Robust recovery of motion: Effects of surface orientation and field of view.

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

9 Citations (Scopus)

Abstract

Recovering, from two-dimensional images, certain three-dimensional properties of the scene, such as motion and shape of objects in a scene and their spatial arrangement, is one of the primary goals of a machine vision system. Given a textured scene, motion can be recovered rather easily if the structure of the scene, usually in the form of a depth map of the scene, is known. In theory, it is also possible to recover shape (a depth map of the scene) if the relative motion between the viewer and objects in the scene is known. The authors study the sensitivity of the solution of the first problem to inaccuracies in the knowledge of the depth map of the scene. First a brightness change constraint equation, is used to give closed-form solutions for the motion parameters in two cases: known depth, and small depth variations relative to the absolute distance of the scene from the viewer. They then investigate the robustness of the solution for the motion parameters in terms of the scene structure, modeled as piecewise planar patches. They demonstrate the behavior of the solution with the variations of the orientation of the surface patch being viewed and the size of the field of view. Using a quantitative measure, they show the need for a large field of view to recover motion robustly. The eigenvalue-eigenvector decomposition of a 6 × 6 matrix allows the authors to analyze some well-known ambiguities in recovering motion.

Original languageEnglish
Title of host publicationUnknown Host Publication Title
Place of PublicationSilver Spring, MD, United States
PublisherPubl by IEEE
Pages404-410
Number of pages7
ISBN (Print)0818608625
StatePublished - Dec 1 1988
Externally publishedYes

Fingerprint

Recovery
Eigenvalues and eigenfunctions
Computer vision
Luminance
Decomposition

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Negahdaripour, S., & Yu, C. H. (1988). Robust recovery of motion: Effects of surface orientation and field of view. In Unknown Host Publication Title (pp. 404-410). Silver Spring, MD, United States: Publ by IEEE.

Robust recovery of motion : Effects of surface orientation and field of view. / Negahdaripour, Shahriar; Yu, Chih Ho.

Unknown Host Publication Title. Silver Spring, MD, United States : Publ by IEEE, 1988. p. 404-410.

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

Negahdaripour, S & Yu, CH 1988, Robust recovery of motion: Effects of surface orientation and field of view. in Unknown Host Publication Title. Publ by IEEE, Silver Spring, MD, United States, pp. 404-410.
Negahdaripour S, Yu CH. Robust recovery of motion: Effects of surface orientation and field of view. In Unknown Host Publication Title. Silver Spring, MD, United States: Publ by IEEE. 1988. p. 404-410
Negahdaripour, Shahriar ; Yu, Chih Ho. / Robust recovery of motion : Effects of surface orientation and field of view. Unknown Host Publication Title. Silver Spring, MD, United States : Publ by IEEE, 1988. pp. 404-410
@inproceedings{ef0805ff77e846bab85d6c8f524cb462,
title = "Robust recovery of motion: Effects of surface orientation and field of view.",
abstract = "Recovering, from two-dimensional images, certain three-dimensional properties of the scene, such as motion and shape of objects in a scene and their spatial arrangement, is one of the primary goals of a machine vision system. Given a textured scene, motion can be recovered rather easily if the structure of the scene, usually in the form of a depth map of the scene, is known. In theory, it is also possible to recover shape (a depth map of the scene) if the relative motion between the viewer and objects in the scene is known. The authors study the sensitivity of the solution of the first problem to inaccuracies in the knowledge of the depth map of the scene. First a brightness change constraint equation, is used to give closed-form solutions for the motion parameters in two cases: known depth, and small depth variations relative to the absolute distance of the scene from the viewer. They then investigate the robustness of the solution for the motion parameters in terms of the scene structure, modeled as piecewise planar patches. They demonstrate the behavior of the solution with the variations of the orientation of the surface patch being viewed and the size of the field of view. Using a quantitative measure, they show the need for a large field of view to recover motion robustly. The eigenvalue-eigenvector decomposition of a 6 × 6 matrix allows the authors to analyze some well-known ambiguities in recovering motion.",
author = "Shahriar Negahdaripour and Yu, {Chih Ho}",
year = "1988",
month = "12",
day = "1",
language = "English",
isbn = "0818608625",
pages = "404--410",
booktitle = "Unknown Host Publication Title",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Robust recovery of motion

T2 - Effects of surface orientation and field of view.

AU - Negahdaripour, Shahriar

AU - Yu, Chih Ho

PY - 1988/12/1

Y1 - 1988/12/1

N2 - Recovering, from two-dimensional images, certain three-dimensional properties of the scene, such as motion and shape of objects in a scene and their spatial arrangement, is one of the primary goals of a machine vision system. Given a textured scene, motion can be recovered rather easily if the structure of the scene, usually in the form of a depth map of the scene, is known. In theory, it is also possible to recover shape (a depth map of the scene) if the relative motion between the viewer and objects in the scene is known. The authors study the sensitivity of the solution of the first problem to inaccuracies in the knowledge of the depth map of the scene. First a brightness change constraint equation, is used to give closed-form solutions for the motion parameters in two cases: known depth, and small depth variations relative to the absolute distance of the scene from the viewer. They then investigate the robustness of the solution for the motion parameters in terms of the scene structure, modeled as piecewise planar patches. They demonstrate the behavior of the solution with the variations of the orientation of the surface patch being viewed and the size of the field of view. Using a quantitative measure, they show the need for a large field of view to recover motion robustly. The eigenvalue-eigenvector decomposition of a 6 × 6 matrix allows the authors to analyze some well-known ambiguities in recovering motion.

AB - Recovering, from two-dimensional images, certain three-dimensional properties of the scene, such as motion and shape of objects in a scene and their spatial arrangement, is one of the primary goals of a machine vision system. Given a textured scene, motion can be recovered rather easily if the structure of the scene, usually in the form of a depth map of the scene, is known. In theory, it is also possible to recover shape (a depth map of the scene) if the relative motion between the viewer and objects in the scene is known. The authors study the sensitivity of the solution of the first problem to inaccuracies in the knowledge of the depth map of the scene. First a brightness change constraint equation, is used to give closed-form solutions for the motion parameters in two cases: known depth, and small depth variations relative to the absolute distance of the scene from the viewer. They then investigate the robustness of the solution for the motion parameters in terms of the scene structure, modeled as piecewise planar patches. They demonstrate the behavior of the solution with the variations of the orientation of the surface patch being viewed and the size of the field of view. Using a quantitative measure, they show the need for a large field of view to recover motion robustly. The eigenvalue-eigenvector decomposition of a 6 × 6 matrix allows the authors to analyze some well-known ambiguities in recovering motion.

UR - http://www.scopus.com/inward/record.url?scp=0024142744&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024142744&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024142744

SN - 0818608625

SP - 404

EP - 410

BT - Unknown Host Publication Title

PB - Publ by IEEE

CY - Silver Spring, MD, United States

ER -