Research Internships: Deducing Anatomy from Skin Movement
Code of project: 2009-late1
Project Supervisor: Dr Derek Magee
Area of interest: This project is linked to the Computer Vision Research Group.
Appropriate for degree programmes: All single and joint honours students from the School of Computing
Pre-requisites:Further information about the prerequisites for this project is available from Dr Derek Magee, but some programming experience is expected.
Project Outline
This project relates to "Proof of concept" of the idea of using external motion sensors attached to the hand/wrist to predict internal anatomy. Internal anatomy (bones, tendons etc.) will be acquired using a MRI scanner. In the first stage external sensors will be modelled as MRI visible fiducials ("virtual sensors"). An interface will be designed for interactive location of the anatomy and fiducials and a simple regression approach between a representation of the anatomy and a representation of the virtual sensors will be evaluated. It is likely the localisation interface will be programmed in C++/Visual studio/OpenGL. Regression analysis may be performed in Matlab. Experience with these technologies/languages is a plus.
The internship will be for a period of 10 weeks (including 1 week paid holidays) at a rate of £270.27/week.