An optimisation of Gaussian mixture models for integer processing units

Claudio Salvadori, Matteo Petracca, Jesus Martinez del Rincon, Sergio A. Velastin, Dimitrios Makris

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)
494 Downloads (Pure)

Abstract

This paper investigates sub-integer implementations of the adaptive Gaussian mixture model (GMM) for background/foreground segmentation to allow the deployment of the method on low cost/low power processors that lack Floating Point Unit (FPU). We propose two novel integer computer arithmetic techniques to update Gaussian parameters. Specifically, the mean value and the variance of each Gaussian are updated by a redefined and generalised "round'' operation that emulates the original updating rules for a large set of learning rates. Weights are represented by counters that are updated following stochastic rules to allow a wider range of learning rates and the weight trend is approximated by a line or a staircase. We demonstrate that the memory footprint and computational cost of GMM are significantly reduced, without significantly affecting the performance of background/foreground segmentation.
Original languageEnglish
Number of pages17
JournalJournal of Real-Time Image Processing
Early online date08 Feb 2014
DOIs
Publication statusPublished - Feb 2014

ASJC Scopus subject areas

  • Information Systems

Fingerprint

Dive into the research topics of 'An optimisation of Gaussian mixture models for integer processing units'. Together they form a unique fingerprint.

Cite this