Filter by faculty:

Found 37 matching student topics

Displaying 1–12 of 37 results

When does computer vision fail?

Computer vision models predict where objects are in an image, and what those objects are. These vision models give robots the ability to perceive their environment and choose safe and smart actions based on this perception.Computer vision models can fail silently when exposed to unexpected or difficult environments - e.g. changes in camera viewpoints, changes in lighting, or when seeing new objects that haven't been seen before. This raises concerns about the safety of using vision models in the real …

Study level
Honours, Vacation research experience scheme
Faculty
Faculty of Engineering
School
School of Electrical Engineering and Robotics

A robot demonstrator for event cameras

Event cameras are bio-inspired sensors capable of providing a continuous stream of events with low latency, and high dynamic range. Opposed to capturing the whole scene at fixed time intervals like conventional cameras, each pixel in an event camera operates independently from the other pixels and responds to changes in the perceived brightness. Recently we proposed the use of event cameras for robot localization. However, the demonstration was limited to a static dataset. In this research project, you will have …

Study level
Vacation research experience scheme
Faculty
Faculty of Engineering
School
School of Electrical Engineering and Robotics
Research centre(s)
Centre for Robotics

Transforming media industries

The Transforming Media Industries research program in the Digital Media Research Centre investigates how the business practices and cultural dynamics of media industries are adapting to profound transformations in the production, distribution, consumption, and regulation of media content in local and global contexts. We examine the operations of power and the potential for innovation, focusing especially on the implications they pose for media makers, the media they make, and their social consequences across the film, television, games, music, news, and …

Study level
PhD, Master of Philosophy
Faculty
Faculty of Creative Industries, Education and Social Justice
School
School of Communication
Research centre(s)
Digital Media Research Centre

Group activity classification in sports with machine learning

Within a team sports environment, coordinated behaviours between teammates are crucial to success. To accurately detect and correctly classify group behaviours, the actions of the individuals must be considered. Within a sporting environment the problem is further complicated by the presence of an opposing team, who are seeking to counter and disrupt the other team.While there is a substantial volume of research concerning activity detection and related tasks such as segmentation and anticipation from video footage, these tasks are less …

Study level
Vacation research experience scheme
Faculty
Faculty of Engineering
School
School of Electrical Engineering and Robotics
Research centre(s)
Centre for Data Science

Path prediction in sports with machine learning

The ability to predict the future movement of an agent has many applications, from anticipating behaviours within an autonomous driving environment to detecting abnormal behaviours in a security setting. Within sports, being able to predict paths has applications for match analysis, strategy planning, and automated broadcasting.Path prediction is typically performed at an individual level, predicting the future path of each person (or the ball) in turn. While such predictions may consider the locations and past movements of other players (both …

Study level
Vacation research experience scheme
Faculty
Faculty of Engineering
School
School of Electrical Engineering and Robotics
Research centre(s)
Centre for Data Science

Machine learning for wildlife monitoring

This project will investigate methods to monitor wildlife using machine learning applied to aerial imagery.While it is highly desirable to use drones and aerial footage to monitor wildlife, there are substantial challenges created by the nature of the data and target wildlife.This, combined with the vast nature of any collected aerial data, makes manual analysis difficult. This challenge motivates the development of machine learning methods to automatically process data and perform tasks, such as:detecting target animalscounting herd animalsclassifying land useassessing …

Study level
Vacation research experience scheme
Faculty
Faculty of Engineering
School
School of Electrical Engineering and Robotics
Research centre(s)
Centre for Data Science

Machine learning for understanding and predicting behaviour

Understanding behaviour and predicting events is a core machine learning task, and has many applications in areas including computer vision (to detect or prediction actions in video) and signal processing (to detect events in medical signals).While a large body of research exists exploring these tasks, a number of common challenges persist including:capturing variations in how behaviours or events appear across different subjects, such that predictions can be accurately made for previously unseen subjectsmodelling and incorporating long-term relationships, such as previously …

Study level
PhD, Master of Philosophy
Faculty
Faculty of Engineering
School
School of Electrical Engineering and Robotics

New technology and the law

Computer vision has developed to a point where machines using artificial intelligence are better and faster than humans at performing many vision-related tasks. For example, we are now often processed through customs based solely on face recognition software. Add to this the fact that the average Australian is photographed on CCTV cameras around 75 times per day. Commercial applications of face recognition technology include Microsoft's Face Application Programming Interface that can be used to classify face images based on gender, …

Study level
PhD, Master of Philosophy
Faculty
null
School
null
Research centre(s)
null
null

Retrospective analysis of treatment outcomes from a university-based myopia control clinic

The primary aim of this project is to retrospectively examine patient response to different myopia control treatments by a number of ocular biometrics such as refractive error, axial length and choroidal thickness. A secondary aim of this case review is to gain an understanding of children’s attitudes and ocular characteristics which may influence selection of myopia control treatments within a specialty university-based myopia control centre, as well as treatment drop-out rates and any adverse events experienced due to treatment.A similar …

Study level
Vacation research experience scheme
Faculty
Faculty of Health
School
School of Optometry and Vision Science

Making TV Australian in the 21st Century

This PhD project will be affiliated with the Making TV Australian in the 21st Century Discovery Project and the Transforming Media Industries research program within the Digital Media Research Centre.The PhD project should align with inquiry related to the changing dynamics of television production and the 'nationing' role of television. Existing practices designed to enable Australian television to achieve national cultural and economic objectives have been deeply transformed by the impact of technological change and foreign ownership. This project investigates …

Study level
PhD
Faculty
Faculty of Creative Industries, Education and Social Justice
School
School of Communication
Research centre(s)
Digital Media Research Centre

Decision modelling in blockchain adoption and environmental implications

Due to the decentralised and immutable nature of distributed ledger systems, blockchain has become a critical priority for organisations across the world. The global blockchain market is expected to grow from $1.57 billion in 2018 to $162.84 billion by 2027.From an ecological perspective, blockchain has raised environmental concerns due to increasing computational power that is required to operate energy-intensive consensus mechanisms. However, it also has the potential to help promote renewable energy through a variety of blockchain-based use cases such …

Study level
PhD, Master of Philosophy, Honours, Vacation research experience scheme
Faculty
Faculty of Science
School
School of Information Systems

Decision modelling to overcome intergenerational discounting

This project aims to address a key obstacle to climate action: intergenerational discounting, a phenomenon that explains the tendency for people to prefer smaller benefits for themselves now, rather than larger benefits for future generations. Intergenerational discounting becomes even more problematic due to a growing global population and increasingly intensive use of natural resources.In this project, we follow the design science approach and aim to establish design principles necessary for decision modelling to overcome intergenerational discounting and achieve genuine and …

Study level
PhD, Master of Philosophy, Honours, Vacation research experience scheme
Faculty
Faculty of Science
School
School of Information Systems

Page 1 of 4