Curtin University of Technology
Skip to content
Link to Curtin homepage
Curtin Department of Computing

Official List of Honours Projects

The following projects are available:

  1. Raj Gopalan
  2. Mihai Lazarescu
  3. Andrew Marriott
  4. Tele Tan
  5. Ling Li
  6. Patrick Peursum
  7. More Honours Projects in 2010

Raj Gopalan

Value based frequent pattern mining

For solving a number of business decision problems, it is necessary to attach values such as costs and prices to the frequent patterns and the association rules discovered by data mining. It will be more efficient if optimal patterns and rules can be found directly by associating cost or price to items during the mining process. This project is aimed at combining optimisation and mining techniques to find value based frequent patterns that are meaningful for decision making.

Associative classification from maximal and closed frequent patterns

Classification in data mining has many applications. Associative classifiers based on frequent patterns are more accurate but not feasible to construct for many practical data sets when there are too many association rules at low support thresholds. Maximal frequent patterns and closed frequent patterns are far more concise and could form the basis of better classifiers. This project is aimed at mining maximal and closed patterns more efficiently using compressed frequent pattern trees and then using those patterns for classification.

Efficient mining of data streams

Mining patterns from dynamic datasets (also known as mining from data streams) such as stock market data and web click streams is a focus of current research interest. The goal of this project is to mine frequent patterns in data streams using more compact data structures. For the same size and rate of data streams, more information can be stored in compact structures and the interval of mining extended resulting in more efficient stream mining.

Mihai Lazarescu

Abnormal Activity Detection in Surveillance Video of Public Areas

The project combines the use of image processing and machine learning to detect abnormal behaviour in enclosed public areas such as underground passage ways. The project requires the development of models of normal behaviour which can then be used in conjunction with machine learning to determine whether illegal activities such as vandalism, loitering and fighting occur in the surveillance video. The project involves work in both object tracking and spatio-temporal pattern recognition.

Automatic Train Passenger Count

This project is done in collaboration with DTI. The goal of the project is to be able to accurately count the passengers getting on/off trains using multiple cameras in order to optimise the train schedule. Each train door will be monitored by a single camera and the aim is to be able to determine at all times how many passengers are on the train. The project complexity comes from the fact that it must be able to handle crowds and be able to produce reliable results under varying lighting conditions.

This project is co-supervised by Dr Tele Tan.

Andrew Marriott

Dialogue Management

Pre-requisites: Basic knowledge of Dialogue Management (see References below). Pattern Matching.

Conditions: None.

References: http://www.mentor.computing.edu.au/, http://www.metaface.computing.edu.au/, http://www.aui.computing.edu.au/

Summary:

Several projects exist within the area of DM - the understanding of dialogues between a user and the computer. Students would be researching ways of improving this Natural Language Understanding process as well as evaluating applications that use DM. Specific projects include the creation of optimised generic Regular expressions from plain english questions as well as non-textual input to a Dialogue Manager such as the use of TV remote controls. The DM can be used standalone or with a Talking Head. A specific project is Pandora - http://www.companions.computing.edu.au/projects/Pandora/ Another is the Talking Linux Penguin Advisor - http://www.aui.computing.edu.au/projects/documents/.

Students should contact me for more information if they are interested in this area.

See: http://www.aui.computing.edu.au/projects/documents/, http://www.aui.computing.edu.au/projects/Dialogue_Manager

Theses: http://www.vhml.org/theses/ek, http://www.vhml.org/theses/desouza

Virtual Human Markup Language

Pre-requisites: Knowledge of XML.

Conditions: Ongoing joint research with DIST, Uni of Genoa, Italy.

References: http://www.vhml.org/

Summary:

VHML is a Curtin initiative started within a European Union 5th Framework project. It is XML based and uses tags to create emotion, facial and body gestures in a Virtual Human interface. It aims to become an international standard via the MPEG committee mechanism. This is a "coming-of-age" field of research. Projects involving low level and high level implementation and evaluation of VHML, the verification and validation of the upgraded VHML specification, and the use of VHML for emotion and gesture recognition exist. A specific project is the production of a redefinable VHML so that the meaning of tags such as <smile> and <angry> can be exactly specified so that the inbuilt Personality of a Talking Head can control the Head more accurately and effectively.

Students should contact me for more information if they are interested in this area.

See: http://www.vhml.org/

Theses: http://www.vhml.org/theses/stalloj, http://www.vhml.org/theses/huynhqh, http://www.vhml.org/theses/LIU

Multi-modal Human Computer Interfaces

Pre-requisites:CG252, CC252

Conditions: In collaboration with Carlo Bonamico, DIST, Italy.

Summary:

It is becoming more important for input to a computer being more than just plain text or GUI based "point and clicks". This research will look at new paradigms for input devices and input types to build a framework to cater for this multi-modal input. Typical input devices will be TV remote-controls, speech, PDA's, etc.

Students should contact me for more information if they are interested in this area.

See: http://www.aui.computing.edu.au/projects/, http://www.aui.computing.edu.au/projects/Smilies, http://www.aui.computing.edu.au/projects/documents/

Theses: http://www.vhml.org/theses/wijayat, http://www.vhml.org/theses/holic

Personality Specification

Pre-requisites: Readings from References below.

