Tracking the untracked
This addresses the challenge of user tracking continuity in motion capture systems, but it appears incremental as it builds on existing tracking data without introducing a new paradigm.
The paper tackles the problem of seamlessly identifying and maintaining continuous tracking history for users in real-time optical position tracking systems like OptiTrack, presenting a theoretical framework that integrates existing tracking data with user identification and activity history for up to 'n' persons.
The issue of seamless identification of users previously tracked using existing real-time optical position tracking system such as the OptiTrack system and maintaining continuous tracking state (history) of each of those users is a hard problem. In this article, we present a theoretical framework to integrate existing tracking systems with features such as user identification and history of up to `n' person activity. In our approach, we assume no direct communication with the tracking system, but access to all data it collects. Also, there are no guarantees that 1) the order of each tracked retro-reflective sphere reported is the same, and 2) that there will be any particular number of spheres in the room at any given time. We describe how the data is fused with existing tracking data to provide a seamless transition between other forms of position tracking.