Naslov
Detecting Underwater Sea Litter Using Deep Neural Networks: An Initial Study

Autori
Musić, Josip ; Kružić, Stanko ; Stančić, Ivo ; Alexandrou, Floris

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), ostalo

Izvornik
Proceedings of 5th International Conference on Smart and Sustainable Technologies (SpliTech 2020) / Rodrigues, Joel ; Nižetić, Sandro - Split : Faculty of electrical engineering, mechanical engineering and naval architecture, 2020

ISBN
978-953-290-100-9

Skup
5th International Conference on Smart and Sustainable Technologies (SpliTech 2020)

Mjesto i datum
Split, Hrvatska, 23.09.2020. - 26.09.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
marine litter ; neural networks ; detection ; classification ; underwater images

Sažetak
The world’s seas and the oceans are under constant negative pressure caused by human activity. It is estimated that more than 150 million tonnes of litter will be accumulated in the world’s oceans until 2025, while up to 12.7 million tonnes of litter will be added to the sea every year. Besides ecology-related issues, marine litter can also hurt the economy of the affected areas. Detection and classification of sea litter thus becomes a first step in tracking the litter and consequently a basis for the development of any automatic or human based marine litter retrieval system. Modern convolutional neural networks are a logical choice for detection and classification algorithms since they have proven themselves time after time in image-based machine learning tasks. Nevertheless, according to the available literature, the application of such neural networks in underwater images for marine litter detection (and classification) has started just recently. Thus, the paper carries out an initial study on the performance of such detection and classification system constructed in several ways and with several architectures, as well as using several sources of training data. It is shown that obtained validation accuracy is around 88% and test accuracy around 85%, depending on the used architecture, and that inclusion of synthetically generated images reduces the network performance on real- world image dataset.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA