EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Towards scalable insect monitoring: Ultra‐lightweight CNNs as on‐device triggers for insect camera traps

Ross J. Gardiner, Sareh Rowlands, Benno I. Simmons

Methods in Ecology and Evolution · 2026-02 · 17 (2) · 357-370

DOI: 10.1111/2041-210x.70098 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Methods in Ecology and Evolution, online erschienen am 03.07.2025. Verfasst von Ross J. Gardiner und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Camera traps, combined with AI, have emerged to achieve automated, scalable biodiversity monitoring. However, passive infrared (PIR) sensors that typically trigger camera traps are poorly suited for detecting small, fast‐moving ectotherms such as insects. Insects comprise over half of all animal species and are key components of ecosystems and agriculture. The need for an appropriate and scalable insect camera trap is critical in the wake of concerning reports of declines in insect populations. This study proposes an alternative to the PIR trigger: ultra‐lightweight convolutional neural networks running on low‐powered hardware to detect insects in a continuous stream of captured images. We train such models to distinguish insect images from backgrounds. Our design achieves zero latency between trigger and image capture. Our models are rigorously tested and achieve high accuracy ranging from 91.8% to 96.4% AUROC on test data and 58.8% to 87.2% AUROC on field data from distributions unseen during training. The high specificity of our models ensures minimal saving of false positive images, maximising deployment storage efficiency. High recall scores indicate a minimal false negative rate, maximising insect detection. Analysis using saliency maps shows the learned representation of our models to be robust, with low reliance on spurious background features. Our method is also shown to operate deployed on off‐the‐shelf, low‐powered microcontroller units, consuming a maximum power draw of less than 300 mW. This paves the way for scalable systems with longer deployment times. Overall, we fully define the properties of a successful trigger for camera traps and show how lightweight AI models, made bespoke for efficient hardware, can be realised with a specific focus on insect ectotherms. We provide these models to the community alongside a complete codebase for future modifications, and we demonstrate how they can be deployed on an example ESP32‐S3 microcontroller platform. This step potentiates a major advancement for ectotherm camera traps and insect monitoring.

Förderung

  • Engineering and Physical Sciences Research Council

Zitieren

APA

Gardiner, R. J., Rowlands, S., & Simmons, B. I. (2026). Towards scalable insect monitoring: Ultra‐lightweight CNNs as on‐device triggers for insect camera traps. Methods in Ecology and Evolution, 17(2), 357-370. https://doi.org/10.1111/2041-210x.70098

Vancouver

Gardiner RJ, Rowlands S, Simmons BI. Towards scalable insect monitoring: Ultra‐lightweight CNNs as on‐device triggers for insect camera traps. Methods in Ecology and Evolution. 2026;17(2):357-370. doi:10.1111/2041-210x.70098

BibTeX
@article{Gardiner2026,
  author = {Gardiner, Ross J. and Rowlands, Sareh and Simmons, Benno I.},
  title = {Towards scalable insect monitoring: Ultra‐lightweight CNNs as on‐device triggers for insect camera traps},
  journal = {Methods in Ecology and Evolution},
  year = {2026},
  volume = {17},
  number = {2},
  pages = {357--370},
  doi = {10.1111/2041-210x.70098}
}
Kostenlos starten →