In this paper, we address markerless full-body articulated human motion tracking from multi-view
video sequences acquired in a studio environment. The tracking is formulated as a multi…

Automatically detecting objects in images or video sequences is one of the most relevant
and frequently tackled tasks in computer vision and pattern recognition. The starting point for …

Object triangulation, 3-D object tracking, feature correspondence, and camera calibration are
key problems for estimation from camera networks. This paper addresses these problems …

… In the precursor of this work, Ivekovic and Trucco (2006) estimate the pose of a subdivision
upper body model from multi-view images. The use of evolutionary optimisation methods to …

We propose an algorithm creating consistent, dense disparity maps from incomplete disparity
data generated by a conventional stereo system used in a wide-baseline configuration. …

In this paper, we describe the GPU implementation of a markerless full-body articulated
human motion tracking system from multi-view video sequences acquired in a studio …

In this paper we describe the application of Particle Swarm Optimisation to the problem of
human body pose estimation from multiple view video sequences. We use a subdivision body …

… Špela Ivekovic Lessells Scholar Royal Society of Edinburgh Edinburgh, UK spela.ivekovic@gmail.com …
Dr Ivekovic is a Lessells Scholar of the Royal Society of Edinburgh. …

This chapter introduces the basic geometric concepts of multiple-view computer vision. The
focus is on geometric models of perspective cameras, and the constraints and properties …

We describe an algorithm for fitting a Catmull-Clark subdivision surface model to an unstructured,
incomplete and noisy data set. We complete the large missing data regions with the a-…