Subtasks are calibration-free augmented view generation (Task 1), context-based predictive tracking (Task 2),, and activity recognition (Task 3).
The base research of the proposed FRE centers around Task 4: an integrated view augmentation and control capability using graphic augmentation of live video streams (e.g., annotations, graphical models of hidden structures, graphical depictions of recognized activities). The ultimate goal is to integrate the contributions in video augmentation, tracking, activity recognition, and deictic control into an interactive command and observation center and two cooperating VSAM surrogates with complementary video analysis and control capabilities.
On To Next Task
Up to Main Page
This page is maintained by Mike Van Wie.
Last update: 11/11/96.