Advances in deep learning-driven photo identification and meta analysis of cetaceans in large data repositories

Barnhill A, Towers JR, Shaw T, Arias M, Becares A, Doniol-Valcroze T, von Fersen L, Genoves R, Rörup T, Sutton GJ, Thornton S, Weiss M, Maier A, Nöth E, Bergler C (2025)

Publication Type: Journal article

Publication year: 2025

Journal

Ecological Informatics Elsevier

Book Volume: 91

Article Number: 103396

DOI: 10.1016/j.ecoinf.2025.103396

Abstract

Photo-identification of cetaceans remains a labor-intensive task, requiring expert annotation of long-tailed image datasets in which most individuals are rarely encountered. We present a scalable, end-to-end framework that automates this process using lightweight deep learning models optimized for resource-constrained environments. Our modular pipeline integrates state-of-the-art detection (YOLOv8-small), individual identification via metric learning (EfficientNet-B0 with a contrastive head), and auxiliary modules for image quality scoring, side classification, and identifiability prediction. Unlike previous approaches limited to single-species applications or high-resource settings, our framework generalizes across five cetacean populations with diverse visual characteristics. We achieve top-1 identification accuracies of 0.92 for Bigg's killer whales (Orcinus orca rectipinnus), 0.96 for Southern resident killer whales (Orcinus orca ater), 0.96 for Lahille's bottlenose dolphins (Tursiops truncatus gephyreus), 0.82 for common minke whales (Balaenoptera acutorostrata scammoni), and 0.85 for humpback whales (Megaptera novaeangliae), yielding a cross-species accuracy of 0.90. To support image triage in large datasets, we include a quality scoring module that predicts image utility using learned embedding features. This module achieves an R2 of 0.799, enabling intelligent prioritization of data. Runtime evaluations show processing speeds of 1.6–3.2 images/s on CPU and 9.6–23.3 FPS with GPU acceleration, making it suitable for archival and real-time applications. We also evaluate the impact of demographic metadata (age, sex) on identification performance and provide practical recommendations for future dataset design. The system is available via a web interface designed to support real-world conservation workflows with minimal computational overhead.

Authors with CRIS profile

Alexander Barnhill Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) (LME) Elmar Nöth Professur für Informatik (Mustererkennung)

Involved external institutions

Tiergarten Nürnberg DE Germany (DE) Ostbayerische Technische Hochschule (OTH) Amberg-Weiden DE Germany (DE)

How to cite

APA:

Barnhill, A., Towers, J.R., Shaw, T., Arias, M., Becares, A., Doniol-Valcroze, T.,... Bergler, C. (2025). Advances in deep learning-driven photo identification and meta analysis of cetaceans in large data repositories. Ecological Informatics, 91. https://doi.org/10.1016/j.ecoinf.2025.103396

MLA:

Barnhill, Alexander, et al. "Advances in deep learning-driven photo identification and meta analysis of cetaceans in large data repositories." Ecological Informatics 91 (2025).

BibTeX: Download