A novel relative camera motion estimation algorithm with applications to visual odometry

Yue Jiang, Mun Cheon Kang, Ming Fan, Sung Ho Chae, Sung-Jea Ko

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

Abstract

In this paper, we propose a novel method to estimate the relative camera motions of three consecutive images. Given a set of point correspondences in three views, the proposed method determines the fundamental matrix representing the geometrical relationship between the first two views by using the eight-point algorithm. Then, by minimizing the proposed cost function with the fundamental matrix, the relative camera motions over three views are precisely estimated. The experimental results show that the proposed method outperforms the conventional two-view and three-view geometry-based method in terms of the accuracy.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages215-216
Number of pages2
ISBN (Electronic)9781538668573
DOIs
Publication statusPublished - 2019 Jan 4
Event20th IEEE International Symposium on Multimedia, ISM 2018 - Taichung, Taiwan, Province of China
Duration: 2018 Dec 102018 Dec 12

Publication series

NameProceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018

Conference

Conference20th IEEE International Symposium on Multimedia, ISM 2018
CountryTaiwan, Province of China
CityTaichung
Period18/12/1018/12/12

Fingerprint

Motion estimation
Cameras
Cost functions
Geometry

Keywords

  • Eight-point algorithm
  • Trifocal tensor
  • Visual odometry

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology

Cite this

Jiang, Y., Kang, M. C., Fan, M., Chae, S. H., & Ko, S-J. (2019). A novel relative camera motion estimation algorithm with applications to visual odometry. In Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018 (pp. 215-216). [8603292] (Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISM.2018.000-4

A novel relative camera motion estimation algorithm with applications to visual odometry. / Jiang, Yue; Kang, Mun Cheon; Fan, Ming; Chae, Sung Ho; Ko, Sung-Jea.

Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 215-216 8603292 (Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018).

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

Jiang, Y, Kang, MC, Fan, M, Chae, SH & Ko, S-J 2019, A novel relative camera motion estimation algorithm with applications to visual odometry. in Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018., 8603292, Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018, Institute of Electrical and Electronics Engineers Inc., pp. 215-216, 20th IEEE International Symposium on Multimedia, ISM 2018, Taichung, Taiwan, Province of China, 18/12/10. https://doi.org/10.1109/ISM.2018.000-4
Jiang Y, Kang MC, Fan M, Chae SH, Ko S-J. A novel relative camera motion estimation algorithm with applications to visual odometry. In Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 215-216. 8603292. (Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018). https://doi.org/10.1109/ISM.2018.000-4
Jiang, Yue ; Kang, Mun Cheon ; Fan, Ming ; Chae, Sung Ho ; Ko, Sung-Jea. / A novel relative camera motion estimation algorithm with applications to visual odometry. Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 215-216 (Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018).
@inproceedings{1e403119c4a64a0bad5cd7fd2f5bd3fe,
title = "A novel relative camera motion estimation algorithm with applications to visual odometry",
abstract = "In this paper, we propose a novel method to estimate the relative camera motions of three consecutive images. Given a set of point correspondences in three views, the proposed method determines the fundamental matrix representing the geometrical relationship between the first two views by using the eight-point algorithm. Then, by minimizing the proposed cost function with the fundamental matrix, the relative camera motions over three views are precisely estimated. The experimental results show that the proposed method outperforms the conventional two-view and three-view geometry-based method in terms of the accuracy.",
keywords = "Eight-point algorithm, Trifocal tensor, Visual odometry",
author = "Yue Jiang and Kang, {Mun Cheon} and Ming Fan and Chae, {Sung Ho} and Sung-Jea Ko",
year = "2019",
month = "1",
day = "4",
doi = "10.1109/ISM.2018.000-4",
language = "English",
series = "Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "215--216",
booktitle = "Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018",

}

TY - GEN

T1 - A novel relative camera motion estimation algorithm with applications to visual odometry

AU - Jiang, Yue

AU - Kang, Mun Cheon

AU - Fan, Ming

AU - Chae, Sung Ho

AU - Ko, Sung-Jea

PY - 2019/1/4

Y1 - 2019/1/4

N2 - In this paper, we propose a novel method to estimate the relative camera motions of three consecutive images. Given a set of point correspondences in three views, the proposed method determines the fundamental matrix representing the geometrical relationship between the first two views by using the eight-point algorithm. Then, by minimizing the proposed cost function with the fundamental matrix, the relative camera motions over three views are precisely estimated. The experimental results show that the proposed method outperforms the conventional two-view and three-view geometry-based method in terms of the accuracy.

AB - In this paper, we propose a novel method to estimate the relative camera motions of three consecutive images. Given a set of point correspondences in three views, the proposed method determines the fundamental matrix representing the geometrical relationship between the first two views by using the eight-point algorithm. Then, by minimizing the proposed cost function with the fundamental matrix, the relative camera motions over three views are precisely estimated. The experimental results show that the proposed method outperforms the conventional two-view and three-view geometry-based method in terms of the accuracy.

KW - Eight-point algorithm

KW - Trifocal tensor

KW - Visual odometry

UR - http://www.scopus.com/inward/record.url?scp=85061652397&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061652397&partnerID=8YFLogxK

U2 - 10.1109/ISM.2018.000-4

DO - 10.1109/ISM.2018.000-4

M3 - Conference contribution

AN - SCOPUS:85061652397

T3 - Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018

SP - 215

EP - 216

BT - Proceedings - 2018 IEEE International Symposium on Multimedia, ISM 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -