Abstract
The rhesus macaque is an important model species in several branches of science, including neuroscience, psychology, ethology, and medicine. The utility of the macaque model would be greatly enhanced by the ability to precisely measure behavior in freely moving conditions. Existing approaches do not provide sufficient tracking. Here, we describe OpenMonkeyStudio, a deep learning-based markerless motion capture system for estimating 3D pose in freely moving macaques in large unconstrained environments. Our system makes use of 62 machine vision cameras that encircle an open 2.45 m × 2.45 m × 2.75 m enclosure. The resulting multiview image streams allow for data augmentation via 3D-reconstruction of annotated images to train a robust view-invariant deep neural network. This view invariance represents an important advance over previous markerless 2D tracking approaches, and allows fully automatic pose inference on unconstrained natural motion. We show that OpenMonkeyStudio can be used to accurately recognize actions and track social interactions.
Highlights
The rhesus macaque is an important model species in several branches of science, including neuroscience, psychology, ethology, and medicine
Pose estimation can currently be done with a high degree of accuracy by commercial marker-based motion capture systems (e.g., Vicon, OptiTrack, and PhaseSpace)
Due to the millions of trainable parameters in deep neural networks, pose estimation requires a large quantity of training data
Summary
The rhesus macaque is an important model species in several branches of science, including neuroscience, psychology, ethology, and medicine. We describe OpenMonkeyStudio, a deep learning-based markerless motion capture system for estimating 3D pose in freely moving macaques in large unconstrained environments. The resulting multiview image streams allow for data augmentation via 3D-reconstruction of annotated images to train a robust view-invariant deep neural network This view invariance represents an important advance over previous markerless 2D tracking approaches, and allows fully automatic pose inference on unconstrained natural motion. Macaques present several problems that make current best markerless motion capture unworkable They have a much greater range of possible body movements than other model organisms. Each body joint has multiple degrees of freedom, which generates a large number of distinctive poses associated with common activities such as bipedal/quadrupedal locomotion, grooming, and social interactions in even modestly sized environments They interact with the world in a fundamentally three-dimensional way, and so they must be tracked in 3D. Application to novel vantage points introduces substantial performance degradation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
