Integration of vision modules and labeling of surface discontinuities

Edward B. Gamble, Davi Geiger, Tomaso Poggio, Daphna Weinshall

Research output: Contribution to journalArticle

Abstract

It is assumed that a major goal of the early vision modules and their integration is to deliver a cartoon of the discontinuities in the scene and to label them in terms of their physical origin. The output of each of the vision modules is noisy, possibly sparse, and sometimes not unique. The authors suggest the use of a coupled Markov random field (MRF) at the output of each module (image cues)--stereo, motion, color, and texture--to achieve two goals: first, to counteract the noise and fill in sparse data and, second, to integrate the image within each MRF to find the module discontinuities and align them with the intensity edges. The authors outline a theory of how to label the discontinuities in terms of depth, orientation, albedo, illumination, and specular discontinuities. They present labeling results using a simple linear classifier operating on the output of the MRF associated with each vision module and coupled to the image data. The classifier has been trained on a small set of a mixture of synthetic and real data.

Original languageEnglish (US)
Pages (from-to)1576-1581
Number of pages6
JournalIEEE Transactions on Systems, Man and Cybernetics
Volume19
Issue number6
DOIs
StatePublished - Nov 1989

Fingerprint

Labeling
Labels
Classifiers
Textures
Lighting
Color

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Integration of vision modules and labeling of surface discontinuities. / Gamble, Edward B.; Geiger, Davi; Poggio, Tomaso; Weinshall, Daphna.

In: IEEE Transactions on Systems, Man and Cybernetics, Vol. 19, No. 6, 11.1989, p. 1576-1581.

Research output: Contribution to journalArticle

Gamble, Edward B. ; Geiger, Davi ; Poggio, Tomaso ; Weinshall, Daphna. / Integration of vision modules and labeling of surface discontinuities. In: IEEE Transactions on Systems, Man and Cybernetics. 1989 ; Vol. 19, No. 6. pp. 1576-1581.
@article{6c7869d41364406aa2ab82b7953173bb,
title = "Integration of vision modules and labeling of surface discontinuities",
abstract = "It is assumed that a major goal of the early vision modules and their integration is to deliver a cartoon of the discontinuities in the scene and to label them in terms of their physical origin. The output of each of the vision modules is noisy, possibly sparse, and sometimes not unique. The authors suggest the use of a coupled Markov random field (MRF) at the output of each module (image cues)--stereo, motion, color, and texture--to achieve two goals: first, to counteract the noise and fill in sparse data and, second, to integrate the image within each MRF to find the module discontinuities and align them with the intensity edges. The authors outline a theory of how to label the discontinuities in terms of depth, orientation, albedo, illumination, and specular discontinuities. They present labeling results using a simple linear classifier operating on the output of the MRF associated with each vision module and coupled to the image data. The classifier has been trained on a small set of a mixture of synthetic and real data.",
author = "Gamble, {Edward B.} and Davi Geiger and Tomaso Poggio and Daphna Weinshall",
year = "1989",
month = "11",
doi = "10.1109/21.44072",
language = "English (US)",
volume = "19",
pages = "1576--1581",
journal = "IEEE Transactions on Systems, Man and Cybernetics",
issn = "0018-9472",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Integration of vision modules and labeling of surface discontinuities

AU - Gamble, Edward B.

AU - Geiger, Davi

AU - Poggio, Tomaso

AU - Weinshall, Daphna

PY - 1989/11

Y1 - 1989/11

N2 - It is assumed that a major goal of the early vision modules and their integration is to deliver a cartoon of the discontinuities in the scene and to label them in terms of their physical origin. The output of each of the vision modules is noisy, possibly sparse, and sometimes not unique. The authors suggest the use of a coupled Markov random field (MRF) at the output of each module (image cues)--stereo, motion, color, and texture--to achieve two goals: first, to counteract the noise and fill in sparse data and, second, to integrate the image within each MRF to find the module discontinuities and align them with the intensity edges. The authors outline a theory of how to label the discontinuities in terms of depth, orientation, albedo, illumination, and specular discontinuities. They present labeling results using a simple linear classifier operating on the output of the MRF associated with each vision module and coupled to the image data. The classifier has been trained on a small set of a mixture of synthetic and real data.

AB - It is assumed that a major goal of the early vision modules and their integration is to deliver a cartoon of the discontinuities in the scene and to label them in terms of their physical origin. The output of each of the vision modules is noisy, possibly sparse, and sometimes not unique. The authors suggest the use of a coupled Markov random field (MRF) at the output of each module (image cues)--stereo, motion, color, and texture--to achieve two goals: first, to counteract the noise and fill in sparse data and, second, to integrate the image within each MRF to find the module discontinuities and align them with the intensity edges. The authors outline a theory of how to label the discontinuities in terms of depth, orientation, albedo, illumination, and specular discontinuities. They present labeling results using a simple linear classifier operating on the output of the MRF associated with each vision module and coupled to the image data. The classifier has been trained on a small set of a mixture of synthetic and real data.

UR - http://www.scopus.com/inward/record.url?scp=0024768636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024768636&partnerID=8YFLogxK

U2 - 10.1109/21.44072

DO - 10.1109/21.44072

M3 - Article

AN - SCOPUS:0024768636

VL - 19

SP - 1576

EP - 1581

JO - IEEE Transactions on Systems, Man and Cybernetics

JF - IEEE Transactions on Systems, Man and Cybernetics

SN - 0018-9472

IS - 6

ER -