Image Thinning by Neural Networks

An image thinning technique using a neural network is proposed. Using different activation functions at different layers, the proposed neural network removes the boundary pixels from four directions in such a manner that the general configuration of the input pattern is unaltered and the connectivity is preserved. The resulting object, called a skeleton, provides an abstraction of the global shape of the object. The skeleton is often useful for geometrical and structural analysis of the object. The output skeleton here satisfies the basic properties of a skeleton, namely connectivity and unit thickness. The proposed method is experimentally found to be more efficient in terms of better medial axis representation and robustness to boundary noise over a few existing algorithms. ID="A1" Correspondence and offprint requests to: Dr A. Datta, Indian Statistical Institute, 203 B. T. Road, Calcutta – 700 108, India. Email: amitava@isical.ac.in     

Branching object generation and animation system with cubic hermite interpolation

This paper presents geometric modelling methods for branching object generation and animation with cubic Hermite curves. The procedure for creating a branching object involves two steps. First, the skeleton of an object is constructed. The skeleton consists of geometrical and topological information about the segments of the object. Secondly, cubic Hermite curves are used to deform and join consecutive segments in the skeleton in order to form the body of the object with C¹ continuity. Cubic Hermite curves are also used to deform partial segments which allow an object to grow with desirable continuity in space and time. The techniques are easily implemented on any computer and allow the user to create a branching object using objects which have diverse shapes as segments.     

On-the-fly Curve-skeleton Computation for 3D Shapes

The curve-skeleton of a 3D object is an abstract geometrical and topological representation of its 3D shape. It maps the spatial relation of geometrically meaningful parts to a graph structure. Each arc of this graph represents a part of the object with roughly constant diameter or thickness, and approximates its centerline. This makes the curve-skeleton suitable to describe and handle articulated objects such as characters for animation. We present an algorithm to extract such a skeleton on-the-fly, both from point clouds and polygonal meshes. The algorithm is based on a deformable model evolution that captures the object's volumetric shape. The deformable model involves multiple competing fronts which evolve inside the object in a coarse-to-fine manner. We first track these fronts' centers, and then merge and filter the resulting arcs to obtain a curve-skeleton of the object. The process inherits the robustness of the reconstruction technique, being able to cope with noisy input, intricate geometry and complex topology. It creates a natural segmentation of the object and computes a center curve for each segment while maintaining a full correspondence between the skeleton and the boundary of the object.     

An optimized real time algorithm for window frost formation suited to mobile devices

We propose a real time simulation for window frost formation on mobile devices that uses both particles and grids. Previous ice formation methods made heavy demands on both memory and computational capacity because they were designed for a desktop environment. In this paper, a frost skeleton grows around a location touched by the user using particles, and the ice surfaces are constructed using a grid. Using a nonlattice random-walk technique, the frost skeleton grows freely and naturally. A hash grid technique is used to search efficiently for neighbor particles during the crystallization process. Finally, some 2.5D details are added to the ice skeleton by adjusting the height of the grid vertices around the skeleton. Experiments show that our method creates realistic frost in real time. Our method can be used to express ice formation effects in touch-based mobile device applications such as weather forecasts or games.     

增强现实系统中基于视觉感知的抓取识别

增强现实系统采用单目光学透视式头盔时必然会使虚拟物体呈现在真实物体之前,使用户无法得知应该在何处抓取虚拟物体,并且系统所得到的抓取数据也会受硬件本身、人和环境等因素影响而产生偏差.从人的视觉感知习惯入手,利用机器人学和光线几何理论实现基于视觉感知的碰撞检测;通过分析抓取过程,得出3条抓取知识规则,并将其与模糊理论结合应用于证据推理.实验结果表明,采用文中方法,用户能轻松地实现抓取,整个交互过程相当自然.     

动态骨架算法

骨架是表示物体形状的一种有效形式.基于距离变换的骨架求解算法得到的骨架尽管准确光滑,但必须仔细地检查其连续性;而当骨架的结构较为复杂时,这种连续性检查会变得非常困难.结合Thinning技术和Snake模型,提出了一个平面二值图的动态骨架算法.首先利用Thinning技术生成连续且拓扑保持的初始骨架,然后根据Snake模型的思想,将初始骨架引导到正确的位置上.动态骨架算法提取的骨架不仅保持了位置的准确和外形的光滑,同时也解决了骨架的连续性问题.     

Skeleton growing: an algorithm to extract a curve skeleton from a pseudonormal vector field

A curve skeleton is used to represent a 3D object in many different applications. It is a 1D curve that captures topology of the 3D object. The proposed method extracts a curve skeleton from the vector field inside the 3D object. A vector at each voxel of the 3D object is calculated using a pseudonormal vector. By using such a calculation, the computation time is significantly reduced compared with using a typical potential field. A curve skeleton is then extracted from the pseudonormal vector field by using a skeleton-growing algorithm. The proposed algorithm uses high-curvature boundary voxels to search for a set of critical points and skeleton branches near high-curvature areas. The set of detected critical points is then used to grow a curve skeleton in the next step. All parameters of our algorithms are calculated from the 3D object itself, without user intervention. The effectiveness of our method is demonstrated in our experiments.     

