Highly precise community science annotations of video camera‐trapped fauna in challenging environments
Abstract As camera trapping grows in popularity and application, some analytical limitations persist including processing time and accuracy of data annotation. Typically images are recorded by camera traps although videos are becoming increasingly collected even though they require much more time fo...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | Remote Sensing in Ecology and Conservation |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/rse2.402 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850243411863404544 |
|---|---|
| author | Mimi Arandjelovic Colleen R. Stephens Paula Dieguez Nuria Maldonado Gaëlle Bocksberger Marie‐Lyne Després‐Einspenner Benjamin Debetencourt Vittoria Estienne Ammie K. Kalan Maureen S. McCarthy Anne‐Céline Granjon Veronika Städele Briana Harder Lucia Hacker Anja Landsmann Laura K. Lynn Heidi Pfund Zuzana Ročkaiová Kristeena Sigler Jane Widness Heike Wilken Antonio Buzharevski Adeelia S. Goffe Kristin Havercamp Lydia L. Luncz Giulia Sirianni Erin G. Wessling Roman M. Wittig Christophe Boesch Hjalmar S. Kühl |
| author_facet | Mimi Arandjelovic Colleen R. Stephens Paula Dieguez Nuria Maldonado Gaëlle Bocksberger Marie‐Lyne Després‐Einspenner Benjamin Debetencourt Vittoria Estienne Ammie K. Kalan Maureen S. McCarthy Anne‐Céline Granjon Veronika Städele Briana Harder Lucia Hacker Anja Landsmann Laura K. Lynn Heidi Pfund Zuzana Ročkaiová Kristeena Sigler Jane Widness Heike Wilken Antonio Buzharevski Adeelia S. Goffe Kristin Havercamp Lydia L. Luncz Giulia Sirianni Erin G. Wessling Roman M. Wittig Christophe Boesch Hjalmar S. Kühl |
| author_sort | Mimi Arandjelovic |
| collection | DOAJ |
| description | Abstract As camera trapping grows in popularity and application, some analytical limitations persist including processing time and accuracy of data annotation. Typically images are recorded by camera traps although videos are becoming increasingly collected even though they require much more time for annotation. To overcome limitations with image annotation, camera trap studies are increasingly linked to community science (CS) platforms. Here, we extend previous work on CS image annotations to camera trap videos from a challenging environment; a dense tropical forest with low visibility and high occlusion due to thick canopy cover and bushy undergrowth at the camera level. Using the CS platform Chimp&See, established for classification of 599 956 video clips from tropical Africa, we assess annotation precision and accuracy by comparing classification of 13 531 1‐min video clips by a professional ecologist (PE) with output from 1744 registered, as well as unregistered, Chimp&See community scientists. We considered 29 classification categories, including 17 species and 12 higher‐level categories, in which phenotypically similar species were grouped. Overall, annotation precision was 95.4%, which increased to 98.2% when aggregating similar species groups together. Our findings demonstrate the competence of community scientists working with camera trap videos from even challenging environments and hold great promise for future studies on animal behaviour, species interaction dynamics and population monitoring. |
| format | Article |
| id | doaj-art-56fd39ed85b049849f04ba80fd631089 |
| institution | OA Journals |
| issn | 2056-3485 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Remote Sensing in Ecology and Conservation |
| spelling | doaj-art-56fd39ed85b049849f04ba80fd6310892025-08-20T02:00:00ZengWileyRemote Sensing in Ecology and Conservation2056-34852024-12-0110670272410.1002/rse2.402Highly precise community science annotations of video camera‐trapped fauna in challenging environmentsMimi Arandjelovic0Colleen R. Stephens1Paula Dieguez2Nuria Maldonado3Gaëlle Bocksberger4Marie‐Lyne Després‐Einspenner5Benjamin Debetencourt6Vittoria Estienne7Ammie K. Kalan8Maureen S. McCarthy9Anne‐Céline Granjon10Veronika Städele11Briana Harder12Lucia Hacker13Anja Landsmann14Laura K. Lynn15Heidi Pfund16Zuzana Ročkaiová17Kristeena Sigler18Jane Widness19Heike Wilken20Antonio Buzharevski21Adeelia S. Goffe22Kristin Havercamp23Lydia L. Luncz24Giulia Sirianni25Erin G. Wessling26Roman M. Wittig27Christophe Boesch28Hjalmar S. Kühl29Department of Primate Behavior and Evolution Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyGerman Centre for Integrative Biodiversity Research (iDiv) Halle‐Jena‐Leipzig Puschstrasse 4 Leipzig 04103 GermanyMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyÉco‐corridors laurentiens 517 rue Saint‐Georges, Saint‐Jérôme Québec J7Z 5B6 CanadaMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyDepartment of Anthropology University of Victoria Cornett Building Victoria British Columbia V8P 5C2 CanadaMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyGerman Centre for Integrative Biodiversity Research (iDiv) Halle‐Jena‐Leipzig Puschstrasse 4 Leipzig 04103 GermanyMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyZooniverse Community Scientist, c/o Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanySchool of Medicine Trinity College Dublin, Public Health and Primary Care Dublin IrelandKyoto University, Wildlife Research Institute 2‐24 Tanaka‐Sekiden‐cho, Sakyo Kyoto 606‐8203 JapanTechnological Primates Research Group Max Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanySapienza University of Rome Piazzale Aldo Moro, 5 Rome 00185 ItalyDepartment of Human Evolutionary Biology Harvard University 11 Divinity Avenue Cambridge Massachusetts 02138 USAMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyMax Planck Institute for