Conditions: Ongoing joint research with various European Universities.

References:http://www.vhml.org/workshops/

Summary:

Since humans are familiar with human faces and the way in which they act and react, any interactive computer-generated character must also act and react in this commonplace, believable fashion. Therefore it must have the consistent human attributes of situated liveness, controlled visual impact, complex behavioural patterns and natural unobtrusive behaviour. These attributes contribute to user trust and acceptance of the character. That is, it must have a consistent personality that provides this complexity. There is a need for a development and evaluation framework to enable personalities in these characters.

Projects include formal specification, development, implementation and evaluation of this framework to ensure the effectiveness of using these characters in systems in diverse areas such as eCommerce, eLearning, intelligent guided browsing and information retrieval, etc.

Students should contact me for more information if they are interested in this area.

See: http://www.aui.computing.edu.au/projects/Personality

Theses: http://www.vhml.org/theses/shepherdson, http://www.vhml.org/theses/ek, http://www.vhml.org/theses/beardsw

Adaptive User Interfaces

Pre-requisites: None

Conditions: In collaboration with Michael Borck and Don Reid.

References: http://www.aui.computing.edu.au/

Summary:

Many projects exist in the development, implementation and evaluation of Talking Head applications that take text and produce videos. For example, coupling the Unix Jokes database with a Talking Head of the correct "look" to produce a stand-up comedian and then evaluating the effectiveness of this.

Or creating a late-night CG news reader for Channel 31 that automatically reads a news feed in an expressive manner dependant upon its personality.

Students should contact me for more information if they are interested in this area.

See: http://www.aui.computing.edu.au/projects/documents/, http://www.aui.computing.edu.au/projects/

Tele Tan

Computational Security Dynamics (CSD)

In these days of heightened security awareness, both employers and employees have a major role to play in making the workplace secure and safe. Security and safety vulnerability in a work place plus the onset of threats determines the risk of these threats from occurring. Current risk assessment procedures perform on critical infrastructures are sometimes inadequate to deal with dynamic threat situations. This project aims to develop a computational simulation system which provides decision makers with the tools needed to access the state of security and preparedness to deal with security and safety related events. The system will interactively model dynamics of people or groups of people within the protected Virtual Space. Agent-based computational simulation techniques, popular in gaming technology will provide the key focus of this project on top of virtual environment modelling and simulation. Simulations created by the system can also be used for computer-assisted training purposes.

Supervisors: Dr Tele Tan and A/Prof Kevin Wong (Murdoch University)

Recovering the 3D Structure of a Face from Exampler Images

This project addresses the problem of pose and illumination variations affecting the performance of real world face recognition systems. First of all, we will explore the use of a shape-from-shading technique to extract the 3D structure of a face using multiple images taken of the person under varying illumination directions using an in-house developed mini light stage. This 3D face structure with the skinning model can then be used to generate further 2D representations of the face under varying pose and illumination variations. This analysis-by-synthesis technique will be used subsequently to address the problem of outdoor, unconstrained face recognition applications.

Supervisor: Dr Tele Tan

Computer Vision and Computer Graphics Convergence: A Human Motion Tracking Application

The problem of tracking human motion using video inputs is an active research area in computer vision. In addition to this, there is a parallel development in the computer graphics (CG) community to inject greater realism and efficiency in rendering dynamic 3D models (e.g. human kinematic motion, clothing, and etc.). From the perspective of video-based human motion tracking, it is becoming obvious that the utility of CG-generated dynamic models can be harnessed to improve its performance. For example, one can harness the body joints constraints whose information can be embedded into the CG human model to define the extent of the joints movement in the video. It is also interesting to determine how this model can be used to alleviate the problem of body self occlusions which is an unsolved problem in tracking. This project will investigate the use of CG human model to assist in the tracking of human motion taken from a single camera.

Supervisor: Dr Ling Li and Dr Tele Tan

Parallel and real-time rendering of CO2 pressure vessel data

Investigate and implement a method of delivering the seismic tomography results from CO2 pressure vessel experiments to a desktop PC in the laboratory (or remote office) in realtime using HPC parallel architecture (i.e. SGI Altix).

The solution will include a visualisation platform (can be existing software) for both Windows and Linux environments, and the processing of sensor (pressure, temperature, seismic, etc) data into suitable forms to be visualised.

Possible visualisation platforms are:

Supervisors: A/Prof Tele Tan (Curtin Department of Computing) and Dr Andrew Squelch (Curtin Department of Exploration Geophysics) assisted by Darran Carey (iVEC)

Virtual mineral collection

Investigate and implement a webserver solution to host and serve 3D virtual models of rocks and minerals, with a local client option for the remote viewing of the collection via the Web. 3D models of rocks and minerals will be obtained via a desktop scanner at UWA and these will form the collection. Some optimisation and/or refinement of the models may be required before inclusion. Some of the 3D models will also be "printed" on the rapid prototype (3D printer) machine also at UWA.

