Highly precise community science annotations of video camera-trapped fauna in challenging environments

Research output: Contribution to journalResearch articleContributedpeer-review

Contributors

  • Mimi Arandjelovic - , Max Planck Institute for Evolutionary Anthropology, German Centre for Integrative Biodiversity Research (iDiv) Halle—Jena—Leipzig (Author)
  • Colleen R. Stephens - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Paula Dieguez - , German Centre for Integrative Biodiversity Research (iDiv) Halle—Jena—Leipzig, Max Planck Institute for Evolutionary Anthropology (Author)
  • Nuria Maldonado - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Gaëlle Bocksberger - , Max Planck Institute for Evolutionary Anthropology, Senckenberg Biodiversity and Climate Research Centre (Author)
  • Marie Lyne Després-Einspenner - , Éco-corridors laurentiens (Author)
  • Benjamin Debetencourt - , Max Planck Institute for Evolutionary Anthropology, Wild Chimpanzee Foundation (Author)
  • Vittoria Estienne - , Max Planck Institute for Evolutionary Anthropology, Wildlife Conservation Society – Congo (Author)
  • Ammie K. Kalan - , University of Victoria BC (Author)
  • Maureen S. McCarthy - , Max Planck Institute for Evolutionary Anthropology, University of Southern California (Author)
  • Anne Céline Granjon - , German Centre for Integrative Biodiversity Research (iDiv) Halle—Jena—Leipzig, Max Planck Institute for Evolutionary Anthropology (Author)
  • Veronika Städele - , Max Planck Institute for Evolutionary Anthropology, Arizona State University (Author)
  • Briana Harder - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Lucia Hacker - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Anja Landsmann - , Max Planck Institute for Evolutionary Anthropology, Leipzig University (Author)
  • Laura K. Lynn - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Heidi Pfund - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Zuzana Ročkaiová - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Kristeena Sigler - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Jane Widness - , Max Planck Institute for Evolutionary Anthropology, Yale University (Author)
  • Heike Wilken - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Antonio Buzharevski - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Adeelia S. Goffe - , Trinity College Dublin (Author)
  • Kristin Havercamp - , Kyoto University (Author)
  • Lydia L. Luncz - , Max Planck Institute for Evolutionary Anthropology (Author)
  • Giulia Sirianni - , University of Rome La Sapienza (Author)
  • Erin G. Wessling - , Harvard University, German Primate Center – Leibniz Institute for Primate Research (Author)
  • Roman M. Wittig - , Max Planck Institute for Evolutionary Anthropology, CSRS, Institut des Sciences Cognitives Marc Jeannerod (Author)
  • Christophe Boesch - , Max Planck Institute for Evolutionary Anthropology, Wild Chimpanzee Foundation (Author)
  • Hjalmar S. Kühl - , Chair of Mammalian Diversity, German Centre for Integrative Biodiversity Research (iDiv) Halle—Jena—Leipzig, Max Planck Institute for Evolutionary Anthropology, Senckenberg Gesellschaft für Naturforschung (Author)

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.

Details

Original languageEnglish
JournalRemote Sensing in Ecology and Conservation
Publication statusAccepted/In press - 2024
Peer-reviewedYes

Keywords

Keywords

  • Camera trap, citizen science, community science, video, wildlife monitoring