Now showing items 1-4 of 4
Automatic object classification for surveillance videos.
The recent popularity of surveillance video systems, specially located in urban scenarios, demands the development of visual techniques for monitoring purposes. A primary step towards intelligent surveillance video systems ...
Motion prediction and interaction localisation of people in crowds
(Queen Mary University of London, 2013-05)
The ability to analyse and predict the movement of people in crowded scenarios can be of fundamental importance for tracking across multiple cameras and interaction localisation. In this thesis, we propose a person ...
Local Deformation Modelling for Non-Rigid Structure from Motion
(Queen Mary University of London, 2013)
Reconstructing the 3D geometry of scenes based on monocular image sequences is a long-standing problem in computer vision. Structure from motion (SfM) aims at a data-driven approach without requiring a priori models of ...
Supervised dictionary learning for action recognition and localization
(Queen Mary University of London, 2012)
Image sequences with humans and human activities are everywhere. With the amount of produced and distributed data increasing at an unprecedented rate, there has been a lot of interest in building systems that can ...