Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
5
pubmed:dateCreated
2008-4-8
pubmed:abstractText
We address the problem of unusual-event detection in a video sequence. Invariant subspace analysis (ISA) is used to extract features from the video, and the time-evolving properties of these features are modeled via an infinite hidden Markov model (iHMM), which is trained using "normal"/"typical" video. The iHMM retains a full posterior density function on all model parameters, including the number of underlying HMM states. Anomalies (unusual events) are detected subsequently if a low likelihood is observed when associated sequential features are submitted to the trained iHMM. A hierarchical Dirichlet process framework is employed in the formulation of the iHMM. The evaluation of posterior distributions for the iHMM is achieved in two ways: via Markov chain Monte Carlo and using a variational Bayes formulation. Comparisons are made to modeling based on conventional maximum-likelihood-based HMMs, as well as to Dirichlet-process-based Gaussian-mixture models.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:month
May
pubmed:issn
1057-7149
pubmed:author
pubmed:issnType
Print
pubmed:volume
17
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
811-22
pubmed:meshHeading
pubmed:year
2008
pubmed:articleTitle
Infinite hidden Markov models for unusual-event detection in video.
pubmed:affiliation
Electrical and Computer Engineering Department, Duke University, Durham, NC 27708-0291, USA. ip6@ee.duke.edu
pubmed:publicationType
Journal Article, Evaluation Studies