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

Abstract 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.

Authors

Institutions

Publication Details

Journal
Methods in Ecology and Evolution
Published
2025-08-25
DOI
https://doi.org/10.1111/2041-210x.70144
Primary Topic
Genomics and Phylogenetic Studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Margarida Santos‐Reis, Kateřina Sam, Wolfram Remmers, Stéphane Boyer et al.
1 links
Methods in Ecology and Evolution
Genomics and Phylogenetic Studies
article

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

Margarida Santos‐Reis, Kateřina Sam, Wolfram Remmers, Stéphane Boyer, Andrea Kaus‐Thiel, Paula Gonçalves, Otso Ovaskainen, Irmgard Krisai‐Greilhüber, Kirsty Quinlan, Elli Groner, Stefan Stoll, Adrian Pinder, F. Vannier, Elise Sivault, Valerie Levesque‐Beaudin, Gergin Blagoev, Bess Hardwick, Markéta Tahadlová, Anna Mrázová, Sébastien Moreau, Lucas Sire, Mikko Pentinsaari, Carlos López‐Vaamonde, Sandra Alcobia, Tommi Mononen, Tereza Vlasatá, Patrick Strutzenberger, Brigitte Gottsberger, Inês T. Rosário, Chris Ho, Adrian Barrett, Lauren Vanderlingen
article en

Abstract

Abstract 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.

Methods in Ecology and Evolution
Université de Tours (FR), Centre National de la Recherche Scientifique (FR), University of Vienna (AT), University of Helsinki (FI), Trier University of Applied Sciences (DE), Sewanee: The University of the South (US), École Pratique des Hautes Études (FR), University of South Bohemia in České Budějovice (CZ), Sorbonne Université (FR), Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement (FR), Hochschule Campus Wien (AT), Sustainability Institute (ZA), Assembly of First Nations (CA), Dead Sea and Arava Science Center (IL), Institut de Systématique, Évolution, Biodiversité (FR), Institute of Entomology (CZ), Department of Biodiversity, Conservation and Attractions (AU), Universitätszahnklinik Wien (AT), AOSOL (Portugal) (PT), University of Duisburg-Essen (DE), University of Guelph (CA), University of Jyväskylä (FI)
Grantová Agentura České Republiky, Horizon 2020 Framework Programme, Biotieteiden ja Ympäristön Tutkimuksen Toimikunta, H2020 European Research Council
Openalex Percentile: Top 80%
Genomics and Phylogenetic Studies
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.