Presentation Type

Poster

Faculty Mentor’s Full Name

Travis Wheeler

Faculty Mentor’s Department

Computer Science

Abstract

We have developed a video-annotation pipeline that can be used to automatically track the movement of particularly social rodents (Degus) during interactive behavior. Using open source software (DeepLabCut), our approach requires methodical training of DeepLabCut neural networks, along with custom post-processing scripts to ensure continuity of the annotation of individual Degus. This tracking work is the first phase in a larger effort to automatically classify and label behaviors observed in video recordings of Degu interactions. Such behavioral annotation will influence our understanding of social behavior in general, with possible long-term impacts on diagnosis and treatment of autism spectrum disorder and other mental health conditions.

Category

Life Sciences

Share

COinS
 
Apr 17th, 3:00 PM Apr 17th, 4:00 PM

Tracking Rodent Social Interactions Using Machine Learning

UC South Ballroom

We have developed a video-annotation pipeline that can be used to automatically track the movement of particularly social rodents (Degus) during interactive behavior. Using open source software (DeepLabCut), our approach requires methodical training of DeepLabCut neural networks, along with custom post-processing scripts to ensure continuity of the annotation of individual Degus. This tracking work is the first phase in a larger effort to automatically classify and label behaviors observed in video recordings of Degu interactions. Such behavioral annotation will influence our understanding of social behavior in general, with possible long-term impacts on diagnosis and treatment of autism spectrum disorder and other mental health conditions.