AUTHOR=Lancaster Tucker J. , Leatherbury Kathryn N. , Shilova Kseniia , Streelman Jeffrey T. , McGrath Patrick T. TITLE=SARTAB, a scalable system for automated real-time behavior detection based on animal tracking and Region Of Interest analysis: validation on fish courtship behavior JOURNAL=Frontiers in Behavioral Neuroscience VOLUME=18 YEAR=2024 URL=https://www.frontiersin.org/journals/behavioral-neuroscience/articles/10.3389/fnbeh.2024.1509369 DOI=10.3389/fnbeh.2024.1509369 ISSN=1662-5153 ABSTRACT=
Methods from Machine Learning (ML) and Computer Vision (CV) have proven powerful tools for quickly and accurately analyzing behavioral recordings. The computational complexity of these techniques, however, often precludes applications that require real-time analysis: for example, experiments where a stimulus must be applied in response to a particular behavior or samples must be collected soon after the behavior occurs. Here, we describe SARTAB (Scalable Automated Real-Time Analysis of Behavior), a system that achieves automated real-time behavior detection by continuously monitoring animal positions relative to behaviorally relevant Regions Of Interest (ROIs). We then show how we used this system to detect infrequent courtship behaviors in