A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification
Published in IEEE OCEANS 2021, 2021
Recommended citation: Stamoulakatos, A., & Tachtatzis, C. (2021). A Comparison of the Performance of 2D and 3D Convolutional Neural Networks for Subsea Survey Video Classification. In OCEANS 2021 (pp. 1-6). IEEE. https://ieeexplore.ieee.org/document/9705912
Subsea pipeline inspections produce vast amounts of video data. This paper evaluates the performance of 2D and 3D Convolutional Neural Networks (CNNs) in capturing both spatial patterns and temporal features from subsea inspection video streams, identifying key trade-offs in accuracy and computation.