Abstract
This paper presents fast, accurate, and automatic methods for detecting seafloor pipelines in multibeam echo sounder data with deep learning. The proposed methods take inspiration from the highly successful ResNet and YOLO deep learning models and tailor them to the idiosyncrasies of the seafloor pipeline detection task.
 We use the area between lines and Hausdorff line distance functions to accurately evaluate how well methods can localize (pipe)lines. The same functions also show promise as loss functions compared to standard mean squared error, which does not include the regression variables' geometrical interpretation.
 The model outperforms the highest likelihood baseline by more than 35% on a region-wise F1-score classification evaluation while being more than eight times more accurate than the baseline in locating pipelines. It is efficient, operating at over eighteen 32-ping image segments per second, which is far beyond real-time requirements.
Highlights
Seafloor pipelines are critical infrastructure to transport oil and gas
All experiments and results are run on the AI HUB provided by the University of Oslo, which consists of 2 x 14 core Intel CPUs, 4 NVIDIA RTX 2080 Ti GPUs, 128GiB RAM, using Ubuntu 16.04
This work demonstrates that deep learning with ResNet50 and single-shot detection can efficiently and accurately detect pipelines in multibeam echo sounder data
Summary
Seafloor pipelines are critical infrastructure to transport oil and gas. As pipeline failures can result in high economic and environmental costs, the pipeline’s integrity must be verified through inspection. The objective of external inspection of seafloor pipelines is to determine the degree of burial and to detect potential free spans, buckles, debris, or damages from human activities such as trawling and anchoring [1]. Considerable variability in the appearance of pipelines in the payload sensor data, makes designing automatic detection algorithms a challenging task. This work investigates whether we can use deep learning methods to detect seafloor pipelines in MBES data. We would use all payload sensors simultaneously during a seafloor pipeline inspection mission.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Proceedings of the Northern Lights Deep Learning Workshop
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
