LUC3D: Multi-animal 3D pose tracking in the browser
Animal behavior unfolds in three dimensions over time, yet accessible scientific tools for analyzing it in its natural form remain limited. Uncertainty from popular 2D pose methods can be refined with multi-camera approaches to produce more accurate 3D estimates. This paper presents LUC3D (Label Unification and Correspondence in 3D Annotation GUI), a browser-based 3D GUI for reducing the amount…
In the realm of animal behavior research, three-dimensional tracking has historically been challenging to implement. Existing tools often rely on limited two-dimensional pose methods, which can lead to inaccuracies and increased manual labor. To address this, a new browser-based tool called LUC3D (Label Unification and Correspondence in 3D Annotation GUI) has been introduced.
LUC3D aims to simplify the process of labeling, proofreading, and tracking multiple animals using multiple cameras. The tool eliminates the need for any installation, making it highly accessible to researchers worldwide. To demonstrate its capabilities, LUC3D has been used to create two datasets of proofread multi-camera 3D triangulated pose data of mouse social behavior.
The paper also presents a protocol for generating consistent 3D labels and introduces a cross-view re-identification tracking algorithm specifically designed for multi-animal multi-camera pose data. By providing these resources, LUC3D seeks to promote the widespread adoption of 3D pose estimation techniques for studying social behavior.
This innovation has the potential to significantly reduce the cost of entry for neuroscience labs, enabling a broader range of institutions to conduct more accurate and comprehensive research on animal behavior.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.