Gaussian Mixture Background Modelling Optimisation for Micro-controllers
This work 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 computer integer arithmetics 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.
C. Salvadori, D. Makris, M. Petracca, J. Martinez del Rincon, and S. A. Velastin. Gaussian mixture background modelling optimisation for micro-controllers. In Advances in
Visual Computing, volume 7431 of Lecture Notes in Computer Science, pages 241–251. Springer Berlin Heidelberg, 2012.
Demo video using "IXMAS" dataset:
Demo video using "Fudan Pedestrian" dataset: