Machine Learning for IWT Ship Traffic Analysis (Object Detection vs. AIS Data)

Master thesis (2023)

Authors

S. Vadachennimalai Selvaraj Mechanical Engineering

Contributors

F. Schulte Transport Engineering and Logistics - Mechanical, Maritime and Materials Engineering (supervisor 1)
P.A. Wenzel Transport Engineering and Logistics - Mechanical, Maritime and Materials Engineering (supervisor 2)
N. Pourmohammadzia Rivers, Ports, Waterways and Dredging Engineering - CEG (supervisor 2)
Faculty
Mechanical Engineering
Copyright: © 2023 Suryaa Vadachennimalai Selvaraj
More Info
expand_more

Published Date

23-10-2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical Engineering

Abstract

The Automatic Identification System (AIS) is used in the maritime domain to improve sea traffic safety by requiring vessels to broadcast real-time information such as identity, speed, location, and course. As it allows global monitoring of almost any larger vessel and has the potential to considerably improve vessel traffic services and collision risk assessment, AIS has been used in an increasing number of applications. This emphasizes why the quality of data transmitted is critical. We are also becoming more aware of the possibilities of spoofing or fabrication of AIS data, which has a direct impact on the dependability of AIS data. This study looks into comparing video surveillance with Automatic Identification System (AIS) data to detect data overlap or spoofing in the maritime environment. An object detection model was proposed and trained to fill the research gap mentioned above. Data from video surveillance and AIS were collected. A comparison of the results of object detection and AIS data was performed using a Python script. The analysis assisted in identifying data variations and understanding the potential and constraints of the current Algorithm. Work for the future is suggested to tackle the current constraints.