[MARMAM] New article on a human-in-the-loop AI approach to detecting cetaceans in large aerial datasets

Raina Fan raina at whaleseeker.com
Fri Mar 10 11:52:05 PST 2023

Dear colleagues,

We're super excited to share our recent publication with you, titled
"Scaling whale monitoring using deep learning: A human-in-the-loop solution
for analyzing aerial datasets" published in Frontiers in Marine Science.

The paper describes our approach to AI-assisted cetacean detection in
detail, shows high agreement with human labellers, and demonstrates a time
savings of up to 97% compared to full manual annotation.

Check out the full article: https://doi.org/10.3389/fmars.2023.1099479
And the related press release on our website:

Abstract: To ensure effective cetacean management and conservation
policies, it is necessary to collect and rigorously analyze data about
these populations. Remote sensing allows the acquisition of images over
large observation areas, but due to the lack of reliable automatic analysis
techniques, biologists usually analyze all images by hand. In this paper,
we propose a human-in-the-loop approach to couple the power of deep
learning-based automation with the expertise of biologists to develop a
reliable artificial intelligence assisted annotation tool for cetacean
monitoring. We tested this approach to analyze a dataset of 5334 aerial
images acquired in 2017 by Fisheries and Oceans Canada to monitor
belugas (*Delphinapterus
leucas*) from the threatened Cumberland Sound population in Clearwater
Fjord, Canada. First, we used a test subset of photographs to compare
predictions obtained by the fine-tuned model to manual annotations made by
three Observers, expert marine mammal biologists. With only 100 annotated
images for training, the model obtained between 90% and 91.4% mutual
agreement with the three Observers, exceeding the minimum inter-observer
agreement of 88.6% obtained between the experts themselves. Second, this
model was applied to the full dataset. The predictions were then verified
by an Observer and compared to annotations made completely manually and
independently by another Observer. The annotating Observer and the
human-in-the-loop pipeline detected 4051 belugas in common, out of a total
of 4572 detections for the Observer and 4298 for our pipeline. This
experiment shows that the proposed human-in-the-loop approach is suitable
for processing novel aerial datasets for beluga counting and can be used to
scale cetacean monitoring. It also highlights that human observers, even
experienced ones, have varied detection bias, underlining the need to
discuss standardization of annotation protocols.

Raina on behalf of the Whale Seeker team

*Raina Fan*
Head of Science Communication and Outreach
Whale Seeker, Inc.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.uvic.ca/pipermail/marmam/attachments/20230310/c0bed691/attachment-0001.html>

More information about the MARMAM mailing list