Event-based Visual Understanding in Complex Environment [Self Funded Students Only]

Events record dynamic changes in environments. They are sparse, but an important information source that draw our attention and make us aware of the dynamic surroundings. Event cameras, inspired by our retina’s perception of changes, are invented to capture such intensity changes in the world asynchronously. Compared to the conventional frame-based cameras, event cameras have advantages in high temporal resolution and low latency (in microseconds), low power, and high dynamic ranges, making them potentially applicable in challenging scenarios for conventional cameras. There has been growing interest and emerging research in event-based visual processing. However, how to effectively integrate the event information for computer vision and robot tasks is still an open question.

This project will explore the use of event cameras to improve visual understanding in complex environments. Complex environments, such as bars, forests, etc., often have changing lighting conditions, moving objects, and severe occlusions, all of which pose challenges to get complete information about the world. The high dynamic nature of these environments requires efficient and effective handling of changes, where events captured by event cameras can provide useful guidance. Our hypotheses include event-informed attention field to eliminate visual clutters for more efficient visual understanding, and the continuity in events to provide effective data association for object detection and tracking.

The student will have access to a newly purchased DAVIS event camera, and will look into 1) the processing and representation of events; 2) data association between the event space and the camera frame space; and 3) the integration of associated event information into visual understanding tasks such as object detection and tracking.

Keywords: visual understanding, event camera

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject.  Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.

This application is open to students worldwide.

How to apply:

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below

This project is accepting applications all year round, for self-funded candidates via https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/computer-science-and-informatics 

In order to be considered candidates must submit the following information: 

• Supporting statement 
• CV 
• In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
• Qualification certificates and Transcripts
• Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
• References x 2 
• Proof of English language (if applicable)

If you have any questions or need more information, please contact COMSC-PGR@cardiff.ac.uk

For more information about this project, please contact Dr Jing Wu, wuj11@cardiff.ac.uk