Computer vision and robotics

Research in computer vision and robotics centres on the computer processing of visual information to make decisions and automate processes using technology. 

computer vision

Our group is focused on developing and applying fundamental computer vision and robotics algorithms. This includes deep learning, robust fitting, generative models, adversarial learning, memory networks, and meta learning (learning to learn). 

We're particularly interested in deep learning for: 

  • semantic image understanding 

  • simultaneous localisation and mapping (SLAM) and 3D scene reconstruction 

  • integrating vision and language (e.g. captioning and visual question answering) 

  • medical imaging. 

Our group’s machine learning algorithms allow machines to describe and reason about what they see, and plan actions accordingly. This supports a wide range of applications throughout society, from children’s toys and self-navigating robots, to automated disease diagnosis and defence technology. 

Higher degrees by research

Whether you intend to work in research or industry, a higher degree by research can give you a competitive edge throughout your career. Find out more about studying a Master of Philosophy or Doctor of Philosophy.

Higher degrees by research