Convolutional Neural Networks for Risso’s Dolphins Identification

Abstract

Photo-identification is one of the best practices to estimate the abundance of cetaceans and, as such, it can help to obtain the biological information necessary to decision-making and actions to preserve the marine environment and its biodiversity. The Risso's dolphin is one of the least-known cetacean species on a global scale, and the distinctive scars on its dorsal fin proved to be extremely useful to photo-identify single individuals. The main novelty of this paper is the development of a new method based on deep learning, called Neural Network Pool (NNPool), and specifically devoted to the photo-identification of Risso's dolphins. This new method also includes the unique function of recognizing unknown vs known dolphins in large datasets with no interaction by the user. Moreover, the new version of DolFin catalogue, collecting Risso's dolphins data and photos acquired between 2013-2018 in the Northern Ionian Sea (Central-eastern Mediterranean Sea), is presented and used here to carry out the experiments. Results have been validated using a further data set, containing new images of Risso's dolphins from the Northern Ionian Sea and the Azores, acquired in 2019. The performance of the NNPool appears satisfying and increases proportionally to the number of images available, thus highlighting the importance of building large-scale data set for the application at hand.

Dolphins and sea turtles may host zoonotic parasites and pathogenic bacteria as indicators of anthropic pressure in the Gulf of Taranto (Northern Ionian Sea, Central-Eastern Mediterranean Sea)

“…The Gulf of Taranto (Fig. 1 ) hosts several species of cetaceans and sea turtles; in particular, the striped dolphin is the most frequent and abundant species, followed by the common bottlenose dolphin ( Tursiops truncatus ), the Risso’s dolphin and the sperm whale ( Physeter macrocephalus ) (Carlucci et al 2014 ; Renò et al 2019 ; Azzolin et al 2020 ; Carlucci et al 2020 ; Maglietta et al 2020 ; Papale et al 2020 ). Concerning the sea turtles, the most frequent species in the basin is the loggerhead sea turtle, followed by the occasionally seen green and leatherback sea turtles ( Dermochelys coriacea ) (Casale et al 2018 ; Pierri et al 2019 ).…”

Machine Learning and Image Processing Methods for Cetacean Photo Identification: A Systematic Review

“…• SPIR is an acronym of smart photo identification of Risso's dolphin (Grampus griseus), representing a fully automated system initially developed to study the presence of Risso's dolphin in the Gulf of Taranto [34], [38], [39], [43], [52]. Data used in this study were collected thanks to the citizen science activities made by the authors, with general public involvement in research activities, side by side with experts.…”

“…Moreover, acting as a best-matching algorithm, the peculiarity of SPIR is that it still provides an answer in terms of probability, even if the dolphin in the query image is unknown, that is, it has never been sighted before, and for this reason, its photos are not included in the reference catalogue. Maglietta et al proposed in [52] a novel methodology, called NNPool, devoted to the automated photo identification of unknown vs. known Risso's dolphins with an accuracy of 87% measured on a validation dataset, which can be used as preprocessing of SPIR to detect the unknown dolphin before performing the photo identification of known dolphins. Finally, SPIR, similar to the other systems, required a cropped image of each fin, and the crop was manually created.…”

Application of a multi-species bio-economic modelling approach to explore fishing traits within eligible cetacean conservation areas in the Northern Ionian Sea (Central Mediterranean Sea)

“…In particular, the spatial distribution and areas where these dolphins realize feeding, resting, socializing, and traveling activities have been identified (Carlucci et al, 2018b;Papale et al, 2020). In addition, other cetacean species occur in the NIS, such as the Risso's dolphin (Grampus griseus, Maglietta et al, 2020;Maglietta et al, 2022;Maglietta et al, 2018;Carlucci et al, 2020a), the sperm whale (Physeter macrocephalus, Bellomo et al, 2019), the Cuvier's beaked whale (Ziphius cavirostris, Podestà et al, 2016;Carlucci et al, 2020b) and the fin whale (Balaenoptera physalus, Dimatteo et al, 2011;Fanizza et al, 2014).…”