PrecisionTrack: Reliable Tracking of Large Groups of Animals Interacting in Complex Environments Over Extended Periods

Large-scale ethological behavioral studies can provide insights into the neuronal processes underlying complex and social behaviors, potentially opening new avenues for mental health research. However, these studies remain tedious and time-consuming, relying on manual annotation of predefined features. Despite recent advances, automatically monitoring complex behaviors in socially interacting animals remains challenging, limiting the scope and scale of experiments. Here, we present PrecisionTrack, an open-source framework designed to track and monitor large groups of interacting animals over prolonged periods. PrecisionTrack shows high spatiotemporal accuracy in crowded social settings, maintains consistent tracking performance over time and supports real-time, online responsiveness. We also introduce the Multi-animal Action Recognition Transformer (MART), which can be seamlessly integrated with PrecisionTrack to extract behavioral insights beyond spatiotemporal localization, including individual actions and social interactions. The entire system is open source and accessible. Overall, combined with a step-by-step guide, PrecisionTrack enables users to train, test and deploy their own social behavior monitoring systems, offering novel possibilities to study complex social behaviors in crowded naturalized environments.