Evolutionary Anthropology Deutscher Platz 6 Leipzig 04103 GermanyGerman Centre for Integrative Biodiversity Research (iDiv) Halle‐Jena‐Leipzig Puschstrasse 4 Leipzig 04103 GermanyAbstract As camera trapping grows in popularity and application, some analytical limitations persist including processing time and accuracy of data annotation. Typically images are recorded by camera traps although videos are becoming increasingly collected even though they require much more time for annotation. To overcome limitations with image annotation, camera trap studies are increasingly linked to community science (CS) platforms. Here, we extend previous work on CS image annotations to camera trap videos from a challenging environment; a dense tropical forest with low visibility and high occlusion due to thick canopy cover and bushy undergrowth at the camera level. Using the CS platform Chimp&See, established for classification of 599 956 video clips from tropical Africa, we assess annotation precision and accuracy by comparing classification of 13 531 1‐min video clips by a professional ecologist (PE) with output from 1744 registered, as well as unregistered, Chimp&See community scientists. We considered 29 classification categories, including 17 species and 12 higher‐level categories, in which phenotypically similar species were grouped. Overall, annotation precision was 95.4%, which increased to 98.2% when aggregating similar species groups together. Our findings demonstrate the competence of community scientists working with camera trap videos from even challenging environments and hold great promise for future studies on animal behaviour, species interaction dynamics and population monitoring.https://doi.org/10.1002/rse2.402Camera trapcitizen sciencecommunity sciencevideowildlife monitoring |
| spellingShingle | Mimi Arandjelovic Colleen R. Stephens Paula Dieguez Nuria Maldonado Gaëlle Bocksberger Marie‐Lyne Després‐Einspenner Benjamin Debetencourt Vittoria Estienne Ammie K. Kalan Maureen S. McCarthy Anne‐Céline Granjon Veronika Städele Briana Harder Lucia Hacker Anja Landsmann Laura K. Lynn Heidi Pfund Zuzana Ročkaiová Kristeena Sigler Jane Widness Heike Wilken Antonio Buzharevski Adeelia S. Goffe Kristin Havercamp Lydia L. Luncz Giulia Sirianni Erin G. Wessling Roman M. Wittig Christophe Boesch Hjalmar S. Kühl Highly precise community science annotations of video camera‐trapped fauna in challenging environments Remote Sensing in Ecology and Conservation Camera trap citizen science community science video wildlife monitoring |
| title | Highly precise community science annotations of video camera‐trapped fauna in challenging environments |
| title_full | Highly precise community science annotations of video camera‐trapped fauna in challenging environments |
| title_fullStr | Highly precise community science annotations of video camera‐trapped fauna in challenging environments |
| title_full_unstemmed | Highly precise community science annotations of video camera‐trapped fauna in challenging environments |
| title_short | Highly precise community science annotations of video camera‐trapped fauna in challenging environments |
| title_sort | highly precise community science annotations of video camera trapped fauna in challenging environments |
| topic | Camera trap citizen science community science video wildlife monitoring |
| url | https://doi.org/10.1002/rse2.402 |
| work_keys_str_mv | AT mimiarandjelovic highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT colleenrstephens highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT pauladieguez highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT nuriamaldonado highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT gaellebocksberger highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT marielynedespreseinspenner highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT benjamindebetencourt highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT vittoriaestienne highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT ammiekkalan highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT maureensmccarthy highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT annecelinegranjon highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT veronikastadele highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT brianaharder highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT luciahacker highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT anjalandsmann highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT lauraklynn highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT heidipfund highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT zuzanarockaiova highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT kristeenasigler highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT janewidness highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT heikewilken highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT antoniobuzharevski highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT adeeliasgoffe highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT kristinhavercamp highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT lydialluncz highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT giuliasirianni highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT eringwessling highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT romanmwittig highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT christopheboesch highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments AT hjalmarskuhl highlyprecisecommunityscienceannotationsofvideocameratrappedfaunainchallengingenvironments |