UROP
Opportunities

Given motion capture samples of Charlie
Chaplin's walk, is it possible to synthesize other motions---say, ascending or
descending stairs---in his distinctive style? More generally, in analogy with
handwritten signatures, do people have characteristic motion signatures that individualize
their movements? If so, can these signatures be extracted from example motions?
Furthermore, can extracted signatures be used to recognize, say, a particular
individual's walk subsequent to observing examples of other movements produced
by this individual?

We are developing algorithms that extract
motion signatures and are using them in the animation of graphical characters.
The mathematical basis of our algorithm is a statistical technique formulated
in terms of tensor algebra. For example, given a corpus of walking, stair ascending,
and stair descending motion data collected over a group of subjects, plus a
sample walking motion for a new subject, our algorithms can synthesize never
before seen ascending and descending motions in the distinctive style of this
new individual.

We are also applying our tensor
algebraic approach to ensembles of human facial images in order to extract
facial signatures that characterize the appearance of particular individuals.
We will use these facial signatures to synthesize realistic and
non-photorealistic images of people.

This project will introduce students to
computer graphics, computer vision, and machine learning techniques.

**Prerequisites: **Linear algebra and/or signal processing

**Contact
Information:**

M.
Alex O. Vasilescu

Media
Lab

Office:
E15-321

E-mail:
maov@media.mit.edu

Phone: