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

A spatiotemporal (ST) image cube, created by stacking a temporally dense sequence of images together, is a temporally coherent data representation. Using ST surface flow, i.e., the extension of optical flow to ST surfaces, it is shown how ST flow curves can be recovered and then used to detect groups of flow curves such that each group represents a single object or surface in the scene undergoing motion. The algorithm forms clusters of similar flow curves and is based on constraints called the temporal uniqueness constraints. First, a point in an image can only move to at most one point in the next image. Second, a point in an image can come from at most one point in the previous image. When these constraints are violated, or it appears that they are violated, occlusion or disocclusion has occurred and therefore can also be detected. Successful grouping of coherent regions of the ST cube for two gray-level image sequences is shown. >

/pdf/long-range-spatiotemporal-motion-understanding-using-fh8iau5oyu.pdf

Long-range spatiotemporal motion understanding using spatiotemporal flow curves

This thesis investigates the problem of facial image analysis. Human faces contain a lot of information that is useful for many applications. For instance, the face and iris are important biometric features for security applications. Facial activity analysis such as face expression recognition is helpful for perceptual user interfaces. Developing new methods to improve recognition performance is a major concern in this thesis.
In approaching the recognition problem of facial image analysis, the key idea is to use learning-based methods whenever possible. For face recognition, we propose a face cyclograph representation to encode continuous views of faces, motivated by psychophysical studies on human object recognition. For face expression recognition, we apply a machine learning technique to solve the feature selection and classifier training problems simultaneously, even in the small sample case.
Iris recognition has high recognition accuracy among biometric features, however, there are still some issues to address to make more practical use of the iris. One major problem is how to capture iris images automatically without user interaction, i.e., not asking users to adjust their eye positions. Towards this goal, a two-camera system consisting of a face camera and an iris camera is designed and implemented based on facial landmark detection. Another problem is iris localization. A new type of feature based on texture difference is incorporated into an objective function in addition to image gradient. By minimizing the objective function, the iris localization performance can be improved significantly. Finally, a method is proposed for iris encoding using a set of specially designed filters. These filters can take advantage of efficient integral image computation methods so that the filtering process is fast no matter how big the filters are.

/pdf/face-expression-and-iris-recognition-using-learning-based-3znwl2vtos.pdf

Face, Expression, and Iris Recognition Using Learning-based Approaches

The authors address the problem of qualitative shape recovery from moving surfaces. The analysis is unique in that they consider specular interreflections and explore the effects of both motion parallax and changes in shading. To study this situation they define an image flow field called the reflection flow field, which describes the motion of reflection points and the motion of the surface. From a kinematic analysis, they show that the reflection flow is qualitatively different from the motion parallax because it is discontinuous at or near parabolic curves. They also show that when the gradient of the reflected image is strong, gradient-based flow measurement techniques approximate the reflection flow field and not the motion parallax. They conclude that reliable qualitative shape information is generally available only at discontinuities in the image flow field. >

Dynamic shading, motion parallax and qualitative shape

The problem in which the 3D motion of an object corresponding to a known polyhedral model is to be computed using only the motion of edge features in a continuous stream of 2D images is considered. Advantage is taken of the spatiotemporal density of the input signal and the limitations of long-range trajectory-prediction methods are avoided. Two parallel algorithms which use feature-based, short-range (spatiotemporally local) motion processes to achieve real-time tracking of modeled objects are presented. Both algorithms have been implemented and tested on a tightly coupled multiprocessor system consisting of an Aspex Pipe for low-level image-feature computations and a Sequent Symmetry for high-level model-based computations. An analysis is given of the actual performance limits of each method using the current hardware configuration. >

Real-time motion tracking of three-dimensional objects

It is observed that arc length of a contour does not change if that contour is moved in the direction of motion on the surface. A function measuring arc length change is defined. The direction of motion of a contour undergoing motion parallel to the image plane is shown to be perpendicular to the gradient of this function. This gradient approximates the direction of motion when object motion in the scene is not parallel to the image plane or when perspective projection is used. This method has been implemented and is shown to compute the ST (spatiotemporal) surface flow in sequences of edge images and gray level images. >

/pdf/computing-spatiotemporal-surface-flow-snz3rqecbf.pdf

Charles R. Dyer

Papers

Long-range spatiotemporal motion understanding using spatiotemporal flow curves

Face, Expression, and Iris Recognition Using Learning-based Approaches

Dynamic shading, motion parallax and qualitative shape

Real-time motion tracking of three-dimensional objects

Computing spatiotemporal surface flow