Occlusions and binocular stereo

Davi Geiger, Bruce Ladendorf, Alan Yuille

Research output: Contribution to journalArticle

Abstract

Binocular stereo is the process of obtaining depth information from a pair of cameras. In the past, stereo algorithms have had problems at occlusions and have tended to fail there (though sometimes post-processing has been added to mitigate the worst effects). We show that, on the contrary, occlusions can help stereo computation by providing cues for depth discontinuities. We describe a theory for stereo based on the Bayesian approach, using adaptive windows and a prior weak smoothness constraint, which incorporates occlusion. Our model assumes that a disparity discontinuity, along the epipolar line, in one eye always corresponds to an occluded region in the other eye thus, leading to an occlusion constraint. This constraint restricts the space of possible disparity values, thereby simplifying the computations. An estimation of the disparity at occluded features is also discussed in light of psychophysical experiments. Using dynamic programming we can find the optimal solution to our system and the experimental results are good and support the assumptions made by the model.

Original languageEnglish (US)
Pages (from-to)211-226
Number of pages16
JournalInternational Journal of Computer Vision
Volume14
Issue number3
DOIs
StatePublished - Apr 1995

Fingerprint

Binoculars
Dynamic programming
Cameras
Processing
Experiments

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Occlusions and binocular stereo. / Geiger, Davi; Ladendorf, Bruce; Yuille, Alan.

In: International Journal of Computer Vision, Vol. 14, No. 3, 04.1995, p. 211-226.

Research output: Contribution to journalArticle

Geiger, Davi ; Ladendorf, Bruce ; Yuille, Alan. / Occlusions and binocular stereo. In: International Journal of Computer Vision. 1995 ; Vol. 14, No. 3. pp. 211-226.
@article{ae6e369a4cab468c907378612e990e61,
title = "Occlusions and binocular stereo",
abstract = "Binocular stereo is the process of obtaining depth information from a pair of cameras. In the past, stereo algorithms have had problems at occlusions and have tended to fail there (though sometimes post-processing has been added to mitigate the worst effects). We show that, on the contrary, occlusions can help stereo computation by providing cues for depth discontinuities. We describe a theory for stereo based on the Bayesian approach, using adaptive windows and a prior weak smoothness constraint, which incorporates occlusion. Our model assumes that a disparity discontinuity, along the epipolar line, in one eye always corresponds to an occluded region in the other eye thus, leading to an occlusion constraint. This constraint restricts the space of possible disparity values, thereby simplifying the computations. An estimation of the disparity at occluded features is also discussed in light of psychophysical experiments. Using dynamic programming we can find the optimal solution to our system and the experimental results are good and support the assumptions made by the model.",
author = "Davi Geiger and Bruce Ladendorf and Alan Yuille",
year = "1995",
month = "4",
doi = "10.1007/BF01679683",
language = "English (US)",
volume = "14",
pages = "211--226",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Occlusions and binocular stereo

AU - Geiger, Davi

AU - Ladendorf, Bruce

AU - Yuille, Alan

PY - 1995/4

Y1 - 1995/4

N2 - Binocular stereo is the process of obtaining depth information from a pair of cameras. In the past, stereo algorithms have had problems at occlusions and have tended to fail there (though sometimes post-processing has been added to mitigate the worst effects). We show that, on the contrary, occlusions can help stereo computation by providing cues for depth discontinuities. We describe a theory for stereo based on the Bayesian approach, using adaptive windows and a prior weak smoothness constraint, which incorporates occlusion. Our model assumes that a disparity discontinuity, along the epipolar line, in one eye always corresponds to an occluded region in the other eye thus, leading to an occlusion constraint. This constraint restricts the space of possible disparity values, thereby simplifying the computations. An estimation of the disparity at occluded features is also discussed in light of psychophysical experiments. Using dynamic programming we can find the optimal solution to our system and the experimental results are good and support the assumptions made by the model.

AB - Binocular stereo is the process of obtaining depth information from a pair of cameras. In the past, stereo algorithms have had problems at occlusions and have tended to fail there (though sometimes post-processing has been added to mitigate the worst effects). We show that, on the contrary, occlusions can help stereo computation by providing cues for depth discontinuities. We describe a theory for stereo based on the Bayesian approach, using adaptive windows and a prior weak smoothness constraint, which incorporates occlusion. Our model assumes that a disparity discontinuity, along the epipolar line, in one eye always corresponds to an occluded region in the other eye thus, leading to an occlusion constraint. This constraint restricts the space of possible disparity values, thereby simplifying the computations. An estimation of the disparity at occluded features is also discussed in light of psychophysical experiments. Using dynamic programming we can find the optimal solution to our system and the experimental results are good and support the assumptions made by the model.

UR - http://www.scopus.com/inward/record.url?scp=0029288203&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029288203&partnerID=8YFLogxK

U2 - 10.1007/BF01679683

DO - 10.1007/BF01679683

M3 - Article

AN - SCOPUS:0029288203

VL - 14

SP - 211

EP - 226

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 3

ER -