Automatic Annotation of Subsea Pipelines using Deep Learning
| Autor: | Andrew Hamilton, W. Craig Michie, Christos Tachtatzis, Javier Cardona, Robert Atkinson, Hein Filius, Chris McCaig, Anastasios Stamoulakatos, Gaetano Di Caterina, Ivan Andonovic, Pavlos I. Lazaridis, David Murray, Xavier Bellekens, Md. Moinul Hossain |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
TK 02 engineering and technology transfer learning lcsh:Chemical technology Q1 computer.software_genre Biochemistry Convolutional neural network Article Analytical Chemistry Annotation 0202 electrical engineering electronic engineering information engineering lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation business.industry Event (computing) Deep learning multi-label image classification deep learning 021001 nanoscience & nanotechnology Pipeline (software) Atomic and Molecular Physics and Optics Pipeline transport sub-sea pipeline survey Automatic image annotation 020201 artificial intelligence & image processing Data mining Artificial intelligence 0210 nano-technology business TC computer visual inspection |
| Zdroj: | Sensors (Basel, Switzerland) Sensors Volume 20 Issue 3 Sensors, Vol 20, Iss 3, p 674 (2020) |
| ISSN: | 1424-8220 |
| Popis: | Regulatory requirements for sub-sea oil and gas operators mandates the frequent inspection of pipeline assets to ensure that their degradation and damage are maintained at acceptable levels. The inspection process is usually sub-contracted to surveyors who utilize sub-sea Remotely Operated Vehicles (ROVs), launched from a surface vessel and piloted over the pipeline. ROVs capture data from various sensors/instruments which are subsequently reviewed and interpreted by human operators, creating a log of event annotations a slow, labor-intensive and costly process. The paper presents an automatic image annotation framework that identifies/classifies key events of interest in the video footage viz. exposure, burial, field joints, anodes, and free spans. The reported methodology utilizes transfer learning with a Deep Convolutional Neural Network (ResNet-50), fine-tuned on real-life, representative data from challenging sub-sea environments with low lighting conditions, sand agitation, sea-life and vegetation. The network outputs are configured to perform multi-label image classifications for critical events. The annotation performance varies between 95.1% and 99.7% in terms of accuracy and 90.4% and 99.4% in terms of F1-Score depending on event type. The performance results are on a per-frame basis and corroborate the potential of the algorithm to be the foundation for an intelligent decision support framework that automates the annotation process. The solution can execute annotations in real-time and is significantly more cost-effective than human-only approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|