Implementing location independent invocation

The problems of finding objects in large and wide-area networks where objects may change their location in volatile memory as well as on stable storage are presented. The authors discuss possible solutions and describe those adopted in the Hermes system (a corporate wide, real life office application). They have designed and developed a location-independent-invocation (LII) mechanism that combines finding with invocation, using temporal location information. The mechanism also updates the system's knowledge of an object's location as a side-effect of invocation and object migration. Assumptions about object mobility indicate that objects are likely to be found within a few propagations of an invocation. If they cannot be found in this way, stable-storage and name services are used to locate the object. The major contribution of this work is to show how LII can be achieved in a large and dynamic environment in which objects are supported by neither are operating system nor the programming language     

Efficient handling of tuples with embedded large objects

Modern database systems and storage manager toolkits usually provide a large object abstraction. Very often large objects are not used as standalone entities, but rather embedded within an aggregate of different types, i.e. a tuple. Depending on the large object's size and access probability, query performance is determined by the representation of the large object: either inlined within the aggregate or swapped out to a separate object. This paper describes a sound and general large object interface extension which automatically switches the representation of large objects according to their actual size. The optimum threshold size for switching the large object's representation is determined, based upon a linear cost model. Furthermore, a SHORE-based implementation and its performance are presented. It turns out that switching the representation of large objects yields great performance improvements for objects whose size is varying from quite small to large.     

Domain connected graph: the skeleton of a closed 3D shape for animation

In previous research, three main approaches have been employed to solve the skeleton extraction problem: medial axis transform (MAT), generalized potential field and decomposition-based methods. These three approaches have been formulated using three different concepts, namely surface variation, inside energy distribution, and the connectivity of parts. By combining the above mentioned concepts, this paper creates a concise structure to represent the control skeleton of an arbitrary object. First, an algorithm is proposed to detect the end, connection and joint points of an arbitrary 3D object. These three points comprise the skeleton, and are the most important to consider when describing it. In order to maintain the stability of the point extraction algorithm, a prong-feature detection technique and a level iso-surfaces function-based on the repulsive force field was employed. A neighborhood relationship inherited from the surface able to describe the connection relationship of these positions was then defined. Based on this relationship, the skeleton was finally constructed and named domain connected graph (DCG). The DCG not only preserves the topology information of a 3D object, but is also less sensitive than MAT to the perturbation of shapes. Moreover, from the results of complicated 3D models, consisting of thousands of polygons, it is evident that the DCG conforms to human perception.     

A model-based vision system for industrial parts using a small computer

A model-based vision system has been successfully implemented in a small computer environment. This approach uses a basic solid modeling system to develop three-dimensional models of mechanical parts. From those models, two-dimensional projections are taken for every stable state of the object, with many orientations around the object's vertical axis for each stable state. These two-dimensional projections are treated as synthetic binary images, from which a variety of features may be measured and extracted. A similar procedure is used for a binary image of an object from a real scene, and features are also extracted for that image. A simple matching procedures uses the model-based feature sets to determine the real object's stable state position and orientation. This paper describes the system in detail and shows examples of its use.     

A Shape Metric for Blum Ribbons

A Blum ribbon is a figure whose boundary is the envelope of a family of circles the centers of which lie along a single unbranched curve called its medial axis. Define a Blum ribbon to be simple if its medial axis is the line segment joining points (0,0) and (1,0). Any Blum ribbon can be made simple by flexing the medial axis, rotating, then dilating, all of which are basic transformations in Blum's geometry of shape. The Lie group SL(2, R) acts on circles centered on the x-axis by linear fractional transformations. By means of this action it is possible to associate to any simple Blum ribbon a curve in SL(2, R). A distance between corresponding points lying on such curves is defined using the bi-invariant metric on SL(2, R). Resulting scale-invariant metrics on the set of figures defined as Blum ribbons are described and it is shown that these metrics can provide effective measures of shape difference.     

Context-based object-class recognition and retrieval by generalized correlograms

We present a novel approach for retrieval of object categories based on a novel type of image representation: the Generalized Correlogram (GC). In our image representation, the object is described as a constellation of GCs where each one encodes information about some local part and the spatial relations from this part to others (i.e., the part's context). We show how such a representation can be used with fast procedures that learn the object category with weak supervision and efficiently match the model of the object against large collections of images. In the learning stage, we show that by integrating our representation with Boosting the system is able to obtain a compact model that is represented by very few features, where each feature conveys key properties about the object's parts and their spatial arrangement. In the matching step, we propose direct procedures that exploit our representation for efficiently considering spatial coherence between the matching of local parts. Combined with an appropriate data organization such as Inverted Files, we show that thousands of images can be evaluated efficiently. The framework has been applied to different standard databases and we show that our results are favorably compared against state-of-the-art methods in both computational cost and accuracy.     

