This dataset contains the trained models and the test data set presented in the paper "Recognizing European mammals and birds in camera trap images using convolutional neural networks". In this paper, we present convolutional neural network models based on the EfficientNetV2 and ConvNext architectures to recognize both mammals and bird species in camera trap images. In the archive files "model_ConvNextBase.tar" and "model_EfficientNetV2.tar", we provide downloads for our best trained models in the Tensorflow2 SavedModel format (https://www.tensorflow.org/guide/saved_model). A script to load and run the models can be found in our Git-Repository: https://github.com/umr-ds/Marburg-Camera-Traps. We also provide a download for the Marburg Open Forest (MOF) data set consisting of a collection of over 2000 images showing 18 animal species in the archive file "data_MOF.tar". This file contains two folders named "img" and "md", respectively. The "img" folder contains the images grouped in subfolders by recording date and camera trap id. The "md" folder contains the metadata which constists of the bounding box detections for each image. The metadata is grouped into yaml-files for each species.
To the files


AuthorsSchneider, Daniel
ContributorsLindner, Kim
Vogelbacher, Markus
Bellafkir, Hicham
Mühling, Markus
Farwig, Nina
Freisleben, Bernd
RelationshipIs Referenced By: (URL) https://github.com/umr-ds/Marburg-Camera-Traps
Is Referenced By: (URL) https://inf-cv.uni-jena.de/wordpress/wp-content/uploads/2023/09/Talk-8-Daniel-Schneider.pdf
LicenseCreative Commons Attribution 4.0
show more


NameFormatSizeChecksum (MD5)
data_MOF.tar .tar1.455Gb5e9faec564dc3053d8f4999091544733
model_ConvNextBase.tar .tar343.5Mb3bb8881b72e18d82aab5cec6b5918d43
model_EfficientNetV2.tar .tar222.6Mb10a57993de643a7b9482260ecb8c7255
license_CC-BY-4.0.txt .txt18.21Kb380b31767eeb6303e3bc300d8846f180
Creative Commons Attribution 4.0
Except where otherwise noted, this item's license is described as Creative Commons Attribution 4.0