The problem of tracking curves in dense visual clutter is challenging. Kalman filtering is inadequate because it is based on Gaussian densities which, being unimodal, cannot repre...
This paper presents a visual particle filter for tracking a variable number of humans interacting in indoor environments, using multiple cameras. It is built upon a 3-dimensional,...
We present a method for efficiently generating a representation of a multi-modal posterior probability distribution. The technique combines ideas from RANSAC and particle filterin...
We have developed an image-based human-machine interface that tracks the surgeon’s face robustly in real-time(30Hz) and does not require to use any body-contacted sensing devices...
In this paper we present a method of robustly detect circles in a line drawing image. The method is fast, robust and very reliable, and is capable of assessing the quality of its ...