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. >

A method for registration of 3-D shapes

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.

/pdf/object-detection-with-discriminatively-trained-part-based-4cnosvuqcp.pdf

Object Detection with Discriminatively Trained Part-Based Models

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.

/pdf/a-taxonomy-and-evaluation-of-dense-two-frame-stereo-4c20etkubp.pdf

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

A comparative study of texture measures with classification based on featured distributions

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.

Planning Algorithms: Introductory Material

: In an earlier report, a new class of multilayer bounded cellular automata was defined and shown to improve the lower bound recognition time for many basic array recognition tasks. The investigation of pyramid cellular acceptors is continued by presenting new results on their capabilities as two-dimensional pattern-recognizing machines.

Cellular Pyramids for Image Analysis.

This paper introduces a special class of cellular automata, called triangle cellular automata, which accept as input strings of length a power of two. In particular, we study the special case in which state information can only move upward through a complete binary tree of finite-state automata. It is shown that this class of cellular automata can accept various string languages in O(log n) time, where n is the length of the input string defining the initial states of the leaf vertices in the tree. Extensions to two dimensions, defining a pyramid cellular automaton, are also given.

Triangle cellular automata

A system has been developed that automatically extracts the iris region from photographs, computes the iris color in CIE u ́v ́ diagram color space, and corrects the color based on a standard calibration target. This system has advantages over previous manual methods in that it (1) is much less time-consuming because it is fully automatic, (2) corrects for the variability inherent in a film-based photographic process, (3) allows for greater objectivity and reproducibility, and (4) uses a mathematical foundation that enables quantification and statistical analysis. Preliminary experimental results show that color correction significantly improves grading accuracy. We would like to thank Dennis Hafford and Jane Armstrong for providing assistance and the iris images. The support of the National Eye Institute of the National Institutes of Health under Grant No. N01-EY-02130 is gratefully acknowledged. University of Wisconsin-Madison Department of Computer Sciences TR# 1495

Quantification and Correction of Iris Color

A major issue in computer vision is the interpretation of three-dimensional (3D) motion of moving objects from a continuous stream of two-dimensional (2D) images. In this paper we consider the problem where the 3D motion of an object corresponding to a known 3D model is to be tracked using only the motion of 2D features in the stream of images. Two general solution paradigms for this problem are characterized: (1) motion-searching, which hypothesizes and tests 3D motion parameters, and (2) motion-calculating, which uses back-projection to directly estimate 3D motion from image-feature motion. Two new algorithms for computing 3D motion based on these two paradigms are presented. One of the major novel aspects of both algorithms is their use of the assumption that the input image stream is spatiotemporally dense. This constraint is psychologically plausible since it is also used by the short-range motion processes in the human visual system.

Real-time, parallel motion tracking of three dimensional objects from spatiotemporal sequences

A pyramid linking algorithm for texture segmentation is presented. It is based on the computation of spatial properties of long, straight edge segments at fixed orientations. Features are computed for each edge segment in terms of the distances to the nearest neighboring edge segments of given orientations. This produces a set of sparse “edge separation maps” of features which are then used as the basis of a pyramid linking procedure for hierarchically grouping edges into homogeneously textured regions. Segmentation is performed in one bottom-up pass of linking nodes to their most similar parent. Results are shown using both the raw and smoothed edge separation features. All of the steps of the procedure can be efficiently implemented as parallel operations on a pyramid machine.

Charles R. Dyer

Papers

Cellular Pyramids for Image Analysis.

Triangle cellular automata

Quantification and Correction of Iris Color

Real-time, parallel motion tracking of three dimensional objects from spatiotemporal sequences

Segmentation of textured images by pyramid linking