A Noise-Driven Paradigm for Solving the Stereo Correspondence Problem

Author(s):  
Patrice Delmas ◽  
Georgy Gimel’farb ◽  
Jiang Liu ◽  
John Morris
2016 ◽  
Vol 371 (1697) ◽  
pp. 20150255 ◽  
Author(s):  
Sid Henriksen ◽  
Seiji Tanabe ◽  
Bruce Cumming

The first step in binocular stereopsis is to match features on the left retina with the correct features on the right retina, discarding ‘false’ matches. The physiological processing of these signals starts in the primary visual cortex, where the binocular energy model has been a powerful framework for understanding the underlying computation. For this reason, it is often used when thinking about how binocular matching might be performed beyond striate cortex. But this step depends critically on the accuracy of the model, and real V1 neurons show several properties that suggest they may be less sensitive to false matches than the energy model predicts. Several recent studies provide empirical support for an extended version of the energy model, in which the same principles are used, but the responses of single neurons are described as the sum of several subunits, each of which follows the principles of the energy model. These studies have significantly improved our understanding of the role played by striate cortex in the stereo correspondence problem. This article is part of the themed issue ‘Vision in our three-dimensional world’.


2005 ◽  
Vol 65 (3) ◽  
pp. 147-162 ◽  
Author(s):  
Abhijit S. Ogale ◽  
Yiannis Aloimonos

2002 ◽  
Vol 14 (6) ◽  
pp. 1371-1392 ◽  
Author(s):  
Jenny C. A. Read

I present a probabilistic approach to the stereo correspondence problem. Rather than trying to find a single solution in which each point in the left retina is assigned a partner in the right retina, all possible matches are considered simultaneously and assigned a probability of being correct. This approach is particularly suitable for stimuli where it is inappropriate to seek a unique partner for each retinal position—for instance, where objects occlude each other, as in Panum's limiting case. The probability assigned to each match is based on a Bayesian analysis previously developed to explain psychophysical data (Read, 2002). This provides a convenient way to incorporate constraints that enable the ill-posed correspondence problem to be solved. The resulting model behaves plausibly for a variety of different stimuli.


2017 ◽  
Vol 7 (1) ◽  
Author(s):  
Marc Osswald ◽  
Sio-Hoi Ieng ◽  
Ryad Benosman ◽  
Giacomo Indiveri

Abstract Stereo vision is an important feature that enables machine vision systems to perceive their environment in 3D. While machine vision has spawned a variety of software algorithms to solve the stereo-correspondence problem, their implementation and integration in small, fast, and efficient hardware vision systems remains a difficult challenge. Recent advances made in neuromorphic engineering offer a possible solution to this problem, with the use of a new class of event-based vision sensors and neural processing devices inspired by the organizing principles of the brain. Here we propose a radically novel model that solves the stereo-correspondence problem with a spiking neural network that can be directly implemented with massively parallel, compact, low-latency and low-power neuromorphic engineering devices. We validate the model with experimental results, highlighting features that are in agreement with both computational neuroscience stereo vision theories and experimental findings. We demonstrate its features with a prototype neuromorphic hardware system and provide testable predictions on the role of spike-based representations and temporal dynamics in biological stereo vision processing systems.


Author(s):  
Neil D. B. Bruce ◽  
John K. Tsotsos

The stereo correspondence problem is a topic that has been the subject of considerable research effort. What has not yet been considered is an analogue of stereo correspondence in the domain of attention. In this chapter, the authors bring this problem to light, revealing important implications for computational models of attention, and in particular, how these implications constrain the problem of computational modeling of attention. A model is described which addresses attention in the stereo domain, and it is revealed that a variety of behaviors observed in binocular rivalry experiments are consistent with the model’s behavior. Finally, the authors consider how constraints imposed by stereo vision may suggest analogous constraints in other non-stereo feature domains with significant consequence to computational models of attention.


Neuron ◽  
2003 ◽  
Vol 37 (4) ◽  
pp. 693-701 ◽  
Author(s):  
Peter Janssen ◽  
Rufin Vogels ◽  
Yan Liu ◽  
Guy A Orban

Sign in / Sign up

Export Citation Format

Share Document