Visual odometry and image mosaicing for NDE

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Miniature robotic vehicles are receiving increasing attention for use in non-destructive testing (NDT) due to their attractiveness in terms of cost, safety and their accessibility to areas where manual inspection is not practical. Cameras can play several roles in a robotic system as a result of the information rich nature of the 2D image signal including object/shape recognition, motion estimation and ranging. This paper considers a robot configured with a single camera that monitors the surface of the structure under the robot as it moves. Visual odometry is demonstrated that can reliably track the robot's position. An image mosaicing approach is presented that calculates the robot's path using the complete image set, taking account of overlapping images that were not consecutive in the image stream. It is shown that this significantly reduced the absolute error of the positional estimate. The system was found to work well on surfaces that were not highly reflecting including steel which is common in industrial plant.
LanguageEnglish
Pages17-25
Number of pages9
JournalNDT and E International
Volume57
DOIs
Publication statusAccepted/In press - Jul 2013

Fingerprint

robots
Robots
Robotics
robotics
Cameras
cameras
Steel
Motion estimation
Nondestructive examination
Industrial plants
industrial plants
Inspection
inspection
safety
vehicles
steels
costs
Costs
estimates

Keywords

  • robotic
  • visual
  • positioning
  • mosaicing

Cite this

@article{d7fe3307ba96488d946c468b6859a7e9,
title = "Visual odometry and image mosaicing for NDE",
abstract = "Miniature robotic vehicles are receiving increasing attention for use in non-destructive testing (NDT) due to their attractiveness in terms of cost, safety and their accessibility to areas where manual inspection is not practical. Cameras can play several roles in a robotic system as a result of the information rich nature of the 2D image signal including object/shape recognition, motion estimation and ranging. This paper considers a robot configured with a single camera that monitors the surface of the structure under the robot as it moves. Visual odometry is demonstrated that can reliably track the robot's position. An image mosaicing approach is presented that calculates the robot's path using the complete image set, taking account of overlapping images that were not consecutive in the image stream. It is shown that this significantly reduced the absolute error of the positional estimate. The system was found to work well on surfaces that were not highly reflecting including steel which is common in industrial plant.",
keywords = "robotic, visual, positioning, mosaicing",
author = "Gordon Dobie and Rahul Summan and MacLeod, {Charles Norman} and Stephen Pierce",
year = "2013",
month = "7",
doi = "10.1016/j.ndteint.2013.03.002",
language = "English",
volume = "57",
pages = "17--25",
journal = "NDT and E International",
issn = "0963-8695",

}

Visual odometry and image mosaicing for NDE. / Dobie, Gordon; Summan, Rahul; MacLeod, Charles Norman; Pierce, Stephen.

In: NDT and E International, Vol. 57, 07.2013, p. 17-25.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Visual odometry and image mosaicing for NDE

AU - Dobie, Gordon

AU - Summan, Rahul

AU - MacLeod, Charles Norman

AU - Pierce, Stephen

PY - 2013/7

Y1 - 2013/7

N2 - Miniature robotic vehicles are receiving increasing attention for use in non-destructive testing (NDT) due to their attractiveness in terms of cost, safety and their accessibility to areas where manual inspection is not practical. Cameras can play several roles in a robotic system as a result of the information rich nature of the 2D image signal including object/shape recognition, motion estimation and ranging. This paper considers a robot configured with a single camera that monitors the surface of the structure under the robot as it moves. Visual odometry is demonstrated that can reliably track the robot's position. An image mosaicing approach is presented that calculates the robot's path using the complete image set, taking account of overlapping images that were not consecutive in the image stream. It is shown that this significantly reduced the absolute error of the positional estimate. The system was found to work well on surfaces that were not highly reflecting including steel which is common in industrial plant.

AB - Miniature robotic vehicles are receiving increasing attention for use in non-destructive testing (NDT) due to their attractiveness in terms of cost, safety and their accessibility to areas where manual inspection is not practical. Cameras can play several roles in a robotic system as a result of the information rich nature of the 2D image signal including object/shape recognition, motion estimation and ranging. This paper considers a robot configured with a single camera that monitors the surface of the structure under the robot as it moves. Visual odometry is demonstrated that can reliably track the robot's position. An image mosaicing approach is presented that calculates the robot's path using the complete image set, taking account of overlapping images that were not consecutive in the image stream. It is shown that this significantly reduced the absolute error of the positional estimate. The system was found to work well on surfaces that were not highly reflecting including steel which is common in industrial plant.

KW - robotic

KW - visual

KW - positioning

KW - mosaicing

UR - http://www.scopus.com/inward/record.url?scp=84876245854&partnerID=8YFLogxK

U2 - 10.1016/j.ndteint.2013.03.002

DO - 10.1016/j.ndteint.2013.03.002

M3 - Article

VL - 57

SP - 17

EP - 25

JO - NDT and E International

T2 - NDT and E International

JF - NDT and E International

SN - 0963-8695

ER -