EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An active ensemble classifier for detecting animal sequences from global camera trap data

Tommi Mononen, Bess Hardwick, Sandra Alcobia, Adrian Barrett, Gergin A. Blagoev, Stéphane Boyer, Paula Gonçalves, Brigitte Gottsberger, Elli Groner, Chris C. Y. Ho, Marketa Houska Tahadlova, Andrea Kaus‐Thiel und 20 weitere

Methods in Ecology and Evolution · 2025-10 · 16 (10) · 2500-2516

DOI: 10.1111/2041-210x.70144 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Methods in Ecology and Evolution, online erschienen am 25.08.2025. Verfasst von Tommi Mononen und 31 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Biotieteiden ja Ympäristön Tutkimuksen Toimikunta, Grantová Agentura České Republiky, H2020 European Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Camera traps can generate huge amounts of images, and thus reliable methods for their automated processing are in high demand: in particular to find those images or image sequences that actually include animals. Automatically filtering out images that are empty or contain humans can be challenging, as images can be taken in different landscapes, habitats and light. Weather and seasonal conditions can vary greatly. Most of the images can be empty, because cameras using passive infrared sensors (PIR) trigger easily due to moving vegetation or rapidly varying shadows and sunny spots. Animals in images are often hiding behind vegetation, and camera traps will see them from previously unseen angles. Therefore, conventional animal image detection methods based on deep learning need huge training sets to achieve good accuracy. We present a novel background removal approach based on movement masked images computed using sequences of images. Our deep vision classifier uses these movement images for classification instead of the original images. Additionally, we apply a deep active learning (active learning for deep models) for collecting training samples to reduce the number of annotations required from the user. Our method performed well in singling out image sequences that actually include animals, thus filtering out the majority of images that were empty or contained humans. Most importantly, the method performed well also for backgrounds and animal species not seen in the training data. Active learning brought good separation between classes already with small training sets, without the need for laborious large‐scale pre‐annotation. We present a reliable and efficient method for filtering out empty image sequences and sequences containing humans. This greatly facilitates camera trapping research by enabling researchers to restrict the task of animal classification to only those image sequences that actually contain animals.

Förderung

  • Biotieteiden ja Ympäristön Tutkimuksen Toimikunta
  • Grantová Agentura České Republiky
  • H2020 European Research Council

Zitieren

APA

Mononen, T., Hardwick, B., Alcobia, S., Barrett, A., Blagoev, G. A., Boyer, S., Gonçalves, P., Gottsberger, B., Groner, E., Ho, C. C. Y., Tahadlova, M. H., Kaus‐Thiel, A., Krisai‐Greilhuber, I., Levesque‐Beaudin, V., Lopez‐Vaamonde, C., Moreau, S., Mrazova, A., Pentinsaari, M., Pinder, A., …, & Ovaskainen, O. (2025). An active ensemble classifier for detecting animal sequences from global camera trap data. Methods in Ecology and Evolution, 16(10), 2500-2516. https://doi.org/10.1111/2041-210x.70144

Vancouver

Mononen T, Hardwick B, Alcobia S, Barrett A, Blagoev GA, Boyer S, et al. An active ensemble classifier for detecting animal sequences from global camera trap data. Methods in Ecology and Evolution. 2025;16(10):2500-2516. doi:10.1111/2041-210x.70144

BibTeX
@article{Mononen2025,
  author = {Mononen, Tommi and Hardwick, Bess and Alcobia, Sandra and Barrett, Adrian and Blagoev, Gergin A. and Boyer, Stéphane and Gonçalves, Paula and Gottsberger, Brigitte and Groner, Elli and Ho, Chris C. Y. and Tahadlova, Marketa Houska and Kaus‐Thiel, Andrea and Krisai‐Greilhuber, Irmgard and Levesque‐Beaudin, Valerie and Lopez‐Vaamonde, Carlos and Moreau, Sebastien and Mrazova, Anna and Pentinsaari, Mikko and Pinder, Adrian and Quinlan, Kirsty and Remmers, Wolfram and Rosário, Inês T. and Sam, Katerina and Santos‐Reis, Margarida and Sire, Lucas and Sivault, Elise and Stoll, Stefan and Strutzenberger, Patrick and Vanderlingen, Lauren and Vannier, Fabrice and Vlasata, Tereza and Ovaskainen, Otso},
  title = {An active ensemble classifier for detecting animal sequences from global camera trap data},
  journal = {Methods in Ecology and Evolution},
  year = {2025},
  volume = {16},
  number = {10},
  pages = {2500--2516},
  doi = {10.1111/2041-210x.70144}
}
Kostenlos starten →