Open-source AI model for Sub-Saharan African camera trap species classification
The DeepFauna Sub-Saharan Africa Model is an open-source species classification model for camera trap imagery covering Sub-Saharan African wildlife. It has been developed to help conservation organisations, ecologists, universities, citizen science groups, and field research teams process large volumes of camera trap data without needing commercial platforms or machine learning expertise.
The model classifies 36 classes relevant to Sub-Saharan Africa, including iconic megafauna, antelope and ungulate species, primates, smaller mammals, one bird species, people, and vehicles. It is designed to run as part of a two-stage detect-then-classify pipeline, making it a natural companion to our Trap Tracker Sub-Saharan Africa Wildlife Detector.
DeepFauna Sub-Saharan Africa is released as part of our wider aim to make conservation AI more accessible, transparent, and useful to the organisations that need it most.
Model Overview
DeepFauna Sub-Saharan Africa is a species classifier fine-tuned on a curated dataset of camera trap and field imagery from Sub-Saharan African conservation deployments. It is intended to provide a strong, practical classification stage for camera trap analysis across the region, particularly for users who need local, offline, inspectable, and non-commercial tools.
Weights are exported in ONNX format, allowing the model to run across platforms and hardware without requiring the original training framework.
How it works: a two-stage pipeline
DeepFauna Sub-Saharan Africa is a classifier, not a standalone detector. It names an animal, person, or vehicle once that subject has been located and cropped from the full image. In practice it is run in two stages:
- Detection: the companion Sub-Saharan Africa Wildlife Detector locates animals, people, or vehicles in the full frame.
- Classification: each detected crop is passed to DeepFauna Sub-Saharan Africa, which assigns one of 36 class labels and a detection stage and are not passed to the species classifier, which supports responsible, privacy-aware processing.
People and vehicles are handled at the detection stage and are not passed to the species classifier, which supports responsible, privacy-aware processing.
Supported Classes
DeepFauna Sub-Saharan Africa classifies 36 classes:
Cheetah (Acinonyx jubatus jubatus), Car, Blue wildebeest (Connochaetes taurinus), Plains zebra (Equus quagga), Baboon (Papio sp.), Giraffe (Giraffa camelopardalis), African elephant (Loxodonta africana), Lion (Panthera leo), Person, Rhino, African buffalo (Syncerus caffer), Eland (Tragelaphus oryx), Spotted hyena (Crocuta crocuta), Impala (Aepyceros melampus), Black-backed jackal (Canis mesomelas), Sable antelope (Hippotragus equinus), Rabbit (Oryctolagus cuniculus), Warthog (Phacochoerus africanus), Chimpanzee (Pan troglodytes), Giant pangolin (Smutsia gigantea), Crested porcupine (Hystrix cristata), Aardvark (Orycteropus afer), Hippopotamus (Hippopotamus amphibius), Gemsbok (Oryx gazella), Ostrich (Struthio camelus), Hartebeest (Alcelaphus buselaphus), Waterbuck (Kobus ellipsiprymnus), Gorilla (Gorilla sp.), Bongo (Tragelaphus eurycerus), Kob (Kobus kob), Helmeted guineafowl (Numida meleagris), Common duiker (Sylvicapra grimmia), Genet (Genetta sp.), Giant pouched rat (Cricetomys sp.), Vervet monkey (Chlorocebus tantalus), Leopard (Panthera pardus).
Unlike our UK classifier, Car is a genuine, populated class here — vehicle crops from field and reserve deployments are common enough in this dataset to warrant a dedicated class, rather than being filtered out entirely at the detection stage.
Training Data
The model was fine-tuned on labelled animal, person, and vehicle crops, split into training, validation, and test sets. Data was collected through Sub-Saharan African conservation deployments, spanning daylight RGB and infrared night-time imagery, motion blur, partial occlusion, and multi-animal frames.
The raw training images are not released, as many were provided under partner-specific data agreements that pre-date this open model release.