Linear One-Sided Stability of MAT for Weakly Injective Domain

Medial axis transform (MAT) is very sensitive to noise, in the sense that, even if a shape is perturbed only slightly, the Hausdorff distance between the MATs of the original shape and the perturbed one may be large. But it turns out that MAT is stable, if we view this phenomenon with the one-sided Hausdorff distance, rather than with the two-sided Hausdorff distance. In this paper, we show that, if the original domain is weakly injective, which means that the MAT of the domain has no end point which is the center of an inscribed circle osculating the boundary at only one point, the one-sided Hausdorff distance of the original domain's MAT with respect to that of the perturbed one is bounded linearly with the Hausdorff distance of the perturbation. We also show by example that the linearity of this bound cannot be achieved for the domains which are not weakly injective. In particular, these results apply to the domains with sharp corners, which were excluded in the past. One consequence of these results is that we can clarify theoretically the notion of extracting the essential part of the MAT, which is the heart of the existing pruning methods.     

A medial axis transformation for grayscale pictures

Blum's medial axis transformation (MAT) for binary pictures yields medial axis points that lie midway between opposite borders of a region or along angle bisectors. This note discusses a generalization of the MAT in which a score is computed for each point P of a grayscale picture based on the gradient magnitudes at pairs of points that have P as their midpoint. These scores are high at points that lie midway between pairs of antiparallel edges or along angle bisectors, so that they define a MAT-like ``skeleton,' which we may call the GRADMAT. However, this skeleton is rather sensitive to the presence of noise edges or to irregularities in the region edges, and it also is subject to artifacts created by pairs of edges belonging to different objects.     

A diffusion mechanism for obstacle detection from size-changeinformation

A mechanism fur the visual detection of obstacles is presented. A new immediacy measure, representing the imminence of collision between an object and a moving observer, is defined. A diffusion process on the image domain, whose initial condition is determined by the motion field normal to the object's boundary, is shown to converge asymptotically to the immediacy measure. A network of locally connected cells, derived from a finite-difference approximation of the diffusion equation, estimates the immediacy measure from normal velocity and boundary information provided by a motion measurement and segmentation stage. The algorithm's performance on real image sequences is demonstrated     

联合骨架与边界特征的平面形状分解

在形状分析及其相关应用中,将形状分解成有意义的几个部分往往具有重要意义。骨架与轮廓都蕴含了丰富的物体形状全局与局部信息。提出一种联合骨架与边界特征的平面形状分解方法。该算法引入符合视觉特性的弯曲度比率作为约束,获得可控的分解结果以满足不同细节尺度的要求。算法充分利用对轮廓进行离散曲线演化时得到的信息,避免几个重要的部分被合并为一个整体。由于采用了鲁棒的骨架生成方法,使得算法对较高噪声干扰具有一定的鲁棒性,且能使得一个重要的部分不被进一步误分解。以MPEG7形状库等形状为实验对象,对算法的有效性进行了验证。分解实验结果均较为符合人类的主观感觉,同时对噪声污染的形状也具有较为鲁棒的结果。     

Constructing medial axis transform of planar domains with curved boundaries

The paper describes an algorithm for generating an approximation of the medial axis transform (MAT) for planar objects with free form boundaries. The algorithm generates the MAT by a tracing technique that marches along the object boundary rather than the bisectors of the boundary entities. The level of approximation is controlled by the choice of the step size in the tracing procedure. Criteria based on distance and local curvature of boundary entities are used to identify the junction or branch points and the search for these branch points is more efficient than while tracing the bisectors. The algorithm works for multiply connected objects as well. Results of implementation are provided.     

Appearance Sampling of Real Objects for Variable Illumination

The appearance of an object greatly changes under different lighting conditions. Even so, previous studies have demonstrated that the appearance of an object under varying illumination conditions can be represented by a linear subspace. A set of basis images spanning such a linear subspace can be obtained by applying the principal component analysis (PCA) for a large number of images taken under different lighting conditions. Since little is known about how to sample the appearance of an object in order to correctly obtain its basis images, it was a common practice to use as many input images as possible. In this study, we present a novel method for analytically obtaining a set of basis images of an object for varying illumination from input images of the object taken properly under a set of light sources, such as point light sources or extended light sources. Our proposed method incorporates the sampling theorem of spherical harmonics for determining a set of lighting directions to efficiently sample the appearance of an object. We further consider the issue of aliasing caused by insufficient sampling of the object's appearance. In particular, we investigate the effectiveness of using extended light sources for modeling the appearance of an object under varying illumination without suffering the aliasing caused by insufficient sampling of its appearance.     

