Feature-Based Object Recognition and Localization in 3D-Space,Using a Single Video Image

We introduce a robust algorithm to recognize objects in 3D space from one 2D video image and to localize the objects in all six degrees of freedom. Point-like attached features are used in the input image and additional edge information provides grouping. In an initial phase, a 3D model of all objects to be recognized is stored in the computer represented by their features. Combining the location of the detected features in the 2D input scene with the features of the 3D computer model, each single feature gives a subspace as possible solutions of the location parameters to be determined. The points of intersection of the corresponding trajectories are accumulated as possible solutions in a Hough table. The location of the highest peak in the space of hypothetical solutions delivers the desired rotation and translation parameters, even for partially hidden objects. The fully analytical algorithm is adapted to weak perspective (orthographic and scale) as well as to perspective projection. An application to range images leads to the automated feature modeling of the required 3D reference objects.     

The delineation of tree crowns in Australian mixed species forests using hyperspectral Compact Airborne Spectrographic Imager (CASI) data

In mixed-species forests of complex structure, the delineation of tree crowns is problematic because of their varying dimensions and reflectance characteristics, the existence of several layers of canopy (including understorey), and shadowing within and between crowns. To overcome this problem, an algorithm for delineating tree crowns has been developed using eCognition Expert and hyperspectral Compact Airborne Spectrographic Imager (CASI-2) data acquired over a forested landscape near Injune, central east Queensland, Australia. The algorithm has six components: 1) the differentiation of forest, non-forest and understorey; 2) initial segmentation of the forest area and allocation of segments (objects) to larger objects associated with forest spectral types (FSTs); 3) initial identification of object maxima as seeds within these larger objects and their expansion to the edges of crowns or clusters of crowns; 4) subsequent classification-based separation of the resulting objects into crown or cluster classes; 5) further iterative splitting of the cluster classes to delineate more crowns; and 6) identification and subsequent merging of oversplit objects into crowns or clusters. In forests with a high density of individuals (e.g., regrowth), objects associated with tree clusters rather than crowns are delineated and local maxima counted to approximate density. With reference to field data, the delineation process provided accuracies > ∼70% (range 48-88%) for individuals or clusters of trees of the same species with diameter at breast height (DBH) exceeding 10 cm (senescent and dead trees excluded), with lower accuracies associated with dense stands containing several canopy layers, as many trees were obscured from the view of the CASI sensor. Although developed using 1-m spatial resolution CASI data acquired over Australian forests, the algorithm has application elsewhere and is currently being considered for integration into the Definiens product portfolio for use by the wider community.     

Agglomerative Fuzzy K-Means Clustering Algorithm with Selection of Number of Clusters

In this paper, we present an agglomerative fuzzy $k$-means clustering algorithm for numerical data, an extension to the standard fuzzy $k$-means algorithm by introducing a penalty term to the objective function to make the clustering process not sensitive to the initial cluster centers. The new algorithm can produce more consistent clustering results from different sets of initial clusters centers. Combined with cluster validation techniques, the new algorithm can determine the number of clusters in a data set, which is a well known problem in $k$-means clustering. Experimental results on synthetic data sets (2 to 5 dimensions, 500 to 5000 objects and 3 to 7 clusters), the BIRCH two-dimensional data set of 20000 objects and 100 clusters, and the WINE data set of 178 objects, 17 dimensions and 3 clusters from UCI, have demonstrated the effectiveness of the new algorithm in producing consistent clustering results and determining the correct number of clusters in different data sets, some with overlapping inherent clusters.     

Cluster evolution analysis: Identification and detection of similar clusters and migration patterns

Cluster analysis often addresses a specific point in time, ignoring previous cluster analysis products. The present study proposes a model entitled Cluster Evolution Analysis (CEA) that addresses three phenomena likely to occur over time: (1) changes in the number of clusters; (2) changes in cluster characteristics; (3) between-cluster migration of objects.To achieve this goal, two new techniques are implemented: to find similarities between clusters at different points in time, we used the moving average of cluster centroid technique, and to detect prominent migration patterns we used the clustering of clusters technique. The research introduces two new visual tools displaying all the clusters over the entire time period under study in a single graph.The model was tested on five-year trade data of corporate bonds (2010–2014). The results obtained by the CEA model were checked and validated against the bond rating report issued periodically by the local bond rating company.The results proved the model capable of identifying repeated clusters at various points in time, and detecting patterns that predict prospective loss of value, as well as patterns that indicate stability and preservation of value over time.     

