Stuart Ross pointed me to an article in National Geographic that paints a picture of next generation surveillance systems using audio and video. It points out how emerging technology could do more effective surveillance using audio and dideo analysis techniques that are already being developed — of course it takes long time from inception in advanced labs to practice. A part that I liked is
Video and audio provide some data that can’t be gleaned from text-only communications or transcripts of conversations, Arizona’s Meservy said.
For instance, numerous pauses or other “disfluencies” may indicate that a person is “managing a greater cognitive load,” he said. The speaker could be halting because he or she is making up the story as he or she goes along.
Good motivation to address new problems in audio and video analysis and a good lesson to video database systems that believe that speech and hence automatic speech recognition is sufficient to deal with video and audio. Non verbal communication among humans is often more important than verbal — we all know this instictively. Don’t we?