Rapid literature mapping on the recent use of machine learning for wildlife imagery
Machine (especially deep) learning algorithms are changing the way wildlife imagery is processed. They dramatically speed up the time to detect, count, and classify animals and their behaviours. Yet, we currently have very few systematic literature surveys on its use in wildlife imagery. Through a l...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Peer Community In
2023-04-01
|
| Series: | Peer Community Journal |
| Online Access: | https://peercommunityjournal.org/articles/10.24072/pcjournal.261/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206367330238464 |
|---|---|
| author | Nakagawa, Shinichi Lagisz, Malgorzata Francis, Roxane Tam, Jessica Li, Xun Elphinstone, Andrew Jordan, Neil R. O'Brien, Justine K. Pitcher, Benjamin J. Van Sluys, Monique Sowmya, Arcot Kingsford, Richard T. |
| author_facet | Nakagawa, Shinichi Lagisz, Malgorzata Francis, Roxane Tam, Jessica Li, Xun Elphinstone, Andrew Jordan, Neil R. O'Brien, Justine K. Pitcher, Benjamin J. Van Sluys, Monique Sowmya, Arcot Kingsford, Richard T. |
| author_sort | Nakagawa, Shinichi |
| collection | DOAJ |
| description | Machine (especially deep) learning algorithms are changing the way wildlife imagery is processed. They dramatically speed up the time to detect, count, and classify animals and their behaviours. Yet, we currently have very few systematic literature surveys on its use in wildlife imagery. Through a literature survey (a ‘rapid’ review) and bibliometric mapping, we explored its use across: 1) species (vertebrates), 2) image types (e.g., camera traps, or drones), 3) study locations, 4) alternative machine learning algorithms, 5) outcomes (e.g., recognition, classification, or tracking), 6) reporting quality and openness, 7) author affiliation, and 8) publication journal types. We found that an increasing number of studies used convolutional neural networks (i.e., deep learning). Typically, studies have focused on large charismatic or iconic mammalian species. An increasing number of studies have been published in ecology-specific journals indicating the uptake of deep learning to transform the detection, classification and tracking of wildlife. Sharing of code was limited, with only 20% of studies providing links to analysis code. Much of the published research and focus on animals came from India, China, Australia, or the USA. There were relatively few collaborations across countries. Given the power of machine learning, we recommend increasing collaboration and sharing approaches to utilise increasing amounts of wildlife imagery more rapidly and transform and improve understanding of wildlife behaviour and conservation. Our survey, augmented with bibliometric analyses, provides valuable signposts for future studies to resolve and address shortcomings, gaps, and biases.
|
| format | Article |
| id | doaj-art-1c5dd4783c0343f5978caabeb55ffcee |
| institution | Kabale University |
| issn | 2804-3871 |
| language | English |
| publishDate | 2023-04-01 |
| publisher | Peer Community In |
| record_format | Article |
| series | Peer Community Journal |
| spelling | doaj-art-1c5dd4783c0343f5978caabeb55ffcee2025-02-07T10:16:49ZengPeer Community InPeer Community Journal2804-38712023-04-01310.24072/pcjournal.26110.24072/pcjournal.261Rapid literature mapping on the recent use of machine learning for wildlife imagery Nakagawa, Shinichi0https://orcid.org/0000-0002-7765-5182Lagisz, Malgorzata1https://orcid.org/0000-0002-3993-6127Francis, Roxane2https://orcid.org/0000-0003-3172-5445Tam, Jessica3https://orcid.org/0000-0003-3655-1974Li, Xun4https://orcid.org/0000-0002-1717-0669Elphinstone, Andrew5Jordan, Neil R.6https://orcid.org/0000-0002-0712-8301O'Brien, Justine K.7https://orcid.org/0000-0003-2011-9626Pitcher, Benjamin J.8https://orcid.org/0000-0002-8580-0343Van Sluys, Monique9Sowmya, Arcot10https://orcid.org/0000-0001-9236-5063Kingsford, Richard T.11https://orcid.org/0000-0001-6565-4134UNSW Data Science Hub, Evolution & Ecology Research Centre and School of Biological, Earth and Environmental Sciences, UNSW, Sydney, NSW 2052, AustraliaUNSW Data Science Hub, Evolution & Ecology Research Centre and School of Biological, Earth and Environmental Sciences, UNSW, Sydney, NSW 2052, AustraliaCentre for Ecosystem Science and School of Biological, Earth and Environmental Sciences, UNSW, Sydney, NSW 2052, AustraliaCentre for Ecosystem Science and School of Biological, Earth and Environmental Sciences, UNSW, Sydney, NSW 2052, AustraliaSchool of Computer Science and Engineering, UNSW Sydney, NSW 2052, AustraliaTaronga Institute of Science and Learning, Taronga Conservation