Enhancement of sparse 3D reconstruction using a modified match propagation based on particle swarm optimization

Sparse 3D reconstruction, based on interest points detection and matching, does not allow to obtain a suitable 3D surface reconstruction because of its incapacity to recover a cloud of well distributed 3D points on the surface of objects/scenes. In this work, we present a new approach to retrieve a 3D point cloud that leads to a 3D surface model of quality and in a suitable time. First of all, our method uses the structure from motion approach to retrieve a set of 3D points (which correspond to matched interest points). After that, we proposed an algorithm, based on the match propagation and the use of particle swarm optimization (PSO), which significantly increases the number of matches and to have a regular distribution of these matches. It takes as input the obtained matches, their corresponding 3D points and the camera parameters. Afterwards, at each time, a match of best ZNCC value is selected and a set of these neighboring points is defined. The point corresponding to a neighboring point and its 3D coordinates are recovered by the minimization of a nonlinear cost function by the use of PSO algorithm respecting the constraint of photo-consistency. Experimental results show the feasibility and efficiency of the proposed approach.

     

3D object perception using gradient descent

A new algorithm is presented for interpreting two-dimensional (2D) line drawings as three-dimensional (3D) objects without models. Even though no explicit models or additional heuristics are included, the algorithm tends to reach the same 3D interpretations of 2D line drawings that humans do. The algorithm explicitly calculates the partial derivatives of Marill's Minimum Standard Deviation of Angles (MSDA) with respect to all adjustable parameters, and follows this gradient to minimize SDA. For an image with lines meeting atm points formingn angles, the gradient descent algorithm requiresO(n) time to adjust all the points, while Marill's method requiredO(mn) time to do so. Experimental results on various line drawing objects show that this gradient descent algorithm running on a Macintosh II is one to two orders of magnitude faster than the MSDA algorithm running on a Symbolics, while still giving comparable results.     

基于连通距离和连通强度的BIRCH改进算法

为解决利用层次方法的平衡迭代规约和聚类（BIRCH）算法聚类结果依赖于数据对象的添加顺序，且对非球状的簇聚类效果不好以及受簇直径阈值的限制每个簇只能包含数量相近的数据对象的问题，提出一种改进的BIRCH算法。该算法用描述数据对象个体间连通性的连通距离和连通强度阈值替代簇直径阈值，还将簇合并的步骤加入到聚类特征树的生成过程中。在自定义及iris、wine、pendigits数据集上的实验结果表明，该算法比多阈值BIRCH、密度改进BIRCH等现有改进算法的聚类准确率更高，尤其在大数据集上比密度改进BIRCH准确率提高6个百分点，耗时降低61%。说明该算法能够适用于在线实时增量数据，可以识别非球形簇和体积不均匀簇，具有去噪功能，且时间和空间复杂度明显降低。     

Appearance Derivatives for Isonormal Clustering of Scenes

A new technique is proposed for scene analysis, called "appearance clustering.” The key result of this approach is that the scene points can be clustered according to their surface normals, even when the geometry, material, and lighting are all unknown. This is achieved by analyzing an image sequence of a scene as it is illuminated by a smoothly moving distant light source. In such a scenario, the brightness measurements at each pixel form a "continuous appearance profile.” When the source path follows an unstructured trajectory (obtained, say, by smoothly hand-waving a light source), the locations of the extrema of the appearance profile provide a strong cue for the scene point's surface normal. Based on this observation, a simple transformation of the appearance profiles and a distance metric are introduced that, together, can be used with any unsupervised clustering algorithm to obtain isonormal clusters of a scene. We support our algorithm empirically with comprehensive simulations of the Torrance-Sparrow and Oren-Nayar analytic BRDFs, as well as experiments with 25 materials obtained from the MERL database of measured BRDFs. The method is also demonstrated on 45 examples from the CURET database, obtaining clusters on scenes with real textures such as artificial grass and ceramic tile, as well as anisotropic materials such as satin and velvet. The results of applying our algorithm to indoor and outdoor scenes containing a variety of complex geometry and materials are shown. As an example application, isonormal clusters are used for lighting-consistent texture transfer. Our algorithm is simple and does not require any complex lighting setup for data collection.     

