Trainable, vision-based automated home cage behavioral phenotyping

  • Hueihan Jhuang*
  • , Estibaliz Garrote
  • , Nicholas Edelman
  • , Tomaso Poggio
  • , Andrew Steele
  • , Thomas Serre
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

We describe a fully trainable computer vision system enabling the automated analysis of complex mouse behaviors. Our system computes a sequence of feature descriptors for each video sequence and a classifier is used to learn a mapping from these features to behaviors of interest. We collected a very large manually annotated video database of mouse behaviors for training and testing the system. Our system performs on par with human scoring, as measured from the ground-truth manual annotations of thousands of clips of freely behaving mice. As a validation of the system, we characterized the home cage behaviors of two standard inbred and two non-standard mouse strains. From this data, we were able to predict the strain identity of individual mice with high accuracy.

Original languageEnglish
Title of host publicationSelected Papers from the Proceedings of the 7th International Conference on Methods and Techniques in Behavioral Research - Digital Edition, MB'10
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event7th International Conference on Methods and Techniques in Behavioral Research, MB'10 - Eindhoven, Netherlands
Duration: 24 Aug 201027 Aug 2010

Publication series

NameACM International Conference Proceeding Series

Conference

Conference7th International Conference on Methods and Techniques in Behavioral Research, MB'10
Country/TerritoryNetherlands
CityEindhoven
Period24/08/1027/08/10

Keywords

  • Behavior recognition
  • Computer vision
  • Mouse
  • Phenotyping
  • Rodent

Fingerprint

Dive into the research topics of 'Trainable, vision-based automated home cage behavioral phenotyping'. Together they form a unique fingerprint.

Cite this