Dear colleagues,

The following paper is now published open access in Ecological Informatics
and the pipeline therein is in use and available for application to
additional populations at www.finwave.io.

Barnhill, A., Towers, J.R., Shaw, T.J.H., Arias, M., Bécares, A.,
Doniol-Valcroze, T., von Fersen, L., Genoves, R., Rörup, T., Sutton, G.J.,
Thornton, S., Weiss, M., Maier, A., Nöth, E. and Bergler, C. (2025)
Advances in deep learning-driven photo identification and meta analysis of
cetaceans in large data repositories. *Ecol. Inform.* 91:103396.
https://doi.org/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 realtime 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.

For any questions please contact Alex Barnhill and/or Jared Towers at
[email protected] and/or [email protected], respectively.

   Jared
_______________________________________________
MARMAM mailing list
[email protected]
https://lists.uvic.ca/mailman/listinfo/marmam

Reply via email to