Weaves: A Framework for Reconfigurable Programming

This paper presents a language independent runtime framework—called Weaves—for object based composition of unmodified code modules that enables selective sharing of state between multiple control flows through a process. Furthermore, the framework allows dynamic instantiation of code modules and control flows through them. In effect, weaves create intra-process modules (similar to objects in OOP) from code written in any language. Applications can be built by instantiating Weaves to form Tapestries of dynamically interacting code. The framework enables objects to be arbitrarily shared—it is a true superset of both processes as well as threads, with code sharing and fast context switching time similar to threads. Weaves does not require any special support from either the language or application code—practically any code can be weaved. Weaves also include support runtime loading and linking of object modules enabling the next generation of highly dynamic applications. This paper presents the elements of the Weaves framework and its implementation on the Linux platform over source-code independent ELF object files. The current implementation has been validated over Sweep3D, a benchmark for 3D discrete ordinates neutron transport (Koch et al. Trans. Am. Nucl. Soc. 65 (198) [1992]), and a user-level port of the Linux 2.4 family kernel TCP/IP protocol stack.     

Interpreting line drawings of curved objects

In this paper, we study the problem of interpreting line drawings of scenes composed of opaque regular solid objects bounded by piecewise smooth surfaces with no markings or texture on them. It is assumed that the line drawing has been formed by orthographic projection of such a scene under general viewpoint, that the line drawing is error free, and that there are no lines due to shadows or specularities. Our definition implicitly excludes laminae, wires, and the apices of cones.A major component of the interpretation of line drawings is line labelling. By line labelling we mean (a) classification of each image curve as corresponding to either a depth or orientation discontinuity in the scene, and (b) further subclassification of each kind of discontinuity. For a depth discontinuity we determine whether it is a limb—a locus of points on the surface where the line of sight is tangent to the surface—or an occluding edge—a tangent plane discontinuity of the surface. For an orientation discontinuity, we determine whether it corresponds to a convex or concave edge. This paper presents the first mathematically rigorous scheme for labelling line drawings of the class of scenes described. Previous schemes for labelling line drawings of scenes containing curved objects were heuristic, incomplete, and lacked proper mathematical justification.By analyzing the projection of the neighborhoods of different kinds of points on a piecewise smooth surface, we are able to catalog all local labelling possibilities for the different types of junctions in a line drawing. An algorithm is developed which utilizes this catalog to determine all legal labellings of the line drawing. A local minimum complexity rule—at each vertex select those labellings which correspond to the minimum number of faces meeting at the vertex—is used in order to prune highly counter-intuitive interpretations. The labelling scheme was implemented and tested on a number of line drawings. The labellings obtained are few and by and large in accordance with human interpretations.     

噪声数据集上的边界点检测算法

为了有效检测聚类的边界点，提出了结合对象的密度及其Eps-邻域中数据的分布特点进行的边界点检测技术和边界点检测算法 ——BOUND。实验结果表明，BOUND能在含有不同形状、大小簇的噪声数据集上有效地检测出聚类的边界点，并且执行效率高。     

Parallel Thinning Algorithms on 3D (18, 6) Binary Images

Thinning algorithms on binary images are used to generate skeletons that preserve the same connectivity structures as the objects in the original images. Two kinds of skeletons may be appropriate for 3D thinning algorithms: digital curves and digital surfaces. We propose two thinning algorithms on 3D (18, 6) binary images. One algorithm generates skeletons as digital curves and the other algorithm generates skeletons as digital surfaces. Both algorithms are 6-subiteration algorithms—in each iteration, they are applied alternatively to delete border voxels from each of the six directions, upper, lower, north, south, east, and west.     

A hybrid clustering procedure for concentric and chain-like clusters

K-means algorithm is a well known nonhierarchical method for clustering data. The most important limitations of this algorithm are that: (1) it gives final clusters on the basis of the cluster centroids or the seed points chosen initially, and (2) it is appropriate for data sets having fairly isotropic clusters. But this algorithm has the advantage of low computation and storage requirements. On the other hand, hierarchical agglomerative clustering algorithm, which can cluster nonisotropic (chain-like and concentric) clusters, requires high storage and computation requirements. This paper suggests a new method for selecting the initial seed points, so that theK-means algorithm gives the same results for any input data order. This paper also describes a hybrid clustering algorithm, based on the concepts of multilevel theory, which is nonhierarchical at the first level and hierarchical from second level onwards, to cluster data sets having (i) chain-like clusters and (ii) concentric clusters. It is observed that this hybrid clustering algorithm gives the same results as the hierarchical clustering algorithm, with less computation and storage requirements.     

