Representing Actions of Objects in Intelligent Environments

A first step towards an understanding of the semantic content in a video is the reliable detection and recognition of actions performed by objects in the environment. This is a difficult problem due to the enormous variability in an action's appearance when seen from different viewpoints and/or at different times. In this paper we present a novel approach to representing actions that models actions as specific types of 3d objects. Specifically, we observe that any action can be represented as a generalized cylinder, called the action cylinder. Visualizing actions as objects allows rigid, articulated, and non-rigid actions to all be modeled in a uniform framework.