Show simple item record

dc.contributor.advisorAaron F. Bobick.en_US
dc.contributor.authorIntille, Stephen S. (Stephen Sean)en_US
dc.contributor.otherMassachusetts Institute of Technology. Dept. of Architecture. Program in Media Arts and Sciences.en_US
dc.date.accessioned2005-08-22T20:41:53Z
dc.date.available2005-08-22T20:41:53Z
dc.date.copyright1999en_US
dc.date.issued1999en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/9374
dc.descriptionThesis (Ph.D.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 1999.en_US
dc.descriptionIncludes bibliographical references (p. 167-184).en_US
dc.description.abstractDeveloping computer vision sensing systems that work robustly in everyday environments will require that the systems can recognize structured interaction between people and objects in the world. This document presents a new theory for the representation and recognition of coordinated multi-agent action from noisy perceptual data. The thesis of this work is as follows: highly structured, multi-agent action can be recognized from noisy perceptual data using visually grounded goal-based primitives and low-order temporal relationships that are integrated in a probabilistic framework. The theory is developed and evaluated by examining general characteristics of multi-agent action, analyzing tradeoffs involved when selecting a representation for multi-agent action recognition, and constructing a system to recognize multi-agent action for a real task from noisy data. The representation, which is motivated by work in model-based object recognition and probabilistic plan recognition, makes four principal assumptions: (1) the goals of individual agents are natural atomic representational units for specifying the temporal relationships between agents engaged in group activities, (2) a high-level description of temporal structure of the action using a small set of low-order temporal and logical constraints is adequate for representing the relationships between the agent goals for highly structured, multi-agent action recognition, (3) Bayesian networks provide a suitable mechanism for integrating multiple sources of uncertain visual perceptual feature evidence, and (4) an automatically generated Bayesian network can be used to combine uncertain temporal information and compute the likelihood that a set of object trajectory data is a particular multi-agent action. The recognition algorithm is tested using a database of American football play descriptions. A system is described that can recognize single-agent and multi-agent actions in this domain given noisy trajectories of object movements. The strengths and limitations of the recognition system are discussed and compared with other multi-agent recognition algorithms.en_US
dc.description.statementofresponsibilityby Stephen Sean Intille.en_US
dc.format.extent237 p.en_US
dc.format.extent23167653 bytes
dc.format.extent23167410 bytes
dc.format.mimetypeapplication/pdf
dc.format.mimetypeapplication/pdf
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsM.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582
dc.subjectArchitecture. Program in Media Arts and Sciences.en_US
dc.titleVisual recognition of multi-agent actionen_US
dc.typeThesisen_US
dc.description.degreePh.D.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Dept. of Architecture. Program in Media Arts and Sciences.en_US
dc.identifier.oclc44815054en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record