Course summary

How can we design smartphones that sense your mood by reading your facial expressions or recognise hand gestures as a way to make a call? How do we develop systems that quickly and reliably analyse medical scans to assist with cancerous tumour diagnosis or improve the safety of self-driving cars with in-vehicle technology able to detect and modify a vehicle’s behaviour in any environment? These are just some of the fascinating questions that you will strive to answer on this programme. This programme is intended to respond to a growing skills shortage in research and industry for engineers with a high level of training in the analysis and interpretation of images and video. It covers both low-level image processing and high-level interpretation using state-of-the-art machine learning methodologies. In addition, it offers high-level training in programming languages, tools and methods that are necessary for the design and implementation of practical computer vision systems. You will be taught by world- class researchers in the fields of multimedia analysis, vision-based surveillance, structure from motion and human motion analysis. Aside from your lectures, you will be working on cutting-edge, live research projects, gaining hands-on experience.