Back to Project List
Project

Plugin Development for DeepLabCut


Award napari Plugin Accelerator

Project Summary

Quantifying behavior is crucial for a wide range of applications such as animal conservation, ethology, genetics, neuroscience, human biomechanics, and medicine. DeepLabCut (DLC) relies on human-annotated frames in order to train deep neural networks to predict customized, user-defined key points. Key points are defined as body parts, a cell body, or objects. This team will develop a new napari plugin for DLC to label key points and objects. The project aims to develop new code that compiles with hook specifications, create a new hook implementation for combined hierarchical keypoint and segmentation mask labeling GUI, and deploy internal testing and community feedback.

Investigators

Principal Investigator
Mackenzie Mathis, PhD
Mackenzie Mathis, PhD
Co-Principal Investigators
Alexander Mathis, PhD
Alexander Mathis, PhD