A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill.
Estimating the densities of marine prey observed in animal-borne video loggers when encountered by foraging predators represents an important challenge for understanding predator-prey interactions in the marine environment. We used video images collected during the foraging trip of one chinstrap pen...
Published in: | PLOS ONE |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Public Library of Science
2024
|
Subjects: | |
Online Access: | https://doi.org/10.1371/journal.pone.0303633 https://pubmed.ncbi.nlm.nih.gov/38980882 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11232977/ |
id |
ftpubmed:38980882 |
---|---|
record_format |
openpolar |
spelling |
ftpubmed:38980882 2024-09-15T17:41:49+00:00 A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill. Hermanson, Victoria R Cutter, George R Hinke, Jefferson T Dawkins, Matthew Watters, George M 2024 https://doi.org/10.1371/journal.pone.0303633 https://pubmed.ncbi.nlm.nih.gov/38980882 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11232977/ eng eng Public Library of Science https://doi.org/10.1371/journal.pone.0303633 https://pubmed.ncbi.nlm.nih.gov/38980882 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11232977/ Copyright: This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modified, built upon, or otherwise used by anyone for any lawful purpose. The work is made available under the Creative Commons CC0 public domain dedication. PLoS One ISSN:1932-6203 Volume:19 Issue:7 Journal Article 2024 ftpubmed https://doi.org/10.1371/journal.pone.0303633 2024-07-11T16:03:00Z Estimating the densities of marine prey observed in animal-borne video loggers when encountered by foraging predators represents an important challenge for understanding predator-prey interactions in the marine environment. We used video images collected during the foraging trip of one chinstrap penguin (Pygoscelis antarcticus) from Cape Shirreff, Livingston Island, Antarctica to develop a novel approach for estimating the density of Antarctic krill (Euphausia superba) encountered during foraging activities. Using the open-source Video and Image Analytics for a Marine Environment (VIAME), we trained a neural network model to identify video frames containing krill. Our image classifier has an overall accuracy of 73%, with a positive predictive value of 83% for prediction of frames containing krill. We then developed a method to estimate the volume of water imaged, thus the density (N·m-3) of krill, in the 2-dimensional images. The method is based on the maximum range from the camera where krill remain visibly resolvable and assumes that mean krill length is known, and that the distribution of orientation angles of krill is uniform. From 1,932 images identified as containing krill, we manually identified a subset of 124 images from across the video record that contained resolvable and unresolvable krill necessary to estimate the resolvable range and imaged volume for the video sensor. Krill swarm density encountered by the penguins ranged from 2 to 307 krill·m-3 and mean density of krill was 48 krill·m-3 (sd = 61 krill·m-3). Mean krill biomass density was 25 g·m-3. Our frame-level image classifier model and krill density estimation method provide a new approach to efficiently process video-logger data and estimate krill density from 2D imagery, providing key information on prey aggregations that may affect predator foraging performance. The approach should be directly applicable to other marine predators feeding on aggregations of prey. Article in Journal/Newspaper Antarc* Antarctic Antarctic Krill Antarctica antarcticus Chinstrap penguin Euphausia superba Livingston Island PubMed Central (PMC) PLOS ONE 19 7 e0303633 |
institution |
Open Polar |
collection |
PubMed Central (PMC) |
op_collection_id |
ftpubmed |
language |
English |
description |
Estimating the densities of marine prey observed in animal-borne video loggers when encountered by foraging predators represents an important challenge for understanding predator-prey interactions in the marine environment. We used video images collected during the foraging trip of one chinstrap penguin (Pygoscelis antarcticus) from Cape Shirreff, Livingston Island, Antarctica to develop a novel approach for estimating the density of Antarctic krill (Euphausia superba) encountered during foraging activities. Using the open-source Video and Image Analytics for a Marine Environment (VIAME), we trained a neural network model to identify video frames containing krill. Our image classifier has an overall accuracy of 73%, with a positive predictive value of 83% for prediction of frames containing krill. We then developed a method to estimate the volume of water imaged, thus the density (N·m-3) of krill, in the 2-dimensional images. The method is based on the maximum range from the camera where krill remain visibly resolvable and assumes that mean krill length is known, and that the distribution of orientation angles of krill is uniform. From 1,932 images identified as containing krill, we manually identified a subset of 124 images from across the video record that contained resolvable and unresolvable krill necessary to estimate the resolvable range and imaged volume for the video sensor. Krill swarm density encountered by the penguins ranged from 2 to 307 krill·m-3 and mean density of krill was 48 krill·m-3 (sd = 61 krill·m-3). Mean krill biomass density was 25 g·m-3. Our frame-level image classifier model and krill density estimation method provide a new approach to efficiently process video-logger data and estimate krill density from 2D imagery, providing key information on prey aggregations that may affect predator foraging performance. The approach should be directly applicable to other marine predators feeding on aggregations of prey. |
format |
Article in Journal/Newspaper |
author |
Hermanson, Victoria R Cutter, George R Hinke, Jefferson T Dawkins, Matthew Watters, George M |
spellingShingle |
Hermanson, Victoria R Cutter, George R Hinke, Jefferson T Dawkins, Matthew Watters, George M A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill. |
author_facet |
Hermanson, Victoria R Cutter, George R Hinke, Jefferson T Dawkins, Matthew Watters, George M |
author_sort |
Hermanson, Victoria R |
title |
A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill. |
title_short |
A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill. |
title_full |
A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill. |
title_fullStr |
A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill. |
title_full_unstemmed |
A method to estimate prey density from single-camera images: A case study with chinstrap penguins and Antarctic krill. |
title_sort |
method to estimate prey density from single-camera images: a case study with chinstrap penguins and antarctic krill. |
publisher |
Public Library of Science |
publishDate |
2024 |
url |
https://doi.org/10.1371/journal.pone.0303633 https://pubmed.ncbi.nlm.nih.gov/38980882 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11232977/ |
genre |
Antarc* Antarctic Antarctic Krill Antarctica antarcticus Chinstrap penguin Euphausia superba Livingston Island |
genre_facet |
Antarc* Antarctic Antarctic Krill Antarctica antarcticus Chinstrap penguin Euphausia superba Livingston Island |
op_source |
PLoS One ISSN:1932-6203 Volume:19 Issue:7 |
op_relation |
https://doi.org/10.1371/journal.pone.0303633 https://pubmed.ncbi.nlm.nih.gov/38980882 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11232977/ |
op_rights |
Copyright: This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modified, built upon, or otherwise used by anyone for any lawful purpose. The work is made available under the Creative Commons CC0 public domain dedication. |
op_doi |
https://doi.org/10.1371/journal.pone.0303633 |
container_title |
PLOS ONE |
container_volume |
19 |
container_issue |
7 |
container_start_page |
e0303633 |
_version_ |
1810488075686510592 |