It brings together students, teachers, researchers and professors (of applied sciences) from different disciplines. During this semester, teams of (international) students from several study programmes have been working on applied research projects in Computer Vision and Data Science and now the time has come for them to present their findings during short sessions.
Keynote speaker: Toby Breckon
Toby Breckon is a Professor in the Department of Engineering and Department of Computer Science at Durham University and an academic tutor at St. Chads College. Within the department, he leads research in computer vision, image processing and robotic sensing in addition to teaching on the undergraduate (BSc/MEng) and taught postgraduate (MSc) programmes.
Before joining Durham in 2013, he held faculty positions at the School of Engineering, Cranfield University, the UK's only postgraduate-only university, and the School of Informatics, University of Edinburgh. Prior to this he was a mobile robotics research engineer with the UK MoD (DERA) and QinetiQ as well as holding prior positions with the schools inspectorate OFSTED, the Scottish Language Dictionaries organisation and dot-com software house Orbital Software. For more information on Toby Breckon you can visit this link.
12.30 – 13.00 Poster presentation
13.00 – 13.25 Opening
13.25 – 13.55 Keynote speaker
13.55 – 14.25 Student presentations
14.25 – 14.45 Coffee break
14.45 – 16.00 Student presentations
16.00 – 16.30 Bites and drinks
During the breaks and especially during the poster session, there is ample opportunity to have a discussion with the students about the details of their work.
Sign up now!
Please let us know if you will be attending by sending an email.
Centre of Expertise in Computer Vision & Data Science
Computer vision and deep learning offer an attractive technological framework for solving real-life and complex tasks. Deep Learning is a field within machine learning which overlaps with artificial intelligence. The fast development of deep learning has allowed new classes of computer vision problems to be solved more efficiently. Examples are polymer sorting, windmill blade inspection, buoy detection, camera security and more.
The traditional computer vision approach is to engineer a system for performing image processing tasks like feature extraction, classification and detection. With the advent of deep learning, these big image data tasks are solved by training a self-learning system directly with raw data. This has constituted a paradigm shift in the field of computer vision.