Communicating with a Camera in a Public Space via Persistent Gesture

Public cameras are ubiquitous in the 21st century with tens of thousands in many major cities and roadways. Currently these are used unilaterally for viewing only - there is no means for reciprocal communications. We propose that public camera networks will evolve toward hosting multiple tasks, and some of these will require interactivity. However, interactive communication in a public space with many people and other motion poses challenges to video communication via gesture. We examine categories of gesture and choose "persistent" gesture, repeated motion over time, to be the most appropriate. We describe and test three methods for detecting persistent gesture from a camera in a public space, and discuss results of the tradeoff between gesture recognition and duration of gesture.