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

Abstract of papers accepted for publication PaperThe space efficiency of quadtrees

Pictorial communication systems use synthesized pictures, rather than text, to communicate with users. Because such systems depend on images to convey meanings, it is critical to understand how a human user perceives the image meaning (sense). This paper offers an empirical and theoretical study of how humans perceive image senses. We conduct a user study with 113 users to elicit their perceived senses on 400 image sets, from which we discover widespread image sense ambiguities. We examine how the number of images shown relates to sense ambiguity and discover several significant patterns. We then propose a Bayesian model to explain human image perception behaviors, based on a novel random walk process on a WordNet-like sense hierarchy. Our model makes qualitative and quantitative predictions that largely agree with our observations of human perception. It can explain the “basic level” phenomenon known in psychology, and suggests a method for image sense disambiguation in pictorial communication systems.

A Bayesian model for image sense ambiguity in pictorial communication systems

Statistical models such as linear regression drive numerous applications in computer vision and machine learning. The landscape of practical deployments of these formulations is dominated by forward regression models that estimate the parameters of a function mapping a set of p covariates, \(\varvec{x}\), to a response variable, y. The less known alternative, Inverse Regression, offers various benefits that are much less explored in vision problems. The goal of this paper is to show how Inverse Regression in the “abundant” feature setting (i.e., many subsets of features are associated with the target label or response, as is the case for images), together with a statistical construction called Sufficient Reduction, yields highly flexible models that are a natural fit for model estimation tasks in vision. Specifically, we obtain formulations that provide relevance of individual covariates used in prediction, at the level of specific examples/samples — in a sense, explaining why a particular prediction was made. With no compromise in performance relative to other methods, an ability to interpret why a learning algorithm is behaving in a specific way for each prediction, adds significant value in numerous applications. We illustrate these properties and the benefits of Abundant Inverse Regression on three distinct applications.

/pdf/abundant-inverse-regression-using-sufficient-reduction-and-52zuavrrvd.pdf

Abundant Inverse Regression Using Sufficient Reduction and Its Applications

An algorithm is presented that estimates 3D facial landmark coordinates and occlusion state from a single 2D image. Unlike previous approaches, we divide the 3D cascaded shape regression problem into a set of viewpoint domains, which helps avoid problems in the optimization, such as local minima at test time, and averaging conflicting gradient directions in the domain maps during training. These problems are especially important to address in the 3D case, where a wider range of head poses is expected. Parametric shape models are used and are shown to have several desirable qualities compared to the recent trend of modeling shape nonparametrically. Results show quantitatively that our approach is significantly more accurate than recent work.

/pdf/pose-robust-3d-facial-landmark-estimation-from-a-single-2d-3d61zv5t8e.pdf

Pose-Robust 3D Facial Landmark Estimation from a Single 2D Image.

The information conveyed by optical flow is analytically linked to observer motion by decomposing the optical flow field into its vector field components. It is shown that the observer may recover his ego-motion by interpreting the decomposed optical flow field, and he may further utilize his mobility to actively control the shape of the optical flow field, which directly reflects the surface shape of the object. The information of surface geometry discontinuity can be derived more directly from optical flow field by segmenting the whole field. A new method for the segmentation is proposed here, which combines both the magnitude and phase parts of the optical flow. The integration of these two different kinds of information proves to be effective in making various surface geometry boundaries explicit.

Charles R. Dyer

Papers

Abstract of papers accepted for publication PaperThe space efficiency of quadtrees

A Bayesian model for image sense ambiguity in pictorial communication systems

Abundant Inverse Regression Using Sufficient Reduction and Its Applications

Pose-Robust 3D Facial Landmark Estimation from a Single 2D Image.

Observer motion estimation and control from optical flow