I am interested in machine perception of how people perform motor skills, particularly for human-computer interaction. I'm interested in the domains of rowing, dance, surgery, games and everyday activities.
This work involves:
- Rating qualities or styles of motor skills
- Syntactic recognition of motor skills
- Data collection for skilled activities
- Crowd sourcing opinions
- Graphical models and approximate inference
- Performative interaction
I'm also interested in automated analysis of music.
I engage in scientific observation, statistics and philosophy as an engineer and designer of digital computing systems.
I enjoy mutlidisciplinary and interdisciplinary research and design that includes HCI, Ubiquitous Computing, data mining, pattern recognition and machine learning, computer vision, sensors, statistics and probability, participatory research, semiotics, coaching, kinesology and biomechanics.
Public dataset: Gesture database
Past project: Sensing for Sport And Managed Exercise (EPSRC project)
Supervisor: Professor Andy Hopper
Colleagues: George Colouris, Andrei Bejan, Cecily Morrison, Sean Holden, Ian Bezodis, Brian Jones, Andreas Bulling, Pushmeet Kohli, Helena Mentis, Sebastian Nowozin
1. Simon Fothergill, Helena Mentis, Pushmeet Kohli, Sebastian Nowozin, "Instructing People for Training Gestural Interactive Systems," ACM SIGCHI Conference on Human Factors in Computing Systems (CHI 2012), May 2012
2. Simon Fothergill, "Examining the effect of real-time visual feedback on the quality of rowing technique," 8th Conference of the International Sports Engineering Association 2010, Vienna, Austria, series The Engineering of Sport, Springer, Jul 2010
3. Simon Fothergill, Robert Harle, Sean Holden, "Modelling the model athlete: automatic coaching of rowing technique," Joint IAPR Workshops on Structural & Syntactic and Statistical Pattern Recognition, Springer, Dec 2008