Showing papers in "Computer Vision and Image Understanding in 2000"

TL;DR: A new robust estimator MLESAC is presented which is a generalization of the RANSAC estimator which adopts the same sampling strategy as RANSac to generate putative solutions, but chooses the solution that maximizes the likelihood rather than just the number of inliers.

TL;DR: A computer vision system for tracking multiple people in relatively unconstrained environments is described and should provide a useful mechanism for bootstrapping and reinitialization of tracking using more specific but less robust human models.

TL;DR: The progressive probabilistic Hough transform minimizes the amount of computation needed to detect lines by exploiting the difference in the fraction of votes needed to reliably detect lines with different numbers of supporting points.

TL;DR: A completely automatic method to build stable average anatomical models of the human brain using a set of magnetic resonance (MR) images and results showing convergence toward the centroid of the image set used for the computation of the model are provided.

TL;DR: In this article, a multiscale analysis for extracting vessels of different sizes according to the scale of the image is presented. But the method is not suitable for the detection of tubular structures.

TL;DR: This paper investigates the problem of recovering information about the configuration of an articulated object, such as a human figure, from point correspondences in a single image by considering the foreshortening of the segments of the model in the image.

TL;DR: It is argued that scale-based affinity, and hence connectedness, is natural in object definition and demonstrates that this leads to more effective object segmentation.

TL;DR: A new minimal-surface-like model and its variational and partial differential equation (PDE) formulation are introduced and the constructed shape is smoother than any piecewise linear reconstruction.

TL;DR: In this paper, instead of computing the coefficients by a projection of the data onto the eigenimages, they extract them by a robust hypothesize-and-test paradigm using subsets of image points.

TL;DR: The methods presented in this paper apply the minimum extensive modifications possible to a given image to obtain a new one that has many fewer watersheds but is still “close” to the original.

TL;DR: It is shown how the registration function depends on the interpolation method and how a slight resampling of one of the images may drastically improve the smoothness of this function.

TL;DR: SFM is a messy problem and that it could require a flexible “intermediate-level” system incorporating a variety of different algorithms and sophisticated decision rules for combining them, and it is argued that current SFM algorithms perform well only in restricted domains.

TL;DR: A novel method that allows the development of surface point-based three-dimensional statistical shape models is presented and is successfully applied to obtain a statistical shape model for the lumbar vertebrae.

TL;DR: A generalized model of image “appearance change” in which brightness variation over time is represented as a probabilistic mixture of different causes is proposed to provide a richer description of image events and more reliable estimates of image motion in the presense of shadows and specular reflections.

TL;DR: Two new multilocal creaseness measures are proposed that are shown to be free of discontinuities and to have a meaningful dynamic range of response and demonstrate the usefulness in the context of two applications that are currently developing in the field of 3D medical image analysis.

TL;DR: A novel deformable template is presented which detects the boundary of an open hand in a grayscale image without initialization by the user and finds the hand contour in the image in as little as 19 s on a Pentium 150 MHz.

TL;DR: This approach uses multiclass, multidimensional discriminant analysis to automatically select the most discriminating linear features for gesture classification, and a recursive partition tree approximator is proposed to do classification.

TL;DR: A method for preserving the intrinsic orientation of the data during nonrigid warps of the image and a number of similarity measures are proposed, based on the DT itself, on theDT deviatoric, and on indices derived from the DT, to drive an elastic matching algorithm applied to the task of registration of 3D images of the human brain.

TL;DR: This special issue is dedicated to examining the use of techniques from robust statistics in solving computer vision problems, and considers the meaning of robustness in computer vision, and outlines the relationship between techniques inComputer vision and statistics as a means of highlighting future directions.

TL;DR: Empirical results from application of the developed algorithm to transmittance imagery of fluid flows, where the fluids contained a contrast medium, show how information derived from the physical behavior of fluids can be used to motivate a flow-recovery algorithm.

TL;DR: The object recognition system named RIO (relational indexing of objects), which contains a number of new techniques, is able to recognize 3D objects having planar, cylindrical, and threaded surfaces in complex, multiobject scenes.

TL;DR: The contributions in the approach are the incorporation of depth information from stereopsis, the simple implementation of low level modules such as disparity and flow by local phase, and the cue integration along pursuit and saccade mode that allows us a proper target selection based on nearness and motion.

TL;DR: Both theoretical and experimental results show that, if right configurations of the generalized first absolute central moment are used, the filter retains most of its properties when real images are considered and the recovered edge information can be usefully combined.

TL;DR: This paper explicitly model spatial illumination variations as low-order polynomial functions in an energy minimization framework and formulate the parameter estimation problem in a weighted least-squares framework by incorporating the influence function from robust estimation to derive an iterative reweighted least-Squares algorithm.

TL;DR: The reproducibility of the reflectance factors measured by the spectrograph is determined empirically and the measurements are compared to those of a spectrophotometer, and the probability that a measured color is within one CIE L*a*b* unit of the actual color is predicted theoretically.

TL;DR: The proposed approach achieves gray-level reduction using both the image gray-levels and additional local spatial features using a self-organized neural network classifier.

TL;DR: Experimental results for synthetic and real images show that the proposed algorithm performs matching of the line features with affine variation fast and efficiently and provides the degree of dissimilarity in a quantitative way.

TL;DR: A fuzzy logic rule-based system is developed to combine the spatial relationships and other important scene properties to generate the final linguistic interpretation and excellent results from several image examples show the applicability of this approach.

TL;DR: A bibliography of nearly 1700 references related to computer vision and image analysis, arranged by subject matter is presented, including computational techniques; feature detection and segmentation; image and scene analysis; and motion.

TL;DR: Two thinning algorithms on 3D (18, 6) binary images are proposed: one algorithm generates skeletons as digital curves and the other algorithm generates skeleton as digital surfaces.