Citation: Tavakoli, Y.; Pena-Castillo,
L.; Soares, A. A Study on the
Geometric and Kinematic Descriptors
of Trajectories in the Classification of
Ship Types. Sensors 2022, 22, 5588.
https://doi.org/10.3390/s22155588
Academic Editor: Jiachen Yang
Received: 15 June 2022
Accepted: 20 July 2022
Published: 26 July 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Study on the Geometric and Kinematic Descriptors of
Trajectories in the Classification of Ship Types
Yashar Tavakoli * , Lourdes Peña-Castillo and Amilcar Soares
Department of Computer Science, Memorial University of Newfoundland, St. John’s, NL A1B 3X5, Canada;
lourdes@mun.ca (L.P.-C.); asoaresjunio@mun.ca (A.S.)
* Correspondence: yt3165@mun.ca
Abstract:
The classification of ships based on their trajectory descriptors is a common practice that is
helpful in various contexts, such as maritime security and traffic management. For the most part, the
descriptors are either geometric, which capture the shape of a ship’s trajectory, or kinematic, which
capture the motion properties of a ship’s movement. Understanding the implications of the type of
descriptor that is used in classification is important for feature engineering and model interpretation.
However, this matter has not yet been deeply studied. This article contributes to feature engineering
within this field by introducing proper similarity measures between the descriptors and defining
sound benchmark classifiers, based on which we compared the predictive performance of geometric
and kinematic descriptors. The performance profiles of geometric and kinematic descriptors, along
with several standard tools in interpretable machine learning, helped us provide an account of how
different ships differ in movement. Our results indicated that the predictive performance of geometric
and kinematic descriptors varied greatly, depending on the classification problem at hand. We also
showed that the movement of certain ship classes solely differed geometrically while some other
classes differed kinematically and that this difference could be formulated in simple terms. On
the other hand, the movement characteristics of some other ship classes could not be delineated
along these lines and were more complicated to express. Finally, this study verified the conjecture
that the geometric–kinematic taxonomy could be further developed as a tool for more accessible
feature selection.
Keywords:
trajectory; descriptor; classification; ship; feature engineering; feature selection; model
interpretation; knowledge discovery
1. Introduction
As several marine tracking technologies have become more prevalent in reporting
the positions of ships, movement mining practices, in particular the classification of ship
trajectories, have emerged as an active research area. By the classification of ship trajectories,
we mean the supervised learning problem of assigning the correct ship type to a trajectory.
Ship trajectory classification is useful for identifying illegal activities, imposing regulations,
managing navigation, maintaining biodiversity, extracting routes, and detecting anomalies.
Movement is usually expressed using trajectories. A raw trajectory consists of either
an ordered sequence of spatial pairs, each signifying a 2D position (latitude and longitude),
or an ordered sequence of spatiotemporal triplets, each signifying a 2D position along with
a time stamp. Trajectories in higher dimensions are also conceivable. According to [
1
],
it is possible to work with raw trajectories directly or to instead employ certain random
variables called descriptors, which are defined as random variables for either spatial or
spatiotemporal sequences. Therefore, in essence, a descriptor is a scalar value that measures
a certain aspect of the trajectory (e.g., the average speed or straightness) [
2
–
4
] and can
serve as a feature or attribute in the classification terminology. There are a number of
Sensors 2022, 22, 5588. https://doi.org/10.3390/s22155588 https://www.mdpi.com/journal/sensors
