Direct motion stereo

Recovery of observer motion and scene structure

Brian Y. Hayashi, Shahriar Negahdaripour

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Using a stereo vision system, the authors show how the translational motion and scene structure can be recovered directly from image gradients and time derivatives. There is no need to estimate or establish correspondences between features across images. The direction of motion is recovered using a procedure which involves minimizing the sum of the squared error of a linear constraint equation over the entire image. The magnitude of the motion is estimated from the stereo disparity. The scene structure is recovered in the form of a depth map using the recovered motion, image gradients, and time derivatives. Experimental results using real images are presented.

Original languageEnglish
Title of host publicationUnknown Host Publication Title
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages446-450
Number of pages5
ISBN (Print)0818620579
StatePublished - Dec 1 1990
Externally publishedYes
EventProceedings 3rd International Conference on Computer Vision - Osaka, Jpn
Duration: Dec 4 1990Dec 7 1990

Other

OtherProceedings 3rd International Conference on Computer Vision
CityOsaka, Jpn
Period12/4/9012/7/90

Fingerprint

Derivatives
Recovery
Stereo vision

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hayashi, B. Y., & Negahdaripour, S. (1990). Direct motion stereo: Recovery of observer motion and scene structure. In Unknown Host Publication Title (pp. 446-450). Piscataway, NJ, United States: Publ by IEEE.

Direct motion stereo : Recovery of observer motion and scene structure. / Hayashi, Brian Y.; Negahdaripour, Shahriar.

Unknown Host Publication Title. Piscataway, NJ, United States : Publ by IEEE, 1990. p. 446-450.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hayashi, BY & Negahdaripour, S 1990, Direct motion stereo: Recovery of observer motion and scene structure. in Unknown Host Publication Title. Publ by IEEE, Piscataway, NJ, United States, pp. 446-450, Proceedings 3rd International Conference on Computer Vision, Osaka, Jpn, 12/4/90.
Hayashi BY, Negahdaripour S. Direct motion stereo: Recovery of observer motion and scene structure. In Unknown Host Publication Title. Piscataway, NJ, United States: Publ by IEEE. 1990. p. 446-450
Hayashi, Brian Y. ; Negahdaripour, Shahriar. / Direct motion stereo : Recovery of observer motion and scene structure. Unknown Host Publication Title. Piscataway, NJ, United States : Publ by IEEE, 1990. pp. 446-450
@inproceedings{310b7172cb7c4708952174d61a6d7653,
title = "Direct motion stereo: Recovery of observer motion and scene structure",
abstract = "Using a stereo vision system, the authors show how the translational motion and scene structure can be recovered directly from image gradients and time derivatives. There is no need to estimate or establish correspondences between features across images. The direction of motion is recovered using a procedure which involves minimizing the sum of the squared error of a linear constraint equation over the entire image. The magnitude of the motion is estimated from the stereo disparity. The scene structure is recovered in the form of a depth map using the recovered motion, image gradients, and time derivatives. Experimental results using real images are presented.",
author = "Hayashi, {Brian Y.} and Shahriar Negahdaripour",
year = "1990",
month = "12",
day = "1",
language = "English",
isbn = "0818620579",
pages = "446--450",
booktitle = "Unknown Host Publication Title",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Direct motion stereo

T2 - Recovery of observer motion and scene structure

AU - Hayashi, Brian Y.

AU - Negahdaripour, Shahriar

PY - 1990/12/1

Y1 - 1990/12/1

N2 - Using a stereo vision system, the authors show how the translational motion and scene structure can be recovered directly from image gradients and time derivatives. There is no need to estimate or establish correspondences between features across images. The direction of motion is recovered using a procedure which involves minimizing the sum of the squared error of a linear constraint equation over the entire image. The magnitude of the motion is estimated from the stereo disparity. The scene structure is recovered in the form of a depth map using the recovered motion, image gradients, and time derivatives. Experimental results using real images are presented.

AB - Using a stereo vision system, the authors show how the translational motion and scene structure can be recovered directly from image gradients and time derivatives. There is no need to estimate or establish correspondences between features across images. The direction of motion is recovered using a procedure which involves minimizing the sum of the squared error of a linear constraint equation over the entire image. The magnitude of the motion is estimated from the stereo disparity. The scene structure is recovered in the form of a depth map using the recovered motion, image gradients, and time derivatives. Experimental results using real images are presented.

UR - http://www.scopus.com/inward/record.url?scp=0025575626&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025575626&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0818620579

SP - 446

EP - 450

BT - Unknown Host Publication Title

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -