Skip to content
This repository has been archived by the owner on Aug 12, 2024. It is now read-only.

Latest commit

 

History

History
37 lines (30 loc) · 1.58 KB

readme.md

File metadata and controls

37 lines (30 loc) · 1.58 KB
Raw

Freenect Green Screen

Status: Archived

About

Freenect Green Screen is a utility to use your Kinect device's (Gen1) depth sensors capabilities to only show the image of the person in front of it, simulating a green screen effect behind them. It captures the image with the Kinect VGA webcam and writes the edited frame in the virtual webcam provided by v4l2loopback module.

As it makes use of Linux features, it's not portable to other platforms in its current state, as far as I know.

Current and planned features

  • Virtual webcam: create a virtual device seen as a webcam by your OS with the Kinect's VGA image;
  • Green Screen: replace your background with an image;
    • Blurred Background: blur your background instead of a image;
  • Facial recognition: to keep user's face always in frame, when possible;
  • Runtime controls: adjust Kinect's angle, background image and turn on/off facial recognition while it's running;
  • Improved Green Screen: replace your background with a video/gif;

How to use it

Requirements

Build

In the repository's root folder, run:

$ cmake . -DCMAKE_BUILD_TYPE=Release -Bbuild
$ cmake --build build/

Running

In the repository's root folder, run:

$ build/bin/freenect-green-screen -h

License

Freenect Green Screen is released under the MIT License.