Evidence-based recognition of 3-D objects

An evidence-based recognition technique is defined that identifies 3-D objects by looking for their notable features. This technique makes use of an evidence rule base, which is a set of salient or evidence conditions with corresponding evidence weights for various objects in the database. A measure of similarity between the set of observed features and the set of evidence conditions for a given object in the database is used to determine the identity of an object in the scene or reject the object(s) in the scene as unknown. This procedure has polynomial time complexity and correctly identifies a variety of objects in both synthetic and real range images. A technique for automatically deriving the evidence rule base from training views of objects is shown to generate evidence conditions that successfully identify new views of those objects     

Representation and classification of 3-D objects

This paper addresses the problem of generic object classification from three-dimensional depth or meshed data. First, surface patches are segmented on the basis of differential geometry and quadratic surface fitting. These are represented by a modified Gaussian image that includes the well-known shape index. Learning is an interactive process in which a human teacher indicates corresponding patches, but the formation of generic classes is unaided. Classification of unknown objects is based on the measurement of similarities between feature sets of the objects and the generic classes. The process is demonstrated on a group of three-dimensional (3-D) objects built from both CAD and laser-scanned depth data.     

Automatic mesh generation in 2-D and 3-D objects

The object of the paper is to propose a simple method of mesh generation for objects with complicated boundary configurations and present a program which can generate the element data required for Finite Element Analysis based on these methods. The area to be meshed is considered as a combination of different sub-areas which are further sub-divided into the required number of triangular elements. The main part of the program developed in FORTRAN is included in this paper.     

Polyhedral approximation of 3-D objects without holes

An efficient way of building a polyhedral approximation of a set of points in 3-D space is described. The points are the vertices of a planar graph embedded in a surface of genus 0 and are obtained by a laser range finder. The technique presented here is a generalization of an existing algorithm (R. Duda and P. Hart, Pattern Classification and Scene Analysis, Wiley-Interscience, New York 1973) for the polygonal approximation of a simple curve in 2-D space.     

三维动画设计与制作课程项目化教学改革探索

本文对三维动画设计与制作课程的教学方法进行了探索,在课程中引入项目化教学方法,对课程内容和考核方式等进行了改革,在实际教学中对项目化教学与传统教学方法的教学效果进行了比较,结果表明项目化教学有助于提升学生的专业能力,增强教学效果。     

3-D Shaded Computer Animation?Step by Step

A walk through the production process at this commercial CG animation house reveals an emphasis on software tools and the use of intermediate-stage graphics for design flexibility.     

On learning to recognize 3-D objects from examples

Previous results on nonlearnability of visual concepts relied on the assumption that such concepts are represented as sets of pixels. The author uses an approach developed by Haussler (1989) to show that under an alternative, feature-based representation, recognition is probably approximately correct (PAC) learnable from a feasible number of examples in a distribution-free manner     

Quality metric for approximating subjective evaluation of 3-D objects

Many factors, such as the number of vertices and the resolution of texture, can affect the display quality of three-dimensional (3-D) objects. When the resources of a graphics system are not sufficient to render the ideal image, degradation is inevitable. It is, therefore, important to study how individual factors will affect the overall quality, and how the degradation can be controlled given limited resources. In this paper, the essential factors determining the display quality are reviewed. We then integrate two important ones, resolution of texture and resolution of wireframe, and use them in our model as a perceptual metric. We assess this metric using statistical data collected from a 3-D quality evaluation experiment. The statistical model and the methodology to assess the display quality metric are discussed. A preliminary study of the reliability of the estimates is also described. The contribution of this paper lies in: 1) determining the relative importance of wireframe versus texture resolution in perceptual quality evaluation and 2) proposing an experimental strategy for verifying and fitting a quantitative model that estimates 3-D perceptual quality. The proposed quantitative method is found to fit closely to subjective ratings by human observers based on preliminary experimental results.     

Classification of 3-D objects and faces employing view-based clusters

This paper presents the design of a new clustering algorithm for images having wide range of variations in appearances and shape. The major chore of the clustering process involves in creating the partitions, reassigning the elements of the partitions and identifying the compact cluster obtained. The clusters are created from various low-dimensional spaces of the data set. Hierarchically related eigenspaces are employed to reassign the elements of the cluster. The clusters obtained from the proposed clustering scheme are used to form the learning set of the classification module. The quality of clusters generated is evaluated from the classification results. Comparisons on the clustering performance have been made with the well-known K-means and nearest neighbor-based clustering techniques. Excellent performance of the proposed clustering scheme is proved from the results reported. The benchmark datasets for objects and faces having images with large pose variations have been used to illustrate the efficiency and effectiveness of the proposed scheme.     

3-D reconstruction of homogeneous objects from two poisson-distributed projections

It is computationally very convenient to view the problem of reconstructing a homogeneous 3-D object from two orthogonal projections as a flow problem in a capacitated network. This network flow approach is extended here to incorporate the Poisson nature of the projection data, as is the case in X-ray imaging.     

Recognition of 3-D objects by forward checking constrained search

An attempt to recognize 3-D objects from range images is described. Objects are represented by surface patches obtained by segmenting image at depth or orientation discontinuity. To find the best matching pairs between model surface patches (MSPs) and scene surface patches (SSPs), we use forward checking constrained tree search that is a sequential constrained tree search with a forward checking mechanism. It checks geometric constraints between current partial matching pairs and unexplored possible pairs and drastically reduces the number of candidate MSPs matchable to unexplored SSPs. Futhermore, it yields powerful search termination criteria. As an alternative to the sequential search method, we also applied the optimal search algorithm (A^*). To verify advantages of the forward checking, we evaluated the perfomance of the matching algorithms using real range images. The experimental results demonstrated significant gains in computation. Comparing with other methods, our approach is particularly advantageous for the difficult problems in that model objects are very much similar to each other. Our method detects part in difference in advance and so reduces time to discriminate the similar objects. It is confirmed by an evaluation.     

