Related Experiment Videos
SqueakPose Studio, an end-to-end platform for pose estimation and real-time edge-AI deployment
David L Haggerty1,2, Caleb Browning Darden1, David Lovinger1
1Laboratory for Integrative Neuroscience, Institute on Alcohol Abuse and Alcoholism, National Institutes of Health, Bethesda, United States.
Elife
|July 6, 2026
Summary
We developed an integrated system for pose estimation, enabling real-time behavior analysis on edge devices. This platform streamlines workflows from data collection to deployment, enhancing quantitative behavioral research.
Area of Science:
- Computational Neuroscience
- Behavioral Neuroscience
- Machine Learning in Biology
Background:
- Accurate pose estimation is crucial for quantitative behavioral analysis.
- Current deep learning tools often require complex, offline pipelines and high-performance hardware for real-time deployment.
- Existing systems lack integration across dataset creation, training, and real-time application on edge devices.
Purpose of the Study:
- To present an integrated software-hardware ecosystem for pose estimation.
- To enable efficient real-time pose estimation and behavior analysis on embedded edge-computing devices.
- To bridge the gap between offline analysis and real-time experimental needs without specialized hardware.
Main Methods:
- Developed SqueakPose Studio: a software suite for dataset creation, labeling, training, and offline inference using object-detection architectures.
- Integrated SqueakView for real-time model deployment, video capture, and sensor logging on edge hardware.
- Introduced MouseHouse: a modular enclosure for home cage experiments with embedded compute and synchronized data acquisition.
Main Results:
- The system supports efficient end-to-end training and inference on various hardware (CPUs, GPUs, Apple Silicon).
- Achieved seamless real-time deployment on embedded edge devices.
- Ensured consistency between offline analysis and real-time deployment via a shared data format and deterministic timing.
Conclusions:
- The SqueakPose ecosystem provides a unified platform for both conventional offline analysis and embedded, real-time pose estimation.
- Eliminates the need for workstation-grade hardware or external middleware for real-time behavioral tracking.
- Facilitates accessible, quantitative behavior analysis in diverse experimental settings, including home cage environments.
Related Concept Videos
01:24One-Degree-of-Freedom System
In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
01:24Muscle Coordination and Action
Muscle coordination is a complex and finely tuned process essential for smooth and purposeful movements like flexion, extension, adduction, abduction, and rotation. The human body orchestrates the actions of various muscles working in concert, each with a specific role. Four functional types describe how muscles work together: agonist, antagonist, synergist, and fixator.
Agonists
Agonist muscles, often called prime movers, are the primary muscles responsible for producing a specific movement.
Agonists
Agonist muscles, often called prime movers, are the primary muscles responsible for producing a specific movement.
01:24Absolute Motion Analysis- General Plane Motion
Visualize a drone, with its propellers spinning rapidly, hovering mid-air. The fascinating movements and operations of this drone can be comprehended by applying the principle of general plane motion.
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the drone...
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the drone...