Robust segmentation of primitives from range data in the presenceof geometric degeneracy

This paper addresses a common problem in the segmentation of range images. We present methods for the least-squares fitting of spheres, cylinders, cones, and tori to 3D point data, and their application within a segmentation framework. Least-squares fitting of surfaces other than planes, even of simple geometric type, has rarely been studied. Our main application areas of this research are reverse engineering of solid models from depth-maps and automated 3D inspection where reliable extraction of these surfaces is essential. Our fitting method has the particular advantage of being robust in the presence of geometric degeneracy, i.e., as the principal curvatures of the surfaces being fitted decrease, the results returned naturally become closer and closer to those surfaces of “simpler type”, i.e., planes, cylinders, cones, or spheres, which best describe the data. Many other methods diverge because, in such cases, various parameters or their combination become infinite     

Experiments in curvature-based segmentation of range data

This paper focuses on the experimental evaluation of a range image segmentation system which partitions range data into homogeneous surface patches using estimates of the sign of the mean and Gaussian curvatures. The authors report the results of an extensive testing program aimed at investigating the behavior of important experimental parameters such as the probability of correct classification and the accuracy of curvature estimates, measured over variations of significant segmentation variables. Evaluation methods in computer vision are often unstructured and subjective: this paper contributes a useful example of extensive experimental assessment of surface-based range segmentation     

Efficient data structures for model-based 3-D object recognitionand localization from range images

An effective method of surface characterization of 3D objects using surface curvature properties and an efficient approach to recognizing and localizing multiple 3D free-form objects (free-form object recognition and localization) are presented. The approach is surface based and is therefore not sensitive to noise and occlusion, forms hypothesis by local analysis of surface shapes, does not depend on the visibility of complete objects, and uses information from a CAD database in recognition and localization. A knowledge representation scheme for describing free-form surfaces is described. The data structure and procedures are well designed, so that the knowledge leads the system to intelligent behavior. Knowledge about surface shapes is abstracted from CAD models to direct the search in verification of vision hypotheses. The knowledge representation used eases processes of knowledge acquisition, information retrieval, modification of knowledge base, and reasoning for solution     

A statistical estimation method for segmentation of sonar range data

In this paper, we describe how to deal with an important sensorial activity that ultrasonic echo-locating systems for mobile robot navigation have often to perform, namely the extraction of straight line segments from range data and the accurate localization of the corresponding planar targets. It is commonplace that range data segmentation starts with using least squares interpolation algorithms for obtaining straight line segments: it is our goal to prove that caution must be called for in order to avoid somewhat misleading results. The case study concerns the use of a linear array formed by three ultrasonic transducers in a 2D specular environment composed of line and point acoustic targets.The segmentation algorithm we propose is subdivided into two functionally distinct modules, namely identification and localization. The identification module is based on a sequential hypothesis testing between alternative hypotheses that explain the sonar range data as originated from line or point targets. With regard to the localization module, we demonstrate that widely used approaches to sensor modeling are, to some extent, deceptively simple: the estimation accuracy for the localization of planar objects may be decreased by the inability of some traditional sonar sensor models to take properly into account the specularity of reflections. A physically based model of acoustic range sensors acting in specular environments allows us to design a localization module which is capable of producing accurate and unbiased estimates of the parameters of a planar geometric feature.The proposed theoretical framework is validated by the results of some experiments carried out with a spatial locating system consisting of a rotating linear array of three ultrasonic transducers.     

A snake for model-based segmentation of biomedical images

In this work we present a snake based approach for the segmentation of images of computerized tomography (CT) scans. We introduce a new term for the internal energy and another one for external energy which solve common problems associated with classical snakes in this type of images. A simplified minimizing method is also presented.     

Three-dimensional model-based object recognition and segmentation in cluttered scenes

Viewpoint independent recognition of free-form objects and their segmentation in the presence of clutter and occlusions is a challenging task. We present a novel 3D model-based algorithm which performs this task automatically and efficiently. A 3D model of an object is automatically constructed offline from its multiple unordered range images (views). These views are converted into multidimensional table representations (which we refer to as tensors). Correspondences are automatically established between these views by simultaneously matching the tensors of a view with those of the remaining views using a hash table-based voting scheme. This results in a graph of relative transformations used to register the views before they are integrated into a seamless 3D model. These models and their tensor representations constitute the model library. During online recognition, a tensor from the scene is simultaneously matched with those in the library by casting votes. Similarity measures are calculated for the model tensors which receive the most votes. The model with the highest similarity is transformed to the scene and, if it aligns accurately with an object in the scene, that object is declared as recognized and is segmented. This process is repeated until the scene is completely segmented. Experiments were performed on real and synthetic data comprised of 55 models and 610 scenes and an overall recognition rate of 95 percent was achieved. Comparison with the spin images revealed that our algorithm is superior in terms of recognition rate and efficiency.     

Edge-region-based segmentation of range images

In this correspondence, we present a new computationally efficient three-dimensional (3-D) object segmentation technique. The technique is based on the detection of edges in the image. The edges can be classified as belonging to one of the three categories: fold edges, semistep edges (defined here), and secondary edges. The 3-D image is sliced to create equidepth contours (EDCs). Three types of critical points are extracted from the EDCs. A subset of the edge pixels is extracted first using these critical points. The edges are grown from these pixels through the application of some masks proposed in this correspondence. The constraints of the masks can be adjusted depending on the noise present in the image. The total computational effort is small since the masks are applied only over a small neighborhood of critical points (edge regions). Furthermore, the algorithm can be implemented in parallel, as edge growing from different regions can be carried out independently of each other     

