Toward robust multitype and orientation detection of vessels in maritime surveillance

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Samenvatting

Reliable multitype and orientation vessel detection is of vital importance for maritime surveillance. We develop three separate convolutional neural network (CNN) models for high-performance single-class vessel detection and then multiclass vessel-type/orientation detection. We also propose a modular combined network, which enhances the multiclass operation. The initial three models provide reliable F scores of 85, 82, and 76, respectively. In addition, the modular combined approach improves the F scores for the multitype and orientation vessel detection by 2 and 3, respectively. The training and testing were done on a dataset, including the multitype/orientation annotations, covering 31,078 vessel labels (10 vessel types and 5 orientations), which is offered to public access.

Originele taal-2Engels
Artikelnummer033015
TijdschriftJournal of Electronic Imaging
Volume29
Nummer van het tijdschrift3
DOI's
StatusGepubliceerd - 1 mei 2020

Vingerafdruk Duik in de onderzoeksthema's van 'Toward robust multitype and orientation detection of vessels in maritime surveillance'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit