Fusing visual and inertial sensing to recover robot ego-motion

Guillem Alenyà, Elisa Martínez, Carme Torras

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

A method for estimating mobile robot ego-motion is presented, which relies on tracking contours in real-time images acquired with a calibrated monocular video system. After fitting an active contour to an object in the image, 3D motion is derived from the affine deformations suffered by the contour in an image sequence. More than one object can be tracked at the same time, yielding some different pose estimations. Then, improvements in pose determination are achieved by fusing all these different estimations. Inertial information is used to obtain better estimates, as it introduces in the tracking algorithm a measure of the real velocity. Inertial information is also used to eliminate some ambiguities arising from the use of a monocular image sequence. As the algorithms developed are intended to be used in real-time control systems, considerations on computation costs are taken into account.

Original languageEnglish
Pages (from-to)23-32
Number of pages10
JournalJournal of Robotic Systems
Volume21
Issue number1
DOIs
Publication statusPublished - Jan 2004
Externally publishedYes

Fingerprint

Robots
Real time control
Mobile robots
Control systems
Costs

Cite this

Alenyà, Guillem ; Martínez, Elisa ; Torras, Carme. / Fusing visual and inertial sensing to recover robot ego-motion. In: Journal of Robotic Systems. 2004 ; Vol. 21, No. 1. pp. 23-32.
@article{cbb050cdabce4039a5c98033b8ba43d9,
title = "Fusing visual and inertial sensing to recover robot ego-motion",
abstract = "A method for estimating mobile robot ego-motion is presented, which relies on tracking contours in real-time images acquired with a calibrated monocular video system. After fitting an active contour to an object in the image, 3D motion is derived from the affine deformations suffered by the contour in an image sequence. More than one object can be tracked at the same time, yielding some different pose estimations. Then, improvements in pose determination are achieved by fusing all these different estimations. Inertial information is used to obtain better estimates, as it introduces in the tracking algorithm a measure of the real velocity. Inertial information is also used to eliminate some ambiguities arising from the use of a monocular image sequence. As the algorithms developed are intended to be used in real-time control systems, considerations on computation costs are taken into account.",
keywords = "Computer vision, Motion planning, Position control, Three dimensional, Velocity measurement, Monocular video system, Mobile robots, Ego-motion, Contour tracking",
author = "Guillem Aleny{\`a} and Elisa Mart{\'i}nez and Carme Torras",
year = "2004",
month = "1",
doi = "10.1002/rob.10125",
language = "English",
volume = "21",
pages = "23--32",
journal = "Journal of Robotic Systems",
issn = "1556-4959",
publisher = "John Wiley & Sons",
number = "1",

}

Fusing visual and inertial sensing to recover robot ego-motion. / Alenyà, Guillem; Martínez, Elisa; Torras, Carme.

In: Journal of Robotic Systems, Vol. 21, No. 1, 01.2004, p. 23-32.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fusing visual and inertial sensing to recover robot ego-motion

AU - Alenyà, Guillem

AU - Martínez, Elisa

AU - Torras, Carme

PY - 2004/1

Y1 - 2004/1

N2 - A method for estimating mobile robot ego-motion is presented, which relies on tracking contours in real-time images acquired with a calibrated monocular video system. After fitting an active contour to an object in the image, 3D motion is derived from the affine deformations suffered by the contour in an image sequence. More than one object can be tracked at the same time, yielding some different pose estimations. Then, improvements in pose determination are achieved by fusing all these different estimations. Inertial information is used to obtain better estimates, as it introduces in the tracking algorithm a measure of the real velocity. Inertial information is also used to eliminate some ambiguities arising from the use of a monocular image sequence. As the algorithms developed are intended to be used in real-time control systems, considerations on computation costs are taken into account.

AB - A method for estimating mobile robot ego-motion is presented, which relies on tracking contours in real-time images acquired with a calibrated monocular video system. After fitting an active contour to an object in the image, 3D motion is derived from the affine deformations suffered by the contour in an image sequence. More than one object can be tracked at the same time, yielding some different pose estimations. Then, improvements in pose determination are achieved by fusing all these different estimations. Inertial information is used to obtain better estimates, as it introduces in the tracking algorithm a measure of the real velocity. Inertial information is also used to eliminate some ambiguities arising from the use of a monocular image sequence. As the algorithms developed are intended to be used in real-time control systems, considerations on computation costs are taken into account.

KW - Computer vision

KW - Motion planning

KW - Position control

KW - Three dimensional

KW - Velocity measurement

KW - Monocular video system

KW - Mobile robots

KW - Ego-motion

KW - Contour tracking

UR - http://www.scopus.com/inward/record.url?scp=1642420631&partnerID=8YFLogxK

U2 - 10.1002/rob.10125

DO - 10.1002/rob.10125

M3 - Article

VL - 21

SP - 23

EP - 32

JO - Journal of Robotic Systems

JF - Journal of Robotic Systems

SN - 1556-4959

IS - 1

ER -