An optimisation of Gaussian mixture models for integer processing units

作者：Salvadori Claudio^*; Petracca Matteo; del Rincon Jesus Martinez; Velastin Sergio A; Makris Dimitrios

来源：Journal of Real-Time Image Processing, 2017, 13(2): 273-289.

DOI：10.1007/s11554-014-0402-5

• Gaussian mixture model
• Smart-camera
• Computer arithmetic and integerimplementation
• Computer vision optimisation for microcontrollers
• Embedded systems

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. 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 generalized "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.

• 出版日期2017-6