A semi-automatic workflow to process camera trap images in R

This repository contains all scripts needed to run the semi-automatic workflow to process camera trap images described in Böhner et al. (2022). It also contains some example images to test the workflow. The small mammal classification model is available on https://doi.org/10.5281/zenodo.7142734 and will be downloaded automatically when running the workflow.

Clone the repository or download it as a zip-file to run the workflow. Step by step instructions to follow the workflow are provided in the file processing_camera_trap_images_step_by_step.pdf.

The images used for training the small mammal classification model are available on https://doi.org/10.5281/zenodo.7142734 .

Update: small_mammal_classification_model_2025
An updated version of the small mammal classification model is available on https://zenodo.org/records/18470646. The model was retrained with new training images from new locations across Norway.

Citation: Böhner, H., Kleiven, E. F., Ims, R. A., & Soininen, E. M. (2023). A semi-automatic workflow to process images from small mammal camera traps. Ecological Informatics, 76, 102150