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

. The study of the aspect graph of a three-dimensional object has recently become an active area of research in computer vision. The aspect graph provides a complete enumeration of all the possible distinct views of an object, under a particular model for the viewpoint space and a particular definition for "distinct." This paper gives a tutorial introduction to the aspect graph, surveys the current state of the art in algorithms for automati- cally constructing the aspect graph, and describes some possible applications of aspect graphs in computer vision and computer graphics.

Aspect graphs: an introduction and survey of recent results

About 65 percent of family law litigants in Washington State come to court without a lawyer. Plain language forms will give many of these pro se litigants the ability to conduct their lawsuits without legal representation or with limited assistance. Such forms also reduce costs for litigants and the courts. As part of the implementation of the Washington State Plan for Integrated Pro Se Services (Pro Se Project), a joint initiative of the Washington State Access to Justice Board, the Washington State Administrative Office of the Courts, and the Washington State Office of Administrative Hearings, work has been * The authors include Charles R. Dyer, Program Manager of the Pro Se Project, Washington State Access to Justice Board; Kirsten Barron, attorney and current Chair of the Access to Justice Board; Joan E. Fairbanks, Staff Director for the Access to Justice Board; M. Lynn Greiner, attorney and member of the Access to Justice Board; Janet L. Skreen, Senior Court Program Analyst with the Washington State Administrative Office of the Courts; Josefina Cerrillo-Ramirez, attorney with the Northwest Justice Project; Law Fellows Andrew Lee, JD, and Bill Hinsee, JD; and Law student externs Ashley McDonald and Jeff Wyatt aided in the writing of this article. 1 JUDICIAL SERVS. DIV., ADMIN. OFFICE OF THE COURTS, AN ANALYSIS OF PRO SE LITIGANTS IN WASHINGTON STATE 1995–2000 (2001), available at http:// www.courts.wa.gov/wsccr/docs/Final%20Report_Pro_Se_11_01.pdf [hereinafter ANALYSISOF PRO SE LITIGANTS]. Please note that statistical sampling varies from county to county and from case type to case type. The general presumption based on the statistics is that in about 50 percent of the cases, neither side is represented by an attorney, and that in about 80 percent of the cases, one side is not represented. 1066 SEATTLE JOURNAL FOR SOCIAL JUSTICE SEATTLE JOURNAL FOR SOCIAL JUSTICE underway to translate 211 mandatory family law court forms into plain language. This article describes some of the ethical justifications for, and practical benefits of, plain language forms. It also discusses basic linguistic principles that underpin clear, concise, and plain language. The latest version, as of this writing, of one of the most important plain language forms, the Parenting Plan, is appended. This article also examines the broader aspects of plain language adoption nationally. Legal forms have taken on new relevance after the US Supreme Court’s decision in Turner v. Rogers, 2 which obliges judiciaries to take steps to ensure that unrepresented litigants’ rights to due process are adequately protected. Plain language forms are an effective means of dispelling the due process concerns noted in Turner, and a necessary element of a genuinely accessible justice system.

/pdf/improving-access-to-justice-plain-language-family-law-court-2aotk8uuf4.pdf

Improving Access to Justice: Plain Language Family Law Court Forms in Washington State

Four VLSI designs for a line and curve detection chip are presented. Each method is based on Montanari’s dynamic programming algorithm [9.1]. The output of each system is the sequence of coordinates or chain code of the optimal curve(s) detected. One method uses a systolic array of size proportional to the number of rows in the image to detect the optimal curve. To detect a curve of length m requires m passes through the systolic array, taking time proportional to m times the number of columns in the image. A second systolic array design consists of a linearly tapering pipeline of cells. The length of the pipeline is equal to m and the total number of cells in the pipeline is proportional to m3. Time proportional to the image area is required during a single pass through the image. The third systolic approach uses an array of cells of size proportional to m times the number of rows in the image. Only one pass through the image is required to detect the curve, taking time proportional to the number of image columns. Details are given for a VLSI chip design using the third approach. The fourth method describes an algorithm for an SIMD array machine.

Curve Detection in VLSI

This paper describes the parallel simulation of a connectionist network stereo matching algorithm. In the algorithm a relaxation computation uses a variety of consistency measures between candidate matches to determine the correct match for each edge. These measures include disparity consistency, contour consistency, and multiresolution consistency. In the network each node represents a candidate match and the connections between nodes implement the consistency relations. The simulation involves constructing the list of candidate matches, constructing the list of connections between matches, and performing the iterations of the relaxation computation. Within each of these stages of the simulation, computation may be partitioned among a number of processors with very little need for synchronization or mutual exclusion except at the end of the stage. As a result, the implementation of the simulation on a shared-memory multiprocessor produced nearly linear speed-ups for up to nine processors (the maximum available at the time of implementation).

Parallel simulation of a connectionist stereo algorithm on a shared-memory multiprocessor

The joint invariants of the projective group PSL(3,ℝ) on ℝℙ2, the five-point volume cross-ratios, are studied to address the problem of correspondence in a camera network. The distribution of cross-ratios over the unit square as well as in a small local-neighbourhood of a reference point are found to have a heavy tail. No cross ratio value is unique but the collection of five point cross ratios generated by taking all possible combination of five points completely prescribes the curve. Sections of the signature submanifold that admit large enough variation of cross ratios are found to be sufficient in providing correspondence across wide perspectives. Such invariant signatures may be collected independently at cameras with different viewpoints and shared, thereby achieving the registration of objects in the image. Experimental results with license plate database are provided.

/pdf/estimating-correspondence-between-multiple-cameras-using-3ixsij1rlm.pdf

Charles R. Dyer

Papers

Aspect graphs: an introduction and survey of recent results

Improving Access to Justice: Plain Language Family Law Court Forms in Washington State

Curve Detection in VLSI

Parallel simulation of a connectionist stereo algorithm on a shared-memory multiprocessor

Estimating correspondence between multiple cameras using joint invariants