Skip to Main content Skip to Navigation
Journal articles

Quick and energy-efficient Bayesian computing of binocular disparity using stochastic digital signals

Alexandre Coninx 1, 2, * Pierre Bessière 1, 2 Jacques Droulez 1, 2
* Corresponding author
2 AMAC
ISIR - Institut des Systèmes Intelligents et de Robotique
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.
Document type :
Journal articles
Complete list of metadata

https://hal.sorbonne-universite.fr/hal-01398148
Contributor : Gestionnaire Hal-Upmc <>
Submitted on : Wednesday, November 16, 2016 - 5:35:18 PM
Last modification on : Friday, March 19, 2021 - 3:32:55 AM

Links full text

Identifiers

Citation

Alexandre Coninx, Pierre Bessière, Jacques Droulez. Quick and energy-efficient Bayesian computing of binocular disparity using stochastic digital signals. International Journal of Approximate Reasoning, Elsevier, 2016, ⟨10.1016/j.ijar.2016.11.004⟩. ⟨hal-01398148⟩

Share

Metrics

Record views

121