A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification

Anastasios Stamoulakatos, Javier Cardona, Craig Michie, Ivan Andonovic, Pavlos Lazaridis, Xavier Bellekens, Robert Atkinson, Md Moinul Hossain, Christos Tachtatzis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Citations (Scopus)


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.

Original languageEnglish
Title of host publicationOCEANS 2021
Subtitle of host publicationSan Diego - Porto
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages10
ISBN (Electronic)9780692935590
ISBN (Print)9781665427883
Publication statusPublished - 20 Sep 2021
EventOCEANS 2021: San Diego - Porto - San Diego, United States
Duration: 20 Sep 202123 Sep 2021

Publication series

NameOceans Conference Record (IEEE)
ISSN (Print)0197-7385


ConferenceOCEANS 2021: San Diego - Porto
Country/TerritoryUnited States
CitySan Diego


Dive into the research topics of 'A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification'. Together they form a unique fingerprint.

Cite this