Unmanned Aerial Vehicles (UAVs or drones) have been extensively applied in monitoring studies to address marine and terrestrial wildlife animals. The main advantages of UAVs are their operational flexibility and low cost. In the last few years, the need to safeguard and protect the population of cetaceans in the Gulf of Taranto (Northern Ionian Sea, Central-eastern Mediterranean Sea) has grown in importance, and the UAVs video-analysis systems meet this need. In particular, dolphins, which can be potentially harmed by human activities in this area, could benefit a lot from the use and the application of automatic systems, in terms of estimation of group size and abundance. The goal of this study is to develop an automated non-invasive system for the analysis of videos acquired by UAVs, devoted to the estimation of cetaceans group size and abundance. An automated system like the proposed one would allow having an immediate estimate of the number of the encountered cetaceans, onboard the vessel, to be compared with the estimation made by the Marine Mammal Observer (MMO) in charge or it would be a useful support system for the expert when he has to analyze the video in the laboratory. In this paper, as a case of study, the UAVs video-analysis system has been applied on videos acquired by a camera mounted on a drone, during surveys in the Gulf of Taranto. Two different models of machine learning were used, and both the trained models are able to solve the task well albeit with some limitations.

Automated and non-invasive UAV-based system for the monitoring and the group size estimation of dolphins

Dimauro G.
;
Simone L.;Carlucci R.;Maglietta R.
2022-01-01

Abstract

Unmanned Aerial Vehicles (UAVs or drones) have been extensively applied in monitoring studies to address marine and terrestrial wildlife animals. The main advantages of UAVs are their operational flexibility and low cost. In the last few years, the need to safeguard and protect the population of cetaceans in the Gulf of Taranto (Northern Ionian Sea, Central-eastern Mediterranean Sea) has grown in importance, and the UAVs video-analysis systems meet this need. In particular, dolphins, which can be potentially harmed by human activities in this area, could benefit a lot from the use and the application of automatic systems, in terms of estimation of group size and abundance. The goal of this study is to develop an automated non-invasive system for the analysis of videos acquired by UAVs, devoted to the estimation of cetaceans group size and abundance. An automated system like the proposed one would allow having an immediate estimate of the number of the encountered cetaceans, onboard the vessel, to be compared with the estimation made by the Marine Mammal Observer (MMO) in charge or it would be a useful support system for the expert when he has to analyze the video in the laboratory. In this paper, as a case of study, the UAVs video-analysis system has been applied on videos acquired by a camera mounted on a drone, during surveys in the Gulf of Taranto. Two different models of machine learning were used, and both the trained models are able to solve the task well albeit with some limitations.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11586/412093
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact