APA 6th Edition Lorencin, I., Anđelić, N., Mrzljak, V. i Car, Z. (2019). Marine Objects Recognition Using Convolutional Neural Networks. NAŠE MORE, 66 (3), 112-119. https://doi.org/10.17818/NM/2019/3.3
MLA 8th Edition Lorencin, Ivan, et al. "Marine Objects Recognition Using Convolutional Neural Networks." NAŠE MORE, vol. 66, br. 3, 2019, str. 112-119. https://doi.org/10.17818/NM/2019/3.3. Citirano 21.11.2019.
Chicago 17th Edition Lorencin, Ivan, Nikola Anđelić, Vedran Mrzljak i Zlatan Car. "Marine Objects Recognition Using Convolutional Neural Networks." NAŠE MORE 66, br. 3 (2019): 112-119. https://doi.org/10.17818/NM/2019/3.3
Harvard Lorencin, I., et al. (2019). 'Marine Objects Recognition Using Convolutional Neural Networks', NAŠE MORE, 66(3), str. 112-119. https://doi.org/10.17818/NM/2019/3.3
Vancouver Lorencin I, Anđelić N, Mrzljak V, Car Z. Marine Objects Recognition Using Convolutional Neural Networks. NAŠE MORE [Internet]. 2019 [pristupljeno 21.11.2019.];66(3):112-119. https://doi.org/10.17818/NM/2019/3.3
IEEE I. Lorencin, N. Anđelić, V. Mrzljak i Z. Car, "Marine Objects Recognition Using Convolutional Neural Networks", NAŠE MORE, vol.66, br. 3, str. 112-119, 2019. [Online]. https://doi.org/10.17818/NM/2019/3.3
Sažetak One of the challenges of maritime affairs is automatic object recognition from aerial imagery. This can be achieved by utilizing a Convolutional Neural Network (CNN) based algorithm. For purposes of these research a dataset of 5608 marine object images is collected by using Google satellite imagery and Google Image Search. The dataset is divided in two main classes ("Vessels" and "Other objects") and each class is divided into four sub-classes ("Vessels" sub-classes are "Cargo ships", "Cruise ships", "War ships" and "Boats", while "Other objects" sub-classes are "Waves", "Marine animals", “Garbage patches" and "Oil spills"). For recognition of marine objects, an algorithm constructed with three CNNs is proposed. The first CNN for classification on the main classes achieves accuracy of 92.37 %. The CNN used for vessels recognition achieves accuracies of 94.12 % for cargo ships recognition, 98.82 % for cruise ships recognition, 97.64 % for war ships recognition and 95.29 % for boats recognition. The CNN used for recognition of other objects achieves accuracies of 88.56 % for waves and marine animals recognition, 96.92 % for garbage patches recognition and 89.21 % for oil spills recognition. This research has shown that CNN is appropriate artificial intelligence (AI) method for marine object recognition from aerial imagery.