Welcome to the InfoSci Platform
Reference Hub1
Boat Detection in Marina Using Time-Delay Analysis and Deep Learning

Boat Detection in Marina Using Time-Delay Analysis and Deep Learning

Romane Scherrer, Erwan Aulnette, Thomas Quiniou, Joël Kasarherou, Pierre Kolb, Nazha Selmaoui-Folcher
Copyright: © 2022 |Volume: 18 |Issue: 2 |Pages: 16
ISSN: 1548-3924|EISSN: 1548-3932|EISBN13: 9781799893691|DOI: 10.4018/IJDWM.298006
Cite Article Cite Article

MLA

Scherrer, Romane, et al. "Boat Detection in Marina Using Time-Delay Analysis and Deep Learning." IJDWM vol.18, no.2 2022: pp.1-16. http://doi.org/10.4018/IJDWM.298006

APA

Scherrer, R., Aulnette, E., Quiniou, T., Kasarherou, J., Kolb, P., & Selmaoui-Folcher, N. (2022). Boat Detection in Marina Using Time-Delay Analysis and Deep Learning. International Journal of Data Warehousing and Mining (IJDWM), 18(2), 1-16. http://doi.org/10.4018/IJDWM.298006

Chicago

Scherrer, Romane, et al. "Boat Detection in Marina Using Time-Delay Analysis and Deep Learning," International Journal of Data Warehousing and Mining (IJDWM) 18, no.2: 1-16. http://doi.org/10.4018/IJDWM.298006

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

An autonomous acoustic system based on two bottom-moored hydrophones, a two-input audio board and a small single-board computer was installed at the entrance of a marina to detect entering/exiting boat. Windowed time lagged cross-correlations are calculated by the system to find the consecutive time delays between the hydrophone signals and to compute a signal which is a function of the boats' angular trajectories. Since its installation, the single-board computer performs online prediction with a signal processing-based algorithm which achieved an accuracy of 80 %. To improve system performance, a convolutional neural network (CNN) is trained with the acquired data to perform real-time detection. Two classification tasks were considered (binary and multiclass) to both detect a boat and its direction of navigation. Finally, a trained CNN was implemented in a single-board computer to ensure that prediction can be performed in real time.