A sensor for pipe inspection: Model, analysis and image extraction

Olga Duran, Kaspar Althoefer, Lakmal D. Seneviratne

Research output: Contribution to conferencePaperpeer-review

11 Scopus citations

Abstract

Pipe inspection, for many industrial applications, is commonly carried out using CCTV (Closed-Circuit TV) cameras and off-line human analysis via raw image examination for defect detection. Researchers have proposed the use of additional sensors and lighting systems to create ring profiles onto pipe segments. Geometrical changes in the profile are analyzed to determine pipe deformation. However the light intensity information has not been considered in such works. In this paper we propose an intensity-based profiler system. The sensor consists of a laser profiler that is attached to a standard CCTV system. The physical sensor behavior is described using reflectance theory and experimental data. Finally, an image of the pipe wall is generated by extracting the intensity information existing in the pipe pictures. Defects and anomalies can be identified using this extracted image.

Original languageBritish English
Pages597-600
Number of pages4
StatePublished - 2003
EventProceedings: 2003 International Conference on Image Processing, ICIP-2003 - Barcelona, Spain
Duration: 14 Sep 200317 Sep 2003

Conference

ConferenceProceedings: 2003 International Conference on Image Processing, ICIP-2003
Country/TerritorySpain
CityBarcelona
Period14/09/0317/09/03

Fingerprint

Dive into the research topics of 'A sensor for pipe inspection: Model, analysis and image extraction'. Together they form a unique fingerprint.

Cite this