Work

Automatic Identification of Static Harbor Objects Based on Camera Images from a Highly Autonomous Dredger Ship

Year: 2025

Type: article

Abstract: Possible collisions with port infrastructure are a big challenge in the automation of commercial shipping. The first step to avoiding these collisions is identifying static port infrastructure. To minimize the risk of collisions of automated vessels with port infrastructure, this study aims to develop a model for automatically detecting static harbor objects (quay walls and piles) in port areas using a YOLOv5-based deep learning architecture. The existing architecture is adapted by generating a port-specific image dataset using image obfuscation techniques that simulate real-world operational scenarios, additionally improving robustness. To determine optimal hyperparameters, such as image resolution, batch size, or selection of optimization algorithm, multiple experiments were conducted and evaluated. As the proposed system is used in a time critical environment, the evaluation is performed on the basis of model performance as well as inference time.

Source: Journal of Marine Science and Engineering

DOI: 10.3390/jmse13102015

Authors: Timo Siering, Matthias Steidel, Christian Steger

Institutions: Carl von Ossietzky Universität Oldenburg, Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $3,137