Skip to main content

Infinite hidden Markov models for unusual-event detection in video.

Publication ,  Journal Article
Pruteanu-Malinici, I; Carin, L
Published in: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
May 2008

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.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

DOI

EISSN

1941-0042

ISSN

1057-7149

Publication Date

May 2008

Volume

17

Issue

5

Start / End Page

811 / 822

Related Subject Headings

  • Video Recording
  • Subtraction Technique
  • Sensitivity and Specificity
  • Reproducibility of Results
  • Pattern Recognition, Automated
  • Models, Statistical
  • Markov Chains
  • Information Storage and Retrieval
  • Image Interpretation, Computer-Assisted
  • Image Enhancement
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Pruteanu-Malinici, I., & Carin, L. (2008). Infinite hidden Markov models for unusual-event detection in video. IEEE Transactions on Image Processing : A Publication of the IEEE Signal Processing Society, 17(5), 811–822. https://doi.org/10.1109/tip.2008.919359
Pruteanu-Malinici, Iulian, and Lawrence Carin. “Infinite hidden Markov models for unusual-event detection in video.IEEE Transactions on Image Processing : A Publication of the IEEE Signal Processing Society 17, no. 5 (May 2008): 811–22. https://doi.org/10.1109/tip.2008.919359.
Pruteanu-Malinici I, Carin L. Infinite hidden Markov models for unusual-event detection in video. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2008 May;17(5):811–22.
Pruteanu-Malinici, Iulian, and Lawrence Carin. “Infinite hidden Markov models for unusual-event detection in video.IEEE Transactions on Image Processing : A Publication of the IEEE Signal Processing Society, vol. 17, no. 5, May 2008, pp. 811–22. Epmc, doi:10.1109/tip.2008.919359.
Pruteanu-Malinici I, Carin L. Infinite hidden Markov models for unusual-event detection in video. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2008 May;17(5):811–822.

Published In

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

DOI

EISSN

1941-0042

ISSN

1057-7149

Publication Date

May 2008

Volume

17

Issue

5

Start / End Page

811 / 822

Related Subject Headings

  • Video Recording
  • Subtraction Technique
  • Sensitivity and Specificity
  • Reproducibility of Results
  • Pattern Recognition, Automated
  • Models, Statistical
  • Markov Chains
  • Information Storage and Retrieval
  • Image Interpretation, Computer-Assisted
  • Image Enhancement