Imagen de Portada

Artificial Intelligence-Based Prediction Model for Maritime Vessel Type Identification

Guardado en:
Publicado en:Information vol. 16, no. 5 (2025), p. 367
Autor principal: Karna Hrvoje
Otros Autores: Braović Maja, Gudelj Anita, Buličić Kristian
Publicado:
MDPI AG
Materias:
North Atlantic Treaty Organization > NATO
Croatia
Adriatic Sea
Sea vessels
Automatic classification
Deep learning
Maritime security
Data mining
Evacuations & rescues
Automation
Machine learning
Image processing
Decision trees
Cameras
Territorial waters
Neural networks
Artificial intelligence
Computer vision
Prediction models
Situational awareness
Image classification
Design
Algorithms
Information systems
Surveillance
Identification systems
Covert operations
Radar
National parks
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:This paper presents an artificial intelligence-based model for the classification of maritime vessel images obtained by cameras operating in the visible part of the electromagnetic spectrum. It incorporates both the deep learning techniques for initial image representation and traditional image processing and machine learning methods for subsequent image classification. The presented model is therefore a hybrid approach that uses the Inception v3 deep learning model for the purpose of image vectorization and a combination of SVM, kNN, logistic regression, Naïve Bayes, neural network, and decision tree algorithms for final image classification. The model is trained and tested on a custom dataset consisting of a total of 2915 images of maritime vessels. These images were split into three subsections: training (2444 images), validation (271 images), and testing (200 images). The images themselves encompassed 11 distinctive classes: cargo, container, cruise, fishing, military, passenger, pleasure, sailing, special, tanker, and non-class (objects that can be encountered at sea but do not represent maritime vessels). The presented model accurately classified 86.5% of the images used for training purposes and therefore demonstrated how a relatively straightforward model can still achieve high accuracy and potentially be useful in real-world operational environments aimed at sea surveillance and automatic situational awareness at sea.
ISSN:2078-2489
DOI:10.3390/info16050367
Fuente:Advanced Technologies & Aerospace Database