Multi-objective parameter estimation techniques for computer
vision
2005 : $101,000 2006 : $79,000 2007 : $81,000
Category : ARTIFICIAL
INTELLIGENCE AND SIGNAL AND IMAGE
PROCESSING
Administering Institution : The
University of Adelaide
This project
will benefit Australia's scientific knowledge and
technology base in the area of computer vision. By contributing
improved methods for
parameter estimation applicable to a wide variety of technical
problems, the
project will aid the generation
of improved software products in a wide variety of
domains. Examples include: augmented reality systems, with which
virtual reality
artifacts may be immersed within real video; 3D from 2D systems, with
which 3D object structure may be
computed from image streams; and visual robotic systems, with
which the pose of viewed objects may be determined.
ARC Discovery Grant 2007-2009
Prof MJ Brooks and Dr AR Dick
Automated acquisition of surveillance-camera network topology
2007 : $67,000 2008 : $67,000 2009 : $67,000
Category : ARTIFICIAL
INTELLIGENCE AND SIGNAL AND IMAGE
PROCESSING
Administering Institution : The
University of Adelaide
The development of an automated system for acquisition of
camera network topology is a crucial prerequisite to obtaining intelligent
surveillance systems operating at the network level. Such systems will
contribute improved methods for safeguarding Australia from terrorism
and crime by facilitating the tracking of suspicious individuals and
vehicles, and detecting anomalous behaviours in busy environments.
The leading-edge techniques involved will also constitute smart
information use of significant commercial value to Australian
industry.
ARC Discovery Grant 2008-2010
Prof MJ Brooks
Enhanced parameter estimation for multi-component fitting in computer
vision
2008 : $85,000 2009 : $85,000 2010 : $80,000
Category : ARTIFICIAL
INTELLIGENCE AND SIGNAL AND IMAGE
PROCESSING
Administering Institution : The
University of Adelaide
Computer vision is concerned with the development of computational methods that endow machines with the capacity to interpret their visual environment. Emerging applications include automated methods for analysing behaviour exhibited in video and improved techniques for generating special effects in movies. Many vision problems require high-accuracy estimation of parameters embedded within a mathematical model, an area that has seen enormous progress over the last decade. This project will develop leading edge techniques for simultaneously computing parameters that characterise multiple components (such as several objects in motion) rather than a single component, a critical remaining challenge in the field.
The University of
Adelaide
