Monocular image space tracking on a computationally limited MAV

Kyel Ok, Dinesh Gamage, Tom William Drummond, Frank Dellaert, Nicholas Roy

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

We propose a method of monocular camera-inertial based navigation for computationally limited micro air vehicles (MAVs). Our approach is derived from the recent development of parallel tracking and mapping algorithms, but unlike previous results, we show how the tracking and mapping processes operate using different representations. The separation of representations allows us not only to move the computational load of full map inference to a ground station, but to further reduce the computational cost of on-board tracking for pose estimation. Our primary contribution is to show how the cost of tracking the vehicle pose on-board can be substantially reduced by estimating the camera motion directly in the image frame, rather than in the world co-ordinate frame. We demonstrate our method on an Ascending Technologies Pelican quad-rotor, and show that we can track the vehicle pose with reduced on-board computation but without compromised navigation accuracy.
Original languageEnglish
Title of host publicationProceedings of the 2015 IEEE International Confrerence on Robotics and Automation (ICRA)
EditorsAllison Okamura
Place of PublicationWashington DC USA
PublisherIEEE Computer Society
Pages6415 - 6422
Number of pages8
ISBN (Print)9781479969234
DOIs
Publication statusPublished - 2015
EventIEEE International Conference on Robotics and Automation 2015 - Seattle, United States of America
Duration: 26 May 201530 May 2015
http://ewh.ieee.org/soc/ras/conf/FullySponsored/ICRA/2015/icra2015.org/index.html

Conference

ConferenceIEEE International Conference on Robotics and Automation 2015
Abbreviated titleICRA 2015
CountryUnited States of America
CitySeattle
Period26/05/1530/05/15
Internet address

Cite this

Ok, K., Gamage, D., Drummond, T. W., Dellaert, F., & Roy, N. (2015). Monocular image space tracking on a computationally limited MAV. In A. Okamura (Ed.), Proceedings of the 2015 IEEE International Confrerence on Robotics and Automation (ICRA) (pp. 6415 - 6422). Washington DC USA: IEEE Computer Society. https://doi.org/10.1109/ICRA.2015.7140100
Ok, Kyel ; Gamage, Dinesh ; Drummond, Tom William ; Dellaert, Frank ; Roy, Nicholas. / Monocular image space tracking on a computationally limited MAV. Proceedings of the 2015 IEEE International Confrerence on Robotics and Automation (ICRA). editor / Allison Okamura. Washington DC USA : IEEE Computer Society, 2015. pp. 6415 - 6422
@inproceedings{b465a9e89028494a98cea82e4c0bcbb1,
title = "Monocular image space tracking on a computationally limited MAV",
abstract = "We propose a method of monocular camera-inertial based navigation for computationally limited micro air vehicles (MAVs). Our approach is derived from the recent development of parallel tracking and mapping algorithms, but unlike previous results, we show how the tracking and mapping processes operate using different representations. The separation of representations allows us not only to move the computational load of full map inference to a ground station, but to further reduce the computational cost of on-board tracking for pose estimation. Our primary contribution is to show how the cost of tracking the vehicle pose on-board can be substantially reduced by estimating the camera motion directly in the image frame, rather than in the world co-ordinate frame. We demonstrate our method on an Ascending Technologies Pelican quad-rotor, and show that we can track the vehicle pose with reduced on-board computation but without compromised navigation accuracy.",
author = "Kyel Ok and Dinesh Gamage and Drummond, {Tom William} and Frank Dellaert and Nicholas Roy",
year = "2015",
doi = "10.1109/ICRA.2015.7140100",
language = "English",
isbn = "9781479969234",
pages = "6415 -- 6422",
editor = "Allison Okamura",
booktitle = "Proceedings of the 2015 IEEE International Confrerence on Robotics and Automation (ICRA)",
publisher = "IEEE Computer Society",
address = "United States of America",

}

Ok, K, Gamage, D, Drummond, TW, Dellaert, F & Roy, N 2015, Monocular image space tracking on a computationally limited MAV. in A Okamura (ed.), Proceedings of the 2015 IEEE International Confrerence on Robotics and Automation (ICRA). IEEE Computer Society, Washington DC USA, pp. 6415 - 6422, IEEE International Conference on Robotics and Automation 2015, Seattle, United States of America, 26/05/15. https://doi.org/10.1109/ICRA.2015.7140100

Monocular image space tracking on a computationally limited MAV. / Ok, Kyel; Gamage, Dinesh; Drummond, Tom William; Dellaert, Frank; Roy, Nicholas.

Proceedings of the 2015 IEEE International Confrerence on Robotics and Automation (ICRA). ed. / Allison Okamura. Washington DC USA : IEEE Computer Society, 2015. p. 6415 - 6422.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Monocular image space tracking on a computationally limited MAV

AU - Ok, Kyel

AU - Gamage, Dinesh

AU - Drummond, Tom William

AU - Dellaert, Frank

AU - Roy, Nicholas

PY - 2015

Y1 - 2015

N2 - We propose a method of monocular camera-inertial based navigation for computationally limited micro air vehicles (MAVs). Our approach is derived from the recent development of parallel tracking and mapping algorithms, but unlike previous results, we show how the tracking and mapping processes operate using different representations. The separation of representations allows us not only to move the computational load of full map inference to a ground station, but to further reduce the computational cost of on-board tracking for pose estimation. Our primary contribution is to show how the cost of tracking the vehicle pose on-board can be substantially reduced by estimating the camera motion directly in the image frame, rather than in the world co-ordinate frame. We demonstrate our method on an Ascending Technologies Pelican quad-rotor, and show that we can track the vehicle pose with reduced on-board computation but without compromised navigation accuracy.

AB - We propose a method of monocular camera-inertial based navigation for computationally limited micro air vehicles (MAVs). Our approach is derived from the recent development of parallel tracking and mapping algorithms, but unlike previous results, we show how the tracking and mapping processes operate using different representations. The separation of representations allows us not only to move the computational load of full map inference to a ground station, but to further reduce the computational cost of on-board tracking for pose estimation. Our primary contribution is to show how the cost of tracking the vehicle pose on-board can be substantially reduced by estimating the camera motion directly in the image frame, rather than in the world co-ordinate frame. We demonstrate our method on an Ascending Technologies Pelican quad-rotor, and show that we can track the vehicle pose with reduced on-board computation but without compromised navigation accuracy.

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7140100

U2 - 10.1109/ICRA.2015.7140100

DO - 10.1109/ICRA.2015.7140100

M3 - Conference Paper

SN - 9781479969234

SP - 6415

EP - 6422

BT - Proceedings of the 2015 IEEE International Confrerence on Robotics and Automation (ICRA)

A2 - Okamura, Allison

PB - IEEE Computer Society

CY - Washington DC USA

ER -

Ok K, Gamage D, Drummond TW, Dellaert F, Roy N. Monocular image space tracking on a computationally limited MAV. In Okamura A, editor, Proceedings of the 2015 IEEE International Confrerence on Robotics and Automation (ICRA). Washington DC USA: IEEE Computer Society. 2015. p. 6415 - 6422 https://doi.org/10.1109/ICRA.2015.7140100