This research project aims to answer the question: How can video summarisation methods be used for efficient review and data storage of visual sensory data captured during a life-long operation of mobile service robot?
Video summarisation refers to the process of generating a summary that best conveys the most informative content of a longer video.
The research activities that you carry out and the expected outcomes for this project will depend on your study level:
Vacation Research Experience Scheme
You will test multiple video summarisation techniques using already-published code on a long youtube video of a dashcam.
You will test multiple video summarisation techniques using already-published code to summarise a long video captured inside a factory to produce a time-stamped summary of the change in the activities.
Robots of the future will have the ability to record a large amount of visual data. Still, it will be impossible for their owners to review the data when looking for an explanation of particular events, or to investigate the behaviour of the robot and the reason that led it to take particular actions.
Your PhD will investigate this topic and develop new methods for summarising visual memories of mobile service robots during a life-long operation.
Skills and experience
You should have a background and interest in computer vision and machine learning.
You may be able to apply for a research scholarship in our annual scholarship round.
Contact the supervisor for more information.