A groundbreaking tool has been developed that utilizes facial recognition technology to identify and track individual whales and dolphins in their natural habitats. This innovative research was conducted by Philip Patton, a Ph.D. student at the University of Hawaiʻi at Mānoa Hawaiʻi Institute of Marine Biology (HIMB) and published in the prestigious journal Methods in Ecology and Evolution.
“From a conservation standpoint, the ability to recognize individual whales and dolphins over time is incredibly valuable as it allows us to gain insights into their movement patterns and habitat usage,” explains Patton. “This information is crucial for estimating population sizes and trends, which in turn aids in the conservation of these magnificent marine mammals.”
This advanced photo-identification model, inspired by human facial recognition algorithms, was developed for a Kaggle competition organized by Happywhale.com. The competition aimed to challenge engineers to create a tool capable of accurately identifying and differentiating between individual whales and dolphins based on various characteristics such as scarring, pigmentation, and size.
Accelerating the Information Gathering Process
The Marine Mammal Research Program at UH Mānoa utilizes photography to study and inform the management and conservation efforts of marine mammals in Hawaiʻi. With the integration of this algorithm, the data collection process can be significantly expedited.
“By employing this algorithm during our field surveys, we can greatly streamline the information gathering process,” adds Patton. “Once we return to the lab, we can run the photos through the algorithm, which provides us with instant identification and enables us to analyze vital information about population numbers and habitat utilization. This is crucial for the conservation of Hawaiian whales and dolphins.”
Furthermore, this new tool presents a non-invasive approach to studying the social behavior of dolphins, which are highly social creatures. “By recognizing and tracking the same individuals over time, we can gather invaluable information about their behavior and the locations they frequent,” adds Patton.
This publication is the result of an extensive collaboration involving 56 researchers from around the world. These researchers contributed their image data, representing 24 different species spanning six continents, in order to advance cetacean research and conservation efforts.
The study also included the participation of HIMB graduate students Liah McPherson and Jens Curry, as well as Patton’s faculty advisor, Lars Bejder.
More information: Philip T. Patton et al, A deep learning approach to photo–identification demonstrates high performance on two dozen cetacean species, Methods in Ecology and Evolution (2023). DOI: 10.1111/2041-210X.14167
Citation: Individual whale, dolphin ID using facial recognition tech (2023, July 19) retrieved 19 July 2023 from https://phys.org/news/2023-07-individual-whale-dolphin-id-facial.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
Denial of responsibility! SamacharCentrl is an automatic aggregator of Global media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, and all materials to their authors. For any complaint, please reach us at – [email protected]. We will take necessary action within 24 hours.
Shambhu Kumar is a science communicator, making complex scientific topics accessible to all. His articles explore breakthroughs in various scientific disciplines, from space exploration to cutting-edge research.
