EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Detection and Classification of Marine Species Vocalizations Using a YOLO ‐Based Deep Learning Framework

Min Jun Kim iD, Juan Lee, Yongchae Cho, Won-Ki Kim iD, Jungyong Park, Dawoon Lee, Ho Seuk Bae

Ecology and Evolution · 2026-04 · 16 (4)

DOI: 10.1002/ece3.73466 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ecology and Evolution, online erschienen am 15.04.2026. Verfasst von Min Jun Kim und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Energy Systems Engineering Seoul National University Seoul Republic of Korea. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agency for Defense Development.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The underwater acoustic environment is highly complex, where signals from various natural and anthropogenic sources interact and overlap, making monitoring efforts very challenging. Thus, effective detection and classification mechanisms are vital, as they provide key information about marine species and help in understanding how human activities influence the overall marine environment. This study proposes a deep learning–based framework for the automatic detection and classification of marine species vocalizations, inspired by the YOLO (You Only Look Once) architecture. However, a major limitation in developing such frameworks is the limited availability of continuous, well‐annotated monitoring datasets that contain multi‐species recordings. To address this limitation, synthetic monitoring datasets were constructed by combining single‐species vocalizations to simulate realistic monitoring conditions under both non‐overlapping and overlapping scenarios. Augmentation techniques, including CutMix, were implemented to enhance dataset diversity and improve the model's robustness against signal overlap. Experimental results demonstrated that the proposed model achieves strong performance under non‐overlapping conditions and maintains stable detection and classification performance even in overlapping scenarios. These findings suggest that YOLO‐inspired architectures can achieve effective performance across various acoustic conditions. Future studies should focus on incorporating continuous, long‐term field recordings to further improve detection and classification reliability.

Schlagwörter

Stichwörter der Autor:innen

YOLOclassificationdeep learningdetectionmarine species vocalizations

Autor:innen und Institutionen

  • Department of Energy Systems Engineering Seoul National University Seoul Republic of Korea.
  • Research Institute of Energy and Resources Seoul National University Seoul Republic of Korea.
  • Department of Earth and Environmental Sciences Chungbuk National University Cheongju Republic of Korea.
  • Agency for Defense Development Changwon Republic of Korea.

ORCID-Profile: Min Jun Kim, Won-Ki Kim

Förderung

  • Agency for Defense Development

Zitieren

APA

Kim, M. J., Lee, J., Cho, Y., Kim, W. K., Park, J., Lee, D., & Bae, H. S. (2026). Automated Detection and Classification of Marine Species Vocalizations Using a YOLO ‐Based Deep Learning Framework. Ecology and Evolution, 16(4). https://doi.org/10.1002/ece3.73466

Vancouver

Kim MJ, Lee J, Cho Y, Kim WK, Park J, Lee D, et al. Automated Detection and Classification of Marine Species Vocalizations Using a YOLO ‐Based Deep Learning Framework. Ecology and Evolution. 2026;16(4). doi:10.1002/ece3.73466

BibTeX
@article{Kim2026,
  author = {Kim, Min Jun and Lee, Juan and Cho, Yongchae and Kim, Won-Ki and Park, Jungyong and Lee, Dawoon and Bae, Ho Seuk},
  title = {Automated Detection and Classification of Marine Species Vocalizations Using a YOLO ‐Based Deep Learning Framework},
  journal = {Ecology and Evolution},
  year = {2026},
  volume = {16},
  number = {4},
  doi = {10.1002/ece3.73466}
}
Kostenlos starten →