wildlife-datasets 1.0.8

Library for easier access and research of wildlife re-identification datasets

Pipeline for wildlife re-identification including dataset zoo, training tools and trained models. Usage includes classifying new images in labelled databases and clustering individuals in unlabelled databases.

Documentation · Report Bug · Request Feature · :mailbox_with_mail:Email

Dataset for identification of individual animals	Trained model for individual re‑identification	Tools for training re‑identification models

Wildlife Re-Identification (Re-ID) Datasets

The aim of the project is to provide a comprehensive overview of datasets for wildlife individual re-identification and an easy-to-use package for developers of machine learning methods. The core functionality includes:

• overview of 50 publicly available wildlife re-identification datasets and 2 metadatasets.
• utilities to mass download and convert them into a unified format and fix some wrong labels.
• used for training our models MegaDescriptor and WildFusion.
• synergy with WildlifeTools used for training ML models.

An introductory example is provided in a Jupyter notebook. The package provides a natural synergy with WildlifeTools, which provides our MegaDescriptor model and tools for training neural networks.

Do you know about any animal re-identification dataset which is not included? Post it to the discussion forum please.

Changelog

[18/08/2025] Reached 50 datasets by adding BristolGorillas2020 (primates), CattleMuzzle, CoBRAReIdentificationYoungstock, HolsteinCattleRecognition (cows), CzechLynx (lynxes) and WildRaptorID (eagles).
[14/04/2025] Added AnimalCLEF2025, WildlifeReID-10k (unifications of multiple datasets), MultiCamCows2024 (cows) and PrimFace (primates).
[31/10/2024] Added AmvrakikosTurtles, ReunionTurtles, SouthernProvinceTurtles, ZakynthosTurtles (sea turtles), ELPephants (elephants) and Chicks4FreeID (chickens).
[09/05/2024] Added CatIndividualImages (cats), CowDataset (cows) and DogFaceNet (dogs).
[28/02/2024] Added MPDD (dogs), PolarBearVidID (polar bears) and SeaStarReID2023 (sea stars).
[04/01/2024] Received Best paper award at WACV 2024.

Summary of datasets

An overview of the provided datasets is available in the documentation. We include basic characteristics such as publication years, number of images, number of individuals, dataset time spans (difference between the last and first image taken) and additional information such as source, number of poses, inclusion of timestamps, whether the animals were captured in the wild and whether the dataset contains multiple species.

MetaDatasets

Datasets

Installation

The installation of the package is simple by

pip install wildlife-datasets

Adding new datasets

WildlifeDatasets are meant as a community effort to provide an easy access to wildlife re-identification datasets. New datasets may be easily added as described in the documentation.

Basic functionality

We show an example of downloading, extracting and processing the MacaqueFaces dataset.

from wildlife_datasets import analysis, datasets

datasets.MacaqueFaces.get_data('data/MacaqueFaces')
dataset = datasets.MacaqueFaces('data/MacaqueFaces')

The class dataset contains the summary of the dataset. The content depends on the dataset. Each dataset contains the identity and paths to images. This particular dataset also contains information about the date taken and contrast. Other datasets store information about bounding boxes, segmentation masks, position from which the image was taken, keypoints or various other information such as age or gender.

dataset.df

The dataset also contains basic metadata including information about the number of individuals, time span, licences or published year.

dataset.summary

This particular dataset already contains cropped images of faces. Other datasets may contain uncropped images with bounding boxes or even segmentation masks.

dataset.plot_grid()

Additional functionality

For additional functionality including mass loading, datasets splitting or evaluation metrics we refer to the documentation or the notebooks.

Additional datasets

For a list of additional datasets not included in WidlifeDatasets, see this webpage.

Citation

If you like our package, please cite our paper. You may be also interested in our SeaTurtleID2022 dataset published in another paper.

@InProceedings{Cermak_2024_WACV,
    author    = {\v{C}erm\'ak, Vojt\v{e}ch and Picek, Luk\'a\v{s} and Adam, Luk\'a\v{s} and Papafitsoros, Kostas},
    title     = {{WildlifeDatasets: An Open-Source Toolkit for Animal Re-Identification}},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
    month     = {January},
    year      = {2024},
    pages     = {5953-5963}
}