Scenario recognition from video using a hierarchy of Dynamic Belief Networks

Douglas Ayers; Rama Chellappa

Scenario recognition from video using a hierarchy of Dynamic Belief Networks

Research output: Contribution to journal › Article › peer-review

Abstract

Interpreting video is a challenging problem in Computer Vision with promising applications, such as video surveillance and indexing. The focus of this paper is determining if a scenario occurs in a video taken from a moving airplane. Our paradigm for scenario recognition uses Dynamic Belief Networks (DBNs) in a hierarchical fashion. DBNs provide a method for propagating statistical information over time. Larger scenarios are made up of smaller scenarios and actions. DBNs are ideal for situations where prior knowledge is available about the scenarios of interest. This prior knowledge is encoded in the structure of the network. The statistical parameters of the network can either be specified by the user or learned from input sequences.

Original language	English (US)
Pages (from-to)	835-837
Number of pages	3
Journal	Proceedings - International Conference on Pattern Recognition
Volume	15
Issue number	1
State	Published - 2000
Externally published	Yes

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Cite this

@article{0b2b645f81414876855f8afe51708b55,

title = "Scenario recognition from video using a hierarchy of Dynamic Belief Networks",

abstract = "Interpreting video is a challenging problem in Computer Vision with promising applications, such as video surveillance and indexing. The focus of this paper is determining if a scenario occurs in a video taken from a moving airplane. Our paradigm for scenario recognition uses Dynamic Belief Networks (DBNs) in a hierarchical fashion. DBNs provide a method for propagating statistical information over time. Larger scenarios are made up of smaller scenarios and actions. DBNs are ideal for situations where prior knowledge is available about the scenarios of interest. This prior knowledge is encoded in the structure of the network. The statistical parameters of the network can either be specified by the user or learned from input sequences.",

author = "Douglas Ayers and Rama Chellappa",

note = "Funding Information: 'The support of the Defense Advanced Research Agency and the Army Night Vision Laboratory under contract DAAB07-98-C-J019 to SRI International is greatfully acknowledged.",

year = "2000",

language = "English (US)",

volume = "15",

pages = "835--837",

journal = "Proceedings - International Conference on Pattern Recognition",

issn = "1051-4651",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - Scenario recognition from video using a hierarchy of Dynamic Belief Networks

AU - Ayers, Douglas

AU - Chellappa, Rama

N1 - Funding Information: 'The support of the Defense Advanced Research Agency and the Army Night Vision Laboratory under contract DAAB07-98-C-J019 to SRI International is greatfully acknowledged.

PY - 2000

Y1 - 2000

N2 - Interpreting video is a challenging problem in Computer Vision with promising applications, such as video surveillance and indexing. The focus of this paper is determining if a scenario occurs in a video taken from a moving airplane. Our paradigm for scenario recognition uses Dynamic Belief Networks (DBNs) in a hierarchical fashion. DBNs provide a method for propagating statistical information over time. Larger scenarios are made up of smaller scenarios and actions. DBNs are ideal for situations where prior knowledge is available about the scenarios of interest. This prior knowledge is encoded in the structure of the network. The statistical parameters of the network can either be specified by the user or learned from input sequences.

AB - Interpreting video is a challenging problem in Computer Vision with promising applications, such as video surveillance and indexing. The focus of this paper is determining if a scenario occurs in a video taken from a moving airplane. Our paradigm for scenario recognition uses Dynamic Belief Networks (DBNs) in a hierarchical fashion. DBNs provide a method for propagating statistical information over time. Larger scenarios are made up of smaller scenarios and actions. DBNs are ideal for situations where prior knowledge is available about the scenarios of interest. This prior knowledge is encoded in the structure of the network. The statistical parameters of the network can either be specified by the user or learned from input sequences.

UR - http://www.scopus.com/inward/record.url?scp=33750966283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750966283&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:33750966283

SN - 1051-4651

VL - 15

SP - 835

EP - 837

JO - Proceedings - International Conference on Pattern Recognition

JF - Proceedings - International Conference on Pattern Recognition

IS - 1

ER -

Scenario recognition from video using a hierarchy of Dynamic Belief Networks

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this