Linear one-sided stability of MAT for weakly injective 3D domain

Despite its usefulness in many applications, the medial axis transform (MAT) is very sensitive to the change of the boundary in the sense that, even if a shape is perturbed only slightly, the Hausdorff distance between the MATs of the original shape and the perturbed one may be large. However, it is known that MATs of 2D domains are stable if we view this phenomenon with the one-sided Hausdorff distance. This result depends on the fact that MATs are stable if the differences between them are measured with the recently introduced hyperbolic Hausdorff distance. In this paper, we extend the result for the one-sided stability of the MAT to a class of 3D domains called weakly injective, which contains many important 3D shapes typically appearing in solid modeling. Especially, the weakly injective 3D domains can have sharp features like corners or edges. In fact, by using the stability of the MAT under the hyperbolic Hausdorff distance, we obtain an explicit bound for the one-sided Hausdorff distance of the MAT of a weakly injective 3D domain with respect to that of a perturbed domain, which is linear with respect to the domain perturbation. We discuss some consequences of this result concerning the computation and the approximation of the MAT of 3D objects.     

具有鲁棒性的图像骨架提取方法

基于最大正方形的中轴变换,提出了一种二值图像的骨架提取算法。首先通过计算目标像素邻域内最大正方形的所有像素的个数来进行中轴变换,判断骨架点,并提取骨架。如果通过设定一个阈值,再提取骨架,就可以滤除背景中的噪声。实验结果表明:该方法提取的骨架效果好,通过与基于传统中轴变换和形态学提取骨架方法进行比较,该方法抗干扰能力强。     

基于对数极坐标变换和仿射变换的目标识别定位方法

由于传统的模板相关匹配算法在目标图像发生较大旋转和放大时，定位结果可能会发生偏差，因此为了取得精度更高的目标识别结果，提出了一种基于对数极坐标变换粗匹配，结合仿射变换精匹配的目标图像识别定位方法，以用于在视场中自动搜索相对于模板图像有平移、旋转和尺度变化的目标图像。实验结果表明，该算法不仅定位精度高，而且相对于传统的模板匹配算法有更强的鲁棒性。     

增量学习Rao-Blackwellized粒子滤波的跟踪算法

基于特征子空间的目标跟踪方法能适应目标状态的变化,并对光照等外部环境不敏感,但通常假定特征子空间的基向量固定,这样不仅需要离线训练,而且在目标姿态发生较大改变时,跟踪精度会降低。提出一种基于增量学习的Rao-Blackwellized粒子滤波算法,通过在线学习获得特征子空间的基向量,并用解析的方法对目标在子空间的投影参数进行在线更新。实验表明,新算法在目标有较大形变、姿态变化和光照等条件变化时,能保持较高跟踪精度,具有较强的鲁棒性。     

结合语义边界信息的道路环境语义分割方法

语义分割是实现道路语义环境解释的重要方法,深度学习语义分割由于卷积、池化及反卷积的作用使分割边界模糊、不连续以及小目标漏分错分,影响了分割效果,降低了分割精度。针对上述问题,提出了一种结合语义边界信息的新的语义分割方法,首先在语义分割深度模型中构建了一个语义边界检测子网,利用网络中的特征共享层将语义边界检测子网络学习到的语义边界信息传递给语义分割网络;然后结合语义边界检测任务和语义分割任务定义了新的模型代价函数,同时完成语义边界检测和语义分割两个任务,提升语义分割网络对物体边界的描述能力,提高语义分割质量。最后在Cityscapes数据集上进行一系列实验证明,结合语义边界信息的语义分割方法在准确率上比已有的语义分割网络SegNet提升了2.9%,比ENet提升了1.3%。所提方法可以改善语义分割中出现的分割不连续、物体边界不清晰、小目标错分漏分、分割精度不高等问题。     

声传感器网络目标定位算法实现研究

声传感器可以通过分析接收到的目标发出的次声波噪声得到目标的方位角和属性信息,通过对声传感器的组网,融合网内多传感器的信息,可以实现对目标定位的目的。因此定位算法及其实现技术是声传感器网络的核心技术之一。由于声传感器网络中各个探测区域具有不同的特点,首先根据声传感器网络的特点将定位算法进行了分类,提出了一种有效的算法选择机制,减少了时间延迟对于目标定位的影响。同时为了降低目标定位算法的复杂度,提高运行效率,提出了并行处理和数据存储的方案。最后通过仿真验证了方法的有效性。