facebookresearch/labgraph

Real-time hand tracking using WebCam

Ouverte

#89 ouverte le 26 août 2022

 (0 commentaire) (0 réaction) (0 personne assignée)Python (46 forks)auto 404
good first issue

Métriques du dépôt

Stars
 (165 étoiles)
Métriques de merge PR
 (Métriques PR en attente)

Description

🚀 Feature

Hand tracking enables the use of hands as an input method for AR/VR applications. When using hands as input modality, it delivers a new sense of presence, enhances social engagement, and delivers more natural interactions with fully tracked hands and articulated fingers.

MediaPipe can be used for real-time hand tracking. LabGraph can be used to record the data captured from a webcam. It could also be extended to other downstream applications.

This task is to use MediaPipe for real-time hand tracking and labgraph for data logging (hdf5 format).

Additional context

  1. MediaPipe can be found [here] (https://google.github.io/mediapipe/solutions/hands)
  2. The code should be added at folder is https://github.com/facebookresearch/labgraph/tree/main/devices/webcam/
  3. Create setup.py and README.md, where example can be found at: https://github.com/facebookresearch/labgraph/tree/main/extensions/labgraph_viz
  4. Add github action support, reference: https://github.com/facebookresearch/labgraph/actions/workflows/main.yml
  5. Add proper license header.

Guide contributeur