Skip to content

interactionlab/hand-marker-labeling

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-time Hand Marker Labeling System using Deep Learning

This repository contains a deep learning based approach to label hand-markers in real-time. All preprocessing steps, the training process, the trained model itself, and a unity plugin to receive and visualize the labeled data are provided in this repository.

Content

We provide jupyter notbooks to create a machine learning model from the recorded motion capture data step-by-step. Therefore the data has to be exported to .csv files.

For real-time labeling, the motion capture data can be streamed to the Labeling Client. It uses a NatNet client to receive the data and runs the labelNetwork to get the hand labels.

The Unity Client can receive the labeled data and fires a HandDataEvent whenever data is received. To use the Unity Client in you own project import the HandTrackingClient.unitypackage and add the HandTrackingClient to your scene.

We modified the NatNet SDK's python client to be able to receive labeled and unlabeled markers in the Labeling Client.

About

Real-time Hand Marker Labeling System using Deep Learning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published