Society Australia, Mosman, NSW 2088, AustraliaCentre for Ecosystem Science and School of Biological, Earth and Environmental Sciences, UNSW, Sydney, NSW 2052, Australia; Taronga Institute of Science and Learning, Taronga Conservation Society Australia, Mosman, NSW 2088, AustraliaCentre for Ecosystem Science and School of Biological, Earth and Environmental Sciences, UNSW, Sydney, NSW 2052, Australia; Taronga Institute of Science and Learning, Taronga Conservation Society Australia, Mosman, NSW 2088, AustraliaTaronga Institute of Science and Learning, Taronga Conservation Society Australia, Mosman, NSW 2088, Australia; School of Natural Sciences, Macquarie University, Sydney, NSW 2109, AustraliaTaronga Institute of Science and Learning, Taronga Conservation Society Australia, Mosman, NSW 2088, AustraliaSchool of Computer Science and Engineering, UNSW Sydney, NSW 2052, AustraliaCentre for Ecosystem Science and School of Biological, Earth and Environmental Sciences, UNSW, Sydney, NSW 2052, AustraliaMachine (especially deep) learning algorithms are changing the way wildlife imagery is processed. They dramatically speed up the time to detect, count, and classify animals and their behaviours. Yet, we currently have very few systematic literature surveys on its use in wildlife imagery. Through a literature survey (a ‘rapid’ review) and bibliometric mapping, we explored its use across: 1) species (vertebrates), 2) image types (e.g., camera traps, or drones), 3) study locations, 4) alternative machine learning algorithms, 5) outcomes (e.g., recognition, classification, or tracking), 6) reporting quality and openness, 7) author affiliation, and 8) publication journal types. We found that an increasing number of studies used convolutional neural networks (i.e., deep learning). Typically, studies have focused on large charismatic or iconic mammalian species. An increasing number of studies have been published in ecology-specific journals indicating the uptake of deep learning to transform the detection, classification and tracking of wildlife. Sharing of code was limited, with only 20% of studies providing links to analysis code. Much of the published research and focus on animals came from India, China, Australia, or the USA. There were relatively few collaborations across countries. Given the power of machine learning, we recommend increasing collaboration and sharing approaches to utilise increasing amounts of wildlife imagery more rapidly and transform and improve understanding of wildlife behaviour and conservation. Our survey, augmented with bibliometric analyses, provides valuable signposts for future studies to resolve and address shortcomings, gaps, and biases. https://peercommunityjournal.org/articles/10.24072/pcjournal.261/ |
| spellingShingle | Nakagawa, Shinichi Lagisz, Malgorzata Francis, Roxane Tam, Jessica Li, Xun Elphinstone, Andrew Jordan, Neil R. O'Brien, Justine K. Pitcher, Benjamin J. Van Sluys, Monique Sowmya, Arcot Kingsford, Richard T. Rapid literature mapping on the recent use of machine learning for wildlife imagery Peer Community Journal |
| title | Rapid literature mapping on the recent use of machine learning for wildlife imagery
|
| title_full | Rapid literature mapping on the recent use of machine learning for wildlife imagery
|
| title_fullStr | Rapid literature mapping on the recent use of machine learning for wildlife imagery
|
| title_full_unstemmed | Rapid literature mapping on the recent use of machine learning for wildlife imagery
|
| title_short | Rapid literature mapping on the recent use of machine learning for wildlife imagery
|
| title_sort | rapid literature mapping on the recent use of machine learning for wildlife imagery |
| url | https://peercommunityjournal.org/articles/10.24072/pcjournal.261/ |
| work_keys_str_mv | AT nakagawashinichi rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT lagiszmalgorzata rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT francisroxane rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT tamjessica rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT lixun rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT elphinstoneandrew rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT jordanneilr rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT obrienjustinek rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT pitcherbenjaminj rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT vansluysmonique rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT sowmyaarcot rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery AT kingsfordrichardt rapidliteraturemappingontherecentuseofmachinelearningforwildlifeimagery |