Animating Volumetric Models

This paper describes a technique to animate three-dimensional sampled volumes. The technique gives the animator the ability to treat volumes as if they were standard polygonal models and to use all of the standard animation/motion capture tools on volumetric data. A volumetric skeleton is computed from a volumetric model using a multi-resolution thinning procedure. The volumetric skeleton is centered in the object and accurately represents the shape of the object. The thinning process is reversible in that the volumetric model can be reconstructed from the volumetric skeleton. The volumetric skeleton is then connected and imported into a standard graphics animation package for animation. The animated skeleton is used for reconstruction, which essentially recreates a deformed volume around the deformed skeleton. Polygons are never computed and the entire process remains in the volumetric domain. This technique is demonstrated on one of the most complex 3D datasets, the Visible Male, resulting in actual “human animation”.     

Target Reaching by Using Visual Information and Q-learning Controllers

This paper presents a solution to the problem of manipulation control: target identification and grasping. The proposed controller is designed for a real platform in combination with a monocular vision system. The objective of the controller is to learn an optimal policy to reach and to grasp a spherical object of known size, randomly placed in the environment. In order to accomplish this, the task has been treated as a reinforcement problem, in which the controller learns by a trial and error approach the situation-action mapping. The optimal policy is found by using the Q-Learning algorithm, a model free reinforcement learning technique, that rewards actions that move the arm closer to the target.The vision system uses geometrical computation to simplify the segmentation of the moving target (a spherical object) and determines an estimate of the target parameters. To speed-up the learning time, the simulated knowledge has been ported on the real platform, an industrial robot manipulator PUMA 560. Experimental results demonstrate the effectiveness of the adaptive controller that does not require an explicit global target position using direct perception of the environment.     

Analysis and verification of the boundary surfaces of solid objects

Triangulation of complex three-dimensional objects is a time-consuming process, and the boundary surfaces of the object have to be checked very carefully to ensure no crror is made. With the increased use of computer graphics in the generation of complicated object shapes, such as aircraft, space vessels, machine parts, physical models, etc., visual inspection alone is not good enough to affirm the validity of the object, and a thorough verification of the output from a CAD system is necessary to ensure that the object is well defined and complies with the input requirements of the mesh generator.This paper describes such a data verification procedure for general curved surfaces and objects defined by the boundary surface modelling technique. The quality of individual elements, the overall topological structures, and geometrical correctness in terms of intersections, close touches and sharp angles will all be studied and verified. Several engineering objects are analysed to illustrate the practical applications of the procedure.     

Animation through space and time based on a space deformation model

To animate deformable objects through time and space, a new technique that will be referred to as DOGMA is proposed here. It is well suited to animation for both interactive design and real-time visualization. The concept of animation primitives based on an extension to animation of the space deformation model is introduced. Animation primitives can be added to any geometrical modeller because they are independent of the underlying geometrical model of the animated objects. It encapsulates animation through space and time under a unique formalism. A local control of deformations both through space and time is easily specified. A direct manipulation of objects is provided. At any time, animated objects are continuously computed from their corresponding animation primitives. This dispenses with the necessity for major storage of the interpolation process. A fully interactive system offers an interactive environment which enables the user to animate deformable objects in real time.     

梵高风格的笔触骨架线绘制方法研究及应用

将虚拟的数字图像转变为实体艺术作品的需求随着社会发展与日俱增,而梵高作为传奇艺术家,其风格被无数人效仿。利用基于笔刷的图像风格化技术,设计了一种模拟梵高绘画风格的笔触骨架线绘制算法,生成表示笔触抽象轨迹的图谱,用于油画、刺绣等真实艺术作品的辅助创作,提出的辐射方向梯度插值方法较好地模拟了梵高水波纹状的笔触方向布局。     

Analytic Curve Skeletons for 3D Surface Modeling and Processing

We present a new curve skeleton model designed for surface modeling and processing. This skeleton is defined as the geometrical integration of a piecewise harmonic parameterization defined over a disk‐cylinder surface decomposition. This decomposition is computed using a progressive Region Graph reduction based on both geometric and topological criteria which can be iteratively optimized to improve region boundaries. The skeleton has an analytical form with regularity inherited from the surface one. Such a form offers well‐defined surface‐skeleton and skeleton‐surface projections. The resulting skeleton satisfies quality criteria which are relevant for skeleton‐based modeling and processing. We propose applications that benefit from our skeleton model, including local thickness editing, inset surface creation for shell mapping, as well as a new mid‐scale feature preserving smoothing.     

Animation by Deformation of Space-Time Objects

This article presents the properties of animation with space-time objects. A space-time object means here a geometrical object embedded in R⁴ with a volumic topology. Resulting animations are obtained by deforming space-time objects with a free-form deformation model. In this way topological modifications, such as disconnecting or hole making, as well as classical geometrical modifications, can be created in an animated object.     

