Learning methods for dynamic topic modeling in automated behaviour analysis

Olga Isupova, Danil Kuzin, Lyudmila Mihaylova

Research output: Contribution to journalArticlepeer-review

15 Citations (SciVal)

Abstract

Semisupervised and unsupervised systems provide operators with invaluable support and can tremendously reduce the operators' load. In the light of the necessity to process large volumes of video data and provide autonomous decisions, this paper proposes new learning algorithms for activity analysis in video. The activities and behaviors are described by a dynamic topic model. Two novel learning algorithms based on the expectation maximization approach and variational Bayes inference are proposed. Theoretical derivations of the posterior estimates of model parameters are given. The designed learning algorithms are compared with the Gibbs sampling inference scheme introduced earlier in the literature. A detailed comparison of the learning algorithms is presented on real video data. We also propose an anomaly localization procedure, elegantly embedded in the topic modeling framework. It is shown that the developed learning algorithms can achieve 95% success rate. The proposed framework can be applied to a number of areas, including transportation systems, security, and surveillance.
Original languageEnglish
Pages (from-to)3980 - 3993
Number of pages14
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume29
Issue number9
Early online date27 Sept 2017
DOIs
Publication statusPublished - 30 Sept 2018

Keywords

  • behaviour analysis
  • expectation maximisation
  • learning dynamic topic models
  • Unsupervised Learning
  • variational Bayesian approach
  • video analytics

Fingerprint

Dive into the research topics of 'Learning methods for dynamic topic modeling in automated behaviour analysis'. Together they form a unique fingerprint.

Cite this