TY - GEN
T1 - A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification
AU - Stamoulakatos, Anastasios
AU - Cardona, Javier
AU - Michie, Craig
AU - Andonovic, Ivan
AU - Lazaridis, Pavlos
AU - Bellekens, Xavier
AU - Atkinson, Robert
AU - Hossain, Md Moinul
AU - Tachtatzis, Christos
N1 - Funding Information:
The work was partially supported by The Data Lab Innovation Centre, Edinburgh, Scotland, UK (project registration code 16270), the Oil and Gas Innovation Centre, Aberdeen, Scotland UK (project registration code 18PR-16) and N-Sea, Zierikzee, Netherlands. The Data Lab and the Oil and Gas Innovation Centres are funded by the Scottish Funding Council through the Innovation Centres Programme.
Funding Information:
The work was partially supported by The Data Lab Innovation Centre, Edinburgh, Scotland, UK (project registration code 16270), the Oil and Gas Innovation Centre, Aberdeen, Scotland UK (project registration code 18PR-16) and N-Sea, Zierikzee, Netherlands.
Publisher Copyright:
© 2021 MTS.
PY - 2021/9/20
Y1 - 2021/9/20
N2 - Utilising deep learning image classification to automatically annotate subsea pipeline video surveys can facilitate the tedious and labour-intensive process, resulting in significant time and cost savings. However, the classification of events on subsea survey videos (frame sequences) by models trained on individual frames have been proven to vary, leading to inaccuracies. The paper extends previous work on the automatic annotation of individual subsea survey frames by comparing the performance of 2D and 3D Convolutional Neural Networks (CNNs) in classifying frame sequences. The study explores the classification of burial, exposure, free span, field joint, and anode events. Sampling and regularization techniques are designed to address the challenges of an underwater inspection video dataset owing to the environment. Results show that a 2D CNN with rolling average can outperform a 3D CNN, achieving an Exact Match Ratio of 85% and F1-Score of 90%, whilst being more computationally efficient.
AB - Utilising deep learning image classification to automatically annotate subsea pipeline video surveys can facilitate the tedious and labour-intensive process, resulting in significant time and cost savings. However, the classification of events on subsea survey videos (frame sequences) by models trained on individual frames have been proven to vary, leading to inaccuracies. The paper extends previous work on the automatic annotation of individual subsea survey frames by comparing the performance of 2D and 3D Convolutional Neural Networks (CNNs) in classifying frame sequences. The study explores the classification of burial, exposure, free span, field joint, and anode events. Sampling and regularization techniques are designed to address the challenges of an underwater inspection video dataset owing to the environment. Results show that a 2D CNN with rolling average can outperform a 3D CNN, achieving an Exact Match Ratio of 85% and F1-Score of 90%, whilst being more computationally efficient.
KW - Deep Learning
KW - Subsea Inspection
KW - Underwater Pipelines
KW - Video Classification
UR - http://www.scopus.com/inward/record.url?scp=85125933006&partnerID=8YFLogxK
U2 - 10.23919/OCEANS44145.2021.9706125
DO - 10.23919/OCEANS44145.2021.9706125
M3 - Conference contribution
AN - SCOPUS:85125933006
SN - 9781665427883
T3 - Oceans Conference Record (IEEE)
BT - OCEANS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - OCEANS 2021: San Diego - Porto
Y2 - 20 September 2021 through 23 September 2021
ER -