On recovering hyperquadrics from range data

This paper discusses the applications of hyperquadric models in computer vision and focuses on their recovery from range data. Hyperquadrics are volumetric shape models that include superquadrics as a special case. A hyperquadric model can be composed of any number of terms and its geometric bound is an arbitrary convex polytope. Thus, hyperquadrics can model more complex shapes than superquadrics. Hyperquadrics also possess many other advantageous properties (compactness, semilocal control, and intuitive meaning). Our proposed algorithm starts with a rough fit using only six terms in 3D (four in 2D) and adds additional terms as necessary to improve fitting. Suitable constraints are used to ensure proper convergence. Experimental results with real 2D and 3D data are presented     

Robust adaptive segmentation of range images

We propose a novel image segmentation technique using the robust, adaptive least kth order squares (ALKS) estimator which minimizes the kth order statistics of the squares of residuals. The optimal value of k is determined from the data, and the procedure detects the homogeneous surface patch representing the relative majority of the pixels. The ALKS shows a better tolerance to structured outliers than other recently proposed similar techniques. The performance of the new, fully autonomous, range image segmentation algorithm is compared to several other methods     

Recent progress in object recognition from range data

Within the last half decade active devices have been able to provide three-dimensional data directly to vision systems. This paper examines some of the progress that has been made with this data in the field of 3D computer vision. Aspects of this field from acquisition to recognition are discussed and some major research results are reviewed.     

An MRF model-based approach to simultaneous recovery of depth andrestoration from defocused images

In this paper, we propose a MAP-Markov random field (MRF) based scheme for recovering the depth and the focused image of a scene from two defocused images. The space-variant blur parameter and the focused image of the scene are both modeled as MRFs and their MAP estimates are obtained using simulated annealing. The scheme is amenable to the incorporation of smoothness constraints on the spatial variations of the blur parameter as well as the scene intensity. It also allows for inclusion of line fields to preserve discontinuities. The performance of the proposed scheme is tested on synthetic as well as real data and the estimates of the depth are found to be better than that of the existing window-based depth from defocus technique. The quality of the space-variant restored image of the scene is quite good even under severe space-varying blurring conditions     

Explaining the segmentation effect in learning from animations: The role of pausing and temporal cueing

Segmentation of animations, that is presenting them in pieces rather than as a continuous stream of information, has been shown to have a beneficial effect on cognitive load and learning for novices. Two different explanations of this segmentation effect have been proposed. Firstly, pauses are usually inserted between the segments, which may give learners extra time to perform necessary cognitive processes. Secondly, because segmentation divides animations into meaningful pieces, it provides a form of temporal cueing which may support learners in perceiving the underlying structure of the process or procedure depicted in the animation. This study investigates which of these explanations is the most plausible. Secondary education students (N = 161) studied animations on probability calculation, after having been randomly assigned to one of four conditions: non-segmented animations, animations segmented by pauses only, animations segmented by temporarily darkening the screen only, and animations segmented by both pauses and temporarily darkening the screen. The results suggest that both pauses and cues play a role in the segmentation effect, but in a different way.     

计算机数据恢复概析

近几年,互联网技术得到了史无前例的飞速发展,电子商务、电子政务等IT应用也在迅速普及,而保存在电脑、服务器、存储设备里的数据安全隐患频现,因此硬盘及服务器数据恢复技术越来越受到关注。本文主要针对计算机数据丢失问题进行分类探讨,并研究其数据恢复的相关技术。     

Speeding up the EM algorithm for mixture model-based segmentation of magnetic resonance images

Mixture models implemented via the expectation-maximization (EM) algorithm are being increasingly used in a wide range of problems in pattern recognition such as image segmentation. However, the EM algorithm requires considerable computational time in its application to huge data sets such as a three-dimensional magnetic resonance (MR) image of over 10 million voxels. Recently, it was shown that a sparse, incremental version of the EM algorithm could improve its rate of convergence. In this paper, we show how this modified EM algorithm can be speeded up further by adopting a multiresolution kd-tree structure in performing the E-step. The proposed algorithm outperforms some other variants of the EM algorithm for segmenting MR images of the human brain.     

数据异地容灾的实现

日益增长的信息量必然发生大量的数据传输、存储和数据交换,数据安全成为影响整个信息系统的一个重要因素为了应付区域性灾害,如地震、海啸、战争等因素导致多个机房同时损毁,数据永久性丢失,其它如区域性的病毒泛滥、蓄意破坏、严重误操作等人为因素也可能导致同城备份中心失效。建立一套异地数据备份系统已经成为信息系统建设的必要组成部分,会成为保证数据安全的最后一道防线。本文详细阐述了某信息系统数据异地容灾的实现。     

Research issues in model-based visualization of complex data sets

At the most abstract level, data visualization maps discrete values computed over an n-dimensional domain onto pixel colors. It is largely a dimension-reducing process justified by its leverage on human perceptual capacities for extracting information from visual stimuli. The difficulty is to implement a mapping that reveals the data characteristics relevant to the application at hand. Effective visualization solutions let the user control the process parameters interactively and enhance the automatically extracted features. We argue for an intelligent, model-based approach to visualization, which extracts the intrinsic data characteristics and constructs multiresolution graphics models suitable for interactive rendering on commercially available hardware adapters. The model-based approach has four parts, which we summarize     

Robust online detection of pipeline corrosion from range data

We present the Finite-Window Robust Sequential Estimator for the detection and analysis of corrosion in range images of gas pipelines. This statistically robust, real-time technique estimates the pipeline surface range function in the presence of noise, surface deviations, and changes in the underlying model. Deviations from the robust surface fit, corresponding to statistical outliers, represent potential areas of corrosion. Because the algorithm estimates surface parameters over a finite, sliding window of data, it can track moderately high-order surfaces using lower order models. The system is consistent, objective, and non-destructive and can be used with the pipeline in service. Received: 7 September 1999 / Accepted: 2 November 2000