Fast Convergence of Regularised Region-based Mixture of Gaussians for Dynamic Background Modelling

Sriram Varadarajan, Hongbin Wang, Paul Miller, Huiyu Zhou

Research output: Contribution to journalArticle

16 Citations (Scopus)
320 Downloads (Pure)

Abstract

The momentum term has long been used in machine learning algorithms, especially back-propagation, to improve their speed of convergence. In this paper, we derive an expression to prove the O(1/k2) convergence rate of the online gradient method, with momentum type updates, when the individual gradients are constrained by a growth condition. We then apply these type of updates to video background modelling by using it in the update equations of the Region-based Mixture of Gaussians algorithm. Extensive evaluations are performed on both simulated data, as well as challenging real world scenarios with dynamic backgrounds, to show that these regularised updates help the mixtures converge faster than the conventional approach and consequently improve the algorithm’s performance.
Original languageEnglish
Pages (from-to)45-58
Number of pages14
JournalComputer Vision and Image Understanding
Volume136
Early online date08 Jan 2015
DOIs
Publication statusPublished - Jul 2015

Fingerprint Dive into the research topics of 'Fast Convergence of Regularised Region-based Mixture of Gaussians for Dynamic Background Modelling'. Together they form a unique fingerprint.

  • Cite this