Motion Vector Field Estimation Using Brightness Constancy Assumption and Epipolar Geometry Constraint

S. Hosseinyalamdary, A. Yilmaz

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

Abstract

In most Photogrammetry and computer vision tasks, finding the corresponding points among images is required. Among many, the Lucas-Kanade optical flow estimation has been employed for tracking interest points as well as motion vector field estimation. This paper uses the IMU measurements to reconstruct the epipolar geometry and it integrates the epipolar geometry constraint with the brightness constancy assumption in the Lucas-Kanade method. The proposed method has been tested using the KITTI dataset. The results show the improvement in motion vector field estimation in comparison to the Lucas-Kanade optical flow estimation. The same approach has been used in the KLT tracker and it has been shown that using epipolar geometry constraint can improve the KLT tracker. It is recommended that the epipolar geometry constraint is used in advanced variational optical flow estimation methods
Original languageEnglish
Title of host publicationISPRS Technical Commission I Symposium
EditorsCharles Toth
PublisherInternational Society for Photogrammetry and Remote Sensing (ISPRS)
Pages9-16
VolumeII-1
DOIs
Publication statusPublished - 2014
Externally publishedYes

Publication series

NameISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
PublisherCopernicus GmbH
ISSN (Print)2194-9042

Fingerprint

Luminance
Optical flows
Geometry
Photogrammetry
Computer vision

Cite this

Hosseinyalamdary, S., & Yilmaz, A. (2014). Motion Vector Field Estimation Using Brightness Constancy Assumption and Epipolar Geometry Constraint. In C. Toth (Ed.), ISPRS Technical Commission I Symposium (Vol. II-1, pp. 9-16). (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences). International Society for Photogrammetry and Remote Sensing (ISPRS). https://doi.org/10.5194/isprsannals-II-1-9-2014
Hosseinyalamdary, S. ; Yilmaz, A. / Motion Vector Field Estimation Using Brightness Constancy Assumption and Epipolar Geometry Constraint. ISPRS Technical Commission I Symposium. editor / Charles Toth. Vol. II-1 International Society for Photogrammetry and Remote Sensing (ISPRS), 2014. pp. 9-16 (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences).
@inbook{2f0c816f4fa94ae5913214a29a7ed3d6,
title = "Motion Vector Field Estimation Using Brightness Constancy Assumption and Epipolar Geometry Constraint",
abstract = "In most Photogrammetry and computer vision tasks, finding the corresponding points among images is required. Among many, the Lucas-Kanade optical flow estimation has been employed for tracking interest points as well as motion vector field estimation. This paper uses the IMU measurements to reconstruct the epipolar geometry and it integrates the epipolar geometry constraint with the brightness constancy assumption in the Lucas-Kanade method. The proposed method has been tested using the KITTI dataset. The results show the improvement in motion vector field estimation in comparison to the Lucas-Kanade optical flow estimation. The same approach has been used in the KLT tracker and it has been shown that using epipolar geometry constraint can improve the KLT tracker. It is recommended that the epipolar geometry constraint is used in advanced variational optical flow estimation methods",
author = "S. Hosseinyalamdary and A. Yilmaz",
year = "2014",
doi = "10.5194/isprsannals-II-1-9-2014",
language = "English",
volume = "II-1",
series = "ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
publisher = "International Society for Photogrammetry and Remote Sensing (ISPRS)",
pages = "9--16",
editor = "Charles Toth",
booktitle = "ISPRS Technical Commission I Symposium",

}

Hosseinyalamdary, S & Yilmaz, A 2014, Motion Vector Field Estimation Using Brightness Constancy Assumption and Epipolar Geometry Constraint. in C Toth (ed.), ISPRS Technical Commission I Symposium. vol. II-1, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, International Society for Photogrammetry and Remote Sensing (ISPRS), pp. 9-16. https://doi.org/10.5194/isprsannals-II-1-9-2014

Motion Vector Field Estimation Using Brightness Constancy Assumption and Epipolar Geometry Constraint. / Hosseinyalamdary, S.; Yilmaz, A.

ISPRS Technical Commission I Symposium. ed. / Charles Toth. Vol. II-1 International Society for Photogrammetry and Remote Sensing (ISPRS), 2014. p. 9-16 (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences).

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

TY - CHAP

T1 - Motion Vector Field Estimation Using Brightness Constancy Assumption and Epipolar Geometry Constraint

AU - Hosseinyalamdary, S.

AU - Yilmaz, A.

PY - 2014

Y1 - 2014

N2 - In most Photogrammetry and computer vision tasks, finding the corresponding points among images is required. Among many, the Lucas-Kanade optical flow estimation has been employed for tracking interest points as well as motion vector field estimation. This paper uses the IMU measurements to reconstruct the epipolar geometry and it integrates the epipolar geometry constraint with the brightness constancy assumption in the Lucas-Kanade method. The proposed method has been tested using the KITTI dataset. The results show the improvement in motion vector field estimation in comparison to the Lucas-Kanade optical flow estimation. The same approach has been used in the KLT tracker and it has been shown that using epipolar geometry constraint can improve the KLT tracker. It is recommended that the epipolar geometry constraint is used in advanced variational optical flow estimation methods

AB - In most Photogrammetry and computer vision tasks, finding the corresponding points among images is required. Among many, the Lucas-Kanade optical flow estimation has been employed for tracking interest points as well as motion vector field estimation. This paper uses the IMU measurements to reconstruct the epipolar geometry and it integrates the epipolar geometry constraint with the brightness constancy assumption in the Lucas-Kanade method. The proposed method has been tested using the KITTI dataset. The results show the improvement in motion vector field estimation in comparison to the Lucas-Kanade optical flow estimation. The same approach has been used in the KLT tracker and it has been shown that using epipolar geometry constraint can improve the KLT tracker. It is recommended that the epipolar geometry constraint is used in advanced variational optical flow estimation methods

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2014/chap/hosseinyalamdary_mot.pdf

U2 - 10.5194/isprsannals-II-1-9-2014

DO - 10.5194/isprsannals-II-1-9-2014

M3 - Chapter

VL - II-1

T3 - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SP - 9

EP - 16

BT - ISPRS Technical Commission I Symposium

A2 - Toth, Charles

PB - International Society for Photogrammetry and Remote Sensing (ISPRS)

ER -

Hosseinyalamdary S, Yilmaz A. Motion Vector Field Estimation Using Brightness Constancy Assumption and Epipolar Geometry Constraint. In Toth C, editor, ISPRS Technical Commission I Symposium. Vol. II-1. International Society for Photogrammetry and Remote Sensing (ISPRS). 2014. p. 9-16. (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences). https://doi.org/10.5194/isprsannals-II-1-9-2014