learnable representation for shapes of arbitrary topology. However, representing open surfaces remains a challenge. Different methods, such as unsigned distance fields (UDF), have been proposed to tackle this issue, but a general solution remains elusive. The generalized winding number (GWN), which is often used to distinguish interior points from exterior points of 3D shapes, is arguably the most promising approach. The GWN changes smoothly in regions where there is a hole in the surface, but it is discontinuous at points on the surface. Effectively, this means that it can be used in lieu of an implicit surface representation while providing information about holes, but, unfortunately, it does not provide information about the distance to the surface necessary for e.g. ray tracing, and special care must be taken when implementing surface reconstruction. Therefore, we introduce the semi-signed distance field (SSDF) representation which comprises both the GWN and the surface distance. We compare the GWN and SSDF representations for the applications of surface reconstruction, interpolation, reconstruction from partial data, and latent vector analysis using two very different data sets. We find that both the GWN and SSDF are well suited for neural representation of open surfaces.     

最大奇异值移位的鲁棒图像信息隐藏

为了提高图像信息隐藏的鲁棒性和不可感知性,提出了一种基于图像块最大奇异值移位的鲁棒信息隐藏算法.算法首先对图像分块并对每个图像块进行奇异值分解,根据图像块最大奇异值的大小选择合适的阈值,并对图像块的最大奇异值进行区间划分,通过将最大奇异值移位到与秘密信息比特相对应的区间实现秘密信息的嵌入.实验结果表明,该算法具有较大的嵌入容量,且在嵌入相同大小的秘密信息时与其他同类算法相比,具有更好的图像视觉质量和鲁棒性.该算法更能适应噪声环境下的信息隐藏.     

Voiced/non-voiced speech classification using adaptive thresholding with bivariate EMD

This paper introduces a robust voiced/non-voiced (VnV) speech classification method using bivariate empirical mode decomposition (bEMD). Fractional Gaussian noise (fGn) is employed as the reference signal to derive a data adaptive threshold for VnV discrimination. The analyzing speech signal and fGn are combined to generate a complex signal which is decomposed into a finite number of complex-valued intrinsic mode functions (IMFs) by using bEMD. The real and imaginary parts of the IMFs represent the IMFs of observed speech and fGn, respectively. The log-energies of both types of IMFs are calculated. There exist similarities between the IMF log-energy representation of fGn and unvoiced speech signals. Hence, the upper confidence limit from IMF log-energies of fGn is used as data adaptive threshold for VnV classification. If the subband log-energy of speech segment exceeds the threshold, the segment is classified as voiced and unvoiced otherwise. The experimental results show that the proposed algorithm performs better than the recently reported methods without requiring any training data for a wide range of SNRs.     

Efficient surface reconstruction method for distributed CAD

This paper describes a new fast Reverse Engineering (RE) method for creating a 3D computerized model from an unorganized cloud of points. The proposed method is derived directly from the problems and difficulties currently associated with remote design over the Internet, such as accuracy, transmission time and representation at different levels of abstraction. With the proposed method, 3D models suitable for distributed design systems can be reconstructed in real time. The mesh reconstruction approach is based on aggregating very large scale 3D scanned data into a Hierarchical Space Decomposition Model (HSDM), realized by the Octree data structure. Then, a Connectivity Graph (CG) is extracted and filled with facets. The HSDM can represent both the boundary surface and the interior volume of an object. Based on the proposed volumetric model, the surface reconstruction process becomes robust and stable with respect to sampling noise. Moreover, the data received from different surface/volume sampling devices can be handled naturally. The hierarchical structure of the proposed volumetric model enables data reduction, while preserving significant geometrical features and object topology. As a result, reconstruction and transmission over the network are efficient. Furthermore, the hierarchical representation provides a capability for extracting models at desired levels of detail, thus enabling designers to collaborate at any product development stage: draft or detailed design.     

改进的卷积网络目标跟踪算法

在目标跟踪算法中深度网络可以对大量图像进行训练和表示,但是对于特定的跟踪对象,离线训练不仅费时,而且在对大量图像进行学习时,其表示和识别能力效果不佳。基于以上问题提出有模板更新的卷积网络跟踪算法,可以在没有离线训练的大量数据时,也能够利用实现强大的目标跟踪能力。在目标跟踪中,从目标周围区域提取一组归一化的局部小区域块作为新的滤波器,围绕目标定义下一帧中的一组特征映射来提取自适应滤波器周围目标,对随后帧提取的归一化样本进行卷积操作生成一组特征图;利用这些特征图获取每个滤波器和目标的局部强度衍射图样之间的相似性,然后对其局部结构信息进行编码;最后,使用来自全局表示的特征图保存该目标的内部几何设计,再通过软收缩方法去噪抑制噪声值,使其低于自适应阈值,生成目标的稀疏表示。有模板更新改进的CNT算法能稳定地跟踪目标,不会发生严重漂移,具有优于传统CNT的良好跟踪效果。     

Bad-scenario-set Robust Optimization Framework With Two Objectives for Uncertain Scheduling Systems

