The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification

TL;DR

SA-FARI is a comprehensive, large-scale dataset of wild animal videos with detailed annotations, designed to advance multi-animal tracking and recognition across diverse species and regions.

Contribution

It introduces the largest open-source multi-animal tracking dataset with extensive annotations, covering 99 species across multiple continents, enabling improved generalization in wildlife video analysis.

Findings

State-of-the-art models achieve promising results on SA-FARI.

Benchmark results highlight challenges in multi-species tracking.

Dataset facilitates development of generalizable wildlife recognition methods.

Abstract

Automated video analysis is critical for wildlife conservation. A foundational task in this domain is multi-animal tracking (MAT), which underpins applications such as individual re-identification and behavior recognition. However, existing datasets are limited in scale, constrained to a few species, or lack sufficient temporal and geographical diversity - leaving no suitable benchmark for training general-purpose MAT models applicable across wild animal populations. To address this, we introduce SA-FARI, the largest open-source MAT dataset for wild animals. It comprises 11,609 camera trap videos collected over approximately 10 years (2014-2024) from 741 locations across 4 continents, spanning 99 species categories. Each video is exhaustively annotated culminating in ~46 hours of densely annotated footage containing 16,224 masklet identities and 942,702 individual bounding boxes, segmentation masks, and species labels. Alongside the task-specific annotations, we publish anonymized camera trap locations for each video. Finally, we present comprehensive benchmarks on SA-FARI using state-of-the-art vision-language models for detection and tracking, including SAM 3, evaluated with both species-specific and generic animal prompts. We also compare against vision-only methods developed specifically for wildlife analysis. SA-FARI is the first large-scale dataset to combine high species diversity, multi-region coverage, and high-quality spatio-temporal annotations, offering a new foundation for advancing generalizable multianimal tracking in the wild. The dataset is available at https://www.conservationxlabs.com/sa-fari.