Paper Info
Title
Quick and energy-efficient Bayesian computing of binocular disparity using stochastic digital signals.
Abstract
Reconstruction of the tridimensional geometry of a visual scene using the binocular disparity information is an important issue in computer vision and mobile robotics, which can be formulated as a Bayesian inference problem. However, computation of the full disparity distribution with an advanced Bayesian model is usually an intractable problem, and proves computationally challenging even with a simple model. In this paper, we show how probabilistic hardware using distributed memory and alternate representation of data as stochastic bitstreams can solve that problem with high performance and energy efficiency. We put forward a way to express discrete probability distributions using stochastic data representations and perform Bayesian fusion using those representations, and show how that approach can be applied to diparity computation. We evaluate the system using a simulated stochastic implementation and discuss possible hardware implementations of such architectures and their potential for sensorimotor processing and robotics. A computing architecture using stochastic bitstreams solves Bayesian fusion problems.An application to binocular disparity computation is proposed and evaluated.Simulated implementation shows high performance and energy efficiency.New nanocomponents generating random bitstreams will allow hardware implementation.The same approach will be applied to other Bayesian sensorimotor problems.
Year
DOI
Venue
2017
10.1016/j.ijar.2016.11.004
Int. J. Approx. Reasoning
Keywords
DocType
Volume
Bayesian inference,Stochastic computing,Sensory processing,Energy efficiency,Hardware implementation,Binocular disparity
Journal
abs/1609.04337
Issue
ISSN
Citations 
C
0888-613X
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Alexandre Coninx1276.95
Pierre Bessière242586.40
Jacques Droulez312115.77