Charles R. Dyer

Bio: Charles R. Dyer is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Motion estimation & Motion field. The author has an hindex of 43, co-authored 141 publications receiving 9919 citations. Previous affiliations of Charles R. Dyer include University of Wisconsin System & University of Maryland, College Park.

Recovering feature and observer position by projected error refinement

Abstract: Recovering three-dimensional information from images is a principal goal of computer vision. An approach called Structure From Motion (SFM) does so without imposing strict requirements on the observ er or scene. In particular , SFM assumes camera motion is unkno w and the scene is only required to be static. This thesis describes a ne w SFM technique called Projected Error Refinement that computes the positions of feature points (i.e., structure) and the locations of the camera or observ (i.e., motion) from a noisy image sequence. The technique addresses limitations of e xisting SFM techniques that mak e them unsuitable e xcept in controlled environments; the approach presented in this thesis models perspecti ve projection, allows unconstrained camera motion, deals with outliers and occlusion, and is scalable. This new technique is recursi ve and thus is suitable for video image streams because ne w images can be added at an y time. Projected Error Refinement vie ws SFM as a geometric in verse projection problem, with the goal of determining the positions of the cameras and feature points such that the projectors defined by each image optimally intersect (projectors are the lines of projection specifying the direction of each feature point from the camera’ s optical center). This is e xpressed as a global optimization problem with the objecti ve function minimizing the mean-squared angular projection error between the solution and the observ ed images. Occlusion is dealt with naturally in this approach because only visible feature points define projectors that are considered during optimization occluded features are ignored. The technique models true perspecti ve projection and is scalable to an arbitrary number of feature points and images. Projected Error Refinement is non-linear and uses an ef ficient parallel iterative refinement algorithm that tak es an initial estimate of the structure and motion parameters and alternately iii refines the cameras’ poses and the positions of the feature points in parallel. The solution can be refined to an arbitrary precision or refinement can be terminated prematurely due to limited processing time. The solution con verges rapidly towards the global minimum e v n when started from a poor initial estimate. Experimental results are gi ven for both 2D and 3D perspecti ve projection using real and synthetic images sequences.

Interactivity and the Dimensionality of Data Displays

Abstract: Using mathematical models of data and displays, we illustrate the importance of distinguishing between independent and dependent variables when counting the dimensions of data sets and displays. The number of independent variables occurring as dimensions of a display model is the most important factor determining its information carrying capacity. Independent variables in a display model also require interactive techniques for their implementation, as illustrated by our VIS-AD system and Beshers’ and Feiner’s worlds within worlds technique. Thus interactivity is critical for visually communicating large amounts of information, and the perceptual properties of interaction techniques are an important topic for visualization research.

Stratified Self Calibration from Screw-Transform Manifolds

Abstract: This paper introduces a new, stratified approach for the metric self calibration of a camera with fixed internal parameters. The method works by intersecting modulus-constraint manifolds, which are a specific type of screw-transform manifold. Through the addition of a single scalar parameter, a 2-dimensional modulus-constraint manifold can become a 3-dimensional Kruppa-constraint manifold allowing for direct self calibration from disjoint pairs of views. In this way, we demonstrate that screw-transform manifolds represent a single, unified approach to performing both stratified and direct self calibration. This paper also shows how to generate the screw-transform manifold arising from turntable (i.e., pairwise-planar) motion and discusses some important considerations for creating a working algorithm from these ideas.

A method for registration of 3-D shapes

Abstract: The authors describe a general-purpose, representation-independent method for the accurate and computationally efficient registration of 3-D shapes including free-form curves and surfaces. The method handles the full six degrees of freedom and is based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point. The ICP algorithm always converges monotonically to the nearest local minimum of a mean-square distance metric, and the rate of convergence is rapid during the first few iterations. Therefore, given an adequate set of initial rotations and translations for a particular class of objects with a certain level of 'shape complexity', one can globally minimize the mean-square distance metric over all six degrees of freedom by testing each initial registration. One important application of this method is to register sensed data from unfixtured rigid objects with an ideal geometric model, prior to shape inspection. Experimental results show the capabilities of the registration algorithm on point sets, curves, and surfaces. >

Object Detection with Discriminatively Trained Part-Based Models

Abstract: We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL data sets. Our system relies on new methods for discriminative training with partially labeled data. We combine a margin-sensitive approach for data-mining hard negative examples with a formalism we call latent SVM. A latent SVM is a reformulation of MI--SVM in terms of latent variables. A latent SVM is semiconvex, and the training problem becomes convex once latent information is specified for the positive examples. This leads to an iterative training algorithm that alternates between fixing latent values for positive examples and optimizing the latent SVM objective function.

A taxonomy and evaluation of dense two-frame stereo correspondence algorithms

Abstract: Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can be easily extended to include new algorithms. We have also produced several new multiframe stereo data sets with ground truth, and are making both the code and data sets available on the Web.

Planning Algorithms: Introductory Material

Abstract: Planning algorithms are impacting technical disciplines and industries around the world, including robotics, computer-aided design, manufacturing, computer graphics, aerospace applications, drug design, and protein folding. This coherent and comprehensive book unifies material from several sources, including robotics, control theory, artificial intelligence, and algorithms. The treatment is centered on robot motion planning but integrates material on planning in discrete spaces. A major part of the book is devoted to planning under uncertainty, including decision theory, Markov decision processes, and information spaces, which are the “configuration spaces” of all sensor-based planning problems. The last part of the book delves into planning under differential constraints that arise when automating the motions of virtually any mechanical system. Developed from courses taught by the author, the book is intended for students, engineers, and researchers in robotics, artificial intelligence, and control theory as well as computer graphics, algorithms, and computational biology.