Motion estimation of 3-D objects using multisensor data fusion

This article presents an approach to estimate the general 3-D motion of a polyhedral object using multiple sensor data some of which may not provide sufficient information for the estimation of object motion. Motion can be estimated continuously from each sensor through the analysis of the instantaneous state of an object. The instantaneous state of an object is specified by the rotation, which is defined by a rotation axis and rotation angle, and the displacement of the center of rotation. We have introduced a method based on Moore-Penrose pseudoinverse theory to estimate the instantaneous state of an object, and a linear feedback estimation algorithm to approach the motion estimation. The motion estimated from each sensor is fused to provide more accurate and reliable information about the motion of an unknown object. The techniques of multisensor data fusion can be categorized into three methods: averaging, decision, and guiding. We present a fusion algorithm which combines averaging and decision. With the assumption that the motion is smooth, our approach can handle the data sequences from multiple sensors with different sampling times. We can also predict the next immediate object position and its motion. The simulation results show our proposed approach is advantageous in terms of accuracy, speed, and versatility.     

A shading model for cloth objects

A fundamental light reflection model that takes into account the internal structure of cloth to render the peculiar gloss of cloth objects is presented. In developing this model, the microscopic structure of textiles was considered. The model represents fabric features such as fiber's cross-sectional shape or weave. By measuring the reflected light intensity from actual cloth objects of several typical materials, it was verified that the model can express the properties of several kinds of cloth, and the parameters in the model were defined     

On recognizing and positioning curved 3-D objects from imagecontours

An approach for explicitly relating the shape of image contours to models of curved three-dimensional objects is presented. This relationship is used for object recognition and positioning. Object models consist of collections of parametric surface patches and their intersection curves; this includes nearly all representations used in computer-aided geometric design and computer vision. The image contours considered are the projections of surface discontinuities and occluding contours. Elimination theory provides a method for constructing the implicit equation of these contours for an object observed under orthographic or perspective projection. This equation is parameterized by the object's position and orientation with respect to the observer. Determining these parameters is reduced to a fitting problem between the theoretical contour and the observed data points. The proposed approach readily extends to parameterized models. It has been implemented for a simple world composed of various surfaces of revolution and tested on several real images     

Recovering 3D motion of multiple objects using adaptive Houghtransform

We present a method to determine 3D motion and structure of multiple objects from two perspective views, using adaptive Hough transform. In our method, segmentation is determined based on a 3D rigidity constraint. Instead of searching candidate solutions over the entire five-dimensional translation and rotation parameter space, we only examine the two-dimensional translation space. We divide the input image into overlapping patches, and, for each sample of the translation space, we compute the rotation parameters of patches using least-squares fit. Every patch votes for a sample in the five-dimensional parameter space. For a patch containing multiple motions, we use a redescending M-estimator to compute rotation parameters of a dominant motion within the patch. To reduce computational and storage burdens of standard multidimensional Hough transform, we use adaptive Hough transform to iteratively refine the relevant parameter space in a “coarse-to-fine” fashion. Our method can robustly recover 3D motion parameters, reject outliers of the flow estimates, and deal with multiple moving objects present in the scene. Applications of the proposed method to both synthetic and real image sequences are demonstrated with promising results     

Artificial neural networks for 3-D motion analysis-Part II:Nonrigid motion

For pt. I see ibid., p. 1386-93 (1995). An approach applying artificial neural net techniques to 3D nonrigid motion analysis is proposed. The 3D nonrigid motion of the left ventricle of a human heart is examined using biplanar cineangiography data, consisting of 3D coordinates of 30 coronary artery bifurcation points of the left ventricle and the correspondences of these points taken over 10 time instants during the heart cardiac cycle. The motion is decomposed into global rigid motion and a set of local nonrigid deformations which are coupled with the global motion. The global rigid motion can be estimated precisely as a translation vecto and a rotation matrix. Local nonrigid deformation estimation is discussed. A set of neural nets similar in structure and dynamics but different in physical size is proposed to tackle the problem of nonrigidity. These neural networks are interconnected through feedbacks. The activation function of the output layer is selected so that a feedback is involved in the output updating. The constraints are specified to ensure stable and globally consistent estimation. The objective is to find the optimal deformation matrices that satisfy the constraints for all coronary artery bifurcation points of the left ventricle. The proposed neural networks differ from other existing neural network models in their unique structure and dynamics.     

Appearance-based recognition of 3-D objects by cluttered background and occlusions

In this article we present a new appearance-based approach for the classification and the localization of 3-D objects in complex scenes. A main problem for object recognition is that the size and the appearance of the objects in the image vary for 3-D transformations. For this reason, we model the region of the object in the image as well as the object features themselves as functions of these transformations. We integrate the model into a statistical framework, and so we can deal with noise and illumination changes. To handle heterogeneous background and occlusions, we introduce a background model and an assignment function. Thus, the object recognition system becomes robust, and a reliable distinction, which features belong to the object and which to the background, is possible. Experiments on three large data sets that contain rotations orthogonal to the image plane and scaling with together more than 100 000 images show that the approach is well suited for this task.     

Recognition of partially occluded 3-D objects by depth map matching

The problem of 3-D object recognition using depth map representations is tackled. Surface patches are extracted for matching using a spherical window. Matching is done using only the outer boundaries of the patches which are closed curves in 3-space formed by the intersection of the spherical window and the object surface.