Development of an Automated Coastal Biofouling Detection System using Artificial Intelligence Object Detection

Veerasingam, S., Asim, F.S., Hashir, P.K., Prince, J.I., Hana Ahmed, Fatma Magdy, E.E.E., Athaulla, R., Ranjani, M., Abisha, B., Mohamed, R.O., Al-Khayat, J.A., Rajendran, S., Vethamony, P., Sadooni, F.N., and Ghani, S., 2024. Development of an automated coastal biofouling detection system using artificial intelligence object detection. In: Phillips, M.R.; Al-Naemi, S., and Duarte, C.M. (eds.), Coastlines under Global Change: Proceedings from the International Coastal Symposium (ICS) 2024 (Doha, Qatar). Journal of Coastal Research, Special Issue No. 113, pp. 846-850. Charlotte (North Carolina), ISSN 0749-0208. The introduction of non-indigenous biofouling organisms (NIBOs) to the coastal environments can play an important role in shaping coastal biodiversity, ecosystem services, economy, and human health. Marine litter, especially plastic debris, can serve as a vector (hitchhiking) for the transport of alien biofouling species in the marine environment. Considering the current rate of plastic waste generation in the Regional Organization for the Protection of the Marine Environment (ROPME) area, it is likely that biofouling may also increase through floating marine litter. In recognition of increasing NIBOs threat to global biodiversity, the International Union for Conservation of Nature (IUCN) Invasive Species Specialist Group (ISSG) has established for conservation of biodiversity. Traditional biofouling detection methods suffer from long detection cycles, low accuracy in large quantities, and difficulty in detecting uncommon fouling organisms. Therefore, applying artificial intelligence-based object detection models biofouling detection is meaningful. Object detection analysis can achieve high-precision and high-efficiency detection of fouling organisms. This study aims to explore the potential of artificial intelligence, particularly object detection models in the automatic detection and classification of biofouling using meta-data. Moreover, this study highlights the research gaps and future research directions in AI based approaches in biofouling management.