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 this paper we present the geometry and the algorithms for organizing a viewer-centered representation of the occluding contour of a polyhedron. The contour is computed from a polyhedral boundary model as it would appear under orthographic projection into the image plane from every viewpoint on the view sphere. Using this representation, we show how to derive constraints on regions in viewpoint space from the relationship between detected image features and our precomputed contour model. Such constraints are based on both qualitative (viewpoint extent) and quantitative (angle measurements and relative geometry) information that has been precomputed about how the contour appears in the image plane as a set of projected curves and T-junctions from self-occlusion. The results we show from an experimental system demonstrate that features of the occluding contour can be computed in a model-based framework, and that their geometry constrains the viewpoints from which a model will project to a set of occluding contour features in an image.

/pdf/viewpoint-from-occluding-contour-wqpli4inoe.pdf

Viewpoint from occluding contour

The authors' approach to stereo vision involves: (1) designing a general-purpose low-level matching algorithm: (2) testing it on a wide range of stereo pairs; and (3) adding mechanisms to the low-level algorithm that solve any remaining problems without interfering with its successful behavior. They begin by building the general support algorithm (GSA), a low-level matching algorithm that integrates the influence of a number of a locally defined constraints cooperatively and in parallel using only positive constraint influences (except for uniqueness). The constraints include uniqueness, coarse-to-fine and fine-to-coarse multiresolution, detailed match, figural continuity, and the disparity gradient. The GSA is implemented in a connectionist network. When tested on a wide-range of natural and synthetic images it produces a high percentage (97%) of correct matching decisions. The errors arise in situations that can not be identified using locally-defined constraints. These include partially occluded periodic regions, occlusions, and significant structural differences between the images. >

/pdf/local-constraint-integration-in-a-connectionist-model-of-2hmd223yjl.pdf

Local constraint integration in a connectionist model of stereo vision

A fast parallel algorithm for the closest pair problem

A model-based approach is developed for recovering 3-dimensional surface orientation from a single image of an arbitrary planar point pattern or polygon. We define an iterative procedure which efficiently computes the correct surface orientation as well as solving the correspondence problem between the set of model features and the set of image features. There are no restrictions on the types of model point patterns and no a priori knowledge about the correspondence is assumed. The number of possible matches considered is linear in the number of points in the worst case, although experimental results show that using our heuristic for ordering candidate correspondences results in only a small constant number of matches that must be tried. The iterative procedure is also robust in that model tolerances and image distortions can be handled by relaxing the termination criterion; the resulting error in orientation is usually of the same order of magnitude as the distortion. Thus the method is of practical value because it uses arbitrary point sets and works on real, noisy data.

Recognition and recovery of the three-dimensional orientation of planar point patterns

We present a framework combining differential geometry and scale-space to show that local geometric invariants of image contours such as tangent, curvature and derivative of curvature can be computed directly and stably from the raw image itself. To solve the problem of noise amplification by differential operations, scale-parameterized local kernels are used to replace differential operations by integral operations, which can be carried out accurately when we adopt a continuous image model. We also show that tangent estimation along contours can be made quite accurately using only eight tangent estimators (a /spl pi//4 quantization) when contour location is known, and high precision and efficiency in computation can be achieved for each of the invariants regardless of the differential order involved.

Charles R. Dyer

Papers

Viewpoint from occluding contour

Local constraint integration in a connectionist model of stereo vision

A fast parallel algorithm for the closest pair problem

Recognition and recovery of the three-dimensional orientation of planar point patterns

Direct computation of differential invariants of image contours from shading