Acquiring 3-D models from sequences of contours

This paper explores shape from contour for acquiring 3-D graphics models. In this method, a continuous sequence of images is taken as an object rotates. A smooth convex shape can be estimated instantaneously from its contour and by the first derivative of contour movement (trace of contour, or contour distribution with time). We also analyze shapes that do not satisfy the conditions of smoothness and visibility, which are indispensable for modeling an object. A region that does not expose as contour yields a nonsmoothness in the tracked contour movement. We can thus detect such a region by contour distribution filtering and extract its accurate location by computing the left and right derivatives of the distribution. This has not been studied previously. These unknown regions are obtained for further investigation using other visual cues. A general approach for building a geometrical object model using contours is then described. The entire process from silhouettes to a 3-D model is based local computation; this is promising for producing shapes in real time. Our direct goal is to establish 3-D graphics models of human faces for the growing needs of visual communications. We have obtained some good results     

Multilevel representation and transmission of real objects with progressive octree particles

We present a multilevel representation scheme adapted to storage, progressive transmission, and rendering of dense data sampled on the surface of real objects. Geometry and object attributes, such as color and normal, are encoded in terms of surface particles associated to a hierarchical space partitioning based on an octree. Appropriate ordering of surface particles results in a compact multilevel representation without increasing the size of the uniresolution model corresponding to the highest level of detail. This compact representation can progressively be decoded by the viewer and transformed by a fast direct triangulation technique into a sequence of triangle meshes with increasing levels of detail. The representation requires approximately 5 bits per particle (2.5 bits per triangle) to encode the basic geometrical structure. The vertex positions can then be refined by means of additional precision bits, resulting in 5 to 9 bits per triangle for representing a 12-bit quantized geometry. The proposed representation scheme is demonstrated with the surface data of various real objects.     

A geospatial technique for detecting distance and Reflection Angle between real and virtual objects

This paper presents a geospatial collision detection technique consisting of two methods: Find Object Distance (FOD) and Find Reflection Angle (FRA). We show how the geospatial collision detection technique using a computer vision system detects a computer generated virtual object and a real object manipulated by a human user and how the virtual object can be reflected on a real floor after being detected by a real object. In the geospatial collision detection technique, the FOD method detects the real and virtual objects, and the FRA method predicts the next moving directions of virtual objects. We demonstrate the two methods by implementing a floor based Augmented Reality (AR) game, Ting Ting, which is played by bouncing fire-shaped virtual objects projected on a floor using bamboo-shaped real objects. The results reveal that the FOD and the FRA methods of the geospatial collision detection technique enable the smooth interaction between a real object manipulated by a human user and a virtual object controlled by a computer. The proposed technique is expected to be used in various AR applications as a low cost interactive collision detection engine such as in educational materials, interactive contents including games, and entertainment equipments. Keywords: Augmented reality, collision detection, computer vision, game, human computer interaction, image processing, interfaces.     

Context preserving maps of tubular structures

When visualizing tubular 3D structures, external representations are often used for guidance and display, and such views in 2D can often contain occlusions. Virtual dissection methods have been proposed where the entire 3D structure can be mapped to the 2D plane, though these will lose context by straightening curved sections. We present a new method of creating maps of 3D tubular structures that yield a succinct view while preserving the overall geometric structure. Given a dominant view plane for the structure, its curve skeleton is first projected to a 2D skeleton. This 2D skeleton is adjusted to account for distortions in length, modified to remove intersections, and optimized to preserve the shape of the original 3D skeleton. Based on this shaped 2D skeleton, a boundary for the map of the object is obtained based on a slicing path through the structure and the radius around the skeleton. The sliced structure is conformally mapped to a rectangle and then deformed via harmonic mapping to match the boundary placement. This flattened map preserves the general geometric context of a 3D object in a 2D display, and rendering of this flattened map can be accomplished using volumetric ray casting. We have evaluated our method on real datasets of human colon models.     

Kinect 下深度信息获取技术及其在三维目标识别中的应用综述

微软公司 2010 年推出的 Kinect 深度传感器能够同步提供场景深度和彩色信息,其应用的一个关键领域就是目标 识别。传统的目标识别大多限制在特殊的情形,如：手势识别、人脸识别,而大规模的目标识别是近年来的研究趋势。 通过 Kinect 得到的 RGB-D 数据集多为室内和办公环境下获取的多场景、多视角、分目标类型的数据集,为大规模的目标 识别算法设计提供了学习基础。同时,Kinect 获取的深度信息为目标识别提供了强有力的线索,利用深度信息的识别方法 较以前的方法具有无法比拟的优势,大大地提高了识别的精度。文章首先对 Kinect 的深度获取技术做了详细介绍;其次 对现有的 3D 目标识别方法进行综述,接着对已有的 3D 测试数据集进行分析和比较;最后对文章进行小结以及对未来 3D 目标识别算法和 3D 测试数据集的发展趋势作了简单的阐述。