Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/23298

Title: Robust surface abnormality detection for a robotic inspection system
Authors: Sharifzadeh, Sara
Biro, Istvan
Lohse, Niels
Kinnell, Peter
Keywords: Automatic abnormality detection
Point Cloud analysis
Feature extraction
Feature classification
Adaptive smoothing
Surface inspection
Issue Date: 2016
Publisher: © IFAC. Published by Elsevier
Citation: SHARIFZADEH, S. ...et al., 2016. Robust surface abnormality detection for a robotic inspection system. IFAC-PapersOnLine, 49(21), pp. 301-308.
Abstract: The detection of surface abnormalities on large complex parts represents a significant automation challenge. This is particularly true when surfaces are large (multiple square metres) but abnormalities are small (less than one mm square), and the surfaces of interest are not simple flat planes. One possible solution is to use a robot-mounted laser line scanner, which can acquire fast surface measurements from large complex geometries. The problem with this approach is that the collected data may vary in quality, and this makes it difficult to achieve accurate and reliable inspection. In this paper a strategy for abnormality detection on highly curved Aluminum surfaces, using surface data obtained by a robot-mounted laser scanner, is presented. Using the laser scanner, data is collected from surfaces containing abnormalities, in the form of surface dents or bumps, of approximately one millimeter in diameter. To examine the effect of scan conditions on abnormality detection, two different curved test surfaces are used, and in addition the lateral spacing of laser scans was also varied. These variables were considered because they influence the distribution of points, in the point cloud (PC), that represent an abnormality. The proposed analysis consists of three main steps. First, a pre-processing step consisting of a fine smoothing procedure followed by a global noise analysis is carried out. Second, an abnormality classifier is trained based on a set of predefined surface abnormalities. Third, the trained classifier is used on suspicious areas of the surface in a general unsupervised thresholding step. This step saves computational time as it avoids analyzing every surface data point. Experimental results show that, the proposed technique can successfully find all present abnormalities for both training and test sets with minor false positives and no false negatives.
Description: This paper was presented at the 7th IFAC Symposium on Mechatronic Systems (MECHATRONICS 2016), Loughborough University, UK, 5-8th Sept. This paper was accepted for publication in the journal IFAC-PapersOnLine and the definitive published version is available at http://dx.doi.org/10.1016/j.ifacol.2016.10.572
Version: Accepted for publication
DOI: 10.1016/j.ifacol.2016.10.572
URI: https://dspace.lboro.ac.uk/2134/23298
Publisher Link: http://dx.doi.org/10.1016/j.ifacol.2016.10.572
ISSN: 2405-8963
Appears in Collections:Conference Papers and Contributions (Mechanical, Electrical and Manufacturing Engineering)

Files associated with this item:

File Description SizeFormat
TuPoT5-16.pdfAccepted version697.29 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.