Recognizing Action Events from Multiple Viewpoints

A first step towards an understanding of the semantic content in a video is the reliable detection and recognition of actions performed by objects. This is a dificult problem due to the enormous vaeability in an action's appearance when seen from different viewpoints and/or at different times. In this paper we address the recognition of actions by taking a novel approach that models actions as special types of 3d objects. Specifically, we observe that any action can be represented as a generalized cylinder, called the action cylinder. Reliable recognition is achieved by recovering the viewpoint transformation between reference (model) and given action cylinders. A set of 8 corresponding points from time-wise corresponding cross-sections is shown to be suficient to align the two cylinders under perspective projection. A surprising conclusion from visualizing actions as objects i s that rigid, articulated, and nonrigid actions can all be modeled an a uniform framework.

• Type: Conference
• Year: 2001
• Where: EVENT
• Authors: Tanveer Fathima Syeda-Mahmood, M. Alex O. Vasilescu, Saratendu Sethi
• Keywords: Action Cylinders, EVENT 2001, Reliable Detection, Time-wise Corresponding Cross-sections