— This paper considers the problem of estimating pose from inertial and bearing-only vision measurements. We present a non-linear observer that evolves directly on the special Eu...
Semanta is a system supporting Semantic Email, implemented as an add-in to two popular Mail User Agents, using existing email transport technology and integrated with the Social Se...
Simon Scerri, Ioana Giurgiu, Brian Davis, Siegfrie...
We propose to use a visual object (e.g., the baseball catcher) detection algorithm to find local, semantic objects in video frames in addition to an audio classification algorit...
We present a post-processing technique that selectively reduces the salience of distracting regions in an image. Computational models of attention predict that texture variation i...
Log-polar imaging is an important topic in space-variant active vision, and facilitates some visual tasks. Translation estimation, though essential for active tracking, is more di...