This paper proposes a robust optimization framework generally for scheduling systems subject to uncertain input data, which is described by discrete scenarios. The goal of robust optimization is to hedge against the risk of system performance degradation on a set of bad scenarios while maintaining an excellent expected system performance. The robustness is evaluated by a penalty function on the bad-scenario set. The bad-scenario set is identified for current solution by a threshold, which is restricted on a reasonable-value interval. The robust optimization framework is formulated by an optimization problem with two conflicting objectives. One objective is to minimize the reasonable value of threshold, and another is to minimize the measured penalty on the bad-scenario set. An approximate solution framework with two dependent stages is developed to surrogate the biobjective robust optimization problem. The approximation degree of the surrogate framework is analyzed. Finally, the proposed bad-scenario-set robust optimization framework is applied to a scenario job-shop scheduling system. An extensive computational experiment was conducted to demonstrate the effectiveness and the approximation degree of the framework. The computational results testified that the robust optimization framework can provide multiple selections of robust solutions for the decision maker. The robust scheduling framework studied in this paper can provide a unique paradigm for formulating and solving robust discrete optimization problems.      

一种进行稀疏编码的复数数据词典快速训练方法

稀疏编码理论应用于信号处理的各个领域,为了获取优化的稀疏编码,需要通过训练获取数据词典.提出了一种复数域数据词典的快速训练方法,将词典训练问题转化为最优化问题并交替地对词典原子和编码进行最优化而得到最终训练词典.在对词典原子的最优化过程中,采用具有记忆性的在线训练算法;而在对编码进行最优化的过程中,采用交换乘子方向方法进行实现.通过实验得出:所提出的算法能够有效地提高数据词典的训练效率,在保证收敛值的同时缩短训练时间,并且对于训练样本中的噪声具有鲁棒性.     

A robust estimator for the tail index of Pareto-type distributions

In extreme value statistics, the extreme value index is a well-known parameter to measure the tail heaviness of a distribution. Pareto-type distributions, with strictly positive extreme value index (or tail index) are considered. The most prominent extreme value methods are constructed on efficient maximum likelihood estimators based on specific parametric models which are fitted to excesses over large thresholds. Maximum likelihood estimators however are often not very robust, which makes them sensitive to few particular observations. Even in extreme value statistics, where the most extreme data usually receive most attention, this can constitute a serious problem. The problem is illustrated on a real data set from geopedology, in which a few abnormal soil measurements highly influence the estimates of the tail index. In order to overcome this problem, a robust estimator of the tail index is proposed, by combining a refinement of the Pareto approximation for the conditional distribution of relative excesses over a large threshold with an integrated squared error approach on partial density component estimation. It is shown that the influence function of this newly proposed estimator is bounded and through several simulations it is illustrated that it performs reasonably well at contaminated as well as uncontaminated data.     

A robust estimator for the tail index of Pareto-type distributions

In extreme value statistics, the extreme value index is a well-known parameter to measure the tail heaviness of a distribution. Pareto-type distributions, with strictly positive extreme value index (or tail index) are considered. The most prominent extreme value methods are constructed on efficient maximum likelihood estimators based on specific parametric models which are fitted to excesses over large thresholds. Maximum likelihood estimators however are often not very robust, which makes them sensitive to few particular observations. Even in extreme value statistics, where the most extreme data usually receive most attention, this can constitute a serious problem. The problem is illustrated on a real data set from geopedology, in which a few abnormal soil measurements highly influence the estimates of the tail index. In order to overcome this problem, a robust estimator of the tail index is proposed, by combining a refinement of the Pareto approximation for the conditional distribution of relative excesses over a large threshold with an integrated squared error approach on partial density component estimation. It is shown that the influence function of this newly proposed estimator is bounded and through several simulations it is illustrated that it performs reasonably well at contaminated as well as uncontaminated data.     

The Bézier Tangential Surface System: a Robust Dual Representation of Tangent Space

This paper develops a robust dual representation for the tangent space of a rational surface. This dual representation of tangent space is a very useful tool for visibility analysis. Visibility constructs that are directly derivable from the dual representation of this paper include silhouettes, bitangent developables and kernels. It is known that the tangent space of a surface can be represented by a surface in dual space, which we call a tangential surface. Unfortunately, a tangential surface is usually infinite. Therefore, for robust computation, the points at infinity must be clipped from a tangential surface. This clipping requires two complementary refinements, the first to allow clipping and the second to do the clipping. First, three cooperating tangential surfaces are used to model the entire tangent space robustly, each defined within a box. Second, the points at infinity on each tangential surface are clipped away while preserving everything that lies within the box. This clipping only involves subdivision along isoparametric curves, a considerably simpler process than exact trimming to the box. The isoparametric values for this clipping are computed as local extrema from an analysis using Sederbergs piecewise algebraic curves. A construction of the tangential surface of a parametric surface is outlined, and it is shown how the tangential surface of a Bézier surface can be expressed as a rational Bézier surface.     

