Abnormality detection strategies for surface inspection using robot mounted laser scanners

Sara Sharifzadeh, Istvan Biro, Niels Lohse, Peter Kinnell

Research output: Contribution to journalArticle

Abstract

The detection of small surface abnormalities on large complex free-form surfaces represents a significant challenge. Often surfaces abnormalities are less than a millimeter square in area but, must be located on surfaces of multiple meters square. To achieve consistent, cost effective and fast inspection, robotic or automated inspection systems are highly desirable. The challenge with automated inspection systems is to create a robust and accurate system that is not adversely affected by environmental variation. Robot-mounted laser line scanner systems can be used to acquire surface measurements, in the form of a point cloud1 (PC), from large complex geometries. This paper addresses the challenge of how surface abnormalities can be detected based on PC data by considering two different analysis strategies. First, an unsupervised thresholding strategy is considered, and through an experimental study the factors that affect abnormality detection performance are considered. Second, a robust supervised abnormality detection strategy is proposed. The performance of the proposed robust detection algorithm is evaluated experimentally using a realistic test scenario including a complex surface geometry, inconsistent PC quality and variable PC noise. Test results of the unsupervised analysis strategy shows that besides the abnormality size, the laser projection angle and laser lines spacing play an important role on the performance of the unsupervised detection strategy. In addition, a compromise should be made between the threshold value and the sensitivity and specificity of the results.
LanguageEnglish
Pages59-74
Number of pages16
JournalMechatronics
Volume51
Early online date19 Mar 2018
DOIs
StatePublished - May 2018
Externally publishedYes

Fingerprint

Inspection
Robots
Lasers
Geometry
Surface measurement
Robotics
Costs

Bibliographical note

Under a Creative Commons license

Keywords

  • Automatic abnormality detection
  • Sensitivity and specificity
  • Surface inspection
  • Feature classification
  • Feature extraction
  • Point cloud analysis

Cite this

Abnormality detection strategies for surface inspection using robot mounted laser scanners. / Sharifzadeh, Sara; Biro, Istvan; Lohse, Niels; Kinnell, Peter.

In: Mechatronics, Vol. 51, 05.2018, p. 59-74.

Research output: Contribution to journalArticle

Sharifzadeh, Sara ; Biro, Istvan ; Lohse, Niels ; Kinnell, Peter. / Abnormality detection strategies for surface inspection using robot mounted laser scanners. In: Mechatronics. 2018 ; Vol. 51. pp. 59-74
@article{841721158c6e4f6f8ca622b113664233,
title = "Abnormality detection strategies for surface inspection using robot mounted laser scanners",
abstract = "The detection of small surface abnormalities on large complex free-form surfaces represents a significant challenge. Often surfaces abnormalities are less than a millimeter square in area but, must be located on surfaces of multiple meters square. To achieve consistent, cost effective and fast inspection, robotic or automated inspection systems are highly desirable. The challenge with automated inspection systems is to create a robust and accurate system that is not adversely affected by environmental variation. Robot-mounted laser line scanner systems can be used to acquire surface measurements, in the form of a point cloud1 (PC), from large complex geometries. This paper addresses the challenge of how surface abnormalities can be detected based on PC data by considering two different analysis strategies. First, an unsupervised thresholding strategy is considered, and through an experimental study the factors that affect abnormality detection performance are considered. Second, a robust supervised abnormality detection strategy is proposed. The performance of the proposed robust detection algorithm is evaluated experimentally using a realistic test scenario including a complex surface geometry, inconsistent PC quality and variable PC noise. Test results of the unsupervised analysis strategy shows that besides the abnormality size, the laser projection angle and laser lines spacing play an important role on the performance of the unsupervised detection strategy. In addition, a compromise should be made between the threshold value and the sensitivity and specificity of the results.",
keywords = "Automatic abnormality detection, Sensitivity and specificity, Surface inspection, Feature classification, Feature extraction, Point cloud analysis",
author = "Sara Sharifzadeh and Istvan Biro and Niels Lohse and Peter Kinnell",
note = "Under a Creative Commons license",
year = "2018",
month = "5",
doi = "10.1016/j.mechatronics.2018.03.001",
language = "English",
volume = "51",
pages = "59--74",
journal = "Mechatronics",
issn = "0957-4158",
publisher = "Elsevier",

}

TY - JOUR

T1 - Abnormality detection strategies for surface inspection using robot mounted laser scanners

AU - Sharifzadeh,Sara

AU - Biro,Istvan

AU - Lohse,Niels

AU - Kinnell,Peter

N1 - Under a Creative Commons license

PY - 2018/5

Y1 - 2018/5

N2 - The detection of small surface abnormalities on large complex free-form surfaces represents a significant challenge. Often surfaces abnormalities are less than a millimeter square in area but, must be located on surfaces of multiple meters square. To achieve consistent, cost effective and fast inspection, robotic or automated inspection systems are highly desirable. The challenge with automated inspection systems is to create a robust and accurate system that is not adversely affected by environmental variation. Robot-mounted laser line scanner systems can be used to acquire surface measurements, in the form of a point cloud1 (PC), from large complex geometries. This paper addresses the challenge of how surface abnormalities can be detected based on PC data by considering two different analysis strategies. First, an unsupervised thresholding strategy is considered, and through an experimental study the factors that affect abnormality detection performance are considered. Second, a robust supervised abnormality detection strategy is proposed. The performance of the proposed robust detection algorithm is evaluated experimentally using a realistic test scenario including a complex surface geometry, inconsistent PC quality and variable PC noise. Test results of the unsupervised analysis strategy shows that besides the abnormality size, the laser projection angle and laser lines spacing play an important role on the performance of the unsupervised detection strategy. In addition, a compromise should be made between the threshold value and the sensitivity and specificity of the results.

AB - The detection of small surface abnormalities on large complex free-form surfaces represents a significant challenge. Often surfaces abnormalities are less than a millimeter square in area but, must be located on surfaces of multiple meters square. To achieve consistent, cost effective and fast inspection, robotic or automated inspection systems are highly desirable. The challenge with automated inspection systems is to create a robust and accurate system that is not adversely affected by environmental variation. Robot-mounted laser line scanner systems can be used to acquire surface measurements, in the form of a point cloud1 (PC), from large complex geometries. This paper addresses the challenge of how surface abnormalities can be detected based on PC data by considering two different analysis strategies. First, an unsupervised thresholding strategy is considered, and through an experimental study the factors that affect abnormality detection performance are considered. Second, a robust supervised abnormality detection strategy is proposed. The performance of the proposed robust detection algorithm is evaluated experimentally using a realistic test scenario including a complex surface geometry, inconsistent PC quality and variable PC noise. Test results of the unsupervised analysis strategy shows that besides the abnormality size, the laser projection angle and laser lines spacing play an important role on the performance of the unsupervised detection strategy. In addition, a compromise should be made between the threshold value and the sensitivity and specificity of the results.

KW - Automatic abnormality detection

KW - Sensitivity and specificity

KW - Surface inspection

KW - Feature classification

KW - Feature extraction

KW - Point cloud analysis

U2 - 10.1016/j.mechatronics.2018.03.001

DO - 10.1016/j.mechatronics.2018.03.001

M3 - Article

VL - 51

SP - 59

EP - 74

JO - Mechatronics

T2 - Mechatronics

JF - Mechatronics

SN - 0957-4158

ER -