Visual recognition of multi-agent action using binary temporal relations

Author

Intille, Stephen S. ; Bobick, Aaron F.

Author_Institution

Perceptual Comput. Group, MIT, Cambridge, MA, USA

Volume

1

fYear

1999

fDate

1999

Abstract

A probabilistic framework for representing and visually recognizing complex multi-agent action is presented. Motivated by work in model-based object recognition and designed for the recognition of action from visual evidence, the representation has three components: (1) temporal structure descriptions representing the temporal relationships between agent goals, (2) belief networks for probabilistically representing and recognizing individual agent goals from visual evidence, and (3) belief networks automatically generated from the temporal structure descriptions that support the recognition of the complex action. We describe our current work on recognizing American football plays from noisy trajectory data

Keywords

belief networks; motion estimation; multi-agent systems; object recognition; belief networks; binary temporal relations; model-based object recognition; motion understanding; multi-agent action; multi-agent action recognition; plan recognition; probabilistic framework; temporal structure descriptions; Computer vision; Contracts; Laboratories; Large-scale systems; Marine vehicles; Object recognition; Research and development; Surveillance; Trajectory; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on.

Conference_Location

Fort Collins, CO

ISSN

1063-6919

Print_ISBN

0-7695-0149-4

Type

conf

DOI

10.1109/CVPR.1999.786917

Filename

786917