支持k-离群度的边界点检测方法

边界是一种有用的模式,为了有效识别边界,根据边界点周围密度不均匀,提出了一种边界点检测算法——BDKD。该算法用数据对象的k-近邻距离与其邻域内数据对象的平均k-近邻距离之比定义其k-离群度,当k-离群度超过阈值时即确定为边界点。实验结果表明,BDKD算法可以准确检测出各种聚类边界,并能去除噪声,特别是对密度均匀的数据集效果理想。     

Multi-View Scene Capture by Surfel Sampling: From Video Streams to Non-Rigid 3D Motion,Shape and Reflectance

In this paper we study the problem of recovering the 3D shape, reflectance, and non-rigid motion properties of a dynamic 3D scene. Because these properties are completely unknown and because the scene's shape and motion may be non-smooth, our approach uses multiple views to build a piecewise-continuous geometric and radiometric representation of the scene's trace in space-time. A basic primitive of this representation is the dynamic surfel, which (1) encodes the instantaneous local shape, reflectance, and motion of a small and bounded region in the scene, and (2) enables accurate prediction of the region's dynamic appearance under known illumination conditions. We show that complete surfel-based reconstructions can be created by repeatedly applying an algorithm called Surfel Sampling that combines sampling and parameter estimation to fit a single surfel to a small, bounded region of space-time. Experimental results with the Phong reflectancemodel and complex real scenes (clothing, shiny objects, skin) illustrate our method's ability to explain pixels and pixel variations in terms of their underlying causes—shape, reflectance, motion, illumination, and visibility.     

三维单目虚实物体球对面碰撞检测算法

为加强增强现实的沉浸感与真实性,实时地进行虚实物体间的碰撞检测至关重要.因此,提出一种基于增强现实和单目视觉的任意形状虚实物体碰撞检测估计算法.通过改进现有的单目二维虚实碰撞检测及响应算法,针对现有碰撞检测算法存在的计算复杂度高的问题,提出一种仅需计算实际物体4个特征点的三维碰撞检测算法;并通过对象分割、特征点提取、碰撞检测和碰撞响应等过程取得与真实世界物理特性一致的三维虚实碰撞响应估计效果.在增强现实有标记和无标记环境下分别进行实验结果表明,碰撞检测的计算量与二维算法相近,且具有景深效果,实现了基于单目视觉的增强现实三维虚实碰撞响应预测和处理.     

A new way to represent the relative position between areal objects

The fuzzy qualitative evaluation of directional spatial relationships (such as “to the right of”, “to the south of...”) between areal objects often relies on the computation of a histogram of angles, which is considered to provide a good representation of the relative position of an object with regard to another. In this paper, the notion of the histogram of forces is introduced. It generalizes and may supersede the histogram of angles. The objects (2D entities) are handled as longitudinal sections (1D entities), not as points (OD entities). It is thus possible to fully benefit from the power of integral calculus and, so, ensure rapid processing of raster data, as well as of vector data, explicitly considering both angular and metric information     

V3COCA: An effective clustering algorithm for complicated objects and its application in breast cancer research and diagnosis

In breast cancer studies, researchers often use clustering algorithms to investigate similarity/dissimilarity among different cancer cases. The clustering algorithm design becomes a key factor to provide intrinsic disease information. However, the traditional algorithms do not meet the latest multiple requirements simultaneously for breast cancer objects. The Variable parameters, Variable densities, Variable weights, and Complicated Objects Clustering Algorithm (V3COCA) presented in this paper can handle these problems very well. The V3COCA (1) enables alternative inputs of none or a series of objects for disease research and computer aided diagnosis; (2) proposes an automatic parameter calculation strategy to create clusters with different densities; (3) enables noises recognition, and generates arbitrary shaped clusters; and (4) defines a flexibly weighted distance for measuring the dissimilarity between two complicated medical objects, which emphasizes certain medically concerned issues in the objects. The experimental results with 10,000 patient cases from SEER database show that V3COCA can not only meet the various requirements of complicated objects clustering, but also be as efficient as the traditional clustering algorithms.     

一种基于密度的K-means算法研究*

针对传统K-means算法必须事先确定聚类数目以及对初始聚类中心的选取比较敏感的缺陷,采用基于密度的思想,通过设定Eps邻域以及Eps邻域内至少包含的对象数minpts来排除孤立点,并将不重复的核心点作为初始聚类中心;采用类内距离和类间距离的比值作为准则评价函数,将准则函数取得最小值时的聚类数作为最佳聚类数,这些改进有效地克服了K-means算法的不足。最后通过几个实例介绍了改进后算法的具体应用,实例表明改进后的算法比原算法有更高的聚类准确性,更能实现类内紧密类间远离的聚类效果。