Training Setup
The model was fine-tuned using:
- Architecture: Vision Transformer ViT-L (DINOv2), fine-tuned from the DeepFaune European camera-trap backbone.
- Approach: transfer learning, with a linear-probe stage followed by full-tuning of a fresh 36-class sub Saharan Africa classification head.
- Input resolution: 518 x 518.
- Training hardware: Blade with 8 x NVIDIA RTX A6000 GPUs
- Framework: PyTorch / timm
- Expert format: ONNX
The classification head is sized to 36 sub Saharan Africaq classes, and the trained model is fully self-contained – at inference it does not depend on the original DeepFaune weights.
Performance
On a held-out test set of 7,338 crops, DeepFauna Sub-Saharan Africa achieves a macro-averaged F1 score of 0.9922 (overall accuracy 0.992) across all 36 classes.
Performance is strong and even across species. The lowest-scoring classes are Gorilla (F1 0.968), Rhino (F1 0.979), and Buffalo (F1 0.981) — Rhino’s lower recall (0.963) likely reflects visual overlap with other large grey-bodied megafauna at distance or in poor light. All other classes score F1 ≥ 0.98, with 11 classes achieving a perfect F1 of 1.000.
Intended Use
This model is intended for non-commercial conservation and ecological monitoring, including:
- Sub-Saharan African camera trap species classification
- biodiversity monitoring
- ecological research
- conservation project workflows
- university and student research
- citizen science projects
- local offline image processing
- pre-filtering large image collections before manual review
The model can be used through TrapTracker tools or integrated into other non-commercial workflows using the ONNX weights, paired with the companion Sub-Saharan Africa Wildlife Detector.
Not Intended For
The model is not intended for:
- commercial resale or paid inference services
- use as a general global wildlife model
- legally sensitive identification tasks
- surveillance or monitoring of people
- replacing expert ecological validation
- making conservation decisions without human review
- classifying species not included in the model classes
Where results are used in scientific, regulatory, or conservation decision-making, users should include appropriate manual checking and validation..
Why We Are Releasing It
Camera trap AI has become increasingly important for biodiversity monitoring, but access to high-performing species recognition tools is often limited by commercial platforms, proprietary weights, pay-per-image models, or cloud-based inference.
This release is intended as a practical counterweight to that trend. The aim is simple: a conservation organisation with limited funding, no machine-learning team, and no GPU should still be able to process camera trap imagery locally and obtain useful species-level classifications across Sub-Saharan African landscapes.
Acknowledgements and Licence
DeepFaune UK is a derivative of the DeepFaune classification model and is built on the DeepFaune consortium’s camera-trap-adapted backbone. We gratefully acknowledge their work. Users of DeepFaune UK must also acknowledge the DeepFaune initiative.
Please cite DeepFaune alongside this model:
- Rigoudy, N., Dussert, G., the DeepFaune consortium, Spataro, B., Miele, V. & Chamaillé-Jammes, S. (2023) The DeepFaune initiative: a collaborative effort towards the automatic identification of the European fauna in camera-trap images. European Journal of Wildlife Research.
IMPORTANT — licence: Because DeepFaune UK is fine-tuned from DeepFaune’s model parameters, it inherits DeepFaune’s model-parameter licence, which is a Creative Commons ShareAlike licence. This means DeepFaune UK must be released under the same ShareAlike terms and with attribution to the DeepFaune consortium.
How To Cite
If you use the model in research, reports, publications, or conservation outputs, please cite the Zenodo DOI for this release. There is no accompanying paper at this time; the release is documented via its Zenodo record, along with an included test report and dataset manifest.
Download
By downloading the model, you agree to use it in accordance with its ShareAlike licence terms, to acknowledge both this model and the DeepFaune initiative, and to acknowledge the model appropriately in any resulting publications, reports, or public outputs.
The model is hosted on the Zenodo platform.
Updates
DeepFauna Sub-Saharan Africa will continue to be developed as new data become available and as the underlying model architecture improves. Future releases will be made available periodically on the Zenodo platform, with clear versioning so that users can track changes, improvements, and compatibility across model updates.