Robust optical-flow based self-motion estimation for a quadrotor UAV

Volker Grabe, Heinrich Bulthoff, Paolo Robuffo Giordano

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

42 Citations (Scopus)

Abstract

Robotic vision has become an important field of research for micro aerial vehicles in the recent years. While many approaches for autonomous visual control of such vehicles rely on powerful ground stations, the increasing availability of small and light hardware allows for the design of more independent systems. In this context, we present a robust algorithm able to recover the UAV ego-motion using a monocular camera and on-board hardware. Our method exploits the continuous homography constraint so as to discriminate among the observed feature points in order to classify those belonging to the dominant plane in the scene. Extensive experiments on a real quadrotor UAV demonstrate that the estimation of the scaled linear velocity in a cluttered environment improved by a factor of 25% compared to previous approaches.

Original languageEnglish
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages2153-2159
Number of pages7
DOIs
Publication statusPublished - 2012 Dec 1
Event25th IEEE/RSJ International Conference on Robotics and Intelligent Systems, IROS 2012 - Vilamoura, Algarve, Portugal
Duration: 2012 Oct 72012 Oct 12

Other

Other25th IEEE/RSJ International Conference on Robotics and Intelligent Systems, IROS 2012
CountryPortugal
CityVilamoura, Algarve
Period12/10/712/10/12

Fingerprint

Optical flows
Motion estimation
Unmanned aerial vehicles (UAV)
Hardware
Robotics
Cameras
Availability
Antennas
Experiments

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Grabe, V., Bulthoff, H., & Robuffo Giordano, P. (2012). Robust optical-flow based self-motion estimation for a quadrotor UAV. In IEEE International Conference on Intelligent Robots and Systems (pp. 2153-2159). [6386234] https://doi.org/10.1109/IROS.2012.6386234

Robust optical-flow based self-motion estimation for a quadrotor UAV. / Grabe, Volker; Bulthoff, Heinrich; Robuffo Giordano, Paolo.

IEEE International Conference on Intelligent Robots and Systems. 2012. p. 2153-2159 6386234.

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

Grabe, V, Bulthoff, H & Robuffo Giordano, P 2012, Robust optical-flow based self-motion estimation for a quadrotor UAV. in IEEE International Conference on Intelligent Robots and Systems., 6386234, pp. 2153-2159, 25th IEEE/RSJ International Conference on Robotics and Intelligent Systems, IROS 2012, Vilamoura, Algarve, Portugal, 12/10/7. https://doi.org/10.1109/IROS.2012.6386234
Grabe V, Bulthoff H, Robuffo Giordano P. Robust optical-flow based self-motion estimation for a quadrotor UAV. In IEEE International Conference on Intelligent Robots and Systems. 2012. p. 2153-2159. 6386234 https://doi.org/10.1109/IROS.2012.6386234
Grabe, Volker ; Bulthoff, Heinrich ; Robuffo Giordano, Paolo. / Robust optical-flow based self-motion estimation for a quadrotor UAV. IEEE International Conference on Intelligent Robots and Systems. 2012. pp. 2153-2159
@inproceedings{b7563d808a904981a3cee44e192bc54b,
title = "Robust optical-flow based self-motion estimation for a quadrotor UAV",
abstract = "Robotic vision has become an important field of research for micro aerial vehicles in the recent years. While many approaches for autonomous visual control of such vehicles rely on powerful ground stations, the increasing availability of small and light hardware allows for the design of more independent systems. In this context, we present a robust algorithm able to recover the UAV ego-motion using a monocular camera and on-board hardware. Our method exploits the continuous homography constraint so as to discriminate among the observed feature points in order to classify those belonging to the dominant plane in the scene. Extensive experiments on a real quadrotor UAV demonstrate that the estimation of the scaled linear velocity in a cluttered environment improved by a factor of 25{\%} compared to previous approaches.",
author = "Volker Grabe and Heinrich Bulthoff and {Robuffo Giordano}, Paolo",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/IROS.2012.6386234",
language = "English",
isbn = "9781467317375",
pages = "2153--2159",
booktitle = "IEEE International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Robust optical-flow based self-motion estimation for a quadrotor UAV

AU - Grabe, Volker

AU - Bulthoff, Heinrich

AU - Robuffo Giordano, Paolo

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Robotic vision has become an important field of research for micro aerial vehicles in the recent years. While many approaches for autonomous visual control of such vehicles rely on powerful ground stations, the increasing availability of small and light hardware allows for the design of more independent systems. In this context, we present a robust algorithm able to recover the UAV ego-motion using a monocular camera and on-board hardware. Our method exploits the continuous homography constraint so as to discriminate among the observed feature points in order to classify those belonging to the dominant plane in the scene. Extensive experiments on a real quadrotor UAV demonstrate that the estimation of the scaled linear velocity in a cluttered environment improved by a factor of 25% compared to previous approaches.

AB - Robotic vision has become an important field of research for micro aerial vehicles in the recent years. While many approaches for autonomous visual control of such vehicles rely on powerful ground stations, the increasing availability of small and light hardware allows for the design of more independent systems. In this context, we present a robust algorithm able to recover the UAV ego-motion using a monocular camera and on-board hardware. Our method exploits the continuous homography constraint so as to discriminate among the observed feature points in order to classify those belonging to the dominant plane in the scene. Extensive experiments on a real quadrotor UAV demonstrate that the estimation of the scaled linear velocity in a cluttered environment improved by a factor of 25% compared to previous approaches.

UR - http://www.scopus.com/inward/record.url?scp=84872345197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872345197&partnerID=8YFLogxK

U2 - 10.1109/IROS.2012.6386234

DO - 10.1109/IROS.2012.6386234

M3 - Conference contribution

AN - SCOPUS:84872345197

SN - 9781467317375

SP - 2153

EP - 2159

BT - IEEE International Conference on Intelligent Robots and Systems

ER -