Visual navigation using planar homographies

B J Liang; N Pears

Visual navigation using planar homographies

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We introduce three new results, which allow homographies of the ground plane to support visual navigation functions for mobile robots using uncalibrated cameras. Firstly, we illustrate how, for pure translation, a homography can be computed from just two pairs of corresponding corner features. Secondly, we show how, for pure translation, we can determine the height of corner features above the ground plane using the recovered homography and a construct based on the cross ratio. This allows us to detect points which can be driven over, as their height is measured to be close to zero, and points which are sufficiently high to drive under. Finally, we show how, in the case of general planar motion, homographies can be used to determine the rotation of the camera and robot.

Original language	English
Title of host publication	2002 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS
Place of Publication	NEW YORK
Publisher	IEEE
Pages	205-210
Number of pages	6
ISBN (Print)	0-7803-7272-7
Publication status	Published - 2002
Event	19th IEEE International Conference on Robotics and Automation (ICRA) - WASHINGTON Duration: 11 May 2002 → 15 May 2002

Conference

Conference	19th IEEE International Conference on Robotics and Automation (ICRA)
City	WASHINGTON
Period	11/05/02 → 15/05/02

Keywords

visual navigation
mobile robots
monocular vision
uncalibrated cameras
PARAMETERS

Cite this

@inproceedings{d9ae6ec5091c49c48c060fcc7e9c2c72,

title = "Visual navigation using planar homographies",

abstract = "We introduce three new results, which allow homographies of the ground plane to support visual navigation functions for mobile robots using uncalibrated cameras. Firstly, we illustrate how, for pure translation, a homography can be computed from just two pairs of corresponding corner features. Secondly, we show how, for pure translation, we can determine the height of corner features above the ground plane using the recovered homography and a construct based on the cross ratio. This allows us to detect points which can be driven over, as their height is measured to be close to zero, and points which are sufficiently high to drive under. Finally, we show how, in the case of general planar motion, homographies can be used to determine the rotation of the camera and robot.",

keywords = "visual navigation, mobile robots, monocular vision, uncalibrated cameras, PARAMETERS",

author = "Liang, {B J} and N Pears",

year = "2002",

language = "English",

isbn = "0-7803-7272-7",

pages = "205--210",

booktitle = "2002 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS",

publisher = "IEEE",

address = "United States",

note = "19th IEEE International Conference on Robotics and Automation (ICRA) ; Conference date: 11-05-2002 Through 15-05-2002",

}

TY - GEN

T1 - Visual navigation using planar homographies

AU - Liang, B J

AU - Pears, N

PY - 2002

Y1 - 2002

N2 - We introduce three new results, which allow homographies of the ground plane to support visual navigation functions for mobile robots using uncalibrated cameras. Firstly, we illustrate how, for pure translation, a homography can be computed from just two pairs of corresponding corner features. Secondly, we show how, for pure translation, we can determine the height of corner features above the ground plane using the recovered homography and a construct based on the cross ratio. This allows us to detect points which can be driven over, as their height is measured to be close to zero, and points which are sufficiently high to drive under. Finally, we show how, in the case of general planar motion, homographies can be used to determine the rotation of the camera and robot.

AB - We introduce three new results, which allow homographies of the ground plane to support visual navigation functions for mobile robots using uncalibrated cameras. Firstly, we illustrate how, for pure translation, a homography can be computed from just two pairs of corresponding corner features. Secondly, we show how, for pure translation, we can determine the height of corner features above the ground plane using the recovered homography and a construct based on the cross ratio. This allows us to detect points which can be driven over, as their height is measured to be close to zero, and points which are sufficiently high to drive under. Finally, we show how, in the case of general planar motion, homographies can be used to determine the rotation of the camera and robot.

KW - visual navigation

KW - mobile robots

KW - monocular vision

KW - uncalibrated cameras

KW - PARAMETERS

M3 - Conference contribution

SN - 0-7803-7272-7

SP - 205

EP - 210

BT - 2002 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS

PB - IEEE

CY - NEW YORK

T2 - 19th IEEE International Conference on Robotics and Automation (ICRA)

Y2 - 11 May 2002 through 15 May 2002

ER -