Enhanced visual odometry algorithm based on elite selection method and voting system

Hao Shen, Chen-Chien James Hsu, Wei Yen Wang, Yin Tien Wang

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

1 Citation (Scopus)

Abstract

In this paper, we address the problems of camera pose estimation accuracy and runtime efficiency by incorporating an elite selection method and a voting system to a conventional visual odometry (VO) method, called the 'enhanced VO algorithm'. The use of elite selection method improves the efficiency of perspective-3-point (P3P) algorithm by only employing an elite subset of landmarks to estimate the camera pose. The proposed voting system, on the other hand, provides reliable consensus set derived from random sample consensus (RANSAC) algorithm such that accuracy of camera pose estimations can be increased. To verify the performances of the proposed approach, we conducted various experiments using a Kinect RGB-D sensor, and the results show that the proposed VO system performs well in terms of not only estimation accuracy but also computational time.

Original languageEnglish
Title of host publication2017 IEEE 7th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017
PublisherIEEE Computer Society
Pages99-100
Number of pages2
ISBN (Electronic)9781509040148
DOIs
Publication statusPublished - 2017 Dec 14
Event7th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017 - Berlin, Germany
Duration: 2017 Sep 32017 Sep 6

Publication series

NameIEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
Volume2017-September
ISSN (Print)2166-6814
ISSN (Electronic)2166-6822

Other

Other7th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017
CountryGermany
CityBerlin
Period17/9/317/9/6

Fingerprint

Cameras
Set theory
Sensors
Experiments

Keywords

  • Kinect RGB-D sensor
  • Perspective-3-point
  • RANSAC
  • SURF
  • Visual odometry

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Media Technology

Cite this

Shen, H., Hsu, C-C. J., Wang, W. Y., & Wang, Y. T. (2017). Enhanced visual odometry algorithm based on elite selection method and voting system. In 2017 IEEE 7th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017 (pp. 99-100). (IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin; Vol. 2017-September). IEEE Computer Society. https://doi.org/10.1109/ICCE-Berlin.2017.8210602

Enhanced visual odometry algorithm based on elite selection method and voting system. / Shen, Hao; Hsu, Chen-Chien James; Wang, Wei Yen; Wang, Yin Tien.

2017 IEEE 7th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017. IEEE Computer Society, 2017. p. 99-100 (IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin; Vol. 2017-September).

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

Shen, H, Hsu, C-CJ, Wang, WY & Wang, YT 2017, Enhanced visual odometry algorithm based on elite selection method and voting system. in 2017 IEEE 7th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017. IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin, vol. 2017-September, IEEE Computer Society, pp. 99-100, 7th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017, Berlin, Germany, 17/9/3. https://doi.org/10.1109/ICCE-Berlin.2017.8210602
Shen H, Hsu C-CJ, Wang WY, Wang YT. Enhanced visual odometry algorithm based on elite selection method and voting system. In 2017 IEEE 7th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017. IEEE Computer Society. 2017. p. 99-100. (IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin). https://doi.org/10.1109/ICCE-Berlin.2017.8210602
Shen, Hao ; Hsu, Chen-Chien James ; Wang, Wei Yen ; Wang, Yin Tien. / Enhanced visual odometry algorithm based on elite selection method and voting system. 2017 IEEE 7th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017. IEEE Computer Society, 2017. pp. 99-100 (IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin).
@inproceedings{70510e599f8c418b85815375a7b724ec,
title = "Enhanced visual odometry algorithm based on elite selection method and voting system",
abstract = "In this paper, we address the problems of camera pose estimation accuracy and runtime efficiency by incorporating an elite selection method and a voting system to a conventional visual odometry (VO) method, called the 'enhanced VO algorithm'. The use of elite selection method improves the efficiency of perspective-3-point (P3P) algorithm by only employing an elite subset of landmarks to estimate the camera pose. The proposed voting system, on the other hand, provides reliable consensus set derived from random sample consensus (RANSAC) algorithm such that accuracy of camera pose estimations can be increased. To verify the performances of the proposed approach, we conducted various experiments using a Kinect RGB-D sensor, and the results show that the proposed VO system performs well in terms of not only estimation accuracy but also computational time.",
keywords = "Kinect RGB-D sensor, Perspective-3-point, RANSAC, SURF, Visual odometry",
author = "Hao Shen and Hsu, {Chen-Chien James} and Wang, {Wei Yen} and Wang, {Yin Tien}",
year = "2017",
month = "12",
day = "14",
doi = "10.1109/ICCE-Berlin.2017.8210602",
language = "English",
series = "IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin",
publisher = "IEEE Computer Society",
pages = "99--100",
booktitle = "2017 IEEE 7th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017",

}

TY - GEN

T1 - Enhanced visual odometry algorithm based on elite selection method and voting system

AU - Shen, Hao

AU - Hsu, Chen-Chien James

AU - Wang, Wei Yen

AU - Wang, Yin Tien

PY - 2017/12/14

Y1 - 2017/12/14

N2 - In this paper, we address the problems of camera pose estimation accuracy and runtime efficiency by incorporating an elite selection method and a voting system to a conventional visual odometry (VO) method, called the 'enhanced VO algorithm'. The use of elite selection method improves the efficiency of perspective-3-point (P3P) algorithm by only employing an elite subset of landmarks to estimate the camera pose. The proposed voting system, on the other hand, provides reliable consensus set derived from random sample consensus (RANSAC) algorithm such that accuracy of camera pose estimations can be increased. To verify the performances of the proposed approach, we conducted various experiments using a Kinect RGB-D sensor, and the results show that the proposed VO system performs well in terms of not only estimation accuracy but also computational time.

AB - In this paper, we address the problems of camera pose estimation accuracy and runtime efficiency by incorporating an elite selection method and a voting system to a conventional visual odometry (VO) method, called the 'enhanced VO algorithm'. The use of elite selection method improves the efficiency of perspective-3-point (P3P) algorithm by only employing an elite subset of landmarks to estimate the camera pose. The proposed voting system, on the other hand, provides reliable consensus set derived from random sample consensus (RANSAC) algorithm such that accuracy of camera pose estimations can be increased. To verify the performances of the proposed approach, we conducted various experiments using a Kinect RGB-D sensor, and the results show that the proposed VO system performs well in terms of not only estimation accuracy but also computational time.

KW - Kinect RGB-D sensor

KW - Perspective-3-point

KW - RANSAC

KW - SURF

KW - Visual odometry

UR - http://www.scopus.com/inward/record.url?scp=85044006460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044006460&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Berlin.2017.8210602

DO - 10.1109/ICCE-Berlin.2017.8210602

M3 - Conference contribution

AN - SCOPUS:85044006460

T3 - IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin

SP - 99

EP - 100

BT - 2017 IEEE 7th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2017

PB - IEEE Computer Society

ER -