Predator video data includes both "live" feeds, and voice-annotated stored data

We envision many applications for collaboration involving video and speech data, e.g., the Atlanta bombing investigations involved many videos from various sources, with no good tools for collaboration/coordination

• Speech is combined with gesture: e.g., "track this"
• Speech is used for collaboration: e.g., "Marcia, look at this"
• Speech is used for freeform annotation: e.g., "I think this is a tank, but I'm not sure" to be used for later access via topic spotting technology

NEXT SLIDE

PREVIOUS SLIDE

RETURN TO STAR LAB HOME PAGE