Research Abstracts - 2006

A General Purpose Motion Capture Database System

Bennett Rogers & Jovan Popovic

Introduction

Motion capture data has become a critical tool in many areas of industry and academia, including movies, computer graphics research, video games, and medicine. Every application of motion data requires a dataset tailored to that specific task, meaning that even as the global collection of data grows, no project benefits from the overall accumulation. Our project aims to develop a motion capture database system capable of supporting a wide range of filetypes and user queries that would lift this data limitation. One of the main challenges in developing the project is developing an internal representation of the data that allows for these different filetypes to be integrated into one database. This representation must provide the ability to return the original data unaltered, while supporting the many types of queries that users will need, such as content-based retrieval and partial subsequence matching. In order to make the searches required for these operations as fast as possible, and to support the quantity of data we would like, all of the data will have to be well indexed. Indexing motion capture data is not a well studied problem. Existing techniques will have to be expanded upon to allow for the range of functionality in this system. The result of the project will be a tool that should reduce the amount of time spent gathering data in many motion applications, and will improve analysis of these applications by allowing greater cooperation and comparison between applications.

Progress

We have taken an intial stab at designing and implementing the database structure in PostgreSQL. We have built a basic interface and motion viewer to work with the database.

Research Support

This research is supported in part by a National Defense Science and Engineering Graduate Fellowship.