A quasi-dense approach to surface reconstruction from uncalibrated images

This paper proposes a quasi-dense approach to 3D surface model acquisition from uncalibrated images. First, correspondence information and geometry are computed based on new quasi-dense point features that are resampled subpixel points from a disparity map. The quasi-dense approach gives more robust and accurate geometry estimations than the standard sparse approach. The robustness is measured as the success rate of full automatic geometry estimation with all involved parameters fixed. The accuracy is measured by a fast gauge-free uncertainty estimation algorithm. The quasi-dense approach also works for more largely separated images than the sparse approach, therefore, it requires fewer images for modeling. More importantly, the quasi-dense approach delivers a high density of reconstructed 3D points on which a surface representation can be reconstructed. This fills the gap of insufficiency of the sparse approach for surface reconstruction, essential for modeling and visualization applications. Second, surface reconstruction methods from the given quasi-dense geometry are also developed. The algorithm optimizes new unified functionals integrating both 3D quasi-dense points and 2D image information, including silhouettes. Combining both 3D data and 2D images is more robust than the existing methods using only 2D information or only 3D data. An efficient bounded regularization method is proposed to implement the surface evolution by level-set methods. Its properties are discussed and proven for some cases. As a whole, a complete automatic and practical system of 3D modeling from raw images captured by hand-held cameras to surface representation is proposed. Extensive experiments demonstrate the superior performance of the quasi-dense approach with respect to the standard sparse approach in robustness, accuracy, and applicability.     

Binary Orientation Trees for Volume and Surface Reconstruction from Unoriented Point Clouds

Given a complete unoriented point set, we propose a binary orientation tree (BOT) for volume and surface representation, which roughly splits the space into the interior and exterior regions with respect to the input point set. The BOTs are constructed by performing a traditional octree subdivision technique while the corners of each cell are associated with a tag indicating the in/out relationship with respect to the input point set. Starting from the root cell, a growing stage is performed to efficiently assign tags to the connected empty sub‐cells. The unresolved tags of the remaining cell corners are determined by examining their visibility via the hidden point removal operator. We show that the outliers accompanying the input point set can be effectively detected during the construction of the BOTs. After removing the outliers and resolving the in/out tags, the BOTs are ready to support any volume or surface representation techniques. To represent the surfaces, we also present a modified MPU implicits algorithm enabled to reconstruct surfaces from the input unoriented point clouds by taking advantage of the BOTs.     

Online learning and fusion of orientation appearance models for robust rigid object tracking

We introduce a robust framework for learning and fusing of orientation appearance models based on both texture and depth information for rigid object tracking. Our framework fuses data obtained from a standard visual camera and dense depth maps obtained by low-cost consumer depth cameras such as the Kinect. To combine these two completely different modalities, we propose to use features that do not depend on the data representation: angles. More specifically, our framework combines image gradient orientations as extracted from intensity images with the directions of surface normals computed from dense depth fields. We propose to capture the correlations between the obtained orientation appearance models using a fusion approach motivated by the original Active Appearance Models (AAMs). To incorporate these features in a learning framework, we use a robust kernel based on the Euler representation of angles which does not require off-line training, and can be efficiently implemented online. The robustness of learning from orientation appearance models is presented both theoretically and experimentally in this work. This kernel enables us to cope with gross measurement errors, missing data as well as other typical problems such as illumination changes and occlusions. By combining the proposed models with a particle filter, the proposed framework was used for performing 2D plus 3D rigid object tracking, achieving robust performance in very difficult tracking scenarios including extreme pose variations.     

基于NDVI阈值法反演地表比辐射率的参数敏感性分析

地表比辐射率是反演地表温度的重要因子,普遍应用于自然界中的水热交换和辐射传输过程。本文通过对基于NDVI阈值法反演地表比辐射率的相关参数进行敏感性研究,确定了影响NDVI阈值法反演地表比辐射率的关键参数,以期通过关键参数获取方法的改进和参数不确定性的降低来提高NDVI阈值法的反演精度。研究以Valor和Caselles在1996年提出的植被指数混合模型为理论基础、湖北省荆门市为研究区域,使用Land-sat TM5数据,采用控制变量法,对NDVI阈值法中影响比辐射率反演精度的大气因子、地形因子、纯像元NDVI阈值、纯像元比辐射率值进行敏感程度的数学分析。研究发现,4大因子敏感性程度:纯像元比辐射率值>纯像元NDVI阈值>地形因子>大气因子,其中纯像元比辐射率值和纯像元NDVI阈值为关键参数;4大因子影响程度:大气因子>纯像元比辐射率值>地形因子>纯像元NDVI阈值。     

Locality Preserving Collaborative Representation for Face Recognition

Face recognition has many applications in pattern recognition and computer vision, and many face recognition methods have been proposed. Among them, the recently proposed collaborative representation based face recognition has attracted the attention of researchers. Many variants and extensions of collaborative representation based classification (CRC) have been presented. However, most of CRC methods do not consider data locality, which is crucial for classification task. In this article, a novel collaborative representation based face recognition method, LP-CRC, is proposed, which balances data locality and collaborative representation. The proposed method incorporates a locality adaptor term into the robust collaborative representation based classification framework, leading to a novel unified objective function. The Augmented Lagrange Multiplier is used to optimize the objective function. Tests on standard benchmarks demonstrate that the proposed face recognition method is superior to existing methods and robust to noise and outliers.