This project aims to explore the feasibility of and the tradeoffs involved with accelerating multi-camera synchronization algorithms on multicore processors. Specifically, this project plans to explore acceleration using ‘traditional’ multicore CPUs and massively-parallel Graphics Processing Units (GPUs). PluralEyes, a product for synchronizing audio and video recordings released by Singular Software, a Vancouver-area company, is the software application informing this research and stands to directly benefit from the insights gained.
The project is aimed to establish and algorithm and computer software for generation of multiple time series of data which represent processes that are closely correlated and auto-correlated (i.e. data in time step i are correlated to the data in time steps i-1, i-2,i-3, etc.). This project is of significant importance to the company. It represents significant improvement of our earlier developments in this field.