David L. Haggerty^1,2, Caleb B. Darden¹, David M. Lovinger¹

Accurate pose estimation underpins quantitative analysis of behavior, yet many deep learning-based tracking tools remain optimized for offline workflows that rely on fragmented software pipelines, workstation-grade GPUs, or external middleware for real-time deployment. Here, we present an integrated software-hardware ecosystem for pose estimation that spans dataset creation, model training, offline analysis, and real-time deployment on embedded edge-computing devices. SqueakPose Studio provides a unified software suite for whole-frame, deep learning-based pose estimation that integrates dataset creation, manual and model-assisted labeling, model training, validation, and large-scale offline inference. For experiments requiring continuous recording and synchronized data acquisition, SqueakView enables real-time model deployment, video capture, and sensor logging on embedded hardware. In parallel, MouseHouse provides a compact, modular enclosure for home cage-based experiments that integrates embedded GPU compute, microcontroller-based timing, and peripheral I/O. A shared data format and deterministic timing architecture ensure consistency between offline analysis and real-time experimentation. Together, SqueakPose Studio, SqueakView, and MouseHouse provide a unified and scalable platform for pose estimation and embedded behavioral experimentation without reliance on workstation-grade hardware or external middleware. This framework enables discovery of previously unobserved behavioral motifs in real time and supports in silico modeling of behavioral sequences relevant to health and disease states.

¹ Laboratory for Integrative Neuroscience, National Institute on Alcohol Abuse and Alcoholism, National Institutes of Health, Bethesda, MD 20892, USA

² PRAT Fellow, National Institute of General Medical Sciences, National Institutes of Health, Bethesda, MD 20892, USA

Funding Support:

NIGMS – NIH: 1FI2GM154674 (DLH)

NIAAA – NIH: 1ZIAAA000407 (DML)