Skip to content

Student topics

Filter by faculty:

Found 37 matching student topics

Displaying 1–12 of 37 results

Develop and implement a non-contact real-time respiratory monitoring technique, using low cost 3D camera technology, and explore its use in abdominal-thoracic cancer sites

Consumer-grade depth sensing technology has in recent years become widely available. A number of vendors have developed similar technologies, for example, Microsoft KinectTM (now discontinued), Intel’s RealSenseTM, the Asus Xtion depth sensor, and the Qualcomm Spectra ISP platform, now in its second generation.The systems make use of camera technology that measures the distance to a surface, rapid image acquisition can then enable real time motion detection of location of the surface. The infra-red transmitter and sensor use a time-of-flight method …

Study level
PhD, Master of Philosophy, Honours, Vacation research experience scheme
Faculty
Science and Engineering Faculty
Lead unit
School of Chemistry, Physics and Mechanical Engineering

Wide field-of-view vision-based aircraft detection

Small-to-medium-sized fixed-wing unmanned aircraft vehicles (UAV) have an incredible range of potential applications in civilian operations including:disaster assessmentsearch-and-rescueenvironmental and infrastructure monitoringremote sensing in agricultureproduct delivery.The national airspace is heavily regulated with strict rules and safety layers designed to mitigate the risk of mid-air collisions. The final safety layer corresponds to human pilots using their eyes and judgment to see and avoid potential mid-air collision threats.Sense and avoid (SAA) refers to the implied regulatory requirement that UAVs be capable of sensing …

Study level
PhD
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

QUT Arm Farm

Deep Learning has seen significant growth and improvements in computer vision systems over the last years. Our work at the Australian Centre for Robotic Vision is looking at how robotic manipulation tasks be improved by using visual feedback. A lot of activities at the intersection at robotics, vision and learning at QUT.

Study level
PhD, Master of Philosophy, Honours, Vacation research experience scheme
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Augmenting robotic grasping through AR/VR setups

The improvement of robotic grasping in the last years has mainly been pushed by new learning techniques. A promising direction is learning from demonstration, where the human operator teaches a robot the tricks of the specific task. On the other hand with these learning techniques it is hard to understand the underlying reasoning.We plan on using augmented reality and virtual reality setups to teach and validate real world robotics grasping approaches.

Study level
PhD, Master of Philosophy, Honours, Vacation research experience scheme
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Human interaction with AI and machine learning systems

Human-Computer Interaction's grand challenge is human-in-the-loop machine learning, which offers potential to better foster learning in both human and machine as they solve complex problems. Machine learning uses statistics and inference to create implicit (black box) models of the world, with little prospect of making the reasoning explicit. Meanwhile, people develop ways of evaluating and interacting with these systems using their cognitive reasoning and social interaction skills.This project will investigate people interacting with a variety of systems that utilise machine …

Study level
PhD, Master of Philosophy, Honours
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Intelligent transport systems

With the advancement in technology, new sources of transportation data (including traffic and transit, among others) have emerged which can potentially facilitate and even revolutionise transport modelling and simulation.My research team focuses on various aspects of the exploitation of emerging data for network planning, operations, management and control. This includes:New insights in travel behaviour modelling, traffic state estimation and predictionTravel patterns and multimodal travel behaviourTransit network monitoring, modelling or controlApplication of data from connected and autonomous vehicleData driven operation of …

Study level
PhD, Master of Philosophy, Honours, Vacation research experience scheme
Faculty
Science and Engineering Faculty
Lead unit
School of Civil Engineering and Built Environment

Deep learning architectures

This project reviews deep learning architectures in the literature and investigates improvements for state-of-the-art algorithms.

Study level
PhD, Master of Philosophy, Honours
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Visual chatbot (AI)

This project aims to create an Artificial Intelligence (AI) agent that can have a natural-language dialogue with humans about the content of an image or a video.

Study level
PhD, Master of Philosophy, Honours
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Deep learning for iris recognition

This project investigates deep learning techniques including Convolutional Neural Networks (CNNs) to perform identity recognition based on the iris region.

Study level
PhD, Master of Philosophy, Honours
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Speech recognition using deep neural networks

The success of automatic speech recognition (ASR) systems is largely driven by the availability of large-volume, high-quality speech data for building the acoustic model. In particular, recent significant quality improvements of ASR systems have been due to progress in the fields of machine learning and artificial intelligence with deep neural network (DNN) based acoustic modeling.A large volume of data is usually required for training a high-dimensional model using a DNN with many hidden layers and millions of parameters in order …

Study level
Master of Philosophy, Honours
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Camera-based positioning system for autonomous vehicles

This project will develop a camera-based positioning system for ground-based autonomous vehicles, including autonomous cars that enables low latency, highly accurate absolute positioning for vehicles relative to a pre-mapped environment.

Study level
PhD, Master of Philosophy, Honours
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Mini-autonomous car

You will be further developing the mini-autonomous car at the QUT robotics group, to enable a range of technology demonstrations and public display options.Some of the key capabilities to add or enhance include:navigationpositioningmappingscene understandingpedestrian detectionroad sign and traffic light detectioncontrol and path planning.

Study level
Honours, Vacation research experience scheme
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Computer Science

Page 1 of 4