This paper describes a new corner detection algorithm, based on the property of corners that
the change of image intensity should be high in all directions. Consequently, the corner …

We describe progress in completely automatically recovering 3D scene structure together
with 3D camera positions from a sequence of images acquired by an unknown camera …

Algorithms to perform point-based motion estimation under orthographic and scaled
orthographic projection abound in the literature. A key limitation of many existing algorithms …

We describe a novel method for directing the attention of an automated surveillance system.
Our starting premise is that the attention of people in a scene can be used as an indicator of …

Object video virtual video (OVVV) is a publicly available visual surveillance simulation test
bed based on a commercial game engine. The tool simulates multiple synchronized video …

We use a change of variables that turns the critical nonlinear Schrödinger equation into the
critical nonlinear Schrödinger equation with isotropic harmonic potential, in any space …

In this paper, a person following behaviour for a mobile robot is presented. The head of the
person is located using skin colour detection. Then, a control loop is fed with the camera …

This thesis establishes a stochastic framework for tracking curves in visual clutter, using a
Bayesian random-sampling algorithm. The approach is rooted in ideas from statistics …

Multibody affine structure from motion (SFM) methods commonly assume independent
motion between objects such that the'measurement matrix'has rank 4k. When multiple views …

Reconstructing a 3D scene from a moving camera is one of the most important issues in the
field of computer vision. In this scenario, not all points are known in all images (eg due to …