Abstract not found

In this paper, we develop a higher-order statistical theory of matching models against images. The basic idea is not only to take into account how much of an object can be seen in the image, but also what parts of it are jointly present. We showthat this additional information can improve the speci city (i.e., reduce the probability of false positive matches) of a recognition algorithm. We demonstrate formally that most commonly used quality of match measures employed by recognition algorithms are based on an independence assumption. Using the Minimum Description Length (MDL) principle and a simple scene-description language as a guide, we show that this independence assumption is not satis ed for common scenes, and propose several important higher-order statistical properties of matches that approximate some aspects of these statistical dependencies. We haveimplemented a recognition system that takes advantage of this additional statistical information and demonstrate its e cacy in comparisons with a standard recognition system based on bounded error matching. We also observe that the existing use of grouping and segmentation methods has signi cant e ects on the performance of recognition systems that are similar to those resulting from the use of higher-order statistical information. Our analysis provides a statistical framework in which to understand the effects of grouping and segmentation on recognition and suggests ways to take better advantage of such information.

Determination of relative three-dimensional (3--D) position, orientation, and relative motion between two reference frames is an important problem in robotic guidance, manipulation, and assembly as well as in other fields such as photogrammetry. A solution to this problem that uses two-dimensional (2--D), intensity images from a single camera is desirable for real-time applications. Where the object geometry is unknown, the estimation of structure is also required. A single camera is advantageous because a standard video camera is low in cost, setup and calibration are simple, physical space requirements are small, reliability is high, and low-cost hardware is available for digitizing and processing the images. A di#culty in performing this measurement is the process of projecting 3--D object features to 2--D images, a nonlinear transformation. Noise is present in the form of perturbations to the assumed process dynamics, imperfections in system modeling, and errors in the feature locations extracted from the 2--D images. This dissertation presents solutions to the remote measurement problem for a dynamic system given a sequence of 2--D intensity images of an object where feature positions of the object are known relative to a base reference frame and where the feature positions are unknown relative to a base reference frame. The 3--D transformation is modeled as a nonlinear stochastic system with the state estimate providing six degree-of-freedom motion and position values. The stochastic model uses the iterated extended Kalman filter as an estimator and as a screw representation of the 3--D transformation based on dual quaternions. Dual quaternions provide a means to represent both rotation and translation in a unified notation. The method has been implemented and tes...

An extension to the alignment approach is proposed that includes a pose refinement step before verification. In the alignment approach the pose estimates of the initial hypotheses tend to be somewhat inaccurate, since they are based on minimal sets of corresponding features. A method is described that refines the pose estimate while simultaneously identifying and incorporating the constraints of all supporting image features. The strategy also makes practical initial alignments based on low resolution features -- which, being less numerous, allow faster running times. Two statistical formulations of model-based recognition are described: MAP Model Matching, and Posterior Marginal Pose Estimation (PMPE). These formulations use a normal model for feature fluctuations. Empirical evidence is provided from the domain of video edge features indicating that normal probability densities are good models of feature fluctuations -- better than uniform densities in that domain. The evid...