Stereo integration, mean Field theory and psychophysics

Alan L. Yuille; Davi Geiger; Heinrich H. Bülthoff

doi:10.1088/0954-898X_2_4_006

Stereo integration, mean Field theory and psychophysics

Alan L. Yuille, Davi Geiger, Heinrich H. Bülthoff

Department of Brain and Cognitive Engineering

Research output: Contribution to journal › Article › peer-review

23 Citations (Scopus)

Abstract

We describe a theoretical formulation for stereo in terms of the Bayesian approach to vision and relates it to psychophysical experiments. The formulation enables us to integrate the depth information from different types of matching primitives, or from different vision modules. We solve the correspondence problem using compatibility constraints between features and prior assumptions on the interpolated surfaces that result from the matching. We use techniques from statistical physics to show how our theory relates to previous work. Finally we show that, by a suitable choice of prior assumptions about surfaces, the theory is consistent with some psychophysical experiments which investigate the relative importance of different matching primitives.

Original language	English
Pages (from-to)	423-442
Number of pages	20
Journal	Network: Computation in Neural Systems
Volume	2
Issue number	4
DOIs	https://doi.org/10.1088/0954-898X_2_4_006
Publication status	Published - 1991

Bibliographical note

Funding Information:
ALY would like to acknowledge support from the Brown/Halvard/MIT Center for Intelligent Control Systems with US Army Research Office grant DAAU)3-86-K-0171 and from DARPA with contract AFOSR-89-0506. HHB work at MlT was supported by the Office of Naval Research, Cognitive and Behavioural Sciences Division. Some of these ideas were initially developed with Mike Gennert We would like to thank Jini Clark, Manfred Fahle, Norbert0 Grzywacz, Stephan Mallat, David Mumford and lbmmy Poggio for many helpful discussions.

ASJC Scopus subject areas

Neuroscience (miscellaneous)

Access to Document

10.1088/0954-898X_2_4_006

Cite this

@article{d8c2de3bf4d24194a2b21e26f0498671,

title = "Stereo integration, mean Field theory and psychophysics",

abstract = "We describe a theoretical formulation for stereo in terms of the Bayesian approach to vision and relates it to psychophysical experiments. The formulation enables us to integrate the depth information from different types of matching primitives, or from different vision modules. We solve the correspondence problem using compatibility constraints between features and prior assumptions on the interpolated surfaces that result from the matching. We use techniques from statistical physics to show how our theory relates to previous work. Finally we show that, by a suitable choice of prior assumptions about surfaces, the theory is consistent with some psychophysical experiments which investigate the relative importance of different matching primitives.",

author = "Yuille, {Alan L.} and Davi Geiger and B{\"u}lthoff, {Heinrich H.}",

note = "Funding Information: ALY would like to acknowledge support from the Brown/Halvard/MIT Center for Intelligent Control Systems with US Army Research Office grant DAAU)3-86-K-0171 and from DARPA with contract AFOSR-89-0506. HHB work at MlT was supported by the Office of Naval Research, Cognitive and Behavioural Sciences Division. Some of these ideas were initially developed with Mike Gennert We would like to thank Jini Clark, Manfred Fahle, Norbert0 Grzywacz, Stephan Mallat, David Mumford and lbmmy Poggio for many helpful discussions.",

year = "1991",

doi = "10.1088/0954-898X_2_4_006",

language = "English",

volume = "2",

pages = "423--442",

journal = "Network: Computation in Neural Systems",

issn = "0954-898X",

publisher = "Informa Healthcare",

number = "4",

}

TY - JOUR

T1 - Stereo integration, mean Field theory and psychophysics

AU - Yuille, Alan L.

AU - Geiger, Davi

AU - Bülthoff, Heinrich H.

N1 - Funding Information: ALY would like to acknowledge support from the Brown/Halvard/MIT Center for Intelligent Control Systems with US Army Research Office grant DAAU)3-86-K-0171 and from DARPA with contract AFOSR-89-0506. HHB work at MlT was supported by the Office of Naval Research, Cognitive and Behavioural Sciences Division. Some of these ideas were initially developed with Mike Gennert We would like to thank Jini Clark, Manfred Fahle, Norbert0 Grzywacz, Stephan Mallat, David Mumford and lbmmy Poggio for many helpful discussions.

PY - 1991

Y1 - 1991

N2 - We describe a theoretical formulation for stereo in terms of the Bayesian approach to vision and relates it to psychophysical experiments. The formulation enables us to integrate the depth information from different types of matching primitives, or from different vision modules. We solve the correspondence problem using compatibility constraints between features and prior assumptions on the interpolated surfaces that result from the matching. We use techniques from statistical physics to show how our theory relates to previous work. Finally we show that, by a suitable choice of prior assumptions about surfaces, the theory is consistent with some psychophysical experiments which investigate the relative importance of different matching primitives.

AB - We describe a theoretical formulation for stereo in terms of the Bayesian approach to vision and relates it to psychophysical experiments. The formulation enables us to integrate the depth information from different types of matching primitives, or from different vision modules. We solve the correspondence problem using compatibility constraints between features and prior assumptions on the interpolated surfaces that result from the matching. We use techniques from statistical physics to show how our theory relates to previous work. Finally we show that, by a suitable choice of prior assumptions about surfaces, the theory is consistent with some psychophysical experiments which investigate the relative importance of different matching primitives.

UR - http://www.scopus.com/inward/record.url?scp=0010533260&partnerID=8YFLogxK

U2 - 10.1088/0954-898X_2_4_006

DO - 10.1088/0954-898X_2_4_006

M3 - Article

AN - SCOPUS:0010533260

SN - 0954-898X

VL - 2

SP - 423

EP - 442

JO - Network: Computation in Neural Systems

JF - Network: Computation in Neural Systems

IS - 4

ER -

Stereo integration, mean Field theory and psychophysics

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this