|
|
 |
|
|
| |
|
|
2004 Projects
-
Object Tracking in Moving Images
Automatically tracking objects in visual images (as well as other
kinds of sensory data such as sonar) is important in many
applications. Examples include air and naval traffic control, security
and defense applications, autonomous robotics (for example RoboCup), and interpreting hand
movements in sign languages (such as Auslan).
There are many factors that make object tracking interesting - and
difficult. These include shape deformation (imagine the changes in
apparent shape that take place as a paper aircraft curves towards you,
or the changes in hand shape as someone communicates in sign
language), occlusion (when the object passes behind another), and many
sources of noise (for example lighting conditions, sonar reflections,
etc).
The aim of these projects is to use adaptive techniques to develop
methods of object tracking that are robust to reasonable levels of
deformation, noise, and limited occlusion. To achieve this model-based
approaches to object segmentation and tracking will be
combined with population-based
global optimisation strategies.
Example Reference
Kumazawa, I., "Target tracking by matching a shape represented by a tree of sigmoid functions", Pattern Recognition Letters,
21, 661-675, 2000
Illustrative Past Projects
Cristobal, T., Discrimination of a Hand from a Face using Template Matching, Honours Thesis, CSSE, UWA, 2003
Tsou, D., The Particle Swarm Optimiser and Recurrent Neural
Networks, Honours Thesis, CSSE, UWA, 2002
-
Optimise This!
Imagine you are given a black box with n inputs and one
output. There is a very complex (unknown) relationship between the inputs and
the output. Your job - find the inputs that maximise the output.
This problem arises in numerous computing (and non-computing)
applications - in fact most areas of life. In general, you cannot be
sure you have the right answer without testing all (possibly
infinitely many) combinations of inputs, and even that would only work
if the black box was deterministic). Luckily, however, real life
systems tend to have some kind of structure that can be exploited.
Global optimisation techniques such as evolutionary algorithms and
particle swarm optimisation attempt to adapt to and exploit the
underlying structure of complex problems. While they have been very
successful on some problems, there are many for which the standard
algorithms fail to find good solutions in a realistic computational
time. The aim of these projects is to improve the performance of
optimsation algorithms by combining global techniques with local
search (a combination sometimes referred to as memetic
algorithms).
Illustrative Past Projects
Tsou, D., The Particle Swarm Optimiser and Recurrent Neural
Networks, Honours Thesis, CSSE, UWA, 2002
Di Pietro, A., Adaptive Learning Techniques for Opponent
Modelling, Honours Thesis, CSSE, UWA, 2000
-
Playing Go by evolving
Snakes
While computers have proven very successful at playing many games,
most notably Chess, the ancient game of Go remains
elusive. Traditional search techniques appear to fail, in part due to
the computational complexity - whereas Chess has an average branching factor
(number of legal moves) of around 35, the branching factor in Go can
be as high as 361. Nevertheless humans do succeed in playing Go.
It seems likely that humans use more of a pattern-matching
approach. The aim of this project is to investigate a new approach to
playing Go by combining global optimisation techniques (eg. evolutionary
algorithms, particle swarm optimisers) with energy minimising
contours, or "snakes" - a technique borrowed from image processing.
As a testbed for the new approach, the agent developed might play
against existing computer Go
programs.
Example Reference
Muller, M., "Computer Go", Artificial Intelligence,
134, 145--179, 2002
Previous years' projects
| |
|
