Human Body Capture and Prediction from Rehearsed Live Performances

We address the problem of 3D human body motion capture and prediction to be used in the context of a live music concert performances. The difficulty of capturing the motion of a performer in this context comes from the harsh environment in which it takes place that includes strong and varying lighting, smoke generators, and other visual pollution. The intern will develop novel technique for the capture and prediction of the motion of the performer, knowing that the performance has been rehearsed beforehand. The partner organization benefits from the expertise in computer animation research that has been conducted over the years at McGill University. This collaboration is also beneficial for the the intern and the university in that the partner has a great experience developing cutting-edge computer vision algorithms that are used in music concerts all over the world. They also provide all the necessary equipment to conduct this research.

Faculty Supervisor:

Paul Kry

Student:

Emma Gouné

Partner:

VYV Corporation

Discipline:

Computer science

Sector:

University:

Program:

Accelerate