Egomotion and the stabilized world

David J. Heeger, Gregory Hager

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

Abstract

The tasks of moving-object detection and motion-based depth recovery as a problem of sensor fusion in the presence of uncertainty are formulated. Two sensor systems are utilized, one providing information about the local image velocity (specifying a point in image-velocity space), and the other providing information about the camera motion (specifying a line segment in image-velocity space). Mahalanobis distance is utilized as a threshold rule for determining consistency between the measurements from the two sensor systems. A framework is suggested for using the resulting segmented flow field to update estimates of the egomotion parameters.

Original languageEnglish (US)
Title of host publicationSecond Int Conf on Comput Vision
PublisherPubl by IEEE
Pages435-440
Number of pages6
ISBN (Print)0818608838
StatePublished - 1988
Externally publishedYes

Fingerprint

Sensors
Flow fields
Fusion reactions
Cameras
Recovery
Object detection
Uncertainty

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Heeger, D. J., & Hager, G. (1988). Egomotion and the stabilized world. In Second Int Conf on Comput Vision (pp. 435-440). Publ by IEEE.

Egomotion and the stabilized world. / Heeger, David J.; Hager, Gregory.

Second Int Conf on Comput Vision. Publ by IEEE, 1988. p. 435-440.

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

Heeger, DJ & Hager, G 1988, Egomotion and the stabilized world. in Second Int Conf on Comput Vision. Publ by IEEE, pp. 435-440.
Heeger DJ, Hager G. Egomotion and the stabilized world. In Second Int Conf on Comput Vision. Publ by IEEE. 1988. p. 435-440
Heeger, David J. ; Hager, Gregory. / Egomotion and the stabilized world. Second Int Conf on Comput Vision. Publ by IEEE, 1988. pp. 435-440
@inproceedings{4f466efbadbc407e8694b4c6c438cd5f,
title = "Egomotion and the stabilized world",
abstract = "The tasks of moving-object detection and motion-based depth recovery as a problem of sensor fusion in the presence of uncertainty are formulated. Two sensor systems are utilized, one providing information about the local image velocity (specifying a point in image-velocity space), and the other providing information about the camera motion (specifying a line segment in image-velocity space). Mahalanobis distance is utilized as a threshold rule for determining consistency between the measurements from the two sensor systems. A framework is suggested for using the resulting segmented flow field to update estimates of the egomotion parameters.",
author = "Heeger, {David J.} and Gregory Hager",
year = "1988",
language = "English (US)",
isbn = "0818608838",
pages = "435--440",
booktitle = "Second Int Conf on Comput Vision",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Egomotion and the stabilized world

AU - Heeger, David J.

AU - Hager, Gregory

PY - 1988

Y1 - 1988

N2 - The tasks of moving-object detection and motion-based depth recovery as a problem of sensor fusion in the presence of uncertainty are formulated. Two sensor systems are utilized, one providing information about the local image velocity (specifying a point in image-velocity space), and the other providing information about the camera motion (specifying a line segment in image-velocity space). Mahalanobis distance is utilized as a threshold rule for determining consistency between the measurements from the two sensor systems. A framework is suggested for using the resulting segmented flow field to update estimates of the egomotion parameters.

AB - The tasks of moving-object detection and motion-based depth recovery as a problem of sensor fusion in the presence of uncertainty are formulated. Two sensor systems are utilized, one providing information about the local image velocity (specifying a point in image-velocity space), and the other providing information about the camera motion (specifying a line segment in image-velocity space). Mahalanobis distance is utilized as a threshold rule for determining consistency between the measurements from the two sensor systems. A framework is suggested for using the resulting segmented flow field to update estimates of the egomotion parameters.

UR - http://www.scopus.com/inward/record.url?scp=0024169619&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024169619&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024169619

SN - 0818608838

SP - 435

EP - 440

BT - Second Int Conf on Comput Vision

PB - Publ by IEEE

ER -