Skip to main content

ORIGINAL RESEARCH article

Front. Mar. Sci.
Sec. Marine Ecosystem Ecology
Volume 11 - 2024 | doi: 10.3389/fmars.2024.1445698
This article is part of the Research Topic Remote Sensing Applications in Marine Ecology Monitoring and Target Sensing View all 4 articles

Localization and Tracking of Beluga Whales in Aerial Video Using Deep Learning

Provisionally accepted
Mostapha Al Saidi Mostapha Al Saidi 1Mohammed G. Al-Jassani Mohammed G. Al-Jassani 1Chiron Bang Chiron Bang 2Greg O'Corry-crowe Greg O'Corry-crowe 3Cortney Watt Cortney Watt 4Maha Ghazal Maha Ghazal 4Hanqi Zhuang Hanqi Zhuang 1*
  • 1 Florida Atlantic University, Boca Raton, United States
  • 2 Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, Florida, United States
  • 3 Harbor Branch Oceanographic Institute, Charles E. Schmidt College of Science, Florida Atlantic University, Fort Pierce, Florida, United States
  • 4 Freshwater Institute, Fisheries and Oceans Canada (DFO), Winnipeg, Manitoba, Canada

The final, formatted version of the article will be published soon.

    Aerial images are increasingly adopted and widely used in various research areas. In marine mammal studies, these imagery surveys serve multiple purposes: determining population size, mapping migration routes, and gaining behavioral insights. A single aerial scan using a drone yields a wealth of data, but processing it requires significant human effort.Our research demonstrates that deep learning models can significantly reduce human effort.They are not only able to detect marine mammals but also track their behavior using continuous aerial (video) footage. By distinguishing between different age classes, these algorithms can inform studies on population biology, ontogeny, and adult-calf relationships. To detect beluga whales from imagery footage, we trained the YOLOv7 model on a proprietary dataset of aerial footage of beluga whales. The deep learning model achieved impressive results with the following precision and recall scores: beluga adult = 92%-92%, beluga calf = 94%-89%.To track the detected beluga whales, we implemented the deep Simple Online and Realtime Tracking (SORT) algorithm. Unfortunately, the performance of the deep SORT algorithm was disappointing, with Multiple Object Tracking Accuracy (MOTA) scores ranging from 27% to 48%.An analysis revealed that the low tracking accuracy resulted from identity switching; that is, an identical beluga whale was given two IDs in two different frames. To overcome the problem of identity switching, a new post-processing algorithm was implemented, significantly improving MOTA to approximately 70%. The main contribution of this research is providing a system that accurately detects and tracks features of beluga whales, both adults and calves, from

    Keywords: marine mammals, Beluga Whale, localization, tracking, deep learning, Aerial Video Footage, multiple object tracking

    Received: 07 Jun 2024; Accepted: 03 Oct 2024.

    Copyright: © 2024 Al Saidi, Al-Jassani, Bang, O'Corry-crowe, Watt, Ghazal and Zhuang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Hanqi Zhuang, Florida Atlantic University, Boca Raton, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.