Cargando…

Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures

A key aspect of ocean protection consists in estimating the abundance of marine mammal population density within their habitat, which is usually accomplished using visual inspection and cameras from line-transect ships, small boats, and aircraft. However, marine mammal observation through vessel sur...

Descripción completa

Detalles Bibliográficos
Autores principales: Araújo, Voncarlos M., Shukla, Ankita, Chion, Clément, Gambs, Sébastien, Michaud, Robert
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9185326/
https://www.ncbi.nlm.nih.gov/pubmed/35684729
http://dx.doi.org/10.3390/s22114107
_version_ 1784724697052610560
author Araújo, Voncarlos M.
Shukla, Ankita
Chion, Clément
Gambs, Sébastien
Michaud, Robert
author_facet Araújo, Voncarlos M.
Shukla, Ankita
Chion, Clément
Gambs, Sébastien
Michaud, Robert
author_sort Araújo, Voncarlos M.
collection PubMed
description A key aspect of ocean protection consists in estimating the abundance of marine mammal population density within their habitat, which is usually accomplished using visual inspection and cameras from line-transect ships, small boats, and aircraft. However, marine mammal observation through vessel surveys requires significant workforce resources, including for the post-processing of pictures, and is further challenged due to animal bodies being partially hidden underwater, small-scale object size, occlusion among objects, and distracter objects (e.g., waves, sun glare, etc.). To relieve the human expert’s workload while improving the observation accuracy, we propose a novel system for automating the detection of beluga whales (Delphinapterus leucas) in the wild from pictures. Our system relies on a dataset named Beluga-5k, containing more than 5.5 thousand pictures of belugas. First, to improve the dataset’s annotation, we have designed a semi-manual strategy for annotating candidates in images with single (i.e., one beluga) and multiple (i.e., two or more belugas) candidate subjects efficiently. Second, we have studied the performance of three off-the-shelf object-detection algorithms, namely, Mask-RCNN, SSD, and YOLO v3-Tiny, on the Beluga-5k dataset. Afterward, we have set YOLO v3-Tiny as the detector, integrating single- and multiple-individual images into the model training. Our fine-tuned CNN-backbone detector trained with semi-manual annotations is able to detect belugas despite the presence of distracter objects with high accuracy (i.e., 97.05 mAP@0.5). Finally, our proposed method is able to detect overlapped/occluded multiple individuals in images (beluga whales that swim in groups). For instance, it is able to detect 688 out of 706 belugas encountered in 200 multiple images, achieving 98.29% precision and 99.14% recall.
format Online
Article
Text
id pubmed-9185326
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91853262022-06-11 Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures Araújo, Voncarlos M. Shukla, Ankita Chion, Clément Gambs, Sébastien Michaud, Robert Sensors (Basel) Article A key aspect of ocean protection consists in estimating the abundance of marine mammal population density within their habitat, which is usually accomplished using visual inspection and cameras from line-transect ships, small boats, and aircraft. However, marine mammal observation through vessel surveys requires significant workforce resources, including for the post-processing of pictures, and is further challenged due to animal bodies being partially hidden underwater, small-scale object size, occlusion among objects, and distracter objects (e.g., waves, sun glare, etc.). To relieve the human expert’s workload while improving the observation accuracy, we propose a novel system for automating the detection of beluga whales (Delphinapterus leucas) in the wild from pictures. Our system relies on a dataset named Beluga-5k, containing more than 5.5 thousand pictures of belugas. First, to improve the dataset’s annotation, we have designed a semi-manual strategy for annotating candidates in images with single (i.e., one beluga) and multiple (i.e., two or more belugas) candidate subjects efficiently. Second, we have studied the performance of three off-the-shelf object-detection algorithms, namely, Mask-RCNN, SSD, and YOLO v3-Tiny, on the Beluga-5k dataset. Afterward, we have set YOLO v3-Tiny as the detector, integrating single- and multiple-individual images into the model training. Our fine-tuned CNN-backbone detector trained with semi-manual annotations is able to detect belugas despite the presence of distracter objects with high accuracy (i.e., 97.05 mAP@0.5). Finally, our proposed method is able to detect overlapped/occluded multiple individuals in images (beluga whales that swim in groups). For instance, it is able to detect 688 out of 706 belugas encountered in 200 multiple images, achieving 98.29% precision and 99.14% recall. MDPI 2022-05-28 /pmc/articles/PMC9185326/ /pubmed/35684729 http://dx.doi.org/10.3390/s22114107 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Araújo, Voncarlos M.
Shukla, Ankita
Chion, Clément
Gambs, Sébastien
Michaud, Robert
Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures
title Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures
title_full Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures
title_fullStr Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures
title_full_unstemmed Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures
title_short Machine-Learning Approach for Automatic Detection of Wild Beluga Whales from Hand-Held Camera Pictures
title_sort machine-learning approach for automatic detection of wild beluga whales from hand-held camera pictures
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9185326/
https://www.ncbi.nlm.nih.gov/pubmed/35684729
http://dx.doi.org/10.3390/s22114107
work_keys_str_mv AT araujovoncarlosm machinelearningapproachforautomaticdetectionofwildbelugawhalesfromhandheldcamerapictures
AT shuklaankita machinelearningapproachforautomaticdetectionofwildbelugawhalesfromhandheldcamerapictures
AT chionclement machinelearningapproachforautomaticdetectionofwildbelugawhalesfromhandheldcamerapictures
AT gambssebastien machinelearningapproachforautomaticdetectionofwildbelugawhalesfromhandheldcamerapictures
AT michaudrobert machinelearningapproachforautomaticdetectionofwildbelugawhalesfromhandheldcamerapictures