Kinect crowd interaction

Most of the state-of-the-art commercial simulation software mainly focuses on providing realistic animations and convincing artificial intelligence to avatars in the scenario. However, works on how to trigger the events and avatar reactions in the scenario in a natural and intuitive way are less noticed and developed. Typical events are usually triggered by predefined timestamps. Once the events are set, there is no easy way to interactively generate new events while the scene is running and therefore difficult to dynamically affect the avatar reactions. Based on this situation, we propose a framework to use human gesture as input to trigger events within a DI-Guy simulation scenario in real-time, which could greatly help users to control events and avatar reactions in the scenario. By implementing such a framework, we will be able to identify user’s intentions interactively and ensure that the avatars make corresponding reactions.