ENA24 is a dataset of 8,789 camera trap images with 9,772 bounding box annotations for 23 wildlife species from Eastern North America. The images are 1920x1080 resolution and annotations are in COCO format. It was originally collected by the University of Missouri and distributed via LILA BC, and is hosted on Hugging Face by davanstrien.
Use Cases
- Train object detection models based on bounding box annotations for 23 wildlife species.
- Benchmark model performance on camera trap imagery based on the 8,789 annotated images.
- Study wildlife distribution and behavior in Eastern North America based on the geographic scope.
- Develop automated species identification tools based on the labeled camera trap images.
Strengths
- Contains 8,789 annotated images, providing a substantial base for model training.
- Includes 9,772 bounding box annotations across 23 species, offering multi-class detection targets.
- Images are provided at a consistent 1920x1080 resolution, which may simplify preprocessing.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment for large-scale training.
- Data may reflect geographic bias inherent to its collection in Eastern North America.
Provenance
- Source
- University of Missouri, distributed via LILA BC.
- Collection Method
- Originally collected via camera traps.
- Time Range
- null
- Freshness
- Last updated 2026-03-19 18:48:58; freshness should be verified.
- Geography
- Eastern North America