Adam Cheyer

MVIEWS: multimodal tools for the video analyst

Full-motion video has inherent advantages over still imagery for characterizing events and movement. Military and intelligence analysts currently view live video imagery from airborne and ground-based video platforms, but few tools exist for efficient exploitation of the video and its accompanying metadata. In pursuit of this goal, SRI has developed MVIEWS, a system for annotating, indexing, extracting, and disseminating information from video streams for surveillance and intelligence applications. MVIEWS is implemented within the Open Agent Architecture, a distributed multiagent framework that enables rapid integration of component technologies; for MVIEWS, these technologies include pen and voice recognition and interpretation, image processing and object tracking, geo-referenced interactive maps, multimedia databases, and human collaborative tools.

Virtual spaces revive real world interaction

As virtual spaces become more realistic, researchers are experimenting with new perspectives for interactions with such environments. Based on several prototypes that explore augmented and virtual reality as well as dialogs with lifelike computer characters, we discuss in this chapter future directions for virtual environment interfaces that look back to the “good old ways” of working in the real world: talking, gesturing, moving, drawing and so forth.