presuppose different correspondences. If a child watches a teacher solving subtraction problems in arithmetic, and then solves for the first time similar but not identical problems on its own, social learning has occurred. But what type of correspondence is at work here? In China and Japan, the ideographic

§ Use differences between images in our left and right eye § How much is this difference for a car at 100 m? • Move our head sideways § Or, the scene is moving § Or we are moving in a car • We know the size and shape of objects § Traffic lights, car headlights and taillights 1 2 Headlights in the Dark • A robot could evaluate its distance from incoming cars at night partly from a model of cars § Distance between headlights known 2 m Object Pose with 1D Image Plane • What happens if we don’t know object’s angle? D

Abstract. We examine how differently oriented components contribute to the discrimination of motion direction along a horizontal axis. Stimuli were two-frame random-dot kinematograms that were narrowband filtered in spatial frequency. On each trial, subjects had to state whether motion was to the left or the right. For each stimulus condition, Dmax (the largest displacement supporting 80 % correct direction discrimination performance) was measured. In experiment 1, Dmax was measured for orientationally narrowband stimuli as a function of their mean orientation. Dmax was found to increase as the orientation of the stimuli became closer to the axis of motion. Experiment 2 used isotropic stimuli in which some orientation bands contained a coherent motion signal, and some contained only noise. When the noise band started at vertical orientations and increased until only horizontal orientations contained a coherent motion signal, Dmax increased slightly. This suggests that near-vertical orientations interfere with motion perception at large displacements when they contain a coherent motion signal. When the noise band started at horizontal and increased until only vertical orientations contained the motion signal, Dmax decreased steadily. This implies that Dmax depends at least partly on the most horizontal motion signal in the stimulus. These results were contrasted with two models. In the first, the visual system utilises the most informative orientations (nearest horizontal). In the second, all available orientations are used equally. Results supported an intermediate interpretation, in which all orientations are used but more informative ones are weighted more heavily. 1

This paper describes a new algorithm for solving the N-camera stereo correspondence problem by transforming it into a maximum-flow problem. Once solved, the minimum-cut associated to the maximumflow yields a disparity surface for the whole image at once. This global approach to stereo analysis

We present an efficient spectral method for finding consistent correspondences between two sets of features. We build the adjacency matrix M of a graph whose nodes represent the potential correspondences and the weights on the links represent pairwise agreements between potential correspondences

This thesis proposal addresses the correspondence problem, especially matching of two views of a scene taken with unknown cameras from unknown and arbitrary viewpoints. This task is known under the name of Wide Baseline Stereo Matching. Our recent research related to this field is described

In the Post Correspondence Problem (PCP) an instance (h, g) consists of two morphisms h and g, and the problem is to determine whether or not there exists a word w such that h(w) =g(w). Here we prove that the PCP is decidable for instances with unique blocks and that the infinite PCP is decidable

and branch and bound to handle the correspondence problems arising in geometric vision. The thesis consists of the following papers:

We examine the implications of shape on the process of finding dense correspondence and half-occlusions for a stereo pair of images. The desired property of the disparity map is that it should be a piecewise continuous function which is consistent with the images and which has the minimum number

We consider an extension of the horizontal linear complementarity problem, which we call the extended linear complementarity problem (XLCP). With the aid of a natural bilinear program, we establish various properties of this extended complementarity problem; these include the convexity