Supervisors: A/Prof Tele Tan (Curtin Department of Computing), Prof Suzette Warden (Curtin Department of Design) and Dr Andrew Squelch (iVEC)

Applying face recognition approach to rock surface feature recognition

Investigate the application of face recognition techniques to rock surface feature recognition and frame registration from video streams and, therefore, progress the capability for the auto generation of 3D textured geometric mesh of the relevant rock surface. This has application in the mining and geotech fields.

References:

Supervisors: A/Prof Tele Tan (Curtin Department of Computing) and Dr Andrew Squelch (Curtin Department of Exploration Geophysics)

Ling Li

OpenGL wrapper for creating stereo movies

Write a C wrapper for the standard OpenGL32.dll such that stereo-enabled OpenGL-based visualisation software can export/write the left-right buffers as sequential movie frames to disk. Normal OpenGL calls will pass through the wrapper to the regular OpenGL32.dll. The wrapper is only to be invoked if placed in the directory of the relevant visualisation software or through some other non-intrusive selection procedure.

Supervisors: Dr. Ling Li (Curtin Department of Computing) and Dr Andrew Squelch (iVEC)

Integrate InterSense tracker into visualisation environment

Investigate and implement a method of integrating the InterSense Wireless InertiaCube3 tracker system with a stereo (collaborative) visualisation environment, e.g. GDIS, VTK (including Mayavi), Drishti, or a Virtual Environment (e.g. EON, OpenMASK, OpenSceneGraph) to provide navigation and data interaction suitable to iVEC usage requirements.

Previous similar international work includes: vtkActorToPF, vtkActorToOSG, vtkTracker, vtkTrackerTool and vtkTrackerBuffer.

Refer:

Supervisors: Dr. Ling Li (Curtin Department of Computing) and Dr Andrew Squelch (iVEC)

Integration of haptics device with scientific visualisation software

Investigate and implement the integration of an open source haptic API (e.g. H3D.org) with existing open source scientific visualisation software (e.g. Drishti, VTK or ParaviewGeo), primarily for interpretation of geoscience (i.e. seismic) data sets. A PHANTOM® Premium 1.5 haptic device from SenseAble Technologies is available.

VTK Designer is an existing example of VTK integration with haptics and this may be a useful starting point.

References:

Supervisors: Dr. Ling Li (Curtin Department of Computing) and Dr Andrew Squelch Curtin Department of Exploration Geophysics)

Patrick Peursum

Smart Homes for Aged Care

Nobody wants to end up living in an aged care home, but the risks of a stroke, a heart attack or just falling over and breaking a bone start to stack up, particularly if you are living alone. An ongoing project of Curtin is to build intelligent systems to support and monitor aged people in their own home, allowing them to live independently for longer whilst preserving peace-of-mind that somebody will be alerted if something goes terribly wrong. Curtin has a laboratory wired up with multiple sensors (cameras, microphones, reed switches, X10).

Significant research areas include:

Markerless Motion Capture

Hollywood has been using motion capture systems to limb-level movements for use in animations and computer graphics for over two decades now, but traditional motion capture needs a special motion capture studio equipped with infrared cameras and forces the actor to wear a suit peppered with reflective markers on it. This project is about eliminating the need for markers and special facilities, instead using standard cameras and equipment to estimate and track a person's 3D body posture. Links with the smart home project are particularly relevant here given the rich information that markerless body tracking can provide to intelligent monitoring systems.

Areas include:

Computer Vision with an Active (Pan-Tilt-Zoom) Camera

Many computer vision systems assume the use of fixed cameras. Not only is this restrictive, but it also creates implicit assumptions that make many algorithms useless when applied to a computer-controlled pan-tilt-zoom (PTZ) camera. Thus despite the flexibility of PTZ cameras there has not been much recent research that makes use of them.

Possible projects include:

Mobile Phone Vision

The ubiquity of mobiles and the capabilities of the latest smartphones (GPS, accelerometers, magnetometers, Web access, GPUs) is opening up possibilities for applying computer vision on-the-go. Challenges include the continuous yet unsteady motion of a handheld camera, movement between scenes of vastly different properties and having to do it all efficiently to produce real-time performance.

Applications include:

Clustering and Data Mining

Streaming data is becoming quite common, but machine learning algorithms are only just being developed to handle such 'online' data streams. A major issue is not only clustering the incoming data to assign labels to groups of similar data points, but also detecting when the stream's data characteristics have fundamentally changed (indicating a change in the physical system that the data stream is measuring). Such data stream clustering is also becoming increasingly useful due to the data capture capabilities of modern mobile phones.

Parallel Processing

With the Gigahertz race grinding to an unexpected halt at around 3GHz (Intel thought they could reach 10GHz with the 2002 Pentium-IV!) due to heat issues, CPU manufacturers have been forced towards the multi-core route. In turn, software developers will now be forced to build systems in a multi-threaded concurrent manner in order to make the most of new CPUs. Graphics processors (GPUs) are also fair game for applications given the introduction of GPU-related APIs (CUDA from NVIDIA, the OpenCL project). But bug-free multi-threaded programming is not an easy task, despite several projects that aim to make MT coding 'simple' (eg: OpenMP).

Areas include: