Filter by faculty:

Found 4 matching student topics

Displaying 1–4 of 4 results

Visual place recognition for robots and autonomous vehicles

Knowing where you are is a fundamental capability for robots and autonomous vehicles moving through an environment.Increasingly, technologies in this area are based around camera sensors, performing a process known as Visual Place Recognition (VPR).VPR becomes challenging in the real-world when conditions or viewpoints change: for example in conditions of inclement weather, changing seasons or day-night cycles.Robots and autonomous vehicles must also be able to localise across viewpoint changes: for example driving down the same road but in the opposite …

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

Machine learning for wildlife monitoring

This project will investigate methods to monitor wildlife using machine learning applied to aerial imagery.While it's 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 environment …

Study level
Vacation research experience scheme
Faculty
Science and Engineering Faculty
Lead unit
School of Electrical Engineering and Robotics

Lifelong semantic mapping of large scale environments

When building a map of objects inside a real environment, this map can become quickly outdated as objects are moved around over time. This is especially true when the map is on the scale of a house, warehouse or a city.This PhD project investigates new methods for keeping a high-resolution semantic map up-to-date using partial, and possibly low-resolution, snapshots. These environment snapshots can be captured by sensors mounted on moving agents, such as vehicles and mobile robots. …

Study level
PhD
Faculty
Science and Engineering Faculty
Lead unit
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
Faculty of Law
Lead unit
School of Law

Page 1 of 1