Motion Capture to MIDI

Joseph J Starling


Supervised by Dave Marshall; Moderated by Yukun Lai

The School of computer science has a couple of motion capture systems available to capture full or part human body motion and also datagloves to capture hand and finger motion.

The basic idea of this project is the capture human body gestures and convert this into "musical" information, via MIDI, to control various synthesisers to make interesting sounds. We have a variety of hardware and software based musical sound sources available.

One possible application would be to develop a virtual "air" guitar, piano or other musical instruments.

Prerequisites: Good level of programming and algorithms. C/C++ or Java programming knowledge. Some knowledge of audio/MIDI an advantage.

Initial Plan (19/10/2012) [Zip Archive]

Interim Report (14/12/2012) [Zip Archive]

Final Report (03/05/2013) [Zip Archive]

Publication Form